Data processing method, device, equipment, and computer program

Abstract

The embodiments of the present application provide a data processing method, an apparatus, a device and a medium, which include: in response to a service start operation in a video application, starting a video recording service in the video application; collecting a user voice in the video recording service, determining a target text matching the user voice in prompt text data associated with the video recording service, and marking the target text; and, when the text position of the target text in the prompt text data is the end position of the prompt text data, obtaining target video data corresponding to the video recording service. According to the embodiments of the present application, the effectiveness of the teleprompter function in the video recording service can be improved, and the quality of the video recording can be further improved.

Description

[Technical field]

[0001] This application claims priority to a Chinese patent application filed with the China Patent Office on February 8, 2021, bearing application number 202110179007.4 and entitled "Data Processing Method, Apparatus, Device, and Medium", the entire contents of which are incorporated by reference into this application.

[0002] The present application relates to the field of Internet technology, and in particular to data processing technology. [Background technology]

[0003] With the development of short videos, more and more users (including those who have no experience in filming and editing) have joined the ranks of multimedia creators and started to perform their own performances in front of the camera. For inexperienced multimedia creators, when facing the camera, they often forget words, and even if they memorize the content script, they still have problems such as stuttering and unnatural expressions.

[0004] Therefore, when shooting a short video, the user prints out the script content and places it next to the camera to present it. Summary of the Invention [Problem to be solved by the invention]

[0005] However, when there is a lot of script content, users may not be able to quickly locate the content to be presented or may position it incorrectly, the effect of presenting the lines by printing the script content is not obvious, and when users look at the script content next to the camera, the camera will capture the user's actions, which will further affect the quality of the final video shooting.

[0006] The embodiments of the present application provide a data processing method, device, apparatus, and medium that can enhance the effectiveness of the teleprompter function in a video recording service and further improve the quality of the video recording. [Means for solving the problem]

[0007] One aspect of an embodiment of the present application provides a data processing method executed by a computing device, comprising: initiating a video recording service in the video application in response to a service initiation operation in the video application; collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text; and obtaining target video data corresponding to the video recording service when the text position of the target text in the prompt text data is an end position of the prompt text data. method.

[0008] One aspect of an embodiment of the present application provides a data processing method executed by a computing device, comprising: uploading prompt text data to a teleprompter application; collecting user speech corresponding to the target user and performing text conversion on the user speech to generate user speech text corresponding to the user speech; determining, in the prompt text data, text that is the same as the user spoken text as a target text, and marking the target text in a teleprompter application. method.

[0009] One aspect of an embodiment of the present application provides a data processing device arranged in a computer device, an initiation module for initiating a video recording service in the video application in response to a service initiation operation in the video application; a display module for collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text; an acquiring module for acquiring target video data corresponding to the video recording service when the text position of the target text in the prompt text data is an end position of the prompt text data. Device.

[0010] One aspect of an embodiment of the present application provides a data processing device arranged in a computer device, a prompt text upload module for uploading prompt text data to the teleprompter application; a user voice collection module for collecting user voice corresponding to a target user and performing text conversion on the user voice to generate user voice text corresponding to the user voice; a user spoken text display module for determining, in the prompt text data, text that is the same as the user spoken text as a target text and for marking the target text in a teleprompter application. Device.

[0011] One aspect of an embodiment of the present application provides a computer device including a memory and a processor, the memory being connected to the processor and configured to store a computer program, and the processor being configured to call the computer program to cause the computer device to execute a method provided in any one of the above aspects of the embodiments of the present application.

[0012] One aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program that is loaded and executed by a processor to cause a computing device having a processor to perform a method provided in any one of the above aspects of the embodiments of the present application.

[0013] According to one aspect of the present application, there is provided a computer program product or computer program, the computer program product or computer program comprising computer commands, the computer commands being stored on a computer readable storage medium, a processor of a computing device reading the computer commands from the computer readable storage medium, and the processor executing the computer commands to cause the computing device to perform a method provided in any one of the above aspects. Effect of the Invention

[0014] The embodiment of the present application can respond to a service start operation in a video application by starting a video recording service in the video application, collecting a user's voice in the video recording service, determining a target text associated with the user's voice in the prompt text data associated with the video recording service, and marking the target text, so that the user who is speaking can quickly and accurately locate the content of the speech based on the marking child, and improve the effectiveness of the text prompt function in the video recording service. If the text position of the target text in the prompt text data is the end position of the prompt text data, the target video data corresponding to the video recording service is obtained. In this way, after starting a video recording service in a video application, the target text matching the user's voice can be located and marked in the prompt text data, that is, the target text displayed in the video application matches the content spoken by the user, thereby improving the effectiveness of the text prompt function in the video recording service, reducing the risk of recording failure caused by the user forgetting words, and further improving the quality of video recording. [Brief description of the drawings]

[0015] [Figure 1] FIG. 2 is a structural schematic diagram of a network architecture provided in an embodiment of the present application; [Diagram 2] FIG. 2 is a schematic diagram of a data processing scenario provided in an embodiment of the present application. [Diagram 3] FIG. 2 is a schematic flow diagram of a data processing method provided in an embodiment of the present application. [Figure 4] 1 is a schematic diagram of an interface for inputting prompt text data provided in an embodiment of the present application; [Diagram 5] 1 is a schematic diagram of an interface for initiating a video recording service in a video application provided in an embodiment of the present application; [Figure 6] 1 is a schematic diagram of an interface for displaying prompt text data provided in an embodiment of the present application; [Figure 7] 1 is a schematic diagram of an interface for displaying speech rate prompt information provided in an embodiment of the present application; [Figure 8] FIG. 2 is a schematic diagram of an interface for stopping a video recording service provided in an embodiment of the present application; [Figure 9] 1 is a schematic diagram of an interface for performing editing optimization on video recording, provided in an embodiment of the present application; [Figure 10] 1 is a schematic diagram of an interface for recommending tutorial videos based on speech error types provided in an embodiment of the present application; [Figure 11] 1 is an implementation flowchart of a video recording service provided in an embodiment of the present application; [Figure 12] FIG. 2 is a schematic flow diagram of a data processing method provided in an embodiment of the present application. [Figure 13] FIG. 1 is a schematic diagram of an application scenario of the teleprompter provided in an embodiment of the present application. [Figure 14] FIG. 1 is a structural schematic diagram of a data processing device provided in an embodiment of the present application; [Figure 15] FIG. 1 is a structural schematic diagram of a data processing device provided in an embodiment of the present application; [Figure 16] FIG. 2 is a structural schematic diagram of a computer device provided in an embodiment of the present application; [Figure 17] FIG. 1 is a structural schematic diagram of a computer device provided in an embodiment of the present application; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] The technical solutions of the embodiments of the present application are described below clearly and completely with reference to the drawings of the embodiments of the present application.

[0017] Referring to FIG. 1, FIG. 1 is a structural schematic diagram of a network architecture provided in an embodiment of the present application. As shown in FIG. 1, the network architecture may include a server 10d and a user terminal cluster, and the user terminal cluster may include one or more user terminals, but the number of user terminals is not limited here. As shown in FIG. 1, the user terminal cluster may specifically include a user terminal 10a, a user terminal 10b, and a user terminal 10c, etc. The server 10d may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or may even be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, big data, and artificial intelligence platforms. The user terminals 10a, 10b, and 10c, etc. may be smartphones, tablet computers, notebook computers, electronic organizers, mobile Internet devices (mobile The user terminals may include smart terminals with video / image playback capabilities, such as internet devices, MIDs, wearable devices (e.g., smart watches, smart bands, etc.), and smart TVs. As shown in Fig. 1, user terminal 10a, user terminal 10b, user terminal 10c, etc. may each have a network connection with server 10d, such that each user terminal exchanges data with server 10d via the network connection.

[0018] Taking the user terminal 10a shown in Fig. 1 as an example, the user terminal 10a may have installed thereon a video application having a video recording function, such as a video editing application and a short video application. The user may open the video application installed in the user terminal 10a, and the video application may provide the user with a video recording function, which includes a normal shooting method and a teleprompter shooting method, in which the normal shooting method means that when a user is shot using the camera of the user terminal 10a (or an external shooting device having a communication connection with the user terminal 10a), the script content may not be presented to the user, so the user needs to organize (e.g., record) the script content that he or she wishes to express in the video recording in advance, and in which the teleprompter shooting method means that when a user is shot using the built-in camera of the user terminal 10a or an external shooting device, the script content is displayed to the user on the screen of the user terminal 10a, and the script content can be switched and displayed according to the progress of the user's voice (e.g., scroll display, etc.), and here, the script content may also be called prompt text data in the video recording service (prompt text is also called "presentation text"). After a user performs a trigger operation on an entry corresponding to a teleprompter shooting method in the video application (i.e., a teleprompter shooting entry), the user terminal 10a displays a recording page in the video application in response to the trigger operation on the teleprompter shooting entry, and before recording the video, the user can input prompt text data on the recording page or upload existing prompt text data to the recording page.

[0019] When a user starts video recording, the user terminal 10a starts a video recording function in the video application in response to the user's video recording start operation, and during video recording, the user terminal 10a can display the prompt text data on the terminal screen according to the progression of the user's voice. In other words, during video recording, the prompt text data can be displayed according to the progression of the user's voice, and when the user's voice speed is faster, the switching display speed (which may be the scroll speed) of the prompt text data in the video application is faster, and when the user's voice speed is slower, the switching display speed of the prompt text data in the video application is slower, that is, the text of the prompt text data displayed in the video application is adjusted to the user's voice, thereby ensuring the effectiveness of the text prompt function during video recording, helping the user to smoothly complete video recording, and further improving the quality of video recording.

[0020] Also refer to FIG. 2, which is a schematic diagram of a data processing scenario provided in the embodiment of the present application. Taking a video recording scenario as an example, the implementation process of the data processing method provided in the embodiment of the present application will be described. The user terminal 20a shown in FIG. 2 may be any one of the user terminals in the user terminal cluster shown in FIG. 1 above, and a video application having a video recording function is installed in the user terminal 20a. User A (the user A may be the user of the user terminal 20a) can open the video application in the user terminal 20a, enter the home page of the video application, and perform a trigger operation on the shooting entry in the video application. In response to the trigger operation on the shooting entry, the user terminal 20a causes the video application to display a shooting page 20m, and the shooting page 20m can include a shooting area 20b, a filter control 20c, a shooting control 20d, and a beautification control 20e, etc.The shooting area 20b displays the video screen collected by the user terminal 20a. The video screen is a video screen for user A, and may be collected by the camera of the user terminal 20a or a shooting device having a communication connection with the user terminal 20a. The shooting control 20d controls the start and end of video recording. After entering the shooting page 20m, a trigger operation may be performed on the shooting control 20d to indicate the start of shooting. The captured video screen is displayed in the shooting area 20b. During shooting, a trigger operation may be performed again on the shooting control 20d to indicate the stop of shooting. The shooting area 20b displays the video screen. The video screen displayed on the user terminal 20b is frozen to the screen when shooting stopped, and the filter control 20c performs image processing on the video screen collected by the user terminal 20a to achieve specific special effects, for example, a smoothing filter may perform processing such as skin correction, touch-up and smoothing on the portrait image in the collected video screen, and the beautification control 20e performs beautification processing on the portrait image in the video screen collected by the user terminal 20a, for example, automatically repairing the facial shape of the portrait image, enlarging the eyes of the portrait image, making the nose of the portrait image taller, etc.

[0021] The shooting page 20m may further include a teleprompter shooting entry 20f. In order to prevent a situation where user A forgets words during video recording when he / she lacks experience in video recording (forgetting words may cause the video to be re-recorded), user A can select a teleprompter shooting function in the video application, that is, perform a trigger operation on the teleprompter shooting entry 20f in the shooting page 20m. In response to user A's trigger operation of the teleprompter shooting entry 20f, the user terminal 20a switches and displays the shooting page 20m in the video application to a recording page corresponding to the teleprompter shooting entry 20f. On the recording page, a text input area is first displayed, and user A can input script content required for video recording in the text input area, and the script content can be used to present to user A during video recording. In short, during video recording, user A can record according to the script content displayed in the video application. In this case, the script content may also be called prompt text data 20g. In the text input area, statistical information 20h of the script content entered by User A may be further displayed, and the statistical information 20h may include the number of characters of the entered script content (i.e., the number of prompt characters, for example, the number of characters of the script content is 134) and the estimated video length (e.g., 35 seconds) corresponding to the entered script content, and User A may increase or decrease the script content based on the estimated video length.For example, if user A wants to record a 1-minute video and the estimated video length corresponding to the script content input in the text input area is 4 minutes, user A can reduce the script content displayed in the text input area so that the estimated video length corresponding to the reduced script content is about 1 minute (e.g., the estimated video length may be in the range of 55 seconds to 65 seconds); if the estimated video length corresponding to the script content input in the text input area is 35 seconds, user A can increase the script content displayed in the text input area so that the estimated video length corresponding to the increased script content is about 1 minute; and the finally determined script content can be determined as the prompt text data 20g.

[0022] After determining the prompt text data 20g, user A can perform a trigger operation on the "Next" control on the recording page, and in response to the trigger operation on the "Next" control, the user terminal 20a activates the camera (or a photographing device with a communication connection) of the user terminal 20a and enters a video recording preparation state (i.e., before starting video recording). As shown in FIG. 2, on the recording page, a video screen 20i for user A collected by the user terminal 20a is displayed, and prompt information such as "Place your mobile phone in an appropriate position and say "START" to start teleprompter recording" is displayed. That is, user A can adjust his / her position and the position of the user terminal 20a based on the video screen 20i, and after adjusting the position, he / she can start video recording by voice, for example, the user may start video recording by saying "START".

[0023] After user A says "start", the user terminal 20a can initiate an operation in response to user A's voice, initiate video recording in the video application, and display the prompt text data 20g on the recording page. The text displayed on the recording page may only be a part of the text in the prompt text data 20g, for example, a single word in the prompt text data 20g, so that after initiating video recording, the first phrase in the prompt text data 20g can be displayed first. When user A starts speaking during video recording, the user terminal 20a can collect the user voice corresponding to the user A, and the client of the video application installed on the user terminal 20a can transmit the user voice to the background server 20j of the video application and send a voice matching command to the background server 20j. After receiving the user voice and the voice matching command, the background server 20j can convert the user voice into user voice text, and if the user voice text is Chinese (in this case, the prompt text data 20g may also be defaulted to be Chinese), the background server 20j can also convert the user voice text into a first Chinese pinyin (when the user voice text is Chinese, the first syllable information may be called the first Chinese pinyin), of course, after User A inputs the prompt text data 20g into the text input area, the video application client can also transmit the prompt text data 20g to the background server 20j, so that the background server 20j can convert the prompt text data 20g into a second Chinese pinyin (when the user voice text is Chinese, the second syllable information may be called the second Chinese pinyin).The background server 20j can match the first Chinese pinyin with the second Chinese pinyin, search for the same pinyin as the first Chinese pinyin in the second Chinese pinyin, i.e., search for the text position of the first Chinese pinyin in the second Chinese pinyin, and determine the text corresponding to the text position in the prompt text data 20g as the target text (i.e., the text matching the user voice in the prompt text data 20g), and the background server 20j can transmit the target text to the video application client, and the terminal device 20a can mark the target text in the video application (for example, increase the display size of the target text, change the display color of the target text, surround the target text with a circle or a rectangular box, etc.). Here, it should be understood that when User A speaks according to the order of the text prompt data, the prompt text data can be scrolled on the recording page, and when User A does not release the text prompt data according to the order of the text prompt data, the prompt text data can be jumped on the recording page.

[0024] If the target text is a word or phrase, the phrase in which the target application exists can be marked in the video application. As shown in Fig. 2, if the user voice is "weekend", the background server 20j can match the target text corresponding to the user voice in the prompt text data 20g to weekend, in this case, the phrase "Attend a consumer class jointly held by xx and xx in Changsha this weekend" in which the target text "weekend" exists can be marked in the recording page (the text display size is increased and the text is made bold, as shown in the area 20k in Fig. 2).

[0025] The prompt text data 20g may be directly displayed on the recording page, or may be displayed on an independent sub-page displayed on the recording page, and it should be understood that the present application does not limit the display form of the prompt text data 20g on the recording page. The purpose of matching the user voice in the prompt text data 20g is as follows: when determining the text position of the user voice in the prompt text data 20g and converting the user voice into a user voice text, only the consistency between the character pronunciation and the user voice needs to be considered, not the accuracy between the converted user voice text and the user voice, so that matching can be performed by Chinese audio, thereby improving the matching efficiency between the user voice and the prompt text data.

[0026] The user terminal 20a collects the user voice of the user A in real time, determines the target text corresponding to the user voice in the prompt text data 20g in real time through the background server 20n, and scrolls and displays the prompt text data according to the progress of the user voice. For example, when the user A speaks the first phrase in the prompt text data 20g, the first phrase in the prompt text data 20g is marked on the recording page, and when the user A speaks the second phrase in the prompt text data 20g, the first phrase in the prompt text data 20g is switched to the second phrase in the recording page and the second phrase is marked, and the target text marked each time on the recording page is the content spoken by the user A. When the user A speaks the last character in the prompt text data 20g, the user terminal 20a ends the video recording and determines the currently recorded video as the completed video. If the user A is satisfied with the currently recorded video, he / she can save the video, and if he / she is not satisfied with the currently recorded video, he / she can re-record it. Of course, User A can perform editing optimization on the completed video to obtain the final video recording, that is, the target video data.

[0027] During the video recording shown in the embodiment of the present application, prompt text data can be displayed according to the progression of the user's voice, thereby realizing an accurate teleprompter effect for the user and further improving the quality of the video recording.

[0028] Referring to Fig. 3, Fig. 3 is a flow diagram of a data processing method provided in an embodiment of the present application. Here, the data processing method can be executed by a computer device, and the computer device can be a user terminal, an independent server, a cluster composed of multiple servers, a system composed of a user terminal and a server, or a computer program application (including program code), and it can be understood that there is no specific limitation here. As shown in Fig. 3, the data processing method can include the following S101 to S103.

[0029] In S101, in response to a service start operation in the video application, a video recording service in the video application is started.

[0030] When a user wants to convey his / her viewpoint or show his / her life in front of the camera, he / she can record a video in the video application to record a desired video, and finally upload and share the recorded video to the information posting platform so that the user in the information posting platform can view the video. In the embodiment of the present application, the user who needs to record a video is called a target user, and the device used by the target user to record the video is called a computer device. When the target user performs a service start operation for a video recording service in the video application installed in the computer device, the computer device starts the video recording service in the video application in response to the service start operation in the video application, that is, starts the video recording in the video application. Note that the service start operation includes, but is not limited to, contact-type trigger operations such as single click, double click, long press, touch on the screen, and non-contact-type trigger operations such as voice, remote control, and gesture.

[0031] Before the computer device launches the video recording service, the target user can also upload prompt text data required for the video recording service to the video application, and the prompt text data is used to present to the target user in the video recording service, thereby greatly reducing the situation where the target user forgets words during video recording. After the target user opens the video application installed on the computer device, he enters a shooting page in the video application (for example, shooting page 20m in the embodiment corresponding to the above FIG. 2), and the shooting page of the video application may include a teleprompter shooting entry. When a target user performs a trigger operation on a teleprompter shooting entry on the shooting page, the computer device can display a recording page including a text input area for editing text content in the video application in response to the trigger operation on the teleprompter shooting entry in the video application, and the computer device can display prompt text data determined by the information editing operation in the text input area in response to an information editing operation on the text input area, and when the prompt character number corresponding to the prompt text data is greater than a quantity threshold (here, the quantity threshold may be preset according to actual needs, for example, the quantity threshold may be set to 100), display the prompt character number and the video estimated length corresponding to the prompt text number in the text input area.In other words, after the target user performs a trigger operation on the teleprompter shooting entry on the shooting page, the video application switches the shooting page to the recording page, and the target user can edit the script content (i.e., the above-mentioned prompt text data) required for the video recording service in the text input area of ​​the recording page. When editing text in the text input area, the number of prompt characters input in the text input area can be counted in real time, and when the number of prompt characters is greater than a preset quantity threshold, the number of prompt characters and the video estimated length corresponding to the currently input prompt text data can be displayed in the text input area. The teleprompter shooting entry may be displayed on any one page of the video application in addition to the shooting page, and the embodiment of the present application does not limit the display position of the teleprompter shooting entry.

[0032] The estimated video length may be used as a reference for the length of the finished video to be recorded in the subsequent video recording service, and if the estimated video length displayed in the text input area is significantly different from the length of the recorded video desired by the target user, the target user may increase or decrease the text in the text input area. For example, if the estimated video length displayed in the text input area is 35 seconds, but the length of the recorded video desired by the target user is 2 minutes, the target user may continue to edit the text in the text input area until the estimated video length displayed in the text input area falls within a predetermined length range (for example, the estimated video length is between 1 minute 50 seconds and 2 minutes 10 seconds).

[0033] After the computer device responds to a trigger operation on a teleprompter shot entry in the video application, a text upload control may be further displayed on the displayed recording page, and the target user may perform a trigger operation on the text upload control on the recording page to upload edited prompt text data to the recording page, that is, in response to the trigger operation on the text upload control, the computer device may determine the text content uploaded on the recording page as prompt text data, display the prompt text data in the text input area of ​​the recording page, and further display the prompt character number corresponding to the prompt text data and the estimated video length corresponding to the prompt text data. Note that the text upload control may include, but is not limited to, a text paste control and a previous text selection control. When the target user performs a trigger operation on the text pasting control, it indicates that there is no need to provisionally edit the text content and the target user can directly paste the pre-edited prompt text data into the text input area; when the target user performs a trigger operation on the previous text selection control, it indicates that the target user can use the prompt text data from the previous video recording service in the current video recording service, that is, the target user may not be satisfied with the finished video recorded in the previous video recording service, so will record it again in the current video recording service, thereby avoiding duplicate input of the same prompt text data and further improving the input efficiency of prompt text data.

[0034] Also refer to FIG. 4, which is a schematic diagram of an interface for inputting prompt text data provided in an embodiment of the present application. As shown in FIG. 4, after the target user performs a trigger operation on a shooting entry in a video application installed in a user terminal 30a, the user terminal 30a can display a shooting page 30g in the video application in response to the trigger operation on the shooting entry (in this case, the user terminal 30a can be the above-mentioned computer device), and the shooting page 30g may include a shooting area 30b, a filter control 30c, a shooting control 30d, a beautification control 30e, and a teleprompter shooting entry 30f, etc. Note that the function descriptions of the shooting area 30b, the filter control 30c, the shooting control 30d, and the beautification control 30e in the video application can be referred to the function descriptions of the shooting area 20b, the filter control 20c, the shooting control 20d, and the beautification control 20e in the embodiment corresponding to the above FIG. 2, and are not described here in detail.

[0035] When the target user performs a trigger operation on the teleprompter shooting entry 30f on the shooting page 30g, the user terminal 30a can switch the shooting page 30g to a recording page 30h in the video application in response to the trigger operation on the teleprompter shooting entry 30f on the shooting page 30g, and the recording page 30h may include a text input area 30i for directly editing text content. The target user can click the text input area 30i to pop up a keyboard 30p on the recording page 30h, and edit the prompt text data required for the current video recording service through the keyboard 30p, and the user terminal 30a can display the text content determined by the information editing operation as prompt text data in the text input area 30i in response to the information editing operation of the target user. At the same time, the user terminal 30a can perform real-time statistics on the number of prompt characters of the prompt text data entered in the text input area 30i, and when the number of prompt characters of the prompt text data entered in the text input area 30i is greater than a preset quantity threshold (e.g., the quantity threshold is set to 100), the number of prompt characters and the estimated finished product length (i.e., the estimated video length) corresponding to the entered prompt text data can be displayed in the area 30m of the text input area 30i.As shown in FIG 4, the target user can send a message saying, "I will attend a consumer class jointly hosted by xx and xx in Changsha this weekend.When the text content "At that time, others did it online through their official accounts" is input in the text input area 30i, the prompt character count obtained by the user terminal 30a is 32, and the estimated finished product length is 15 seconds, i.e., "The current character count is 32, and the estimated finished product length is 15 seconds" is displayed in the area 30m, and the target user can edit the text content based on the estimated finished product length displayed in the area 30m. After the target user completes editing the text content in the text input area 30i, the text content in the text input area 30i is determined as the prompt text data, and then a trigger operation can be performed on the "Next" control 30n on the recording page 30h to trigger the next operation of the video recording service on the user terminal 30n.

[0036] 4, the text input area 30i may further include a text paste control 30j and a previous text control 30k, and when the target user performs a trigger operation on the text paste control 30j, it indicates that the target user has edited prompt text data in another application and copied the prompt text data from the other application, and the user terminal 30a pastes the prompt text data copied by the target user into the text input area 30i in response to the trigger operation on the text paste control 30j. If the video recorded by the target user in the current video recording service is a re-recorded video recorded in the previous video recording service, the target user can perform a trigger operation on the previous text control 30k, and the user terminal 30a obtains the prompt text data in the previous video recording service and displays the prompt text data in the previous video recording service in the text input area 30i in response to the trigger operation on the previous text control 30k, and the prompt text data used in the previous video recording service is directly used as the prompt text data of the current video recording service. The target user can adjust the prompt text data used in the previous video recording service in the text input area 30i based on the experience with the previous video recording service; for example, if the target user discovers that there is a logical error in phrase 1 in the prompt text data in the previous video recording service, the target user can modify the prompt text data of the previous video recording service in the text input area 30i in the current video recording service.

[0037] Here, the prompt text data entered into the text input area 30i by the text paste control 30j and the previous text control 30k is similarly displayed in the area 30m of the text input area 30i, including the number of characters of the prompt text data and the estimated finished length. In the embodiment of the present application, the target user can use the text paste control 30j and the previous text control 30k to enter the prompt text data in the video recording service into the text input area 30i, thereby improving the efficiency of entering the prompt text data in the video recording service.

[0038] If the service activation operation is a voice-activated operation, the target user can perform a voice-activated operation on a video recording service in the video application after completing the editing operation of the prompt text data, and the computer device can display a recording countdown animation associated with the video recording service on the recording page of the video application in response to the voice-activated operation, and when the recording countdown animation ends, the computer device can launch and execute the video recording service in the video application, i.e., officially start video recording. When the recording countdown animation is played on the recording page, a shooting device corresponding to the computer device can be turned on, and the target user can adjust the position of himself and the computer device according to the video screen displayed on the recording page to find the best shooting angle. The recording page may further display an animation cancel control corresponding to the recording countdown animation, and the target user can cancel the recording countdown animation by canceling the execution of a control trigger operation on the animation after completing the preparation for video recording, i.e., the computer device can cancel the display of the recording countdown animation on the recording page and launch and execute the video recording service in the video application in response to the target user's trigger operation on the animation cancel control. In other words, after the target user activates the video recording service by voice, the video application does not directly enter the formal recording mode, but plays the recording countdown animation on the recording page to provide the target user with a short recording preparation time (i.e., the length of the recording countdown animation, for example, 5 seconds), and enters the formal recording mode after the recording countdown animation is completed. Or, if the target user is ready to record, he or she can cancel the display of the countdown animation and directly enter the formal recording mode.

[0039] Also refer to Fig. 5, which is an interface schematic diagram of launching a video recording service in a video application provided in an embodiment of the present application. After completing the editing operation of the prompt text data, the target user can perform a next operation (for example, perform a trigger operation on the "Next" control 30n in the embodiment corresponding to Fig. 4 above) to end the display of the text input area in the recording page. As shown in FIG. 5, after the target user completes editing the prompt text data and performs the following operation, the text input area in the recording page 40b can be closed, and the video screen of the target user can be displayed in the area 40c of the recording page 40b, and the prompt information 40d ("Put your mobile phone in the appropriate position and say 'start' to start teleprompter shooting") can be displayed on the recording page 40b; that is, before starting the video recording service, the user terminal 40a (in this case, the user terminal 40a can be called a computer device) can start the shooting device associated therewith (e.g., the camera of the user terminal 40a), collect image data of the target user, render the collected image data on a video screen corresponding to the target user, and display the video screen of the target user in the area 40c of the recording page 40b. The target user can adjust his / her position and the camera position according to the video screen displayed in the area 40c to find the best shooting angle.

[0040] After the target user adjusts his / her position and the camera position, that is, after completing the preparation work for video recording, he / she can say "start" to start the video recording service in the video application. After the target user says "start" and performs a voice-activated operation for the video recording service in the video application, the user terminal 40a can display a recording countdown animation in the area 40e of the recording page 40b in response to the voice-activated operation for the video recording service, and the length of the recording countdown animation is 5 seconds. Of course, the first few sentences of the prompt text data (e.g., the first two sentences of the prompt text data) may also be displayed in the area 40e of the recording page 40b.

[0041] When the playback of the recording countdown animation on the recording page 40b is completed, the user terminal 40a can launch and execute the video recording service in the video application. If the target user wants to launch the video recording service before the playback of the recording countdown animation is completed, the target user can click the animation cancel control on the recording page 40b. 40f, a trigger operation can be performed to cancel the recording countdown animation on the playback and recording page 40b, and directly start and run the video recording service. After the official video recording is started, the target user starts to speak, and the user terminal 40a can collect the user voice of the target user, search for the target text matching the user voice from the prompt text data, and mark the target text in the area 40g of the recording page 40b (for example, perform bold and enlargement processing on the target text), and the specific process of determining the target text will be described in the following S102.

[0042] In S102, collect a user's voice in the video recording service, determine a target text matching the user's voice in prompt text data associated with the video recording service, and mark the target text.

[0043] After the formal video recording is started, the computer device can activate the audio collection function to collect the user's voice in the video recording service of the target user, search for target text matching the user's voice in the prompt text data, and mark the target text included in the prompt text data on the recording page. The computer device can collect the user's voice in the video recording service of the target user in real time, perform text conversion on the user's voice to determine the text position corresponding to the user's voice in the prompt text data, determine the target text corresponding to the user's voice based on the text position, and mark the target text on the recording page. The marking child includes, but is not limited to, the display color of the text, the font size of the text, and the background of the text, and the target text can be text data containing the user's voice text, for example, the user's voice text is New Year, in this case the target text can be a complete phrase containing "New Year", for example, wishing you a happy New Year in the coming Year of the Ox.

[0044] The voice directly collected by the computer device is called the user's initial voice. That is, the computer device collects the user's initial voice in the video recording service, and performs voice activity detection (Voice Activity Detection) on the user's initial voice. The computer device can perform a voice activity detection (VAD) to obtain valid voice data in the user initial voice, and determine the valid voice data as the user voice. The computer device can then convert the user voice into a user voice text, and perform text matching between the user voice text and the prompt text data associated with the video recording service to determine a target text matching the user voice text in the prompt text data, and mark the target text on the recording page of the video recording service. In other words, since the user initial voice collected by the computer device may include noise in the environment where the target user exists and pauses in the target user's conversation, the computer device can perform a voice activity detection on the user initial voice to remove the silence and noise in the user initial voice as interference information, and reserve the valid voice data in the user initial voice, in which case the valid voice data may be referred to as the user voice of the target user. The computer device can convert the user voice into a user voice text through a fast speech-to-text model, compare the user voice text with the prompt text data, search for the text position of the user voice text in the prompt text data, and further determine a target text corresponding to the user voice in the text data based on the text position, and mark the target text on the recording page of the video recording service.

[0045] The fast speech-to-text model refers to the process of converting user speech into text, which does not require error correction for the context and does not require consideration of whether semantics are accurate, but only requires determining whether the converted text pronunciation matches the user speech. When determining a target text matching the user speech in the prompt text data, the computer device can determine a target text corresponding to the user speech in the prompt text data based on the pronunciation of the user speech text and the pronunciation of the prompt text data. That is, the computer device can obtain first syllable information corresponding to the user speech text and second syllable information corresponding to the prompt text data associated with the video recording service, obtain target syllable information that is the same as the first syllable information from the second syllable information, and determine a target text corresponding to the target syllable information in the prompt text data.

[0046] The syllable information may be Chinese pinyin information, English phonetic symbol information, etc. If the prompt text data is Chinese, the computer device can convert the user speech text into first pinyin information, convert the prompt text data into second pinyin information, find a text location corresponding to the first pinyin information from the second pinyin information, and determine a target text corresponding to the user speech in the prompt text data based on the text location. If the prompt text data is in another language, such as English, the computer device can convert the user speech text into first phonetic symbol information, convert the prompt text data into second phonetic symbol information, and further determine a target text corresponding to the user speech in the prompt text data based on the first phonetic symbol information and the second phonetic symbol information. For Chinese, the same pronunciation corresponds to different characters, so the efficiency of determining the target text can be improved by a pinyin matching manner, and for a language (e.g., English) in which different pronunciations correspond to different characters, the computer device can directly match the characters included in the user speech text with the characters included in the prompt text data to determine a target text corresponding to the user speech in the prompt text data.

[0047] Here, in the video recording service, the area for displaying the target text in the recording page can be set based on the size of the terminal screen of the computer device. For example, the area 40g in the recording page 40b shown in FIG. 5 above has a display width similar to the screen width of the computer device (e.g., the user terminal 40a) and a display height smaller than the height of the screen of the computer device. When the terminal screen size of the computer device is large (e.g., the display of a desktop computer), if the size width of the area for displaying the target text is similar to the size width of the terminal screen of the computer device, in the video recording service, the target user's action of viewing the target text (e.g., the target user's movement from the left side to the right side of the terminal screen when viewing the target text) is recorded, so that in the final video recording, both the target user's actions and facial expressions are unnatural, and the quality of the video recording is too low. Therefore, in order to ensure that the target user's actions and facial expressions are natural in the video recording, a text prompt area corresponding to the target text can be determined in the recording page of the video recording service based on the position of the photographing device corresponding to the computer device, and the target text can be marked in the text prompt area based on the text position of the target text in the prompt text data. In other words, in the video recording service, when the target user faces the camera and the text prompt area and the camera of the computing device are located in the same orientation, the target user's movements are natural in the video recorded by the video recording service.

[0048] Also refer to FIG. 6, which is a schematic diagram of an interface for displaying prompt text data provided in an embodiment of the present application. As shown in FIG. 6, after the user terminal 50a (i.e., the above-mentioned computer device) determines the target text corresponding to the user voice in the prompt text data, "Participate in the consumer class jointly hosted by xx and xx in Changsha on the weekend", it can determine the text prompt area 50e for displaying the target text in the recording page 50b of the video recording service according to the position of the camera 50d of the terminal device 50a, and the text prompt area 50e is located in the same direction as the camera 50d. After the official video recording is started, the target user's video screen may be displayed in the area 50c of the recording page 50b, and the video recording length may be displayed in the area 50f of the recording page 50b (for example, the video recording length is 00:13 seconds).

[0049] In the video recording service, the computer device can collect the user's initial voice of the target user in real time, obtain the voice length corresponding to the user's initial voice and the number of voice characters contained in the user's initial voice, and determine the ratio of the number of voice characters and the voice length as the user's speaking speed, and when the user's speaking speed is greater than a speaking speed threshold (the speaking speed threshold may be artificially set according to actual needs, for example, the speaking speed threshold is 500 characters / 1 minute), display speaking speed prompt information on the recording page, and the speaking speed prompt information is used to present to the target user associated with the video recording service to reduce the user's speaking speed. In other words, the computer device can obtain the user's speaking speed of the target user in real time, and when the user's speaking speed is greater than the speaking speed threshold, it may indicate that the target user's speaking speed in the video recording service is too fast, and prompt the target user to appropriately reduce the speaking speed.

[0050] Also refer to FIG. 7, which is a schematic diagram of an interface for displaying speech speed prompt information provided in the embodiment of the present application. As shown in FIG. 7, the user terminal 60a (i.e., the above-mentioned computer device) can determine the user's speech speed of the target user according to the number of voice characters and the voice length contained in the user's initial voice after collecting the user's initial voice of the target user, and when the user's speech speed in the video recording service of the target user is too fast (i.e., larger than the speech speed threshold), the speech speed prompt information 60c (for example, the speech speed prompt information is "current speech speed is too fast, please slow down your speech speed to ensure the quality of video recording") can be displayed on the recording page 60b of the video recording service. Of course, in practical application, the target user can be prompted to slow down his / her speech speed by voice broadcast, but the embodiment of the present application does not limit the display form of the speech speed prompt information.

[0051] During video recording, the recording page of the video recording service may further include a cancel recording control and a complete recording control. After the target user performs a triggering operation on the cancel recording control on the recording page, the computer device can cancel the video recording service in response to the triggering operation on the cancel recording control, delete the video data recorded by the video recording service, and generate recording prompt information for the video recording service, and display the recording prompt information on the recording page, where the recording prompt information may include a re-recording control. After the target user performs a triggering operation on the re-recording control, the computer device can switch the target text displayed on the recording page to prompt text data in response to the triggering operation on the re-recording control, i.e., display the prompt text data in the text input area of ​​the recording page, and restart the video recording service. Of course, the recording prompt information may further include a home page return control, and when the target user performs a triggering operation on the home page return control, the computer device can switch the recording page to the application home page in the video application in response to the triggering operation on the home page return control, i.e., after canceling the running video recording service, not start the video recording service for a while.

[0052] After the target user performs a trigger operation on the recording completion control on the recording page, the computer device can stop the video recording service in response to the trigger operation on the recording completion control, and determine the video data recorded by the video recording service as the target video data whose recording has been completed, that is, if the presentation of the prompt text data has not yet been completed, the video recording service is stopped, and the video recorded before the video recording service is stopped is called the target video data.

[0053] Also refer to FIG. 8, which is a schematic diagram of an interface for stopping a video recording service provided in an embodiment of the present application. As shown in FIG. 8, the user terminal 70a (i.e., the above-mentioned computer device) can determine a target text of the user voice in the prompt text data of the video recording service based on the user voice of the target user in the video recording service, and mark the target text in the recording page 70b, that is, the user terminal 70a can scroll and display the prompt text data according to the progress of the user voice. During video recording, a recording cancel control 70c and a recording completion control 70d may be further displayed on the recording page 70b. When the target user performs a trigger operation on the recording completion control 70d, the user terminal 70a can stop the video recording service in response to the trigger operation on the recording completion control 70d, and save the video data recorded in the current video recording service, that is, complete the current video recording service. When the target user performs a trigger operation on the cancel recording control 70c, the user terminal 70a can cancel the video recording service and delete the video data recorded in this video recording service in response to the trigger operation on the cancel recording control 70c, and the user terminal 70a generates recording prompt information 70e for the target user in the video recording service (for example, the recording prompt information may be "The recorded segment has been cleared, do you want to re-shoot the segment?") and displays the recording prompt information 70e on the recording page 70b of the video recording service. The recording prompt information 70e may include a "return to home page" control and a "re-shoot" control, and when the target user performs a trigger operation on the "return to home page" control, the user terminal 70a can end the video recording service and return to the application home page of the video application from the recording page 70b. That is, the target user stops re-shooting.When the target user performs a trigger operation on the “Retake” control, the user terminal 70a can terminate the video recording service and return to the text input area from the recording page 70b, and display prompt text data in the text input area, i.e., the target user selects to re-record the video.

[0054] In S103, if the text position of the target text in the prompt text data is the end position of the prompt text data, the target video data corresponding to the video recording service is obtained.

[0055] In the video recording service, when the text position of the target text in the prompt text data is the end position of the prompt text data, it indicates that the target user has completed the shooting work of the video recording service, and no operation of the target user is required, the computer device automatically ends the video recording service, saves the video data recorded by the video recording service, and determines the video data recorded by the video recording service as the target video data.

[0056] The computer device can determine the video data saved when the video recording service is stopped as original video data, enter the editing page of the video application, and display the original video data and the editing optimization control corresponding to the original video data on the editing page of the video application. The target user can perform a trigger operation on the editing optimization control displayed on the editing page, in this case, the computer device can display M editing optimization methods for the original video data in response to the trigger operation on the editing optimization control, where M is a positive integer, that is, M can take 1, 2, . . . In the embodiment of the present application, the M editing optimization methods can include, but are not limited to, an editing optimization method for removing slip-ups (which may be referred to as a first editing method), an editing optimization method for removing slip-ups and pauses between phrases (which may be referred to as a second editing method), and when the target user selects an editing optimization method from the M editing optimization methods, the computer device can perform an editing optimization process on the original video data according to the editing optimization method determined by the selection operation in response to the selection operation on the M editing optimization methods, to obtain target video data corresponding to the video recording service. It should be understood that the display area and display size of the original video data and the target video data on the editing page may be adjusted according to actual needs, for example, the display area of ​​the original video data (or the target video data) may be located at the top, bottom, middle area, etc. of the editing page, and the display size of the original video data (or the target video data) may have a display ratio of 16:9, etc.

[0057] The editing optimization manner determined by the selection operation is a first editing manner, that is, when the target user selects the editing optimization manner of removing mispronunciations, the computer device obtains the target voice data included in the original video data, converts the target voice data into a target text result, and performs a text comparison between the target text result and the prompt text data to determine the text different from the prompt text data in the target text result as an error text, and deletes the voice data corresponding to the error text from the original video data to obtain the target video data corresponding to the video recording service. In the process of performing the editing optimization process on the original video data, the computer device can use an accurate speech-to-text model to perform a text conversion process on the target voice data included in the original video data, and the accurate speech-to-text model can learn semantic information in the target voice data, and not only the consistency between the converted text pronunciation and the user voice, but also the semantic information between the user voice needs to be taken into account, and the converted text is corrected for errors according to the context semantic information. The computer device performs voice activity detection on the target voice data included in the original video data to remove noise and silence in the original video data to obtain effective voice data in the original video data, and performs text conversion on the effective voice data using an accurate speech-to-text conversion model to obtain a target text result corresponding to the target voice data, and compares the characters included in the target text result with the characters included in the prompt text data one by one, and further determines the different text between the target text result and the prompt text data as an error text, where the error text may be generated by the target user's misunderstanding in recording the video recording service. The computer device removes the voice data corresponding to the error text from the original video data to obtain a final target video data.

[0058] The editing optimization manner determined by the selection operation is the second editing manner, that is, when the target user selects the editing optimization manner of removing slip-ups and pauses between phrases, the computer device can convert the target voice data included in the original video data into a target text result, and determine the text in the target text result that is different from the prompt text data as error text, and further divide the target text result into N text characters to respectively obtain timestamps of the N text characters in the target voice data, where N is a positive integer, for example, N can be 1, 2, ..., and the computer device can determine voice pause segments in the target voice data according to the timestamps, and delete the voice data corresponding to the voice pause segments and the error text from the original video data to obtain the target video data corresponding to the video recording service. For the process of the computer device determining the error text, the description of selecting the first editing manner above can be referred to, and will not be described in detail here.

[0059] The process of the computer device obtaining the audio pause segment can include the following: the computer device performs a word segmentation process on the target text result corresponding to the target audio data to obtain N text characters and a timestamp of each text character in the target audio data, i.e., a timestamp in the original video data, and obtains a time interval between two adjacent text characters according to a timestamp corresponding to each two adjacent text characters among the N text characters, and if the time interval between the two adjacent text characters is greater than a time length threshold (for example, the time length threshold may be set to 1.5 seconds), the audio segment between the two adjacent text characters can be determined as an audio pause segment, and the number of the audio pause segments can be one, more than one, or even zero (i.e., there is no audio pause segment). For example, according to the arrangement order in the target text result, the N text characters can be represented as text character 1, text character 2, text character 3, text character 4, text character 5, and text character 6, the timestamp of the text character 1 in the original video data is t1, the timestamp of the text character 2 in the original video data is t2, the timestamp of the text character 3 in the original video data is t3, the timestamp of the text character 4 in the original video data is t4, the timestamp of the text character 5 in the original video data is t5, and the timestamp of the text character 6 in the original video data is t6, if the computer device calculates that the time interval between the text character 2 and the text character 3 is greater than the time length threshold, it determines the voice segment between the text character 2 and the text character 3 as the voice pause segment 1, and if the time interval between the text character 5 and the text character 6 is greater than the time length threshold, it determines the voice segment between the text character 5 and the text character 6 as the voice pause segment 2.The final target video data can be obtained by deleting the audio corresponding to the error text, and the video segments corresponding to the audio pause segment 1 and the audio pause segment 2 from the original video data.

[0060] Also refer to Fig. 9, which is a schematic diagram of an interface for performing editing optimization on video recording provided in an embodiment of the present application. As shown in Fig. 9, after the video recording service is completed, the user can enter the editing page 80b of the video application, and preview the video data 80c (such as the above original video data) recorded by the video recording service in the editing page 80b, the video data 80c may be displayed on the editing page 80b according to the ratio of 16:9, and a time axis 80d corresponding to the video data 80c is displayed on the editing page 80b, and the time axis 80d may include video nodes in the video data 80c, and the target user can quickly locate the playback point in the video data 80c according to the video nodes in the time axis 80d. An edit optimization control 80e (which may also be referred to as an edit optimization option button) may further be displayed on the edit page 80b, and when the target user performs a trigger operation on the edit optimization control 80e, the user terminal 80a (i.e., a computing device) pops up a selection page 80f on the edit page 80b in response to the trigger operation on the edit optimization control 80e (in an embodiment of the present application, the selection page may be a certain area on the edit page, a sub-page displayed independently on the edit page, a floating page on the edit page, or a page covering the edit page, but the display form of the selection page is not limited here).

[0061] In the selection page 80f, different editing optimization methods for the video data 80c and the video lengths corresponding to the different editing optimization methods can be displayed. As shown in FIG. 9, if the target user selects "remove mispronunciations" (i.e., the first editing method described above) in the selection page 80f, the video length of the video data 80c after editing optimization is 57 seconds (the video length of the video data 80c is 60 seconds); if the target user selects "remove mispronunciations and pauses between phrases" (i.e., the second editing method described above) in the selection page 80f, the video length of the video data 80c after editing optimization is 50 seconds; if the target user does not perform any processing in the selection page 80f, the video data 80c will be retained as it is and will not be processed. If the target user selects the optimization editing mode of “removing the mispronunciations”, the user terminal 80a can perform a text conversion process on the target voice data in the video data 80c to obtain a target text result corresponding to the target voice data, perform character matching on the target text result and the prompt text data to determine the error text, and delete the voice data corresponding to the error text in the video data 80c to obtain the target video data, where the target video data is the video data from which the mispronunciations have been deleted. If the target user selects the optimization editing mode of “removing the mispronunciations and pauses between phrases”, the user terminal 80a can delete the voice data corresponding to the error text from the video data 80c and the voice pause segments in the video data 80c to obtain the target video data, where the target video data is the video data from which the mispronunciations and pauses between phrases have been deleted. After obtaining the target video data, the target user can save the target video data or upload the target video data to the information disclosure platform so that the user terminal in the information disclosure platform can view the target video data.

[0062] The above error text may include K error subtexts, where K is a positive integer, for example, K may take values ​​of 1, 2, ..., and the computer device may determine an error frequency in the video recording service based on the K error subtexts and the length of the video corresponding to the original video data, and when the error frequency is greater than an error threshold (for example, the error threshold may be set to 2 errors per minute), recognize a speech error type corresponding to each of the K error subtexts, and further push a tutorial video associated with the speech error type in the video application to a target user associated with the video recording service. In other words, the computer device may recommend a corresponding tutorial video in the video application to the target user based on the speech error type corresponding to the error text, and the speech error type may include, but is not limited to, common words not standard, pronunciation error, and unclear pronunciation. For example, if the video duration of the original video data is 1 minute, and the target user encounters three errors in the original video data, the computer device can determine the speech error types of the error subtexts corresponding to the three errors, and if the speech error type is a non-standard common language type, the computer device can push a common language tutorial video to the target user in the video application; if the speech error type is a pronunciation error type, the computer device can push a Chinese language tutorial video to the target user in the video application; and if the speech error type is an unclear pronunciation type, the computer device can push a dubbed tutorial video to the target user in the video application.

[0063] Also refer to Fig. 10, which is a schematic diagram of an interface for recommending tutorial videos based on speech error types provided in an embodiment of the present application. As shown in Fig. 10, assuming that a target user selects an editing optimization method of "remove mispronunciations", an editing optimization is performed on the original video data recorded in the video recording service to obtain a target video data 90c after editing optimization (i.e., a recorded video with mispronunciations removed), and the user terminal 90a (i.e., the above-mentioned computer device) can display the target video data 90c on an editing page 90b, and further display a time axis 90d on the editing page 90b, where the time axis 90d can include video nodes associated with the target video data 90c, and a specific time point in the target video data 90c can be located and played by triggering the video nodes on the time axis 90d, and the target user can preview the target video data 90c on the editing page 90b. Based on the speech error type corresponding to the error text in the editing optimization process, the user terminal 90a can push a tutorial video matching the speech error type to the target user in the video application. As shown in FIG. 10, if the speech error type corresponding to the error text is a type in which common language is not standard, that is, the cause of the misunderstanding is that common language is not standard, the user terminal 90a can obtain a tutorial video for common language video teaching (i.e., a common language tutorial video) from the video application and display the pushed common language tutorial video in area 90e of the editing page 90b.

[0064] Please refer to Fig. 11, which is a flowchart of the implementation of the video recording service provided in the embodiment of the present application. As shown in Fig. 11, the implementation process of the video recording service is described by taking a video application client and a background server as an example, where the client and the background server may be referred to as computer devices, and the implementation flow of the video recording service is realized by the following S11 to S25.

[0065] In S11, prompt text data is input. That is, the target user can open the video application client, enter the client's shooting page, and enter the recording page from the teleprompter shooting entry of the shooting page, where the recording page may include a text input area, and the target user can input the prompt text data in the text input area. After the prompt text data editing is completed, the target user can execute S12 to activate "start" by voice, that is, "start" can be the wake word, and when the target user says "start", the client can execute S13 in response to the user's voice activation operation to start the video recording service, that is, start to enter the recording mode.

[0066] In S14, after entering the recording mode, the target user can read the text on the screen (the screen is the screen of the terminal device on which the client is installed, in this case, the text on the screen of the terminal device may be a part of the text content in the prompt text data, for example, when entering the recording mode, the text displayed may be the first two words in the prompt text data), and the client can collect the user initial voice of the target user, transmit the user initial voice to a background server of the video application, and send a text conversion command to the background server. After receiving the user initial voice and the command sent by the client, the background server can execute S15 to detect the user initial voice by a voice activity detection technique (VAD technique), remove noise and silence in the user initial voice, and obtain the user voice (i.e., valid voice data) corresponding to the target user. Here, S15 may be executed by the client through a local voice activity detection module, or the background server may execute using the VAD technique.

[0067] In S16, the background server can convert the user voice into characters (i.e., user voice text) by using a fast character conversion model to perform text conversion on the user voice. Then, execute S17 to convert the user voice text into pinyin (characters) (in the embodiment of this application, the text prompt data is Chinese by default). Furthermore, execute S18, the background server can obtain the prompt text data input by the target user, convert the prompt text data into pinyin, and match the pinyin of the user voice text with the pinyin of the prompt text data. Then, execute S19 to find the character position matching the user voice in the prompt text data, and send the character position of the user voice in the prompt text data to the client.

[0068] In S20, after receiving the character position transmitted by the background server, the client can determine a target text corresponding to the user's voice according to the character position, and mark the target text on the recording page of the client, that is, the prompt text data can be scrolled according to the character position, and when the target user reads the last character of the prompt text data, the client can execute S21 to end the video recording service. Of course, the target user can also trigger the recording completion control or the recording cancellation control on the recording page to end the video recording service.

[0069] When the video recording service is completed, the client can transmit the recorded video corresponding to the video recording service (i.e., the above-mentioned original video data) to the background server and send a text conversion command to the background server. After receiving the text conversion command, the background server can execute S22 to convert the voice data included in the recorded video into text (i.e., the target text result) by using an accurate text conversion model to perform text conversion on the voice data included in the recorded video, and obtain the appearance time of the characters in the video recording, in other words, the timestamp of the characters in the video recording. In this case, the background server can execute S23 and S24 in parallel.

[0070] In S23, the background server can compare the target text result with the prompt text data to find the slip-up portion in the video recording (i.e., the voice data corresponding to the above error text). In S24, the background server can find the pause portion in the user voice included in the recorded video according to the appearance time (i.e., the timestamp) of the text in the recorded video. The background server can transmit both the slip-up portion and the pause portion in the recorded video to the client. After receiving the slip-up portion and the pause portion transmitted by the background server, the client can execute S25, and provide different editing optimization methods to the target user in the client according to the slip-up portion and the pause portion, and the target user can select an appropriate editing optimization method from the multiple editing optimization methods provided in the client, and the client can perform editing optimization on the recorded video according to the editing optimization method selected by the target user to obtain the final target video data.

[0071] In an embodiment of the present application, after a user inputs prompt text data into a video application, the user can start a video recording service by voice, and during the recording of the video recording service, a teleprompter function can be provided to the user, and a target text matching the user's voice is located in the prompt text data, and the target text is marked in the video application, that is, the target text displayed in the video application matches the content spoken by the user, which can improve the effectiveness of the text prompt function in the video recording service, reduce the risk of recording failure caused by the user forgetting the words, and further improve the quality of the recorded video. The video recording service can be started and stopped by the user's voice, which can reduce the user's operation in the video recording service and improve the effect of video recording, and after the video recording service is finished, editing optimization can be automatically performed on the video recording in the video recording service, which can further improve the quality of the video recording.

[0072] Please refer to Figure 12, which is a flow diagram of a data processing method provided in an embodiment of the present application. It should be understood that the data processing method can be executed by a computer device, and the computer device may be a user terminal, a stand-alone server, a cluster composed of multiple servers, or a system composed of a user terminal and a server, a computer program application (including program code), and is not specifically limited here. As shown in Figure 12, the data processing method can include the following S201 to S203.

[0073] At S201, prompt text data is uploaded to a teleprompter application.

[0074] The target user can input prompt text data into the teleprompter application, or upload edited prompt text data to the teleprompter application. The computer device can upload prompt text data to the teleprompter application in response to the target user's text input operation or text upload operation. That is, when using the teleprompter function provided by the teleprompter application, it is necessary to upload prompt text data to the teleprompter application. Note that the computer device in the embodiment of the present application refers to a device on which the teleprompter application is installed, and may be called a teleprompter.

[0075] In S202, a user's voice corresponding to a target user is collected, and a user's voice is converted into text to generate a user's voice text corresponding to the user's voice.

[0076] The computer device collects the user initial voice of the target user, performs voice segment detection on the user initial voice, and removes noise and silence contained in the user initial voice to obtain user voice corresponding to the target user (i.e., valid voice data in the user initial voice), and performs text conversion on the user voice to generate user voice text corresponding to the user voice.

[0077] In S203, in the prompt text data, the text that is the same as the user voice text is determined as the target text, and the target text is marked in the teleprompter application.

[0078] The computer device can convert the user voice text into first syllable information, convert the prompt text data into second syllable information, compare the first syllable information with the second syllable information, determine a text position of the user voice text in the prompt text data, determine a target text matching the user voice in the prompt text data according to the text position, and mark the target text in a teleprompter application. For a more detailed description of S202 and S203, please refer to S102 in the embodiment corresponding to FIG. 3 above, and no further description is given here.

[0079] The number of target users may be one or more, and different target users correspond to different prompt text data. When the number of target users is one, the process of determining and displaying the target text in the teleprompter application can refer to S102 in the embodiment corresponding to FIG. 3 above. When the number of target users is more than one, the computer device can collect user voice, perform voiceprint recognition on the user voice, determine a user identity corresponding to the collected user voice according to the voiceprint recognition result, determine a target text corresponding to the user voice in the prompt text data corresponding to the user identity, and mark the target text in the teleprompter application. Voiceprint recognition refers to extracting voiceprint features (such as spectrum, inverse spectrum, formant, fundamental tone, reflection coefficient, etc.) from user voice data and recognizing the voiceprint features to determine a user identity corresponding to the user voice, therefore, voiceprint recognition is also called speaker recognition.

[0080] In the following, the number of target users is two, that is, the target users include a first user and a second user, and the prompt text data includes a first prompt text corresponding to the first user and a second prompt text corresponding to the second user, and the computer device obtains the user voiceprint feature in the user voice, and determines a user identity corresponding to the user voice according to the user voiceprint feature, and if the user identity is the first user, determines a text equal to the user voice text in the first prompt text as a target text, and marks the target text in the teleprompter application, and if the user identity is the second user, determines a text equal to the user voice text in the second prompt text as a target text, and marks the target text in the teleprompter application. In other words, if the number of target users is multiple, it is necessary to first determine a user identity corresponding to the user voice, and then determine a target text matching the user voice in the prompt text data corresponding to the user identity, and mark the target text, so as to improve the effectiveness of the teleprompter function in the teleprompter application.

[0081] Also refer to FIG. 13, which is a schematic diagram of the application scenario of the teleprompter provided in the embodiment of the present application. The data processing process is described by taking the teleprompter scenario of a party as an example. As shown in FIG. 13, the lines 90a (i.e., prompt text data) of the host of the party can be pre-edited and uploaded to the teleprompter (a device in which the above-mentioned teleprompter application exists, which may be understood as providing the function of providing lines to the host). The lines 90a can include the lines of host A and the lines of host B. After receiving the lines 90a, the teleprompter can store the lines 90a in the locale. During the party, the teleprompter can collect the voice data of all the hosts in real time. After collecting the user voice of the host, the teleprompter can perform voiceprint recognition on the user voice and determine the user identity corresponding to the user voice according to the voiceprint recognition result. If the user status of the collected user voice is Mr. A, the teleprompter can search for target text (e.g., "have warm winter blessings and contented joy") that matches the collected user voice from the lines of the presenter Mr. A, and mark "have warm winter blessings and contented joy" on the teleprompter.

[0082] If the user status of the collected user voice is Mr. B, the teleprompter can search for target text (e.g., "For the past year, we have been sweating") that matches the collected user voice from the lines of the presenter Mr. B and mark "For the past year, we have been sweating" on the teleprompter.

[0083] In an embodiment of the present application, the teleprompter can mark phrases that the target user is reading, automatically recognize the target user's voice as the target user is reading, and scroll prompt text data on the teleprompter, thereby improving the effectiveness of the text prompt function on the teleprompter.

[0084] Please refer to Fig. 14, which is a structural schematic diagram of a data processing device provided in an embodiment of the present application. The data processing device performs the steps in the embodiment corresponding to Fig. 3 above. As shown in Fig. 14, the data processing device 1 can include a launching module 101, a display module 102 and an acquisition module 103.

[0085] The initiation module 101 is configured to initiate a video recording service in the video application in response to a service initiation operation in the video application.

[0086] The display module 102 is configured to collect a user's voice at the video recording service, determine target text matching the user's voice in prompt text data associated with the video recording service, and mark the target text.

[0087] If the text position of the target text in the prompt text data is the end position of the prompt text data, the target video data corresponding to the video recording service is obtained.

[0088] Regarding the specific implementation of the functions of the start-up module 101, the display module 102, and the acquisition module 103, it is sufficient to refer to S101 to S103 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0089] In some possible embodiments, the data processing device 1 may further include a first recording page display module 104, an editing module 105, a first estimated duration display module 106, a second recording page display module 107, a text upload module 108, and a second estimated duration display module 109.

[0090] The first recording page display module 104 is configured to display a recording page including a text entry area in the video application in response to a trigger operation for a teleprompter shot entry in the video application prior to initiating a video recording service in the video application.

[0091] The editing module 105 is configured to, in response to an information editing operation on the text entry area, display prompt text data in the text entry area determined by the information editing operation.

[0092] The first estimated duration display module 106 is configured to display the prompt character count and the video estimated duration corresponding to the prompt text data in the text entry area if the prompt character count corresponding to the prompt text data is greater than a quantity threshold.

[0093] The second recording page display module 107 is configured to display a recording page including a text upload control and a text input area in the video application in response to a trigger operation on a teleprompter shot entry in the video application before invoking a video recording service in the video application. The text upload module 108 is configured to determine the text content uploaded on the recording page as prompt text data in response to a trigger operation on the text upload control, and display the prompt text data in the text input area.

[0094] The second estimated duration display module 109 displays the number of prompt characters corresponding to the prompt text data and the estimated video duration corresponding to the prompt text data.

[0095] Regarding the specific implementation of the functions of the first recording page display module 104, the editing module 105, the first estimated time display module 106, the second recording page display module 107, the text upload module 108 and the second estimated time display module 109, refer to S101 in the embodiment corresponding to Fig. 3 above, and no detailed description is given here. When the first recording page display module 104, the editing module 105 and the first estimated time display module 106 perform the corresponding operation, the second recording page display module 107, the text upload module 108 and the second estimated time display module 109 all suspend the operation, and when the second recording page display module 107, the text upload module 108 and the second estimated time display module 109 perform the corresponding operation, the first recording page display module 104, the editing module 105 and the first estimated time display module 106 all suspend the operation. The first recording page display module 104 and the second recording page display module 107 may be merged into the same recording page display module, and the first estimated duration display module 106 and the second estimated duration display module 109 may be merged into the same estimated duration display module.

[0096] In some possible embodiments, the service-initiated operation includes a voice-initiated operation.

[0097] The activation module 101 may include a countdown animation display unit 1011 and a recording service activation unit 1012 .

[0098] The countdown animation display unit 1011 is configured to display a recording countdown animation associated with the video recording service on the recording page of the video application in response to a voice-activated operation in the video application.

[0099] The recording service initiating unit 1012 is configured to initiate and run a video recording service in the video application when the recording countdown animation ends.

[0100] Regarding the specific implementation of the functions of the countdown animation display unit 1011 and the recording service starting unit 1012, it is sufficient to refer to S101 in the embodiment corresponding to the above FIG. 3, and no detailed description will be given here.

[0101] In some possible embodiments, the recording countdown animation includes an animation cancel control.

[0102] The data processing device 1 further includes a countdown animation cancellation module 110 for canceling the display of the recording countdown animation and launching and executing the video recording service in the video application in response to a trigger operation on an animation cancellation control when the recording countdown animation ends and before launching and executing the video recording service in the video application.

[0103] For the specific implementation of the function of the countdown animation cancellation module 110, refer to S101 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0104] In some possible embodiments, the display module 102 may include a voice activity detection unit 1021 , a target text determination unit 1022 , and a target text display unit 1023 .

[0105] The voice activity detection unit 1021 is configured to collect a user's initial voice in the video recording service, perform voice activity detection on the user's initial voice to obtain valid voice data in the user's initial voice, and determine the valid voice data as the user's voice.

[0106] The target text determination unit 1022 is configured to convert the user speech into user speech text, and perform text matching between the user speech text and prompt text data associated with the video recording service to determine target text in the prompt text data that matches the user speech text.

[0107] The target text display unit 1023 is configured to mark the target text in a recording page of the video recording service.

[0108] For the specific implementation of the functions of the voice activity detection unit 1021, the target text determination unit 1022 and the target text display unit 1023, see S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0109] In some possible embodiments, the target text determining unit 1022 may include a syllable information obtaining subunit 10221 and a syllable matching subunit 10222.

[0110] The syllable information obtaining subunit 10221 is configured to obtain first syllable information of the user voice text, and obtain second syllable information of the prompt text data associated with the video recording service.

[0111] The syllable matching subunit 10222 is configured to obtain target syllable information in the second syllable information that is the same as the first syllable information, and determine a target text corresponding to the target syllable information in the prompt text data.

[0112] Regarding the specific implementation of the functions of the syllable information acquisition subunit 10221 and the syllable matching subunit 10222, it is sufficient to refer to S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0113] In some possible embodiments, the target text display unit 1023 is It may include a presentation area determination subunit 10231 and a marking subunit 10232 .

[0114] The presentation area determining subunit 10231 is configured to determine a text prompt area corresponding to the target text on a recording page of the video recording service.

[0115] The marking subunit 10232 is configured to mark the target text in the text prompt area based on a text position of the target text in the prompt text data.

[0116] Regarding the specific implementation of the functions of the presentation area determination subunit 10231 and the marking subunit 10232, reference may be made to S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0117] In some possible embodiments, the record page includes a cancel record control.

[0118] The data processing device 1 may further include a recording cancel module 111 , a recording prompt information display module 112 and a re-recording module 113 .

[0119] The recording cancel module 111 is configured to cancel the video recording service and delete the video data recorded by the video recording service in response to a trigger operation on the recording cancel control.

[0120] The record prompt information display module 112 is configured to generate record prompt information for a video recording service and display the record prompt information including a re-record control on a recording page.

[0121] The re-recording module 113 is configured to, in response to a trigger operation on the re-recording control, switch the target text displayed on the recording page to display the prompt text data.

[0122] For the specific functional implementation of the recording cancel module 111, the recording prompt information display module 112 and the re-recording module 113, see S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0123] In some possible embodiments, the recording page includes a recording complete control.

[0124] The data processing device 1 includes: The system may include a recording completion module 114 that, when the text position of the target text in the prompt text data is the end position of the prompt text data, stops the video recording service in response to a trigger operation on a recording completion control before obtaining the target video data corresponding to the video recording service, and determines the video data recorded by the video recording service as the target video data.

[0125] For the specific implementation of the functions of the recording completion module 114, see S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0126] In some possible embodiments, the acquisition module 103 may include: an original video acquisition unit 1031 , an optimization control display unit 1032 , an optimization method display unit 1033 , and an optimization processing unit 1034 .

[0127] The original video obtaining unit 1031 is configured to stop the video recording service when the text position of the target text in the prompt text data is the end position of the prompt text data, and determine the video data recorded by the video recording service as the original video data.

[0128] The optimization control display unit 1032 is configured to display the original video data and the editing optimization controls corresponding to the original video data on an edit page of the video application.

[0129] The optimization scheme display unit 1033 is configured to display M (M is a positive integer) edit optimization schemes for the original video data in response to a trigger operation on the edit optimization control.

[0130] The optimization processing unit 1034 is configured to, in response to a selection operation for the M editing optimization methods, obtain target video data by performing an editing optimization processing on the original video data based on the editing optimization method determined by the selection operation.

[0131] For the specific functional implementation forms of the original video acquisition unit 1031, the optimization control display unit 1032, the optimization method display unit 1033 and the optimization processing unit 1034, refer to S103 in the embodiment corresponding to Figure 3 above, and no detailed description will be given here.

[0132] In some executable embodiments, the optimization processing unit 1034 may include a first speech conversion subunit 10341, a text comparison subunit 10342, a speech deletion subunit 10343, a second speech conversion subunit 10344, a timestamp acquisition subunit 10345, and a speech pause segment determination subunit 10346.

[0133] The first voice conversion subunit 10341 is configured to obtain target voice data contained in the original video data and convert the target voice data into a target text result when the editing optimization method determined by the selection operation is the first editing method.

[0134] The text comparison subunit 10342 is configured to perform a text comparison on the target text result and the prompt text data, to determine the text in the target text result that is different from the prompt text data as the error text.

[0135] The audio deleting subunit 10343 is configured to obtain the target video data by deleting the audio data corresponding to the error text in the original video data.

[0136] The second voice conversion subunit 10344 is configured to convert the target voice data included in the original video data into a target text result when the editing optimization method determined by the selection operation is a second editing method, and determine the text different from the prompt text data in the target text result as error text.

[0137] The timestamp obtaining subunit 10345 is configured to obtain a timestamp for each of the N text characters in the target audio data by dividing the target text result into N (N is a positive integer) text characters.

[0138] The audio pause segment determination subunit 10346 is configured to determine an audio pause segment in the target audio data based on a timestamp, and obtain the target video data by deleting audio data corresponding to the audio pause segment and the error text in the original video data.

[0139] Regarding the specific functional implementation forms of the first speech conversion subunit 10341, the text comparison subunit 10342, the speech deletion subunit 10343, the second speech conversion subunit 10344, the time stamp acquisition subunit 10345 and the speech pause segment determination subunit 10346, it is sufficient to refer to S103 in the embodiment corresponding to the above FIG. 3, and no detailed description is given here. When the first speech conversion subunit 10341, the text comparison subunit 10342 and the speech deletion subunit 10343 perform corresponding operations, the second speech conversion subunit 10344, the time stamp acquisition subunit 10345 and the speech pause segment determination subunit 10346 all pause the execution of operations, and when the second speech conversion subunit 10344, the time stamp acquisition subunit 10345 and the speech pause segment determination subunit 10346 perform corresponding operations, the first speech conversion subunit 10341, the text comparison subunit 10342 and the speech deletion subunit 10343 all pause the execution of operations.

[0140] In some possible embodiments, the data processing device 1 may further include a user speech rate determining module 115 and a speech rate prompt information display module 116 .

[0141] The user speech rate determining module 115 is configured to obtain a speech length corresponding to the user's initial speech and a number of speech characters included in the user's initial speech, and determine a ratio between the number of speech characters and the speech length as the user's speech rate.

[0142] The speaking rate prompt information display module 116 is configured to display speaking rate prompt information on the recording page when the user's speaking rate is greater than a speaking rate threshold, and the speaking rate prompt information is for prompting a target user associated with the video recording service to reduce the user's speaking rate.

[0143] For the specific functional implementation of the user speech rate determining module 115 and the speech rate prompt information display module 116, see S102 in the embodiment corresponding to FIG. 3 above, and no detailed description will be given here.

[0144] In some possible embodiments, the error text includes K error subtexts, where K is a positive integer.

[0145] The data processing device 1 may further include an error frequency determination module 117 , an error type recognition module 118 and a tutorial video push module 119 .

[0146] The error frequency determination module 117 is configured to determine an error frequency in the video recording service based on the K error subtexts and the video length corresponding to the original video data.

[0147] The error type recognition module 118 is configured to recognize a speech error type corresponding to each of the K error subtexts if the error frequency is greater than an error threshold.

[0148] The tutorial video push module 119 is configured to push a tutorial video associated with the speech error type in a video application to a target user associated with a video recording service.

[0149] For the specific functional implementation of the error frequency determination module 117, the error type recognition module 118 and the tutorial video push module 119, see S103 in the embodiment corresponding to FIG. 3 above, and no further description is given here.

[0150] In an embodiment of the present application, after a user inputs prompt text data into a video application, the user can start a video recording service by voice; during recording of the video recording service, a teleprompter function can be provided to the user, and target text matching the user's voice can be located in the prompt text data and marked in the video application; that is, the target text displayed in the video application can match what the user is speaking, thereby improving the effectiveness of the text prompt function in the video recording service, reducing the risk of recording failure caused by the user forgetting the words, and further improving the quality of the recorded video; starting or stopping the video recording service by the user's voice can reduce user operations in the video recording service and improve the effect of video recording; after the video recording service is finished, editing optimization can be automatically performed on the video recording in the video recording service, thereby further improving the quality of the recorded video.

[0151] Please refer to Fig. 15, which is a structural schematic diagram of a data processing device provided in an embodiment of the present application. The data processing device can execute the steps in the embodiment corresponding to Fig. 12 above. As shown in Fig. 15, the data processing device 2 can include a prompt text upload module 21, a user voice collection module 22 and a user voice text display module 23.

[0152] The prompt text upload module 21 is configured to upload prompt text data to a teleprompter application.

[0153] The user voice collection module 22 is configured to collect a user voice corresponding to a target user, and perform text conversion on the user voice to generate a user voice text corresponding to the user voice.

[0154] The user spoken text display module 23 is configured to determine the text in the prompt text data that is the same as the user spoken text as the target text, and mark the target text in a teleprompter application.

[0155] For specific implementations of the prompt text upload module 21, the user voice collection module 22, and the user voice text display module 23, see S201 to S203 in the embodiment corresponding to FIG. 12 above, and no detailed description will be given here.

[0156] The target users include a first user and a second user, and the prompt text data includes a first prompt text corresponding to the first user and a second prompt text corresponding to the second user.

[0157] The user voice text display module 23 includes a user identity determining unit 231 , a first determining unit 232 and a second determining unit 233 .

[0158] The user identity determination unit 231 is configured to obtain a user voiceprint feature in the user voice, and determine a user identity corresponding to the user voice according to the user voiceprint feature.

[0159] The first determining unit 232 is configured to determine, if the user identity is the first user, a text that is the same as the user voice text in the first prompt text as a target text, and mark the target text in a teleprompter application.

[0160] The second determining unit 233 is configured to determine, if the user identity is the second user, a text that is the same as the user voice text in the second prompt text as a target text, and mark the target text in the teleprompter application.

[0161] For the specific implementation of the user status determination unit 231, the first determination unit 232 and the second determination unit 233, refer to S203 in the embodiment corresponding to FIG. 12 above, and no detailed description will be given here.

[0162] In an embodiment of the present application, the teleprompter can mark phrases that the target user is reading, automatically recognize the target user's voice as the target user is reading, and scroll prompt text data on the teleprompter, thereby improving the effectiveness of the text prompt function on the teleprompter.

[0163] Referring to FIG. 16, FIG. 16 is a structural schematic diagram of a computer device provided in an embodiment of the present application. As shown in FIG. 16, the computer device 1000 may include a processor 1001, a network interface 1004 and a memory 1005, and the above computer device 1000 may further include a user interface 1003 and at least one communication bus 1002. The communication bus 1002 is configured to realize the connection communication between these components. The user interface 1003 may include a display and a keyboard, and preferably, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may include a standard wired interface and a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a non-volatile memory. The memory 1005 may be, for example, at least one magnetic disk memory. The memory 1005 may further be at least one storage device remote from the processor 1001. As shown in FIG. 16, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.

[0164] In the computer device 1000 shown in FIG. 16, the network interface 1004 can provide a network communication function, the user interface 1003 is an interface that mainly provides input to a user, and the processor 1001 calls a device control application program stored in the memory 1005 to: initiating a video recording service in the video application in response to a service initiation operation in the video application; collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text; obtaining target video data corresponding to a video recording service when the text position of the target text in the prompt text data is the end position of the prompt text data.

[0165] It should be understood that the computer device 1000 described in the embodiment of the present application may execute the data processing method described in the embodiment corresponding to Fig. 3 above, or may execute the data processing device 1 described in the embodiment corresponding to Fig. 14 above, and no detailed description is given here, nor is any detailed description given of the beneficial effects of using the same method.

[0166] Please refer to FIG. 17, which is a structural schematic diagram of a computer device provided in an embodiment of the present application. As shown in FIG. 17, the computer device 2000 includes a processor 2001, a network interface 2004 and a memory 2005, and the computer device 2000 may further include a user interface 2003 and at least one communication bus 2002. The communication bus 2002 is configured to realize the connection communication between these components. The user interface 2003 may include a display and a keyboard, and preferably, the user interface 2003 may include a standard wired interface, a wireless interface. The network interface 2004 may include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 2005 may be a high-speed RAM memory, or a non-volatile memory. 17, the memory 2005 may be at least one storage device remote from the processor 2001. As shown in FIG. 17, the memory 2005 as a computer readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.

[0167] In the computer device 2000 shown in FIG. 17, the network interface 2004 can provide a network communication function, the user interface 2003 is an interface that mainly provides input to a user, and the processor 2001 calls a device control application program stored in the memory 2005, uploading prompt text data to a teleprompter application; collecting user speech corresponding to the target user and performing text conversion on the user speech to generate user speech text corresponding to the user speech; determining, in the prompt text data, a text that is the same as the user's voice text as a target text, and marking the target text in a teleprompter application.

[0168] Here, it should be understood that the computer device 2000 described in the embodiment of the present application may execute the data processing method described in the embodiment corresponding to Fig. 6 above, or may execute the data processing device 2 described in the embodiment corresponding to Fig. 14 above, and no detailed description is given here. In addition, no detailed description is given of the beneficial effects of using the same method.

[0169] In addition, the embodiment of the present application further provides a computer-readable storage medium, in which a computer program executed by the data processing device 1 mentioned above is stored, the computer program includes program commands, and the processor executes the program commands to realize the description of the data processing method in the embodiment corresponding to any one of Figures 3, 11, and 12 above, so no detailed description is given here. Also, the description of the beneficial effects of using the same method is not detailed. For technical details not disclosed in the embodiment of the computer-readable storage medium of the present application, please refer to the description of the method embodiment of the present application. For example, the program commands are located and executed in one computing device, or executed in multiple computing devices located at one location, or executed in multiple computing devices connected to each other via a communication network, and a blockchain system is constituted by multiple computing devices distributed at multiple locations and connected to each other via a communication network.

[0170] In addition, the embodiments of the present application further provide a computer program product or a computer program, which includes computer commands, and the computer commands are stored in a computer-readable storage medium. A processor of a computer device reads the computer commands from the computer-readable storage medium, and the processor executes the computer commands to cause the computer device to execute the data processing method described in the embodiments corresponding to any one of Figures 3, 11, and 12 above, so no detailed description is given here. Also, no detailed description is given of the beneficial effects of using the same method. For technical details not disclosed in the embodiments of the computer program product or computer program of the present application, please refer to the description of the method embodiments of the present application.

[0171] As can be understood by those skilled in the art, the implementation of all or part of the flow of the above-mentioned embodiment methods can be completed by instructing relevant hardware through a computer program, and the computer program is stored in a computer-readable storage medium, and when the program is executed, it contains the flow of each embodiment of the above-mentioned method. The storage medium can be a magnetic disk, an optical disk, a ROM (Read-Only The memory may be a random access memory (RAM) or a random access memory (RAM).

[0172] What has been disclosed above is merely a preferred embodiment of the present application, and cannot limit the scope of the claims of the present application, and therefore, equivalent modifications made according to the claims of the present application shall be included within the scope of the present application.

Claims

1. 1. A computer device implemented method for processing data, comprising: initiating a video recording service in the video application in response to a service initiation operation in the video application; collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text; if the text position of the target text in the prompt text data is an end position of the prompt text data, obtaining target video data corresponding to the video recording service; When the text position of the target text in the prompt text data is an end position of the prompt text data, obtaining target video data corresponding to the video recording service includes: when the text position of the target text in the prompt text data is the end position of the prompt text data, stopping the video recording service, and determining the video data recorded by the video recording service as original video data; displaying the original video data and edit optimization controls corresponding to the original video data on an edit page of the video application; displaying M edit optimization methods for the original video data in response to a trigger operation on the edit optimization control, where M is a positive integer; and in response to a selection operation for the M edit optimization methods, performing an edit optimization process on the original video data based on the edit optimization method determined by the selection operation to obtain the target video data. method.

2. before initiating a video recording service in the video application; displaying a recording page in the video application, the recording page including a text entry area, in response to a triggering action in the video application for a teleprompter shot entry; in response to an information editing operation on the text input area, displaying prompt text data determined by the information editing operation in the text input area; and if a number of prompt characters corresponding to the prompt text data is greater than a quantity threshold, displaying the number of prompt characters and an estimated video length corresponding to the prompt text data in the text input area. The method of claim 1.

3. before initiating a video recording service in the video application; displaying a recording page in the video application in response to a triggering action for a teleprompter capture entry in the video application, the recording page including a text upload control and a text entry area; determining a text content uploaded on the video recording page as prompt text data in response to a trigger operation on the text upload control, and displaying the prompt text data in the text input area; and displaying a number of prompt characters corresponding to the prompt text data and an estimated video length corresponding to the prompt text data. The method of claim 1.

4. The service activation operation includes a voice activation operation; The step of starting a video recording service in the video application in response to a service start operation in the video application includes: displaying a recording countdown animation associated with the video recording service on a recording page of the video application in response to a voice activation in the video application; and when the recording countdown animation ends, launching and executing the video recording service in the video application. The method of claim 1.

5. the recording countdown animation includes an animation cancel control; When the recording countdown animation has finished, before launching and executing the video recording service in the video application. The method further includes the step of canceling display of the recording countdown animation in response to a trigger operation on the animation cancel control, and activating and executing the video recording service in the video application. The method according to claim 4.

6. The steps of collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text include: collecting a user's initial voice in the video recording service, performing a voice activity detection on the user's initial voice to obtain effective voice data in the user's initial voice, and determining the effective voice data as the user's voice; converting the user speech into user speech text and performing text matching between the user speech text and prompt text data associated with the video recording service to determine target text in the prompt text data that matches the user speech text; marking the target text on a recording page of the video recording service. The method of claim 1.

7. performing text matching between the user speech text and prompt text data associated with the video recording service to determine target text in the prompt text data that matches the user speech text, the step including: obtaining first syllable information of the user voice text and obtaining second syllable information of prompt text data associated with the video recording service; obtaining target syllable information in the second syllable information that is the same as the first syllable information, and determining a target text in the prompt text data that corresponds to the target syllable information. The method according to claim 6.

8. The step of marking the target text on a recording page of the video recording service includes: determining a text prompt area on a recording page of the video recording service that corresponds to the target text; marking the target text in the text prompt area based on a text position of the target text in the prompt text data. The method according to claim 6.

9. the recording page includes a recording cancel control; in response to a trigger operation on the recording cancel control, canceling the video recording service and deleting video data recorded by the video recording service; generating record prompt information for the video recording service and displaying the record prompt information including a re-record control on the recording page; and in response to a trigger operation on the re-recording control, switching a target text displayed on the recording page to the prompt text data and displaying the target text data. The method according to any one of claims 4 to 8.

10. the recording page includes a recording completion control; If the text position of the target text in the prompt text data is the end position of the prompt text data, before obtaining the target video data corresponding to the video recording service, The method further includes the step of stopping the video recording service in response to a trigger operation on the recording completion control, and determining video data recorded by the video recording service as the target video data. The method according to any one of claims 4 to 8.

11. The step of obtaining the target video data by performing an edit optimization process on the original video data based on the edit optimization method determined by the selection operation includes: if the editing optimization mode determined by the selection operation is a first editing mode, obtaining target voice data included in the original video data, and converting the target voice data into a target text result; performing a text comparison between the target text result and the prompt text data to determine text in the target text result that differs from the prompt text data as error text; and obtaining the target video data by deleting audio data corresponding to the error text in the original video data. The method of claim 1.

12. The step of obtaining the target video data by performing an edit optimization process on the original video data based on the edit optimization method determined by the selection operation includes: if the editing optimization mode determined by the selection operation is a second editing mode, converting target voice data included in the original video data into a target text result, and determining a text in the target text result that is different from the prompt text data as an error text; Segmenting the target text result into N text characters, where N is a positive integer, to obtain timestamps for each of the N text characters in the target audio data; determining an audio pause segment in the target audio data based on the time stamp, and deleting the audio pause segment and audio data corresponding to the error text in the original video data to obtain the target video data. The method of claim 1.

13. During the execution of said video recording service, obtaining a length of the voice corresponding to the user's initial voice and a number of voice characters included in the user's initial voice, and determining a ratio of the number of voice characters to the length of the voice as a speaking speed of the user; and if the user's speaking rate is greater than a speaking rate threshold, displaying speaking rate prompt information on the recording page, the speaking rate prompt information being for prompting a target user associated with the video recording service to reduce the user's speaking rate. The method according to claim 6.

14. the error text includes K error subtexts, where K is a positive integer; determining an error frequency in the video recording service based on the K error subtexts and a video length corresponding to the original video data; recognizing a speech error type corresponding to each of the K error sub-texts if the error frequency is greater than an error threshold; and pushing, in the video application, a tutorial video associated with the speech error type to a target user associated with the video recording service. The method according to any one of claims 11 to 12.

15. A data processing device disposed in a computer device, comprising: an initiation module for initiating a video recording service in a video application in response to a service initiation operation in the video application; a display module for collecting user speech at the video recording service, determining target text matching the user speech in prompt text data associated with the video recording service, and marking the target text; an acquiring module for acquiring target video data corresponding to the video recording service when the text position of the target text in the prompt text data is an end position of the prompt text data; The acquisition module includes: If the text position of the target text in the prompt text data is the end position of the prompt text data, stop the video recording service, and determine the video data recorded by the video recording service as original video data; displaying the original video data and edit optimization controls corresponding to the original video data on an edit page of the video application; displaying M edit optimization methods for the original video data (M being a positive integer) in response to a trigger operation on the edit optimization control; In response to a selection operation for the M edit optimization methods, an edit optimization process is performed on the original video data based on the edit optimization method determined by the selection operation, thereby obtaining the target video data. Device.

16. A memory and a processor are included. The memory is connected to the processor and is configured to store a computer program, the processor being configured to call the computer program so as to cause the computing device to carry out the method according to any one of claims 1 to 8. Computer equipment.

17. A program for causing a computer to execute the method according to any one of claims 1 to 8.

Images