Character input method, system and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a character input method, system and device, electronic equipment and a storage medium, the character input method is applied to wearable equipment, the wearable equipment comprises a camera, the method comprises the steps that multiple frames of target images containing an earphone are collected through the camera, and the earphone comprises a light emitting module; identifying the light image content of the light emitting module in each frame of the target image; determining a handwriting track according to the bright image content in each frame of the target image; and inputting the text content corresponding to the handwriting track. By implementing the embodiment, the convenience and accuracy of the character input method of the wearable device can be improved.

Description

Technical Field

[0001] The present application relates to the field of human-computer interaction technology, and in particular to a text input method, system, device, electronic device and storage medium. Background Art

[0002] Wearable devices, as a kind of portable devices, are usually small and convenient. The display screens of wearable devices are usually small, such as smart watches and smart bracelets. Therefore, the text input method of wearable devices has always been a pain point. There are currently two main input methods: users input by touching the virtual keyboard on a smaller display screen, and input by voice. The former is extremely challenging to the recognition accuracy of the touch screen, and the latter has high requirements for natural language processing (different languages, accents, slang, etc.). And for wearable devices, input through the virtual keyboard is usually input with one hand, which means that the keyboard can only be arranged in a one-handed way, and the user operation is cumbersome; and voice input is not very friendly to the input of long texts, and voice input cannot be used in any scenario. Therefore, how to improve the convenience and accuracy of the text input method of wearable devices has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application disclose a text input method, system, device, electronic device and storage medium, which can improve the convenience and accuracy of the text input method of a wearable device.

[0004] The embodiment of the present application discloses a text input method, which is applied to a wearable device, wherein the wearable device includes a camera, and the method includes:

[0005] Capturing multiple frames of target images including the earphones through the camera, wherein the earphones include a light-emitting module;

[0006] Identifying the light image content of the light-emitting module in each frame of the target image;

[0007] Determine the handwriting trajectory according to the bright image content in the target image of each frame;

[0008] Input the text content corresponding to the handwriting track.

[0009] In one embodiment, the light emitting module is used to emit light according to a target color; and the step of identifying the light image content of the light emitting module in each frame of the target image includes:

[0010] Performing color feature recognition on the target image of each frame, determining an image area corresponding to the target color in the target image of each frame as bright image content, and determining image position information corresponding to the bright image content in the target image of each frame;

[0011] The step of determining the handwriting trajectory according to the bright image content in each frame of the target image comprises:

[0012] The handwriting trajectory is determined according to the image position information corresponding to the bright image content in the target image of each frame.

[0013] In one embodiment, the wearable device is communicatively connected to the headset; before the camera captures multiple frames of target images including the headset, the method further includes:

[0014] Generate a control instruction according to the target color, and send the control instruction to the headset, wherein the control instruction is used to instruct the headset to control the light-emitting module to emit light according to the target color;

[0015] The target color is a preset color, or the target color is a color corresponding to the ambient color of the current environment.

[0016] In one embodiment, the method further comprises:

[0017] The target images of the multiple frames including the earphones captured by the camera within the target time period are used as a target image group corresponding to a single character;

[0018] The step of determining the handwriting trajectory according to the bright image content in each frame of the target image comprises:

[0019] The handwriting trajectory corresponding to the single character is determined according to the bright image content of each frame of the target image in the target image group.

[0020] In one embodiment, the headset further includes an interactive control; before using the target image containing the headset captured by the camera within the target time period as the target image corresponding to the single character, the method further includes:

[0021] receiving a first signal sent by the headset, and taking a time point when the first signal is received as a first time point, wherein the first signal is a signal sent to the wearable device when the headset detects a first interaction operation through the interaction control;

[0022] receiving a second signal sent by the headset, and taking the time point of receiving the second signal as the second time point; the second signal is a signal sent to the wearable device when the headset detects a second interactive operation through the interactive control;

[0023] The time period between the first time point and the second time point is taken as the target time period.

[0024] In one embodiment, before using the target image containing the earphone captured by the camera within the target time period as the target image corresponding to the single character, the method further includes:

[0025] Performing color feature recognition on each frame of the target image containing the earphone captured by the camera to determine whether the light-emitting module in each frame of the target image is in a light-emitting state;

[0026] If it is detected that the light emitting module in the first target image is not in a light emitting state, and the light emitting module in the next target image of the first target image is in a light emitting state, the acquisition moment corresponding to the next target image is taken as the third time point;

[0027] If it is detected that the light-emitting module in the second target image is in a light-emitting state, and the light-emitting module in the next target image of the second target image is not in a light-emitting state, taking the acquisition moment corresponding to the second target image as the fourth time point;

[0028] The time period between the third time point and the fourth time point is taken as the target time period.

[0029] In one embodiment, before acquiring multiple frames of target images including the earphone by the camera, the method further includes:

[0030] When it is detected that the input method of the wearable device is switched to the handwriting input method, a status acquisition instruction is sent to the headset, so that the headset feeds back the headset status to the wearable device according to the status acquisition instruction; the headset status includes one of a charging state, a wearing state, and a non-wearing state;

[0031] If the earphone is in the unworn state, the step of capturing multiple frames of target images containing the earphone through the camera is performed.

[0032] In one embodiment, after sending the status acquisition instruction to the headset so that the headset feeds back the headset status to the wearable device according to the status acquisition instruction, the method further includes:

[0033] If the earphone is in the charging state, outputting a first prompt message, wherein the first prompt message is used to prompt the user to take out the earphone from the earphone charging compartment;

[0034] If the earphone is in the wearing state, a second prompt message is output, where the second prompt message is used to prompt the user to take the earphone off the ear.

[0035] In one embodiment, the wearable device includes a smart watch, the smart watch includes a host body and a bracket, the camera is arranged on the host body, the host body is connected to the bracket and the host body can be flipped relative to the bracket to form different flipping angles, so that the camera obtains different shooting directions;

[0036] The step of collecting a plurality of frames of target images including the earphone by the camera includes:

[0037] Detecting a flip angle of the host body relative to the bracket;

[0038] When the flip angle is within a preset angle range, a plurality of frames of target images including the earphone are collected by the camera.

[0039] In one embodiment, the smart watch further includes an earphone charging compartment, which is disposed in the bracket. When the host body is in a first posture, the earphone charging compartment is in a closed state, and when the host body is in a second posture, the earphone charging compartment is in an open state, wherein the first posture is a state in which the host body is stacked on the bracket, and the second posture is a state in which the host body is at a certain flip angle relative to the bracket;

[0040] The method further comprises:

[0041] If it is detected that the host body is flipped from the second posture to the first posture and the earphone charging compartment is in the closed state, the input method of the smart watch is switched to the target input method.

[0042] The embodiment of the present application discloses a handwriting input system, the system comprising a wearable device and a headset, the wearable device comprising a camera, the headset comprising a light emitting module;

[0043] The earphone is used to control the light-emitting module to emit light;

[0044] The wearable device is used to collect multiple frames of target images containing headphones through the camera; identify the light image content of the light-emitting module in each frame of the target image; determine a handwriting trajectory based on the light image content in each frame of the target image; and input text content corresponding to the handwriting trajectory.

[0045] The embodiment of the present application discloses a text input device, which is applied to a wearable device, wherein the wearable device includes a camera, and the device includes:

[0046] An image acquisition module, used for acquiring multiple frames of target images including the earphone through the camera, wherein the earphone includes a light-emitting module;

[0047] A content recognition module, used to recognize the light image content of the light-emitting module in each frame of the target image;

[0048] A trajectory determination module, used for determining a handwriting trajectory according to the bright image content in the target image of each frame;

[0049] The content input module is used to input the text content corresponding to the handwriting track.

[0050] In one embodiment, the light emitting module is used to emit light according to the target color; the content recognition module is also used to recognize the color features of the target image in each frame, determine the image area corresponding to the target color in each frame of the target image as the bright image content, and determine the image position information corresponding to the bright image content in each frame of the target image. The trajectory determination module is also used to determine the handwriting trajectory according to the image position information corresponding to the bright image content in each frame of the target image.

[0051] In one embodiment, the wearable device is communicatively connected to the headset; the text input device also includes an instruction sending module, which is used to generate a control instruction according to a target color, and send the control instruction to the headset, wherein the control instruction is used to instruct the headset to control the light-emitting module to emit light according to the target color; the target color is a preset color, or the target color is a color corresponding to the ambient color of the current environment.

[0052] In one embodiment, the text input device further includes an image grouping module, which is used to group multiple frames of target images containing headphones captured by the camera within a target time period as a target image group corresponding to a single character. The trajectory determination module is also used to determine the handwriting trajectory corresponding to the single character based on the light image content of each frame of the target image in the target image group.

[0053] In one embodiment, the headset also includes an interactive control; the text input device also includes a signal receiving module, which is used to receive a first signal sent by the headset, and use the time point when the first signal is received as the first time point, and the first signal is a signal sent to the wearable device when the headset detects a first interactive operation through the interactive control; receive a second signal sent by the headset, and use the time point when the second signal is received as the second time point; the second signal is a signal sent to the wearable device when the headset detects a second interactive operation through the interactive control; and use the time period between the first time point and the second time point as the target time period.

[0054] In one embodiment, the text input device also includes a color recognition module for performing color feature recognition on each frame of the target image containing the earphone captured by the camera to determine whether the light-emitting module in each frame of the target image is in a light-emitting state; if it is detected that the light-emitting module in the first target image is not in a light-emitting state, and the light-emitting module in the next target image of the first target image is in a light-emitting state, the acquisition time corresponding to the next target image is taken as the third time point; if it is detected that the light-emitting module in the second target image is in a light-emitting state, and the light-emitting module in the next target image of the second target image is not in a light-emitting state, the acquisition time corresponding to the second target image is taken as the fourth time point; the time period between the third time point and the fourth time point is taken as the target time period.

[0055] In one embodiment, the instruction sending module is also used to send a status acquisition instruction to the headset when it is detected that the input method of the wearable device is switched to a handwriting input method, so that the headset can feedback the headset status to the wearable device according to the status acquisition instruction; the headset status includes one of a charging state, a wearing state and a not-worn state; if the headset status is in the not-worn state, the step of capturing multiple frames of target images containing the headset through the camera is executed.

[0056] In one embodiment, the text input device also includes an information prompt module, which is used to output a first prompt message if the earphone is in the charging state, and the first prompt message is used to prompt the earphone to be removed from the earphone charging compartment; if the earphone is in the wearing state, a second prompt message is output, and the second prompt message is used to prompt the earphone to be removed from the ear.

[0057] In one embodiment, the wearable device includes a smart watch, which includes a host body and a bracket, the camera is arranged on the host body, the host body is connected to the bracket and the host body can be flipped relative to the bracket to form different flip angles, so that the camera can obtain different shooting directions; the image acquisition module is also used to detect the flip angle of the host body relative to the bracket; when the flip angle is within a preset angle range, multiple frames of target images containing headphones are acquired through the camera.

[0058] In one embodiment, the smart watch also includes an earphone charging compartment, which is arranged in the bracket, and when the host body is in a first posture, the earphone charging compartment is in a closed state, and when the host body is in a second posture, the earphone charging compartment is in an open state, wherein the first posture is a state in which the host body is stacked on the bracket, and the second posture is a state in which the host body is at a certain flip angle relative to the bracket; the text input device also includes an input method switching module, which is used to switch the input method of the smart watch to the target input method if it is detected that the host body is flipped from the second posture to the first posture and the earphone charging compartment is in the closed state.

[0059] The present application discloses an electronic device, including:

[0060] A memory storing executable program code;

[0061] a processor coupled to the memory;

[0062] The processor calls the executable program code stored in the memory to execute the method described in any one of the above embodiments.

[0063] An embodiment of the present application discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the method described in any one of the above embodiments.

[0064] Through the text input method, system, device, electronic device and storage medium disclosed in the embodiments of the present application, the wearable device can capture multiple frames of target images containing headphones through a camera, and the headphones can include a light-emitting module. The wearable device can identify the light image content of the light-emitting module of the headphones in each frame of the target image, and determine the handwriting trajectory according to the light image content in each frame of the target image, and then input the text content corresponding to the handwriting trajectory; in the embodiments of the present application, the headphones can control the light-emitting module to emit light, and the wearable device can capture the moving trajectory of the light-emitting module on the headphones as a handwriting trajectory through the camera, so that the headphones have the function of a stylus, and the user can realize handwriting input to the wearable device by moving the headphones. The wearable device identifies the light-emitting module in the target image captured by the camera and determines the handwriting trajectory, and finally can input the text content corresponding to the handwriting trajectory, which conforms to the user's text input habits and the input method is simple to operate, thereby improving the convenience and accuracy of the text input method of the wearable device. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1-A is a schematic diagram of a text input system disclosed in an embodiment of the present application;

[0067] Figure 1-B It is a structural schematic diagram of a smart watch including an earphone charging compartment disclosed in an embodiment of the present application;

[0068] Figure 1-C It is a schematic diagram of an application scenario of a text input method disclosed in an embodiment of the present application;

[0069] Figure 2 It is a flowchart of a text input method disclosed in an embodiment of the present application;

[0070] Figure 3 It is a flowchart of another text input method disclosed in an embodiment of the present application;

[0071] Figure 4 It is a flowchart of another text input method disclosed in the embodiment of the present application;

[0072] Figure 5 is a timing diagram of interaction between a wearable device and a headset disclosed in an embodiment of the present application;

[0073] Figure 6 It is a modular schematic diagram of a text input device disclosed in an embodiment of the present application;

[0074] Figure 7 It is a structural block diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0075] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0076] It should be noted that the terms "including" and "having" in the embodiments of the present application and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0077] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, the first prompt information may be referred to as the second prompt information, and similarly, the second prompt information may be referred to as the first prompt information. Both the first prompt information and the second prompt information are prompt information, but they are not the same prompt information.

[0078] The embodiments of the present application disclose a text input method, system, device, electronic device and storage medium, which can improve the convenience and accuracy of the text input method of a wearable device.

[0079] The following is a detailed description with reference to the accompanying drawings.

[0080] like Figure 1-A As shown, Figure 1-A 1 is a schematic diagram of a text input system disclosed in an embodiment of the present application. The text input system may include a wearable device 110 and a headset 120. The headset 120 may be communicatively connected to the wearable device 11. The communication connection method may include, but is not limited to, a Bluetooth connection and a ZigBee (ZigBee protocol) connection. The wearable device 110 includes a camera 1100. The wearable device 110 in FIG. 1 is in the form of a smart watch, but is not specifically limited thereto. The position of the camera 1100 on the wearable device 110 is also only an example. As shown by the lines in FIG. 1, the camera 1100 corresponds to a certain field of view, and the headset 120 is located within the shooting range of the camera 1100. The headset 120 includes a light emitting module 121. The headset 120 can control the light emitting module 121 to emit light. Similarly, the position of the light emitting module 121 on the headset 120 is also only an example.

[0081] Among them, the earphone 120 controls the light-emitting module 121 to emit light, and the wearable device 110 can collect multiple frames of target images containing the earphone 120 through the camera 1100, identify the light image content of the light-emitting module 121 in each frame of the target image, and determine the handwriting trajectory according to the light image content in each frame of the target image, and then input the text content of the handwriting trajectory.

[0082] In order to further improve the convenience of the text input method, the wearable device may include an earphone charging compartment. In some embodiments, Figure 1-B As shown, Figure 1-B It is a structural schematic diagram of a smart watch including an earphone charging compartment disclosed in an embodiment of the present application. The wearable device may include a smart watch 110. The smart watch 110 may include a host body 111, an earphone charging compartment 112, a bracket 113, a strap 114 and a connecting portion 115. The camera 1100 is arranged on the host body 111. The host body 111 is connected to the bracket 113 and the host body 111 can be flipped relative to the bracket 113 to form different flipping angles, so that the camera 1100 can obtain different shooting directions. Among them, the earphone charging compartment 112 can be arranged on the bracket 113, and the earphones that are communicatively connected to the smart watch 110 can be charged in the earphone charging compartment 112 of the smart watch 110. Optionally, the earphones in the earphone charging compartment 112 may include one or more, Figure 1-B The two earphones are only an example and are not limited thereto. The number of earphones may be determined based on various factors such as the size and structure of the smart watch, and is usually two.

[0083] In the embodiment of the present application, the smart watch including the earphone charging compartment can be applied to the text input method, such as Figure 1-C As shown, Figure 1-C It is a schematic diagram of an application scenario of a text input method disclosed in an embodiment of the present application, wherein when a certain flip angle is formed between the host body 111 and the bracket 113, the user can take out the earphone 120 from the earphone charging compartment 112, the earphone 120 controls the light-emitting module 121 to emit light, and the camera 111 can capture a target image including the earphone 120 within the field of view.

[0084] Optionally, the host body 111 can be divided into different postures according to different flip angles, and different postures can correspond to different states of the earphone charging compartment 112. In one embodiment, when the host body 111 is in a first posture, the earphone charging compartment 112 is in a closed state, and when the host body 111 is in a second posture, the earphone charging compartment 112 is in an open state, wherein the first posture is a state in which the host body 111 is stacked on the bracket 113, such as Figure 1-B As shown, Figure 1-B The main body 111 in the figure can be regarded as a state of being stacked on the bracket 113, and the second posture is a state in which the main body 111 is flipped at a certain angle relative to the bracket 113, such as Figure 1-C As shown, Figure 1-C The main body 111 can be regarded as being in a state of being flipped at a certain angle relative to the bracket 113.

[0085] like Figure 2 As shown, Figure 2 : is a flowchart of a text input method disclosed in an embodiment of the present application. The text input method can be applied to the wearable device in the above embodiment. The text input method may include the following steps:

[0086] Step 210: Capture multiple frames of target images including the earphones through a camera.

[0087] In some embodiments, when the user of the wearable device needs to input text through the wearable device, the wearable device can detect the user's input method switching operation, and according to the input method switching operation, switch the current input method of the wearable device to the handwriting input method, or, when the default input method of the wearable device is the handwriting input method, the wearable device can directly load the handwriting input method when detecting a scene where text input is required. Different from the use of the display screen of the wearable device as a handwriting area in the related art, in the embodiment of the present application, the user can use the headset including the light-emitting module as a handwriting input device with a handwriting function, and the headset can control the light-emitting module to emit light, and the user can realize handwriting input by moving the headset within the camera range of the camera of the wearable device. The wearable device can capture multiple frames of target images containing the headset through the camera. Optionally, the camera of the wearable device can capture multiple frames of target images containing the headset according to a preset acquisition frequency. For example, the wearable device can capture 60 frames of target images per second through the camera, but is not limited to this.

[0088] It should be noted that the images captured by the camera in the embodiment of the present application are not necessarily all target images, that is, the camera in the embodiment of the present application may also capture images that do not contain headphones. The wearable device can detect whether there are headphones within the field of view of the camera, and when there are headphones within the field of view of the camera, the image containing headphones captured by the camera is used as the target image, which can improve the accuracy of the target image, thereby improving the accuracy of the text input method. Optionally, the wearable device can perform image detection on the image captured by the camera, identify feature points in the image corresponding to the headphones, and thus determine whether there are headphones within the field of view of the camera. Optionally, a positioning device can be provided on the wearable device and the headphones, such as UWB (UltraWideBand), and the wearable device can determine whether the headphones are within the field of view of the camera based on the relative position between the headphones and the wearable device.

[0089] Optionally, when the wearable device detects the presence of headphones within the field of view of the camera, the wearable device may start to capture multiple frames of target images containing headphones through the camera. Optionally, the wearable device may also start to capture multiple frames of target images containing headphones through the camera when it detects that the user starts to write characters. Among them, the wearable device may determine whether the user starts to write characters based on the signal of the headphones, or the wearable device may determine that the user starts to write characters when it detects that a light-emitting module starts to emit light within the field of view of the camera. The embodiment of the present application does not limit the timing of starting to capture the target image. The main purpose is to enable the captured multiple frames of target images to recognize the user's writing content, thereby improving the accuracy of the text input method.

[0090] In one embodiment, the step of collecting multiple frames of target images including the earphones through a camera may include detecting the flip angle of the host body relative to the bracket, and when the flip angle is within a preset angle range, collecting multiple frames of target images including the earphones through the camera. The preset angle range may be preset by the user or by the staff when the smart watch leaves the factory, and there is no restriction on this. It is generally believed that within the preset angle range, the handwriting posture of the user can be more closely matched, thereby improving the convenience of the text input method.

[0091] Step 220: Identify the light image content of the light-emitting module in each frame of the target image.

[0092] The wearable device can identify the light module of the headset contained in each frame of the target image to determine the light image content of the light module in each frame of the target image, and the light image content can include the image area of ​​the light module in the target image. Furthermore, the wearable device can also obtain image information corresponding to the light image content of the light module in each frame of the target image, and the image information can include one or more of image position information, light color information, and light brightness information of the light image content in the target image.

[0093] Step 230: determining the handwriting trajectory according to the bright image content in each frame of the target image.

[0094] In some embodiments, the wearable device can determine the moving trajectory of the headset according to the image position information corresponding to the bright image content in each frame of the target image, and the moving trajectory can be used as the handwriting trajectory. The wearable device can arrange the image position information corresponding to the bright image content in each frame of the target image in the order of the acquisition time corresponding to each frame of the target image from first to last, and determine the trajectory point of the moving trajectory corresponding to the light-emitting module of the headset according to the image position information corresponding to the bright image content in each frame of the target image, thereby determining the handwriting trajectory.

[0095] Optionally, when the wearable device can also obtain other image information such as luminous color information and luminous brightness information corresponding to the bright image content in each frame of the target image, it can determine whether to retain the image position information of the bright image content in the target image according to other image information corresponding to the bright image content in each frame of the target image, so as to determine the trajectory point of the moving trajectory. As an example, it can be determined whether the luminous color information corresponding to the bright image content in each frame of the target image indicates the target color. If the luminous color information corresponding to the bright image content in the target image indicates the target color, the image position information of the bright image content in the target image can be retained to determine the trajectory point of the moving trajectory. Wherein, the target color may refer to the color of light emitted by the light module when the headset is used as a handwriting input device. For example, the target color may be red. If the luminous color information corresponding to the bright image content in the target image indicates red, the image position information of the bright image content in the target image is retained. Otherwise, the image position information of the bright image content in the target image is discarded and is not used to determine the trajectory point of the moving trajectory. By implementing this embodiment, target images that do not meet the requirements can be eliminated based on the luminous color information and luminous brightness information corresponding to the luminous image content, thereby improving the accuracy of the handwriting trajectory and thus improving the accuracy of the text input method.

[0096] Step 240: input text content corresponding to the handwriting track.

[0097] The wearable device can determine the text content corresponding to the handwriting trajectory through a character recognition method, so that the text content corresponding to the handwriting trajectory can be input, wherein the character recognition method may include but is not limited to determining characters through a classifier, a character template matching method, a character recognition method based on deep learning, etc. The embodiment of the present application does not limit the type of character recognition method.

[0098] Optionally, when the wearable device detects that the text content corresponding to the handwriting trajectory is a complete single character, it means that the user has just finished writing a single character, and there may be a pause time to think or find the starting position of the next character. The wearable device can suspend the execution of the above steps 210 to 240 until the wearable device determines that the user starts writing the next character, and the camera executes the above steps 210 to 240 again. Optionally, the wearable device can also suspend the execution of the above steps 210 to 240 when a complete single word is detected.

[0099] Among them, the wearable device can determine whether the user starts writing the next character based on the signal of the earphone. The wearable device can also detect the motion characteristics of the earphone or the motion characteristics of the light-emitting module within the field of view of the camera, and determine whether the user starts writing the next character based on the motion characteristics of the earphone or the motion characteristics of the light-emitting module. The motion characteristics can refer to the motion speed. The wearable device can determine that the user starts writing the next character when it detects that the motion speed is greater than the speed threshold. It should be noted that regardless of whether the wearable device is paused or executing the above steps 210 to 240, the camera of the wearable device can be in the camera state. Therefore, the wearable device can detect the motion characteristics of the earphone or the motion characteristics of the light-emitting module within the field of view of the camera.

[0100] The implementation of this embodiment can reduce the workload of the wearable device, reduce the power consumption of the wearable device, and avoid interference from other irrelevant information, thereby avoiding recognition of erroneous text content, and can also improve the accuracy of the text input method.

[0101] Optionally, when the wearable device detects that the earphone leaves the field of view of the camera and reaches a certain time, the camera can be controlled to turn off the camera state, or when the wearable device switches from the handwriting input method to other input methods, the camera can also be controlled to turn off the camera state. Through this method, the power consumption of the wearable device can be further reduced. As an optional implementation, when the wearable device is a smart watch including an earphone charging compartment, if it is detected that the host body flips from the second posture to the first posture, and the earphone charging compartment is in a closed state, the input method of the smart watch is switched to the target input method, wherein the target input method can be the default input method of the smart watch, or it can be the input method before switching to the handwriting input method. That is, the user can automatically switch the input method of the smart watch by flipping the host body from the second posture to the first posture, and can also turn off the camera state, thereby improving the convenience of the text input method.

[0102] In an embodiment of the present application, the wearable device can capture multiple frames of target images containing headphones through a camera. The headphones may include a light-emitting module. The wearable device can identify the light image content of the light-emitting module of the headphones in each frame of the target image, and determine the handwriting trajectory based on the light image content in each frame of the target image, and then input the text content corresponding to the handwriting trajectory; in an embodiment of the present application, the headphones can control the light-emitting module to emit light, and the wearable device can capture the moving trajectory of the light-emitting module on the headphones as a handwriting trajectory through the camera, so that the headphones have the function of a stylus, and the user can realize handwriting input to the wearable device by moving the headphones. The wearable device identifies the light-emitting module in the target image captured by the camera and determines the handwriting trajectory, and finally can input the text content corresponding to the handwriting trajectory, which conforms to the user's text input habits and the input method is simple to operate, thereby improving the convenience and accuracy of the text input method of the wearable device.

[0103] like Figure 3 As shown, Figure 3 : is a flowchart of another text input method disclosed in an embodiment of the present application. The text input method can be applied to the wearable device in the above embodiment. The text input method may include the following steps:

[0104] Step 310: Generate a control instruction according to the target color, and send the control instruction to the headset.

[0105] Before capturing multiple frames of target images including the earphone through the camera, the wearable device can control the light-emitting module of the earphone to emit light, so that the camera can capture the target image including the light-emitting module in the light-emitting state. Therefore, the wearable device can obtain the target color corresponding to the light-emitting module, generate a control instruction according to the target color, and send the control instruction to the earphone. After receiving the control instruction, the earphone can control the light-emitting module to emit light according to the target color according to the control instruction. The target color can be a preset color, or the target color can be a color corresponding to the ambient color of the current environment.

[0106] As an optional implementation, the wearable device can collect the current environment image through a camera, and perform color feature analysis on the current environment image to determine the environment color of the current environment, and then determine the color corresponding to the environment color of the current environment as the target color. Among them, the environment color of the current environment can include multiple colors, and can also include the image proportion occupied by various colors, and can also include the area size of the largest color block of various colors in the current environment image. The wearable device can analyze the conflict degree of various colors in the current environment according to the environment color of the current environment. It should be understood that the higher the conflict degree of the color, the easier it is to detect the color in the current environment. Therefore, the wearable device can select the color with the highest conflict degree as the target color. Optionally, the wearable device can be preset with multiple colors, so as to analyze the conflict degree of each preset color in the current environment, or the wearable device can also analyze the conflict degree of the three basic colors of red, yellow and blue in the current environment. Implementing this implementation can improve the detection accuracy of the light-emitting module of the wearable device, thereby improving the accuracy of text input.

[0107] Step 320: Capture multiple frames of target images including the earphones through a camera.

[0108] In order to enable the camera to capture the target image containing the earphone, before capturing multiple frames of the target image containing the earphone through the camera, the wearable device may also first obtain the earphone status of the earphone, and determine whether to execute the next step according to the earphone status of the earphone. The next step may refer to step 320 or step 310, without limitation.

[0109] In one embodiment, when it is detected that the input method of the wearable device is switched to the handwriting input method, the wearable device can send a status acquisition instruction to the headset, so that the headset can feedback the headset status to the wearable device according to the status acquisition instruction. If the headset status is in a not worn state, the step of capturing multiple frames of target images containing the headset through the camera is executed.

[0110] The earphone status includes one of a charging status, a wearing status, and a non-wearing status. The charging status is the status of the earphone being charged in the earphone charging compartment, the wearing status is the status of the earphone being worn on the user's ear, and the non-wearing status is the status of the earphone not being charged in the earphone charging compartment and not being worn on the user's ear. When the earphone is in a wearing status or a charging status, it can be considered that the earphone cannot be used as a handwriting input device. Optionally, if step 310 is not executed, if the earphone status is in a non-wearing status, the wearable device may first execute step 310 and then execute step 320.

[0111] By implementing this embodiment, the probability that the acquired image is the target image can be higher, thereby avoiding the acquisition of a large number of non-target images and reducing the amount of calculation of the wearable device.

[0112] As an optional implementation, if the earphone is in a charging state, the wearable device may output a first prompt message, and if the earphone is in a wearing state, the wearable device may output a second prompt message. The first prompt message is used to prompt the user to remove the earphone from the earphone charging compartment, and the second prompt message is used to prompt the user to remove the earphone from the ear. Optionally, when the earphone is in a wearing state, the wearable device may also send a signal output instruction containing the second prompt message to the earphone, and the earphone may output the second prompt message according to the signal output instruction. By implementing this implementation, the user is prompted to perform the correct operation of handwriting input through the prompt message, thereby improving the convenience of the text input method.

[0113] Step 330 , performing color feature recognition on each frame of the target image, determining the image area corresponding to the target color in each frame of the target image as the bright image content, and determining the image position information corresponding to the bright image content in each frame of the target image.

[0114] The wearable device can perform color feature recognition on each frame of the target image, and determine the image area corresponding to the target color in each frame of the target image as the light image content. Optionally, the shape of the image area can be determined according to the shape of the light emitting module. The wearable device can determine the image area corresponding to the target color in each frame of the target image and whose area shape matches the shape of the light emitting module as the light image content according to the shape of the light emitting module and the target color, which can improve the accuracy of the light image content.

[0115] The wearable device can also determine the image position information corresponding to the bright image content in each frame of the target image. The image position information may include the center position of the bright image content. For example, if the bright image content is a circle, the image position information may include the position information of the center of the circle. The image position information may also include the position information corresponding to the regional shape of the bright image content. For example, if the bright image content is a circle, then in the image coordinate system, the image position information may include the function expression corresponding to the circle. This application does not limit the image position information.

[0116] Step 340 , determining the handwriting trajectory according to the image position information corresponding to the bright image content in each frame of the target image.

[0117] Step 350: input text content corresponding to the handwriting track.

[0118] In an embodiment of the present application, the wearable device can also generate a control instruction according to the color, and send the control instruction to the headset to instruct the headset to control the light-emitting module to emit light according to the target color. Through the communication between the wearable device and the headset, the interaction between the devices is enhanced, the degree of automation of the text input method is improved, and thus the convenience of the text input method is improved. The wearable device can also perform color feature recognition on each frame of the target image, determine the image area corresponding to the target color in each frame of the target image as the bright image content, and determine the image position information corresponding to the bright image content in each frame of the target image, and then determine the handwriting trajectory according to the image position information corresponding to the bright image content in each frame of the target image. Recognizing the bright image content based on the target color can improve the accuracy of the determined handwriting trajectory, thereby improving the accuracy of the text input method. When the accuracy is guaranteed, the user does not have to repeatedly enter the incorrectly recognized text, which can also improve the convenience of the text input method.

[0119] like Figure 4 As shown, Figure 4 : is a flowchart of another text input method disclosed in an embodiment of the present application. The text input method can be applied to the wearable device in the above embodiment. The text input method may include the following steps:

[0120] Step 410: Capture multiple frames of target images including the earphones through a camera.

[0121] Step 420 , taking multiple frames of target images including the earphone captured by the camera within the target time period as a target image group corresponding to a single character.

[0122] In order to ensure the recognition accuracy, when the input method of the wearable device is a handwriting input method, a single character is usually recognized instead of multiple characters at the same time. The wearable device can determine the target time period corresponding to the single character, and use the multiple frames of target images containing the earphones captured by the camera during the target time period as the target image group corresponding to the single character. The target time period can refer to the time period when the user writes a single character by moving the earphones.

[0123] Optionally, the target time period may be a time period determined by the wearable device according to the signal of the earphone. The earphone may detect the user's interactive operation and send a signal to the wearable device. For example, the earphone may include an interactive control, and the user may perform an interactive operation through the interactive control. The interactive operation may include but is not limited to touching and pressing the interactive control. Optionally, the target time period may also be a time period in which the light-emitting module is in a light-emitting state in each target image captured by the camera. The wearable device may detect whether the light-emitting module in the target image is in a light-emitting state.

[0124] In one embodiment, the wearable device may receive a first signal sent by the headset, and use the time point of receiving the first signal as the first time point. The wearable device may also receive a second signal sent by the headset, and use the time point of receiving the second signal as the second time point. The time period between the first time point and the second time point is used as the target time period. Figure 5 As shown, Figure 5 This is a timing diagram of the interaction between a wearable device and a headset disclosed in an embodiment of the present application. In the process of determining the target time period, the wearable device can continuously collect target images through a camera. Figure 5 Only the sequence of step 420 and before is shown, which does not mean that the text input method is terminated after the target image group corresponding to a single character is determined.

[0125] The first signal may be a signal sent to the wearable device when the headset detects a first interactive operation through the interactive control, and the second signal may be a signal sent to the wearable device when the headset detects a second interactive operation through the interactive control. Optionally, the first interactive operation and the second interactive operation may also be different operations for the same control, for example, the first interactive operation is pressing, and the second interactive operation is touching, and the difference between the two is the different operating forces, thereby reducing the number of headset controls and reducing costs.

[0126] As an optional implementation, the interactive control of the headset may include a first interactive control and a second interactive control. When the headset detects a first interactive operation for the first interactive control, the headset may send a first signal to the wearable device. When the headset detects a second interactive operation for the second interactive control, the headset may send a second signal to the wearable device. Optionally, the first interactive control and the second interactive control may be a volume increase button and a volume decrease button of the headset. When the headset is in a worn state, that is, when the user is using the headset as an audio output device, the first interactive control and the second interactive control may be used to control the volume of the audio. When the headset is not worn and the input method of the wearable device is a handwriting input method, that is, when the user is using the headset as a handwriting input device, the first interactive control and the second interactive control may be used to interact with the wearable device for signal. By implementing this implementation, the existing controls of the headset can be used as controls for signal interaction with the wearable device during handwriting input, thereby improving the utilization rate of each control in the headset, and when the user is familiar with the existing controls of the headset, the user's learning cost can be reduced, and the convenience of the text input method can be improved.

[0127] As an optional implementation, the first interactive operation and the second interactive operation can be the same interactive operation for the same control, but the headset can determine the first interactive operation and the second interactive operation according to the order of the interactive operations. Among them, when the light-emitting module of the headset is in a light-emitting state and the camera is in a working state, the headset can determine that the interactive operation is the first interactive operation when the interactive operation is detected for the first time, and determine that the interactive operation is the second interactive operation when the interactive operation is detected for the second time, and determine it as the first interactive operation again when it is detected next time, and determine it as the second interactive operation again when it is detected next time, and so on, until the handwriting input is completed. The implementation of this implementation can improve the diversity of text input methods, simplify the user's interactive operations, and further improve the convenience of text input methods.

[0128] In one embodiment, the wearable device can perform color feature recognition on each frame of the target image containing the earphone captured by the camera to determine whether the light-emitting module in each frame of the target image is in a light-emitting state. If it is detected that the light-emitting module in the first target image is not in a light-emitting state, and the light-emitting module in the next target image of the first target image is in a light-emitting state, the collection time corresponding to the next target image is taken as the third time point. If it is detected that the light-emitting module in the second target image is in a light-emitting state, and the light-emitting module in the next target image of the second target image is not in a light-emitting state, the collection time corresponding to the second target image is taken as the fourth time point, and the time period between the third time point and the fourth time point is taken as the target time period.

[0129] In this embodiment, the headset may not communicate with the wearable device, but the headset still needs to detect the user's third interaction operation and / or fourth interaction operation. When the headset detects the third interaction operation, the headset can control the light-emitting module of the headset to emit light, and when the headset detects the fourth interaction operation, the headset can control the light-emitting module of the headset to stop emitting light. Therefore, the time point corresponding to the third interaction operation can correspond to the third time point, and the time point corresponding to the fourth interaction operation can correspond to the fourth time point. Through this embodiment, the communication delay between the headset and the wearable device can be ignored, the error of the target time period caused by the communication delay is avoided, the accuracy of the target time period is improved, and thus the accuracy of the handwriting input is improved. Based on the same reasons as the above content, the convenience of the text input method is also improved.

[0130] With respect to the above two embodiments, considering that the user needs to perform two interactive operations each time writing a single character, the writing process is relatively cumbersome. As an optional implementation, the headset may also only detect the user's second interactive operation or fourth interactive operation without detecting the first interactive operation or the third interactive operation, thereby reducing the number of user operations and improving the convenience of the text input method.

[0131] Optionally, when the second interaction operation is detected, the earphone may send a second interaction signal to the wearable device, and after a first preset duration, send a first interaction signal to the wearable device. The first preset duration may be determined according to the user's writing habit. When the wearable device receives the first interaction signal, it may input a writing prompt message to prompt the user that they can start writing the next character. Among them, the first preset duration may be the time it takes for the user to move the earphone to the starting position of writing the next character after completing the second interaction operation. Or, after recognizing the text content corresponding to the previous character, the wearable device may input multiple text contents. For example, for a single character, it may recognize two text contents, namely "日" and "目". The wearable device may receive the user's selection operation for the target text content among the multiple text contents, and thus determine the target text content as the text content corresponding to the previous character. The first preset duration may also be the time it takes for the earphone to move to the starting position of writing the next character after completing the selection operation.

[0132] Optionally, when the fourth interaction operation is detected, the earphone may control the light-emitting module to stop emitting light, and after a preset duration, control the light-emitting module to emit light. The second preset duration may be determined according to the user's writing habit. The light-emitting module emitting light may also be used to prompt the user that they can start writing the next character. Among them, the second preset duration may be the time it takes for the user to move the earphone to the starting position of writing the next character after completing the fourth interaction operation. Or, after recognizing the text content corresponding to the previous character, the wearable device may input multiple text contents. For example, for a single character, it may recognize "日" and "目". The wearable device may receive the user's selection operation for the target text content among the multiple text contents, and thus determine the target text content as the text content corresponding to the previous character. The preset duration may also be the time it takes for the earphone to move to the starting position of writing the next character after completing the selection operation.

[0133] Step 430: Identify the bright image content in each frame of the target image in the target image group.

[0134] Step 440: Determine the handwriting trajectory corresponding to a single character according to the bright image content of each frame of the target image in the target image group.

[0135] Step 450: Input the text content corresponding to the handwriting trajectory.

[0136] In an embodiment of the present application, the wearable device can also use multiple frames of target images containing headphones captured by the camera within the target time period as a target image group corresponding to a single character, and then determine the handwriting trajectory corresponding to the single character based on the light image content of each frame of the target image in the target image group. The recognition unit of handwriting input is based on a single character, which not only improves the recognition accuracy of the text content, but also conforms to the user's handwriting input habits, thereby improving the convenience of the text input method.

[0137] like Figure 6 As shown, Figure 6 6 is a modular schematic diagram of a text input device disclosed in an embodiment of the present application. The text input device 600 may include an image acquisition module 610, a content recognition module 620, a trajectory determination module 630, and a content input module 640, wherein:

[0138] An image acquisition module 610, used to acquire multiple frames of target images including the earphone through a camera, where the earphone includes a light-emitting module;

[0139] A content recognition module 620 is used to recognize the light image content of the light module in each frame of the target image;

[0140] A trajectory determination module 630, for determining a handwriting trajectory according to the bright image content in each frame of the target image;

[0141] The content input module 640 is used to input text content corresponding to the handwriting track.

[0142] In one embodiment, the light emitting module is used to emit light according to the target color; the content recognition module 620 is also used to recognize the color features of each frame of the target image, determine the image area corresponding to the target color in each frame of the target image as the bright image content, and determine the image position information corresponding to the bright image content in each frame of the target image. The trajectory determination module 630 is also used to determine the handwriting trajectory according to the image position information corresponding to the bright image content in each frame of the target image.

[0143] In one embodiment, the wearable device is communicatively connected to the earphone; the text input device also includes an instruction sending module, which is used to generate a control instruction according to the target color and send the control instruction to the earphone, and the control instruction is used to instruct the earphone to control the light-emitting module to emit light according to the target color; the target color is a preset color, or the target color is a color corresponding to the ambient color of the current environment.

[0144] In one embodiment, the text input device further includes an image grouping module, which is used to group multiple frames of target images including the earphone captured by the camera within the target time period as a target image group corresponding to a single character. The trajectory determination module 630 is also used to determine the handwriting trajectory corresponding to a single character according to the light image content of each frame of the target image in the target image group.

[0145] In one embodiment, the headset also includes an interactive control; the text input device also includes a signal receiving module, which is used to receive a first signal sent by the headset, and use the time point when the first signal is received as the first time point, the first signal being a signal sent to the wearable device when the headset detects a first interactive operation through the interactive control; receive a second signal sent by the headset, and use the time point when the second signal is received as the second time point; the second signal is a signal sent to the wearable device when the headset detects a second interactive operation through the interactive control; and use the time period between the first time point and the second time point as the target time period.

[0146] In one embodiment, the text input device also includes a color recognition module for performing color feature recognition on each frame of the target image containing the earphone captured by the camera to determine whether the light-emitting module in each frame of the target image is in a light-emitting state; if it is detected that the light-emitting module in the first target image is not in a light-emitting state, and the light-emitting module in the next target image of the first target image is in a light-emitting state, the acquisition time corresponding to the next target image is taken as the third time point; if it is detected that the light-emitting module in the second target image is in a light-emitting state, and the light-emitting module in the next target image of the second target image is not in a light-emitting state, the acquisition time corresponding to the second target image is taken as the fourth time point; the time period between the third time point and the fourth time point is taken as the target time period.

[0147] In one embodiment, the instruction sending module is also used to send a status acquisition instruction to the headset when it is detected that the input method of the wearable device is switched to the handwriting input method, so that the headset can feedback the headset status to the wearable device according to the status acquisition instruction; the headset status includes one of a charging state, a wearing state and a not-worn state; if the headset status is in the not-worn state, the step of capturing multiple frames of target images containing the headset through the camera is executed.

[0148] In one embodiment, the text input device also includes an information prompt module, which is used to output a first prompt message if the earphone is in a charging state, and the first prompt message is used to prompt the earphone to be removed from the earphone charging compartment; if the earphone is in a wearing state, a second prompt message is output, and the second prompt message is used to prompt the earphone to be removed from the ear.

[0149] In one embodiment, the wearable device includes a smart watch, which includes a host body and a bracket. The camera is arranged on the host body. The host body is connected to the bracket and the host body can be flipped relative to the bracket to form different flip angles so that the camera can obtain different shooting directions; the image acquisition module 610 is also used to detect the flip angle of the host body relative to the bracket; when the flip angle is within a preset angle range, multiple frames of target images containing headphones are captured through the camera.

[0150] In one embodiment, the smart watch also includes an earphone charging compartment, which is arranged in a bracket. When the host body is in a first posture, the earphone charging compartment is in a closed state, and when the host body is in a second posture, the earphone charging compartment is in an open state, wherein the first posture is a state in which the host body is stacked on the bracket, and the second posture is a state in which the host body is flipped at a certain angle relative to the bracket; the text input device also includes an input method switching module, which is used to switch the input method of the smart watch to the target input method if it is detected that the host body is flipped from the second posture to the first posture and the earphone charging compartment is in a closed state.

[0151] In an embodiment of the present application, the wearable device can capture multiple frames of target images containing headphones through a camera. The headphones may include a light-emitting module. The wearable device can identify the light image content of the light-emitting module of the headphones in each frame of the target image, and determine the handwriting trajectory based on the light image content in each frame of the target image, and then input the text content corresponding to the handwriting trajectory; in an embodiment of the present application, the headphones can control the light-emitting module to emit light, and the wearable device can capture the moving trajectory of the light-emitting module on the headphones as a handwriting trajectory through the camera, so that the headphones have the function of a stylus, and the user can realize handwriting input to the wearable device by moving the headphones. The wearable device identifies the light-emitting module in the target image captured by the camera and determines the handwriting trajectory, and finally can input the text content corresponding to the handwriting trajectory, which conforms to the user's text input habits and the input method is simple to operate, thereby improving the convenience and accuracy of the text input method of the wearable device.

[0152] like Figure 7 As shown, in one embodiment, an electronic device is provided, which may include:

[0153] A memory 710 storing executable program codes;

[0154] a processor 720 coupled to the memory 710;

[0155] The processor 720 calls the executable program code stored in the memory 710 to implement the text input method provided in the above embodiments.

[0156] The memory 710 may include a random access memory (RAM) or a read-only memory (ROM). The memory 710 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 710 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device during use, etc.

[0157] The processor 720 may include one or more processing cores. The processor 720 uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 710, and calling data stored in the memory 710. Optionally, the processor 720 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 720 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 720, but may be implemented separately through a communication chip.

[0158] It can be understood that the electronic device may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, WiFi (Wireless Fidelity) module, speakers, Bluetooth modules, sensors, etc., and no limitation is made here.

[0159] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the methods described in the above embodiments.

[0160] In addition, an embodiment of the present application further discloses a computer program product. When the computer program product is run on a computer, the computer can execute all or part of the steps in any one of the text input methods described in the above embodiments.

[0161] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0162] The above is a detailed introduction to a text input method, system, device, electronic device and storage medium disclosed in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A text input method, characterized in that: Applied to a wearable device, the wearable device includes a camera, and the method includes: Capturing multiple frames of target images including the earphones through the camera, wherein the earphones include a light-emitting module; Identifying the light image content of the light-emitting module in each frame of the target image; Determine the handwriting trajectory according to the bright image content in the target image of each frame; Input the text content corresponding to the handwriting track.

2. The method according to claim 1, characterized in that The light-emitting module is used to emit light according to the target color; and the identifying of the light image content of the light-emitting module in each frame of the target image includes: Performing color feature recognition on the target image of each frame, determining an image area corresponding to the target color in the target image of each frame as bright image content, and determining image position information corresponding to the bright image content in the target image of each frame; The step of determining the handwriting trajectory according to the bright image content in each frame of the target image comprises: The handwriting trajectory is determined according to the image position information corresponding to the bright image content in the target image of each frame.

3. The method according to claim 2, characterized in that The wearable device is communicatively connected to the headset; before the camera captures multiple frames of target images containing the headset, the method further includes: Generate a control instruction according to the target color, and send the control instruction to the headset, wherein the control instruction is used to instruct the headset to control the light-emitting module to emit light according to the target color; The target color is a preset color, or the target color is a color corresponding to the ambient color of the current environment.

4. The method according to claim 1, characterized in that The method further comprises: The target images of the multiple frames including the earphones captured by the camera within the target time period are used as a target image group corresponding to a single character; The step of determining the handwriting trajectory according to the bright image content in each frame of the target image comprises: The handwriting trajectory corresponding to the single character is determined according to the bright image content of each frame of the target image in the target image group.

5. The method according to claim 4, characterized in that The headset also includes an interactive control; before using the target image containing the headset captured by the camera within the target time period as the target image corresponding to the single character, the method also includes: receiving a first signal sent by the headset, and taking a time point when the first signal is received as a first time point, wherein the first signal is a signal sent to the wearable device when the headset detects a first interaction operation through the interaction control; receiving a second signal sent by the headset, and taking the time point of receiving the second signal as the second time point; the second signal is a signal sent to the wearable device when the headset detects a second interactive operation through the interactive control; The time period between the first time point and the second time point is taken as the target time period.

6. The method according to claim 4, characterized in that Before using the target image containing the earphone captured by the camera within the target time period as the target image corresponding to the single character, the method further includes: Performing color feature recognition on each frame of the target image containing the earphone captured by the camera to determine whether the light-emitting module in each frame of the target image is in a light-emitting state; If it is detected that the light emitting module in the first target image is not in a light emitting state, and the light emitting module in the next target image of the first target image is in a light emitting state, the acquisition moment corresponding to the next target image is taken as the third time point; If it is detected that the light-emitting module in the second target image is in a light-emitting state, and the light-emitting module in the next target image of the second target image is not in a light-emitting state, taking the acquisition moment corresponding to the second target image as the fourth time point; The time period between the third time point and the fourth time point is taken as the target time period.

7. The method according to claim 1, characterized in that Before collecting a plurality of frames of target images including the earphone by the camera, the method further includes: When it is detected that the input method of the wearable device is switched to the handwriting input method, a status acquisition instruction is sent to the headset, so that the headset feeds back the headset status to the wearable device according to the status acquisition instruction; the headset status includes one of a charging state, a wearing state, and a non-wearing state; If the headset is in the unworn state, the step of capturing multiple frames of target images containing the headset through the camera is performed.

8. The method according to claim 7, characterized in that After sending the status acquisition instruction to the earphone so that the earphone feeds back the earphone status to the wearable device according to the status acquisition instruction, the method further includes: If the earphone is in the charging state, outputting a first prompt message, wherein the first prompt message is used to prompt the user to take out the earphone from the earphone charging compartment; If the earphone is in the wearing state, a second prompt message is output, where the second prompt message is used to prompt the user to take the earphone off the ear.

9. The method according to any one of claims 1 to 8, characterized in that: The wearable device includes a smart watch, the smart watch includes a host body and a bracket, the camera is arranged on the host body, the host body is connected to the bracket and the host body can be flipped relative to the bracket to form different flipping angles, so that the camera can obtain different shooting directions; The step of collecting a plurality of frames of target images including the earphone by the camera includes: Detecting a flip angle of the host body relative to the bracket; When the flip angle is within a preset angle range, a plurality of frames of target images including the earphone are collected by the camera.

10. The method according to claim 9, characterized in that The smart watch further comprises an earphone charging compartment, which is arranged in the bracket. When the host body is in a first posture, the earphone charging compartment is in a closed state, and when the host body is in a second posture, the earphone charging compartment is in an open state, wherein the first posture is a state in which the host body is stacked on the bracket, and the second posture is a state in which the host body is at a certain flip angle relative to the bracket; The method further comprises: If it is detected that the host body is flipped from the second posture to the first posture and the earphone charging compartment is in the closed state, the input method of the smart watch is switched to the target input method.

11. A text input system, characterized in that: The system includes a wearable device and a headset, wherein the wearable device includes a camera, and the headset includes a light emitting module; The earphone is used to control the light-emitting module to emit light; The wearable device is used to collect multiple frames of target images containing headphones through the camera; identify the light image content of the light-emitting module in each frame of the target image; Determine a handwriting trajectory according to the bright image content in the target image in each frame; and input text content corresponding to the handwriting trajectory.

12. A handwriting input device, characterized in that: Applied to a wearable device, the wearable device includes a camera, and the device includes: An image acquisition module, used for acquiring multiple frames of target images including the earphone through the camera, wherein the earphone includes a light-emitting module; A content recognition module, used to recognize the light image content of the light-emitting module in each frame of the target image; A trajectory determination module, used for determining a handwriting trajectory according to the bright image content in the target image of each frame; The content input module is used to input the text content corresponding to the handwriting track.

13. An electronic device, characterized in that: include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method according to any one of claims 1 to 10.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 10.

Images