Text input method, apparatus, device, storage medium and program product

Abstract

Embodiments of the present application disclose a text input method, device, equipment, storage medium and program product, and belong to the technical field of human-computer interaction. The method comprises: in response to a picture floating instruction for a target picture, displaying the target picture in a floating window; in response to a text input instruction, displaying the floating window and target text while displaying a text input interface, the target text being obtained by text recognition on picture content displayed in the floating window, the picture content belonging to the target picture; and in response to an input instruction for the target text, inputting the target text into a text input box of the text input interface. The method provided by the embodiments of the present application is convenient for a user to correct text according to picture content in the floating window, does not require switching between a picture and a text input interface, and is helpful to improve text input efficiency. Moreover, the displayed target text corresponds to the displayed picture content in the floating window, which is convenient for the user to input required text into the text input box and improves text input efficiency.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular to a text input method, apparatus, device, storage medium, and program product. Background Technology

[0002] Currently, when inputting text in images, users mostly use text recognition functions to identify the text in the image, facilitating quick input of text in images.

[0003] In related technologies, after recognizing the text in an image, the user copies the recognized text into a text input box. When a large amount of text is recognized, if only a portion is needed, it can be selected and copied.

[0004] However, when the recognized text is inaccurate or the selected and copied text is inaccurate, users need to switch between the image and text input interfaces multiple times to proofread the text information, which affects the efficiency of text input. Summary of the Invention

[0005] This application provides a text input method, apparatus, device, storage medium, and program product, which can improve text input efficiency. The technical solution is as follows:

[0006] On one hand, embodiments of this application provide a text input method, the method comprising:

[0007] In response to an image hover command for the target image, the target image is displayed in a floating window;

[0008] In response to a text input command, while displaying the text input interface, the floating window and the target text are also displayed. The target text is obtained by text recognition of the image content displayed in the floating window, and the image content belongs to the target image.

[0009] In response to an input instruction for the target text, the target text is input into the text input box of the text input interface.

[0010] On the other hand, embodiments of this application provide a text input device, the device comprising:

[0011] The image display module is used to display the target image in a floating window in response to an image hover command for the target image;

[0012] The text display module is used to respond to a text input command by displaying the floating window and the target text while displaying the text input interface. The target text is obtained by text recognition of the image content displayed in the floating window, and the image content belongs to the target image.

[0013] A text input module is used to input the target text into the text input box of the text input interface in response to an input command for the target text.

[0014] On the other hand, embodiments of this application provide a terminal device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the text input method as described above.

[0015] On the other hand, embodiments of this application provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the text input method as described above.

[0016] On the other hand, embodiments of this application provide a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. The processor of a terminal device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the terminal device to perform the text input method provided in the various optional implementations of the above aspects.

[0017] The beneficial effects of the technical solutions provided in this application include at least the following:

[0018] In this embodiment, an image floating function is provided. When the terminal receives an image floating command for a target image, the target image can be displayed in a floating window. When the user is inputting text, the floating window is displayed simultaneously with the text input interface, making it convenient for the user to proofread the text based on the image content in the floating window without switching between the image and text input interfaces, thus improving text input efficiency. In addition, the terminal can also perform text recognition on the image content displayed in the floating window and display the recognized target text. The displayed target text corresponds to the image content displayed in the floating window. When the user needs to input the target text contained in the currently displayed image content, an input command for the required target text can be triggered, allowing the required text to be input into the text input box without having to perform multiple selection and copy operations on the recognized text, further improving text input efficiency. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a text input method provided in an exemplary embodiment of this application is shown;

[0021] Figure 2 A schematic diagram of an interface illustrating a text input process in an exemplary embodiment of this application is shown;

[0022] Figure 3 A flowchart of a text input method provided by another exemplary embodiment of this application is shown;

[0023] Figure 4 This illustration shows an interface diagram of a floating window and target text, illustrating an exemplary embodiment of this application.

[0024] Figure 5 This invention provides a schematic diagram of the structure of a text recognition algorithm according to an exemplary embodiment of the present application.

[0025] Figure 6 This illustration shows a schematic diagram of an interface for updating image content within a floating window, provided in an exemplary embodiment of this application.

[0026] Figure 7 A flowchart of a text input method provided by another exemplary embodiment of this application is shown;

[0027] Figure 8 A schematic diagram of the interface for rotating a target image provided in an exemplary embodiment of this application is shown;

[0028] Figure 9 This illustration shows a schematic diagram of an interface for capturing a target image, provided in an exemplary embodiment of this application.

[0029] Figure 10 A flowchart illustrating a text input method provided in another exemplary embodiment of this application is shown;

[0030] Figure 11 This is a structural block diagram of a text input device provided in an exemplary embodiment of this application;

[0031] Figure 12 A structural block diagram of a terminal device provided in an exemplary embodiment of this application is shown. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0033] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0034] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0035] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0036] Computer vision (CV) is a science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing and measuring targets, and then performs image processing to create images more suitable for human observation or transmission to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image segmentation, image semantic understanding, image retrieval, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), etc. The text input method involved in the embodiments of this application is an application of computer vision technology in image text recognition.

[0037] In related technologies, text recognition can be performed on images when it is necessary to record text information within them. However, text recognition on images may be inaccurate, requiring users to correct the copied and pasted text. This correction process necessitates switching between the image and text input interfaces, impacting text input efficiency.

[0038] Furthermore, when an image contains a significant amount of text, the user may only need a portion of it. However, text recognition processes will identify all the text in the image. Therefore, after text recognition, the user needs to select the desired text and copy it into the text input box. This process requires multiple copy-paste operations, and the copied and pasted text may be inaccurate, necessitating reopening the image for proofreading. Consequently, text input efficiency is low.

[0039] This application provides a text input method. When text information from a target image needs to be input, the target image can be displayed in a floating state using an image hover command. This allows the target image to be displayed while the text input interface is displayed, facilitating text proofreading and input. Furthermore, text recognition is performed only on the image content displayed within the floating window, and users can select the text to input as needed, improving text input efficiency.

[0040] The method provided in this application embodiment can be applied to the conversation scenario of social applications. It can display a target image floating in the conversation scenario. The terminal can perform text recognition on the image content in the floating window and display the target text on the conversation interface. When an input instruction for the target text is received, the target text is entered into the text input box, which makes it convenient for the user to record the text information of the target image and send it.

[0041] Alternatively, it can also be applied to information entry scenarios. When information needs to be entered based on text information in a target image, the target image can be displayed floating in the information entry interface. The terminal can perform text recognition on the image content in the floating window and display the target text in the information entry interface. When an input instruction for the target text is received, the target text is entered into the text input box to facilitate information entry.

[0042] The above application scenarios are for illustrative purposes only. The method provided in this application embodiment can also be applied to other scenarios where image and text information is input, and this embodiment does not limit this application.

[0043] Please refer to Figure 1 This document illustrates a flowchart of a text input method provided in an exemplary embodiment of this application. This embodiment uses the method applied to a terminal as an example for illustration, and the method includes the following steps.

[0044] Step 101: In response to the image hover command for the target image, display the target image in a floating window.

[0045] Optionally, the target image can be an image currently displayed on the terminal's screen, or an image already stored on the terminal, such as an image in the gallery.

[0046] In one possible implementation, the user can trigger an image hover command by performing a trigger operation on the target image. When the terminal receives the image hover command, a floating window is created above the currently displayed interface, and the target image is displayed within the floating window.

[0047] Optionally, the floating window can be a movable floating window. Users can move the floating window to any position on the interface by performing a movement operation. When the terminal receives a movement operation on the floating window, it can acquire the movement trajectory and adjust the floating window's position accordingly. Furthermore, the floating window remains displayed while the terminal switches between currently displayed interfaces. The terminal can switch to any terminal interface, such as switching to other interfaces within the same application, or switching to interfaces of different applications; the floating window remains displayed throughout the switching process. For example, after creating a floating window within the application interface of a first application, the floating window will remain displayed when the terminal switches to the application interface of a second application.

[0048] Optionally, the floating window can be a fixed-size window or an adjustable window. In one possible implementation, the terminal can adjust the size of the floating window according to the size of the target image to match the two. Alternatively, in another possible implementation, the user can adjust the size of the floating window through window adjustment operations.

[0049] Indicative, such as Figure 2 As shown, when a floating command for the target image 201 is received, the target image 201 is displayed in the floating window 202.

[0050] Step 102: In response to the text input command, while displaying the text input interface, a floating window and the target text are displayed. The target text is obtained by text recognition of the image content displayed in the floating window, and the image content belongs to the target image.

[0051] When a text input command is received, it indicates that the user may need to input text information from the target image. Therefore, in one possible implementation, when the terminal receives a text input command, it displays a text input interface, and simultaneously displays a floating window and the target text. That is, while the text input interface is displayed, the floating window and the target text are also displayed, facilitating text input from the image. The text input interface includes text input boxes and text editing controls, etc.

[0052] Optionally, a text input command is used to trigger text input. When an operation to initiate the input function is received, it is determined that a text input command has been received. In one possible scenario, in a social application, after the terminal receives an image hover command for a target image in the first chat interface, the target image is displayed in a floating window. When a trigger operation is received for a message input box in the second chat interface, it is determined that a text input command has been received, and the text input interface, the floating window, and the target text are displayed.

[0053] Optionally, the target text is the text obtained by performing text recognition on the image content displayed in the floating window. That is, in this embodiment, text recognition is performed only on the image content displayed in the floating window, and not on the entire image content of the target image. The displayed target text corresponds to the image content displayed in the floating window. When the image content displayed in the floating window changes, the displayed target text changes accordingly.

[0054] Furthermore, since there may be situations where it is not necessary to input all the text information in the target image, in one possible implementation, after the terminal recognizes the target text, the target text is first displayed, and when an input instruction for the target text is received, the target text is then input.

[0055] Indicative, such as Figure 2 As shown, in the chat interface, when a text input command is received, a text input interface 203 is displayed. The text input interface 203 contains a text input box 205, and simultaneously displays a floating window 202 and target text 204. The target text 204 is obtained by text recognition of the image content in the floating window 202.

[0056] It should be noted that the process of text recognition of the image content displayed in the floating window can be performed by the terminal, that is, the terminal recognizes the target text and displays the target text; or, it can be performed by the server, the server performs text recognition of the image content displayed in the floating window and sends the recognized target text to the terminal, and the terminal displays the target text. This embodiment does not limit this.

[0057] Step 103: In response to the input instruction for the target text, input the target text into the text input box of the text input interface.

[0058] When the terminal receives an input instruction for target text, it can input the target text into the text input box. In one possible implementation, the terminal inputs the target text after the already edited text in the current text input box, or inputs it at the cursor position in the current text input box.

[0059] Indicative, such as Figure 2As shown, when an input instruction for target text 204 is received, the target text 204 is input into the text input box 205 of the text input interface.

[0060] Compared to related technologies that involve recognizing text from the entire image and then selecting and copying the desired text, the method provided in this embodiment can recognize the content of a partial image and display the target text corresponding to that partial image content. Users can choose whether to input the target text into the text input box as needed. When an input instruction for the target text is received, the target text is input into the text input box, thereby reducing the need for users to select and copy text multiple times and improving text input efficiency.

[0061] In summary, this application provides an image floating function. When the terminal receives an image floating command for a target image, the target image can be displayed in a floating window. When the user is inputting text, the floating window can be displayed on top of the text input interface, making it convenient for the user to proofread the text based on the image content in the floating window without switching between the image and text input interfaces, thus improving text input efficiency. Furthermore, the terminal can also perform text recognition on the image content displayed in the floating window and display the recognized target text on top of the text input interface. The displayed target text corresponds to the image content displayed in the floating window. When the user needs to input the target text contained in the currently displayed image content, an input command for the required target text can be triggered, allowing the required text to be input into the text input box without needing to select and copy the recognized text multiple times, further improving text input efficiency.

[0062] In this embodiment, the terminal displays a floating window and target text on top of the text input interface, and the displayed target text corresponds to the image content displayed in the floating window. In one possible implementation, an image sliding mechanism is provided, allowing the target image displayed in the floating window to be slidably displayed. The user can slide the image to the target image content containing the desired text, and the terminal performs text recognition on the image content displayed in the floating window to obtain the target text required by the user. An exemplary embodiment will be described below.

[0063] Please refer to Figure 3 This illustration shows a flowchart of a text input method provided by another exemplary embodiment of this application. This embodiment uses the method applied to a terminal as an example for explanation, and the method includes the following steps.

[0064] Step 301: In response to the trigger operation on the target image, display the image floating control.

[0065] In one possible implementation, a user can trigger the display of a functional interface by performing a trigger operation on a target image. This interface includes various functional controls, including but not limited to controls corresponding to functions such as forwarding, capturing, and storing the image. In this embodiment, the functional interface includes a floating image control; when a trigger operation on the target image is received, the terminal can display the functional interface containing the floating image control.

[0066] Step 302: In response to the trigger operation of the image floating control, determine that the image floating command has been received, and display the target image in the floating window.

[0067] When the terminal receives a trigger operation on the image floating control, the terminal confirms that it has received the image floating instruction and displays the target image in the floating window. Optionally, the trigger operation can be a click operation, a double click operation, a long press operation, etc., and this embodiment does not limit it.

[0068] Step 303: In response to the text input command, a floating window is displayed while the text input interface is displayed.

[0069] In this embodiment, to facilitate text input and proofreading, a floating window is displayed simultaneously with the text input interface. In one possible implementation, the floating window is displayed above the text input interface. To avoid obscuring the text within the text input box, the terminal may also display a floating window above an area outside the text input box display area. This method may include the following steps:

[0070] Step 1: Determine the location of the text input box within the text input interface.

[0071] The terminal first needs to determine the location area of ​​the text input box in the text input interface. In one possible implementation, the terminal can obtain the position information of each control in the text input interface to determine the location area of ​​the text input box in the text input interface.

[0072] Step 2: Display a floating window on top of the area outside the location area.

[0073] In one possible implementation, after determining the location area of ​​the text input box, the terminal can define the area that does not overlap with the location area of ​​the text input box as the display area of ​​the floating window, and display the floating window on top of the display area.

[0074] Furthermore, the text input interface also includes other controls, such as text editing controls for editing text. To avoid the floating window affecting text input, the terminal can directly determine the display area of ​​the text input interface and display the floating window on top of the area outside the display area of ​​the text input interface.

[0075] In addition, to facilitate the input and proofreading of image text, a floating window can be displayed above the text input box for easy text comparison.

[0076] Indicative, such as Figure 4 As shown, the text input box is located in position area 401, and the terminal can display a floating window 402 on top of the area outside position area 401.

[0077] Step 304: Perform text recognition on the image content displayed in the floating window.

[0078] In one possible implementation, the terminal may use an Optical Character Recognition (OCR) algorithm to perform text recognition on the image content displayed in the floating window.

[0079] Optionally, the Fast Oriented Text Spotting (FOTS) algorithm can be used for text recognition. FOTS is a fast end-to-end text recognition model that uses a convolutional neural network to learn image features. The learned features are shared between text detection and text recognition, enabling simultaneous text detection and recognition.

[0080] like Figure 5 As shown, feature extraction is first performed using a shared convolutional network to obtain the feature map of image 501. The feature map is simultaneously input into two branches: the text detection branch 502 is used to predict the detection bounding box, and the text recognition branch first uses the RoIRotate operator 503 to extract text candidate features corresponding to the text detection results from the feature map, and then inputs the text candidate features into the text recognition branch 504 for text recognition. The text recognition branch 504 includes a recursive neural network (RNN) encoder and a connectionist temporal classification (CTC) decoder, and text recognition is performed through both.

[0081] The above is only an illustrative description of the OCR algorithm. Other OCR algorithms can also be used for text recognition, such as the End-to-End Text Spotting algorithm, the PSENet text detection algorithm, etc. This embodiment does not limit the use of these algorithms.

[0082] Step 305: If the target text is recognized, display the target text.

[0083] Since the image content displayed in the floating window may not contain text information, or the text information it contains may be irregular and therefore unrecognizable, there is no need to display the target text in this case. When the target text is recognized, the terminal displays the target text.

[0084] In one possible implementation, the terminal can display the target text in any area above the current display interface. The target text may be displayed above the text input interface display area and the floating window display area, without affecting text input. Therefore, the target text can be displayed directly above the area where the text is not obscured. In another possible implementation, to facilitate simultaneous viewing of edited text and target text, the target text can be displayed above the text input box. To avoid obscuring the information below the display area (i.e., the edited text within the text input box), the terminal can create a transparent layer and display the target text within this transparent layer. Optionally, the transparent layer can correspond to the window size of the floating window to ensure that the target text contained within the image content of the floating window is displayed.

[0085] The method for setting a transparent layer can be adopted according to the specific platform. For example, on the Android platform, a transparent activity function can be used to set a transparent layer.

[0086] Optionally, the transparent layer can be a movable layer. When the terminal receives a drag operation on the transparent layer, it can move the transparent layer according to the drag trajectory. Furthermore, the size of the transparent layer can be adjusted; when the terminal receives a scaling operation on the transparent layer, it can be scaled accordingly.

[0087] In one possible implementation, displaying the target text includes the following steps:

[0088] Step 1: Create a transparent layer above the location area.

[0089] In one possible implementation, the terminal can create a transparent layer on top of the text input box to display the target text. The target text will not obscure the existing text in the text input box, making it easy to view both the existing text and the target text simultaneously.

[0090] Optionally, when creating a transparent layer, the layer size of the transparent layer can be determined based on the window size of the floating window, and the transparent layer can be created based on the layer size.

[0091] Indicative, such as Figure 4 As shown, a transparent layer 403 is created above the area corresponding to the text input box 401.

[0092] Step 2: Display the target text in a transparent layer.

[0093] After the terminal creates a transparent layer, the target text is displayed in the transparent layer.

[0094] Indicative, such as Figure 4 As shown, the target text is displayed within the transparent layer 403.

[0095] Step 306: In response to the sliding operation of the target image in the floating window, update the image content displayed in the floating window.

[0096] In related technologies, text recognition is performed on the entire image, and the user selects the desired text from the recognized text for copying and pasting. This process requires first selecting the text, then copying and pasting it. If there is a large amount of text in different locations, multiple selection and copying processes are needed, resulting in low text input speed.

[0097] In this embodiment, the terminal can recognize only the image content displayed within the floating window. The image content displayed within the floating window can be adjusted accordingly based on the sliding operation of the target image. That is, when the user slides the target image within the floating window to the area where text recognition is required, the terminal only performs text recognition on the image content contained in the floating window, and recognizes the portion of text required by the user.

[0098] Optionally, a sliding control can be set within the floating window, allowing users to trigger the sliding of a target image by activating the control. When the terminal receives a trigger operation on the sliding control, it confirms that a sliding operation on the target image has been received and updates the image content displayed in the floating window. Alternatively, users can directly slide the target image; when the terminal receives a sliding operation on the target image, it slides the target image and updates the image content displayed in the floating window.

[0099] Optionally, users can slide the target image in any direction, such as vertical, horizontal, or diagonal. This embodiment does not limit this.

[0100] Indicative, such as Figure 4 As shown, a sliding control 404 is set in the floating window. When a trigger operation is received on the sliding control 404, the target image displayed in the floating window can be slid and the target content displayed in the floating window can be updated.

[0101] When the target image contains a lot of content, it may not be possible to accurately slide the target image to the desired position. Therefore, in one possible implementation, when the terminal receives a sliding operation on the target image, it indicates the position of the image content currently displayed in the floating window in the target image, so that the user can easily view the sliding position.

[0102] Optionally, in response to a sliding operation on the target image within the floating window, a thumbnail of the target image containing an indicator area is displayed around the perimeter of the floating window. The indicator area is used to indicate the location of the image content displayed in the floating window within the target image.

[0103] When the terminal receives a swipe operation on the target image within the floating window, a thumbnail of the target image is simultaneously displayed, along with an indicator area within the thumbnail. As the content of the image displayed within the floating window is updated, the position of the indicator area within the target image thumbnail is updated accordingly, and the content within the indicator area remains identical to the image content displayed within the floating window. Optionally, the target image thumbnail can be displayed on the right, left, or top of the floating window; this embodiment does not limit this.

[0104] Indicative, such as Figure 6 As shown, a target image thumbnail 601 is displayed on the right side of the floating window. The target image thumbnail 601 contains an indicator area 602, which is used to indicate the position area of ​​the image content 603 in the floating window within the target image.

[0105] In response to the end of the swipe operation, the display of the target image thumbnail stops. When the terminal detects that the swipe operation has ended, it stops updating the image content in the floating window and stops displaying the target image thumbnail. In one possible implementation, when the terminal detects that the swipe operation has ended, it can highlight an indicator area to indicate the position of the currently displayed image content in the floating window within the target image. After highlighting the indicator area, the display of the target image thumbnail stops, i.e., the position indication stops.

[0106] Step 307: In response to the end of the swipe operation, perform text recognition on the updated image content in the floating window to obtain the updated target text.

[0107] After the swipe operation ends, the terminal performs text recognition on the updated image content in the floating window to obtain the updated target text, and then displays the updated target text.

[0108] Step 308: Update the displayed target text based on the updated target text.

[0109] Once the terminal obtains the updated target text, it can update the currently displayed target text. When the target text is displayed in a transparent layer, the terminal can update the target text displayed in the transparent layer. In other words, the target text displayed in the transparent layer updates along with the content of the image within the floating window, and the two remain identical.

[0110] In one possible implementation, users can adjust the image content displayed in the floating window to the image content that needs to be recognized by sliding the target image. This allows them to directly obtain the required text information without having to select text from a large amount of text, thus improving text input efficiency.

[0111] Indicative, such as Figure 6 As shown, after the sliding operation ends, the target image thumbnail 601 stops displaying, and the image content 603 in the floating window is updated to image content 604. Correspondingly, the target text in the transparent layer 605 changes accordingly.

[0112] Step 309: In response to the trigger operation on the transparent layer, determine that an input instruction for the target text has been received, and input the target text into the text input box.

[0113] In this embodiment, when the terminal recognizes the target text corresponding to the image content in the floating window, it first displays the target text in a transparent layer. Only when it receives an input instruction for the target text will the terminal input the target text into the text input box.

[0114] In one possible implementation, when the terminal receives a trigger operation on the transparent layer, it determines that an input instruction for the target text has been received. The trigger operation can be a single click, a double click, or a long press, etc.

[0115] After the target image is slid to the area where text recognition is required, the terminal can further display the target text corresponding to the image content, allowing the user to confirm whether it is the desired text. Once confirmed as the desired text, the text can be entered into the text input box by triggering an operation on the transparent layer. Even if the recognized target text is not the desired text, the target image can be slid further to update the target text displayed in the transparent layer, improving text input accuracy and eliminating the need for text selection, copying, and pasting, thus enhancing text input efficiency.

[0116] Indicative, such as Figure 4 As shown, when a trigger operation is received on the transparent layer 403, the target text is entered into the text input box 401.

[0117] In this embodiment, when a text input instruction is received, a floating window is displayed above the area outside the text input box, and the target text is displayed in a transparent layer above the text input box to avoid displaying the text input information.

[0118] Furthermore, in this embodiment, the text input process is simplified by using image sliding and real-time display of the target text through a transparent layer. When the user only needs part of the text, they can simply slide the image and trigger the transparent layer to input the required text into the text input box, avoiding multiple text selections and copy-pasting processes, thus improving text input efficiency. Moreover, since there is no need to manually select, copy, and paste text, the accuracy of text input can be improved.

[0119] In the above embodiments, when a text input command is received, the terminal displays the target text on top of the text input interface. In another possible scenario, if text recognition is inaccurate, the user may need to input manually. In the case of manual input, the terminal can stop text recognition, i.e., stop displaying the target text. This method may include the following steps:

[0120] Step 1: In response to the trigger operation on the text input box, start the edit mode. In the edit mode, the target text is not displayed.

[0121] Users can activate edit mode by triggering the text input box, and then use the text editing controls in the text input interface to edit the text.

[0122] Optionally, the trigger operation for the text input box can be a double-click operation. In one possible implementation, if a trigger operation for the text input box is received when the terminal is not displaying the target text, the terminal will not perform text recognition, but will only acquire the editable text.

[0123] In another possible implementation, if a trigger operation on the text input box is received when the terminal is displaying the target text, the terminal stops displaying the target text and stops text recognition.

[0124] Optionally, when editing mode ends, the terminal restarts text recognition, performs text recognition on the image content within the floating window, and displays the target text. The end of editing mode can be triggered by a trigger operation on the text input box. That is, when editing mode is active, if the terminal receives another trigger operation on the text input box, the terminal exits editing mode and restarts the display of the target text.

[0125] Step 2: Obtain the edited text and display it in the input text box.

[0126] The terminal can determine the text to be edited based on the trigger operation of the text input control in the text input interface, and display the edited text in the text input box.

[0127] In one possible implementation, the text direction of the target image may differ from the text input direction, and the image size of the target image may not match the window size of the floating window. Therefore, the terminal can make adaptive adjustments to facilitate the recognition of the image content within the floating window. An exemplary embodiment will be described below.

[0128] Please refer to Figure 7 This illustration shows a flowchart of a text input method provided by another exemplary embodiment of this application. This embodiment uses the method applied to a terminal as an example for explanation, and the method includes the following steps.

[0129] Step 701: In response to the image hover command on the target image, obtain the text direction of the text in the target image.

[0130] The text orientation in the target image may not match the text input orientation. For example, the text orientation in the target image might be vertical, while the text input orientation is horizontal. In such cases, the target image needs to be adjusted to facilitate the text recognition process. One possible implementation allows the user to manually adjust the target image. An image rotation control is provided in the interface; when the terminal receives a trigger operation on the image rotation control, the target image is rotated. In another possible implementation, the terminal can automatically adjust the text orientation in the target image. In this method, the terminal first obtains the text orientation in the target image to determine whether adjustment is necessary.

[0131] Step 702: When the text direction is different from the text input direction, rotate the target image and display the rotated target image in a floating window. The text direction of the rotated target image is the same as the text input direction.

[0132] Here, text input direction refers to the direction in which text is entered into the text input box. In one possible implementation, when the terminal detects that the text direction corresponding to the target image is different from the text input direction, the target image is rotated to make the text direction the same as the text input direction. The terminal can then directly display the rotated target image in a floating window.

[0133] Indicative, such as Figure 8 As shown, the text direction in the target image 801 does not match the text input direction. Therefore, the terminal rotates the target image and displays the rotated target image 802 in a floating window.

[0134] Furthermore, different images may have different sizes. If the floating window has a fixed window size, there may be a mismatch between the floating window and the image size, affecting the display of text information. Therefore, in one possible implementation, when displaying the target image within the floating window, the terminal can adaptively adjust the floating window according to the image size of the target image, ensuring that the window size matches the image size. When the terminal receives a floating command for the target image, it can obtain the image size of the target image and determine the window size of the floating window accordingly. When determining the window size, since the image can slide in the sliding direction, the terminal can identify the text in that direction. However, in non-sliding directions, there may be areas that cannot be displayed. Therefore, the terminal can determine the corresponding window size based on the size of the text area in the non-sliding direction of the image, ensuring that the floating window can fully display the text in the non-sliding direction of the image. For example, when the target image can only slide vertically, the terminal can determine the horizontal size of the floating window based on the horizontal size of the target image, keeping the two the same.

[0135] Furthermore, if the rotated target image is displayed in the floating window, the window size of the floating window is determined based on the size of the rotated target image, the floating window is created based on the determined window size, and the rotated target image is displayed in the floating window.

[0136] Step 703: In response to the text input command, while displaying the text input interface, a floating window and the target text are displayed.

[0137] Step 704: In response to the input instruction for the target text, the target text is input into the text input box of the text input interface.

[0138] The implementation methods of steps 703 and 704 can be referred to the above embodiments, and will not be repeated in this embodiment.

[0139] Step 705: In response to the stop floating operation of the floating window, stop displaying the floating window.

[0140] In one possible implementation, when the terminal receives a stop-floating operation on the floating window, the floating window and the target text are stopped from being displayed on top of the text input interface. The stop-floating operation can be a single click, double click, or long press on the floating window, etc., and this embodiment does not limit the specific type of operation.

[0141] Furthermore, if the target text is displayed on the current interface, the terminal will stop displaying the target text at the same time as stopping the display of the floating window.

[0142] In another possible implementation, if the terminal does not receive a stop operation on the floating window within a preset time period and does not receive any text input information, the floating window will be stopped from being displayed for a long time to avoid the floating window being displayed for a long time.

[0143] Step 706: In response to the trigger operation of the input completion control in the text input interface, the text in the text input box is sent and the floating window is stopped from being displayed.

[0144] In another possible implementation, after the user has finished typing text in the text input box, the text can be sent via an input completion control. For example, in a chat interface, the text input area includes a message sending control. When a trigger operation is received on the message sending control, it is confirmed that a trigger operation has been received on the input completion control, and the terminal sends the text in the text input box.

[0145] In this situation, the user has completed text input, therefore the terminal can stop displaying the floating window to prevent it from continuing to appear. Simultaneously, the terminal stops displaying the target text.

[0146] In this embodiment, when the text direction of the target image is different from the text input direction, the terminal can rotate the target image to correct the text direction, which facilitates text recognition and input and improves text input efficiency.

[0147] In the above embodiments, when creating a floating window, the size of the floating window can be adjusted to match the size of the target image. In another possible implementation, the terminal can create a fixed floating window, and when displaying the target image within the floating window, the size of the target image can be adjusted to match the size of the floating window. Alternatively, the user can manually adjust the target image.

[0148] Optionally, in response to a scaling operation on the target image, the target image is scaled, and the scaled target image is displayed in a floating window. When the terminal receives a scaling operation on the target image, the terminal can scale the target image according to the scaling operation and display the scaled target image in the floating window. In one possible implementation, an image scaling control can be provided in the floating window. When a trigger operation is received on the image scaling control, the terminal determines that a scaling operation on the target image has been received and performs scaling operation on the target image. Alternatively, the scaling operation on the target image can be performed directly; this embodiment does not limit this approach.

[0149] In one possible scenario, the terminal enlarges the target image. However, this enlargement alters the image's clarity, potentially blurring the text within the target image. Therefore, after enlarging the target image, the terminal can perform image processing to improve text recognition accuracy.

[0150] Optionally, if the target image has been enlarged, image super-resolution processing can be performed on the target image to obtain a super-resolution image.

[0151] The terminal can perform image super-resolution processing on the magnified target image to improve image resolution, thereby improving the clarity of text in the target image and helping to improve the accuracy of text recognition. Optionally, the image super-resolution processing can use any image super-resolution algorithm, such as algorithms related to deep learning, such as Super-Resolution Convolutional Neural Network (SRCNN), Deeply Recursive Convolutional Network (DRCN), and Super-Resolution Generative Adversarial Network (SRGAN). This embodiment does not limit this.

[0152] After performing image super-resolution processing on the target image, the super-resolution image is displayed in a floating window. The terminal can then perform text recognition based on the super-resolution image of the target image.

[0153] In one possible implementation, the target image may contain not only text information but also image information. Only the text information needs to be recognized. Therefore, to further improve text input efficiency, the terminal can perform cropping processing on the target image, which can improve the efficiency of the user locating the required text. In one possible implementation, displaying the target image in a floating window may further include the following steps:

[0154] Step 1: If the target image contains both image and text information, crop the target image to obtain a partial image, which is the area of ​​the target image containing text information.

[0155] In one possible implementation, after the terminal acquires the target image, it can detect the image content of the target image. If the target image is detected to contain only text information, it can be directly displayed in a floating window. However, if the target image is detected to also contain image information, it can be cropped to obtain a partial image containing only the text from the target image. The cropping process for the target image may include the following steps:

[0156] Step 1: Extract the image region within the target image to obtain the text region of the target image. The image region is the area containing image information.

[0157] The terminal first determines the location of the image information within the target image, i.e., determines the image region, and then crops the image region. The remaining image region after cropping is the text region of the target image.

[0158] Indicative, such as Figure 9As shown, the target image 901 contains image information. Therefore, the terminal can crop the image region 902 to obtain the first remaining region 903 and the second remaining region 904, which are the text regions of the target image.

[0159] Step 2: Following the text order in the target image, stitch the text regions together to obtain a partial image.

[0160] Once the remaining image area is obtained, the terminal can stitch together the text regions according to the original text order in the target image to obtain a partial image. In other words, the terminal maintains the original text order in the target image and stitches together the remaining areas after cropping the image to obtain a partial image.

[0161] Indicative, such as Figure 9 As shown, within the target image, the text corresponding to the first remaining region 903 is above the text corresponding to the second remaining region 904. Therefore, when the first remaining region 903 and the second remaining region 904 are spliced ​​together, the first remaining region 903 is above the second remaining region 904, and the spliced ​​image is a partial image 905.

[0162] Step two: Display a partial image within the floating window.

[0163] The terminal can display a stitched partial image in a floating window.

[0164] Alternatively, in another possible implementation, the target image may contain only text information but also a large amount of blank space. The terminal first identifies the blank areas within the target image, then crops these blank areas. The remaining image area after cropping is the text area of ​​the target image. Once the remaining image area is obtained, the terminal can stitch the various text areas together according to the original text order in the target image to obtain a partial image. This avoids the problem of a large amount of blank space in the target image, which would result in low scrolling efficiency and affect text input efficiency.

[0165] In one possible implementation, the text input method can be implemented as follows: Figure 11 As shown, it includes the following steps:

[0166] Step 1001: Receive the image floating command for the target image and display the target image in a floating window.

[0167] Step 1002: Perform text recognition on the content of the image in the floating window.

[0168] When a text input command is received, the terminal performs text recognition on the content of the image in the floating window.

[0169] Step 1003: Determine whether the target text has been identified. If yes, proceed to step 1004; otherwise, proceed to step 1007.

[0170] In one possible scenario, the terminal can recognize the target text corresponding to the image content, in which case the target text can be displayed; in another possible scenario, the terminal cannot recognize the text in the image content, in which case the target text will not be displayed.

[0171] Step 1004: Display the target text within a transparent layer.

[0172] When the terminal recognizes the target text, a transparent layer can be created above the text input box, and the target text can be displayed inside the transparent layer.

[0173] Step 1005: In response to the click operation on the transparent layer, the target text is entered into the text input box.

[0174] When the terminal receives a click operation on the transparent layer, the target text to be displayed can be entered into the text input box.

[0175] Step 1006: Upon receiving a double-click operation on the text input box, start the editing mode.

[0176] When the terminal receives a double-click operation on the text input box, it enters edit mode. In edit mode, the target text is not displayed, and the user can edit the text based on the image content in the floating window. In one possible implementation, the user can edit the text using the text editing controls within the text input interface.

[0177] Step 1007: Determine whether a swipe operation on the target image has been received. If so, proceed to step 1002.

[0178] When a swipe operation is received on the target image, the terminal updates the content of the image in the floating window and updates the target text in the transparent layer according to the content of the image in the floating window.

[0179] Figure 11 This application shows a structural block diagram of a text input device provided in an exemplary embodiment, the device comprising:

[0180] Image display module 1101 is used to display the target image in a floating window in response to an image hover command for the target image;

[0181] The text display module 1102 is used to respond to a text input command and display the floating window and the target text while displaying the text input interface. The target text is obtained by text recognition of the image content displayed in the floating window, and the image content belongs to the target image.

[0182] The text input module 1103 is used to input the target text into the text input box of the text input interface in response to the input instruction for the target text.

[0183] Optionally, the text display module 1102 is further configured to:

[0184] In response to a text input command, the floating window is displayed simultaneously with the text input interface;

[0185] Text recognition is performed on the image content displayed in the floating window;

[0186] If the target text is detected, the target text is displayed.

[0187] Optionally, the text display module 1102 is further configured to:

[0188] Determine the location area of ​​the text input box on the text input interface;

[0189] The floating window is displayed on top of the area outside the specified location region;

[0190] Create the transparent layer on top of the location area;

[0191] The target text is displayed in the transparent layer.

[0192] Optionally, the text input module 1103 is further configured to:

[0193] In response to a trigger operation on the transparent layer, if an input instruction for the target text is received, the target text is input into the text input box.

[0194] Optionally, the device further includes:

[0195] The image update module is used to update the image content displayed in the floating window in response to a sliding operation on the target image in the floating window;

[0196] The text recognition module is used to perform text recognition on the updated image content in the floating window in response to the end of the sliding operation, so as to obtain the updated target text;

[0197] The text update module is used to update the displayed target text based on the updated target text.

[0198] Optionally, the device further includes:

[0199] A thumbnail display module is used to display a target image thumbnail containing an indicator area around the periphery of the floating window in response to a sliding operation of the target image in the floating window. The indicator area is used to indicate the position of the image content displayed in the floating window within the target image.

[0200] The stop display module is used to stop displaying the target image thumbnail in response to the end of the sliding operation.

[0201] Optionally, the device further includes:

[0202] A startup module is used to start the editing mode in response to a trigger operation on the text input box, wherein the target text is not displayed in the editing mode;

[0203] The text input module 1103 is also used to acquire edited text and input the edited text into the input text box.

[0204] Optionally, the image display module 1101 is further configured to:

[0205] In response to a scaling operation on the target image, the target image is scaled, and the scaled target image is displayed in the floating window;

[0206] The device further includes:

[0207] The image processing module is used to perform image super-resolution processing on the target image after it has been magnified, so as to obtain a super-resolution image.

[0208] The image display module 1101 is also used to display the super-resolution image within the floating window.

[0209] Optionally, the image display module 1101 is further configured to:

[0210] In response to a trigger operation on the target image, a floating image control is displayed;

[0211] In response to a trigger operation on the image floating control, the system determines that the image floating command has been received and displays the target image within the floating window.

[0212] Optionally, the image display module 1101 is further configured to:

[0213] Obtain the text direction of the text in the target image;

[0214] When the text direction is different from the text input direction, the target image is rotated, and the rotated target image is displayed in the floating window, wherein the text direction of the rotated target image is the same as the text input direction.

[0215] Optionally, the stop display module is further configured to stop displaying the floating window in response to a stop floating operation on the floating window;

[0216] or,

[0217] Optionally, the stop display module is further configured to, in response to a trigger operation on the input completion control within the text input interface, deliver the text in the text input box and stop displaying the floating window.

[0218] Optionally, the image display module 1101 is further configured to:

[0219] If the target image contains both image information and text information, the target image is cropped to obtain a partial image, which is the area of ​​the target image containing text information.

[0220] The partial image is displayed within the floating window.

[0221] Optionally, the image display module 1101 is further configured to:

[0222] By extracting an image region within the target image, a text region of the target image is obtained, wherein the image region is the region containing the image information;

[0223] The text regions are spliced ​​together according to the text order in the target image to obtain the partial image.

[0224] In summary, this application provides an image floating function. When the terminal receives an image floating command for a target image, the target image can be displayed in a floating window. When the user is inputting text, the floating window can be displayed on top of the text input interface, making it convenient for the user to proofread the text based on the image content in the floating window without switching between the image and text input interfaces, thus improving text input efficiency. Furthermore, the terminal can also perform text recognition on the image content displayed in the floating window and display the recognized target text on top of the text input interface. The displayed target text corresponds to the image content displayed in the floating window. When the user needs to input the target text contained in the currently displayed image content, an input command for the required target text can be triggered, allowing the required text to be input into the text input box without needing to select and copy the recognized text multiple times, further improving text input efficiency.

[0225] It should be noted that the apparatus provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the apparatus can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their implementation process can be found in the method embodiments, which will not be repeated here.

[0226] Please refer to Figure 12 This diagram illustrates a structural block diagram of a terminal device 1200 provided in an exemplary embodiment of this application. The terminal device 1200 may be a portable mobile terminal, such as a smartphone, tablet computer, Moving Picture Experts Group Audio Layer III (MP3) player, or Moving Picture Experts Group Audio Layer IV (MP4) player. The terminal device 1200 may also be referred to as a user device, portable terminal, or other names.

[0227] Typically, terminal device 1200 includes a processor 1201 and a memory 1202.

[0228] Processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1201 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). Processor 1201 may also include a main processor and a coprocessor. The main processor, also known as a central processing unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1201 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1201 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0229] The memory 1202 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1202 are used to store at least one instruction, which is executed by the processor 1201 to implement the method provided in the embodiments of this application.

[0230] In some embodiments, the terminal device 1200 may also optionally include: a peripheral device interface 1203 and at least one peripheral device.

[0231] Peripheral interface 1203 can be used to connect at least one input / output (I / O) related peripheral device to processor 1201 and memory 1202. In some embodiments, processor 1201, memory 1202 and peripheral interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1201, memory 1202 and peripheral interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0232] Those skilled in the art will understand that Figure 12 The structure shown does not constitute a limitation on the terminal device 1200, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0233] This application also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by the processor to implement the text input method described in the above embodiments.

[0234] According to one aspect of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium, a processor of a terminal device reading the computer instructions from the computer-readable storage medium, the processor executing the computer instructions, causing the terminal device to perform the text input method provided in various alternative implementations of the above aspect.

[0235] Those skilled in the art will recognize that the functions described in the embodiments of this application in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0236] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A text input method, characterized in that, The method includes: In response to an image hover command for the target image, the target image is displayed in a floating window; In response to a text input command, a floating window and target text are displayed simultaneously with the text input interface. The target text is obtained by text recognition of the image content displayed in the floating window, and the image content belongs to the target image. The process of displaying the floating window and target text simultaneously with the text input interface includes: determining the position area of ​​the text input box on the text input interface; displaying the floating window on top of an area outside the position area; creating a transparent layer on top of the position area; and displaying the target text in the transparent layer. The method further includes: In response to a sliding operation on the target image within the floating window, update the image content displayed within the floating window; In response to the end of the sliding operation, text recognition is performed on the updated image content in the floating window to obtain the updated target text; Based on the updated target text, the target text displayed in the transparent layer is updated, and the target text is updated along with the update of the image content in the floating window; In response to a trigger operation on the transparent layer, an input instruction for the target text is received, and the target text is input into the text input box of the text input interface.

2. The method according to claim 1, characterized in that, The step of displaying the floating window and the target text simultaneously with displaying the text input interface includes: In response to a text input command, the floating window is displayed simultaneously with the text input interface; Text recognition is performed on the image content displayed in the floating window; If the target text is detected, the target text is displayed.

3. The method according to claim 1, characterized in that, The method further includes: In response to a sliding operation on the target image within the floating window, a thumbnail of the target image containing an indicator area is displayed around the periphery of the floating window. The indicator area is used to indicate the position of the image content displayed in the floating window within the target image. In response to the end of the swiping operation, the display of the target image thumbnail stops.

4. The method according to claim 1, characterized in that, The method further includes: In response to a trigger operation on the text input box, an edit mode is initiated, in which the target text is not displayed; Obtain the edited text and enter the edited text in the input text box.

5. The method according to claim 1, characterized in that, Displaying the target image within the floating window includes: In response to a scaling operation on the target image, the target image is scaled, and the scaled target image is displayed in the floating window; The method further includes: When the target image is magnified, image super-resolution processing is performed on the target image to obtain a super-resolution image; The super-resolution image is displayed in the floating window.

6. The method according to claim 1, characterized in that, The step of displaying the target image in a floating window in response to an image hover command for the target image includes: In response to a trigger operation on the target image, a floating image control is displayed; In response to a trigger operation on the image floating control, the system determines that the image floating command has been received and displays the target image within the floating window.

7. The method according to claim 1, characterized in that, Displaying the target image within the floating window includes: Obtain the text direction of the text in the target image; When the text direction is different from the text input direction, the target image is rotated, and the rotated target image is displayed in the floating window, wherein the text direction of the rotated target image is the same as the text input direction.

8. The method according to claim 1, characterized in that, The method further includes: In response to the operation of stopping the floating window, the display of the floating window is stopped; or, In response to a trigger operation on the input completion control within the text input interface, the text in the text input box is transmitted, and the floating window is stopped from being displayed.

9. The method according to claim 1, characterized in that, Displaying the target image within the floating window includes: If the target image contains both image information and text information, the target image is cropped to obtain a partial image, which is the area of ​​the target image containing text information. The partial image is displayed within the floating window.

10. The method according to claim 9, characterized in that, The step of cropping the target image to obtain a partial image includes: By cropping an image region within the target image, a text region of the target image is obtained, wherein the image region is the region containing the image information; The text regions are spliced ​​together according to the text order in the target image to obtain the partial image.

11. A text input device, characterized in that, The device includes: The image display module is used to display the target image in a floating window in response to an image hover command for the target image; A text display module, in response to a text input command, displays a floating window and target text simultaneously with a text input interface. The target text is obtained by text recognition of the image content displayed in the floating window, where the image content belongs to the target image. The process of displaying the floating window and target text simultaneously with the text input interface includes: determining the position area of ​​the text input box on the text input interface; displaying the floating window on top of an area outside the position area; creating a transparent layer on top of the position area; and displaying the target text in the transparent layer. The image update module is used to update the image content displayed in the floating window in response to a sliding operation on the target image in the floating window; The text recognition module is used to perform text recognition on the updated image content in the floating window in response to the end of the sliding operation, so as to obtain the updated target text; The text update module is used to update the target text displayed in the transparent layer based on the updated target text, wherein the target text is updated along with the update of the image content in the floating window; The text input module is used to respond to a trigger operation on the transparent layer, determine that an input instruction for the target text has been received, and input the target text into the text input box of the text input interface.

12. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing at least one program, which is loaded and executed by the processor to implement the text input method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one program, which is loaded and executed by a processor to implement the text input method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor of a terminal device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to implement the text input method as described in any one of claims 1 to 10.

Images