Character input method and device, equipment and storage medium

Abstract

The invention discloses a character input method and device, equipment and a storage medium, and relates to the technical field of smart watches. According to the technical scheme, the method comprises the steps that input starting operation is received, and at least one first gesture image is obtained in response to the input starting operation; comparing the first gesture image with a pre-stored second gesture image corresponding to each character, and determining a target character corresponding to the first gesture image; and according to the shooting sequence of the first gesture image and the corresponding target character, generating the currently input text content. By means of the technical means, the characters input by the user are determined by recognizing the gesture of the user, the problem that in the prior art, mistaken input is frequent due to the fact that keyboard input is prone to mistaken touch is solved, and the character input speed can be increased.

Description

Technical Field

[0001] The present application relates to the technical field of smart watches, and in particular to a text input method, device, equipment and storage medium. Background Art

[0002] With the popularization of the market, smart watches have become a common electronic product in society, providing great convenience for various life and work scenarios. And with the development of smart watch technology, smart watches have gradually moved from the positioning of mobile phone accessories to the direction of independent electronic products. As an independent electronic product, smart watches can be used without relying on mobile phones, and users can even carry smart watches alone in specific scenarios. In the scenario of carrying smart watches alone, users hope that smart watches have text input functions so that they can realize text chat through smart watches.

[0003] In the prior art, a smart watch displays a keyboard on its limited display screen, and the user inputs text by clicking on the keyboard. However, the keyboard area displayed on the smart watch is small, and it is easy to accidentally touch, causing the user to repeatedly delete the incorrectly input characters and then input the correct characters, which slows down the typing speed. Summary of the invention

[0004] The present application provides a text input method, device, equipment and storage medium to determine the text input by the user by recognizing the user's gestures, thereby solving the problem in the prior art that keyboard input is prone to accidental touches and leads to frequent mis-input, and is conducive to improving the text input speed.

[0005] In a first aspect, the present application provides a text input method, comprising:

[0006] receiving an input start operation, and acquiring at least one first gesture image in response to the input start operation;

[0007] Comparing the first gesture image with pre-stored second gesture images corresponding to respective characters, and determining a target character corresponding to the first gesture image;

[0008] The currently input text content is generated according to the shooting order of the first gesture images and the corresponding target characters.

[0009] In a second aspect, the present application provides a text input device, comprising:

[0010] An image acquisition module, configured to receive an input start operation, and acquire at least one first gesture image in response to the input start operation;

[0011] a character determination module, configured to compare the first gesture image with pre-stored second gesture images corresponding to respective characters, and determine a target character corresponding to the first gesture image;

[0012] The text input module is configured to generate the currently input text content according to the shooting order of the first gesture images and the corresponding target characters.

[0013] In a third aspect, the present application provides a text input device, comprising:

[0014] One or more processors; a memory storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the text input method as described in the first aspect.

[0015] In a fourth aspect, the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the text input method as described in the first aspect.

[0016] In the present application, when an input start operation is received and it is confirmed that the user is currently ready to input text through gestures, the camera is turned on and the user's gesture is photographed to obtain a first gesture image; the first gesture image is compared with a plurality of pre-stored second gesture images to determine a second gesture image that is the same as the gesture in the first gesture image, and the character associated with the second gesture image is determined as the target character corresponding to the gesture in the first gesture image; the target characters corresponding to the first gesture image are sorted according to the shooting order of the first gesture image, so as to generate the text content currently input by the user according to the sorted character sequence. Through the above technical means, the user inputs characters by making gestures instead of the user inputting characters by clicking on the watch keyboard, and the characters that the user wants to input are accurately input by recognizing the user's gestures, thereby improving the accuracy of character input, solving the problem of frequent mis-inputs caused by easy mis-touch of keyboard input in the prior art, and helping to improve the speed of text input. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a text input method provided by an embodiment of the present application;

[0018] Figure 2 is a flowchart of obtaining a first gesture image from a video provided by an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a smart watch shooting gesture provided in an embodiment of the present application;

[0020] Figure 4 is a schematic diagram of characters and corresponding gestures provided in an embodiment of the present application;

[0021] Figure 5 is a flowchart of determining a target character corresponding to a first gesture image provided by an embodiment of the present application;

[0022] Figure 6 is a structural schematic diagram of a text input device provided in an embodiment of the present application;

[0023] Figure 7 It is a structural schematic diagram of a text input device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0026] In the more common existing implementation, when a user wants to input text through a smart watch, he can click on the keyboard displayed on the display screen of the smart watch to input text. However, the keyboard area displayed on the smart watch is small, and it is easy to touch by mistake, causing the user to repeatedly delete the wrongly input characters and then enter the correct characters, and the typing speed is slow. If you want to improve the input accuracy of the keyboard, you need to improve the software and hardware functions, which is costly. In addition to keyboard input, you can also input text through voice recognition, but voice recognition is not suitable for long text input, and when the user is in a noisy environment, the sound in the environment will affect the accuracy of voice recognition.

[0027] In order to solve the above problems existing in the prior art, this embodiment provides a text input method.

[0028] The text input method provided in this embodiment can be executed by a text input device, which can be implemented by software and / or hardware, and the basic text input device can be composed of two or more physical entities, or can be composed of one physical entity. For example, the text input device can be a smart watch, or a processor of a smart watch.

[0029] The text input device is installed with at least one type of operating system, and the text input device can install at least one application based on the operating system, and the application can be an application that comes with the operating system, or an application downloaded from a third-party device or server. In this embodiment, the text input device has at least an application that can execute the text input method.

[0030] For ease of understanding, this embodiment is described by taking a smart watch as an example of a subject that executes the text input method.

[0031] Figure 1 A flowchart of a text input method provided by an embodiment of the present application is given. Figure 1 , the text input method specifically includes:

[0032] S110: Receive an input start operation, and acquire at least one first gesture image in response to the input start operation.

[0033] In this embodiment, the input start operation refers to the operation of triggering text input by the user. The input start operation can be an operation of clicking a text box, an operation of switching from other input methods to a gesture input method, or an operation of language control. Other input methods refer to methods such as keyboard input or voice input, and the gesture input method is a method of inputting text through gesture recognition provided in this embodiment.

[0034] When the smartwatch receives the input start operation input by the user, it confirms that the user currently wants to input text, then turns on the camera and prompts the user through the screen to make a gesture corresponding to the character to be input in the camera shooting area. When the user makes a gesture, the camera captures an image containing the user's gesture.

[0035] In this embodiment, the first gesture image refers to an image containing a gesture corresponding to the character input by the user. Exemplarily, after turning on the camera, the smart watch prompts the user through the screen to make a gesture corresponding to the character to be input in the shooting area, and the user can control the camera through a specific voice to capture the user's current gesture to obtain the first gesture image. Alternatively, the camera shoots at a fixed time, and the user makes a gesture corresponding to the character to be input in the shooting area before the camera counts down to shoot, and the camera shoots the user's current gesture after the countdown ends to obtain the first gesture image. For example, the camera captures an image every 3 seconds, then the user first makes a gesture corresponding to the first input character, and then after the camera captures the first gesture image containing the gesture, the user makes a gesture corresponding to the second input character.

[0036] The method of shooting the first gesture image by timed shooting or voice control requires a high degree of cooperation from the user, and the interaction complexity is high, which affects the speed of obtaining the first gesture image. In this regard, this embodiment proposes to shoot a video with a camera, and obtain a first gesture image containing the gesture corresponding to the character input by the user from the video, without the user having to specify the next gesture through voice or at a certain interval, thereby reducing the interaction complexity and optimizing the speed of obtaining the first gesture image. For example, Figure 2 FIG. 1 is a flow chart of obtaining a first gesture image from a video provided by an embodiment of the present application. Figure 2 As shown, the step of acquiring the first gesture image from the video specifically includes S1101-S1103:

[0037] S1101 . In response to an input, start an operation to capture a video through a camera.

[0038] For example, when it is confirmed that the user currently wants to input text, the camera is started, and the camera is used to record the screen of the shooting area to generate a video. After the camera is turned on, the smart watch guides the user through the screen to make gestures corresponding to the characters that the user wants to input in the shooting area. When the user continuously makes gestures corresponding to multiple characters, the camera captures the video and records the gestures corresponding to the multiple characters that the user wants to input.

[0039] In one embodiment, the camera used to capture user gestures may be a conventional camera commonly used in smart watches for video calls. In another embodiment, the camera used to capture user gestures is an infrared thermal camera, which may be arranged on the upper surface of the smart watch together with a conventional camera, or may be arranged separately on the side of the smart watch. When the infrared thermal camera is arranged on the upper surface, the shooting area is above the screen, and when the infrared thermal camera is arranged on the side, the shooting area is on the side of the screen. It is easy to understand that the image captured by a conventional camera is an ordinary color image, which is easily interfered by non-hand objects in the image when recognizing gestures, thereby affecting the accuracy of gesture recognition. The image captured by the infrared thermal camera is a thermal image, and the temperature of the human body is higher than the ambient temperature. The thermal image can highlight the difference between the user's gestures and other objects, thereby ensuring the accuracy of gesture recognition. Figure 3 Schematic diagram of a smart watch shooting gesture provided in an embodiment of the present application. Figure 3 As shown, the smart watch 11 is worn on the user's left hand 12, and the infrared thermal camera is installed on the right side of the smart watch. When the user places the right hand 13 in the shooting area of ​​the infrared thermal camera and makes a gesture, the infrared thermal camera captures an image including the gesture of the right hand 13.

[0040] S1102: Compare adjacent image frames in the captured video to determine continuous image frames containing the same gesture.

[0041] Figure 4 is a schematic diagram of characters and corresponding gestures provided in an embodiment of the present application. Figure 4 As shown in the figure, the characters include 26 letters, and each letter corresponds to a gesture. When the user wants to input the word "hello", he can input the pinyin "nihao", that is, make a continuous gesture in the shooting area of ​​the camera. Figure 4 The gestures corresponding to the letters "N", "I", "H", "A" and "O" in the video. The video captured by the camera includes image frames of the user making gestures corresponding to "N", "I", "H", "A" and "O". Since the recording frequency of the camera is generally 25 to 30 frames per second, when the user makes the gesture corresponding to "N", the camera will continuously capture nearly ten or even more than ten image frames containing the gesture corresponding to "N". When the user switches from the gesture corresponding to "N" to the gesture corresponding to "I", the camera will capture a variety of transition gestures made by the user when switching from the gesture corresponding to "N" to the gesture of "I". The user switches gestures quickly, and the number of image frames containing the same transition gesture captured continuously by the camera is small or may even be only one. The switching of other gestures is the same. It is easy to understand that multiple continuous image frames containing the same gesture in the video may be the first gesture image. Therefore, this embodiment determines the continuous image frames containing the same gesture by comparing adjacent image frames in the video.

[0042] In this embodiment, the similarity of adjacent image frames in the video can be determined. If the similarity is greater than or equal to a preset similarity threshold, it can be determined that the adjacent image frames contain the same gesture. When an image frame contains the same gesture as the previous image frame and the next image frame, it can be determined that the three image frames contain the same gesture. By analogy, the continuous image frames containing the same gesture in the video can be determined. The preset similarity threshold is the minimum similarity between two image frames containing the same gesture set in this embodiment.

[0043] S1103: When the number of the continuous image frames reaches a preset number, determine any image frame in the continuous image frames as a first gesture image.

[0044] The preset number is the minimum number of image frames containing the gesture captured by the camera according to the recording frequency when the user makes a gesture corresponding to the input character set in this embodiment. When the number of consecutive image frames containing the same gesture in the video reaches the preset number, it indicates that the gesture in the consecutive image frames is the gesture corresponding to the character that the user wants to input, and then any image frame in the consecutive image frames is obtained as the first gesture image. When the number of consecutive image frames containing the same gesture in the video is lower than the preset number, it indicates that the gesture in the consecutive image frames is a transition gesture made when the user switches the gesture of inputting characters. The transition gesture does not need to be recognized as a character, so these consecutive image frames can be deleted.

[0045] In one embodiment, when the user wants to continuously input the same character, the distance between the hand and the camera can be adjusted to prompt the smart watch that the same character is currently being continuously input. Assuming that the user wants to input the pinyin "hh", the user can first approach the camera and make a gesture corresponding to "H", then pull the distance between the hand and the camera away, and then pull the distance between the hand and the camera closer. When adjusting the distance between the hand and the camera, the hand remains in the gesture corresponding to "H". At this time, the smart watch can determine from the video captured by the camera a continuous image frame with a number of image frames greater than a preset number and containing a gesture corresponding to "H", and the size of the means corresponding to "H" in the continuous image frame is large or small. Therefore, it can be determined whether the user is currently continuously inputting the same character based on the size of the gesture in each image frame in the continuous image frames with a number of image frames reaching a preset number. Exemplarily, if the area of ​​the gesture image of any image frame in the continuous image frames with a number of image frames greater than or equal to the preset number is less than the preset area threshold, any two image frames in the corresponding continuous image frames are determined as the first gesture image. Among them, when the camera is an infrared thermal camera, the image frame is a thermal image, and the area of ​​the region in the image frame whose temperature reaches the human body temperature is calculated to obtain the gesture map area of ​​the image frame. When the gesture map area is less than the preset area threshold, it indicates that the distance between the hand and the camera in the corresponding image frame is far, and it is determined that the user's hand has made an action of pulling the camera away, and then it is determined that the user is currently continuously inputting two identical characters, so any two image frames are obtained from the continuous image frames as the first gesture image containing the gesture of the user input characters.

[0046] In another embodiment, in order to continuously input the same character, a meaningless character and a corresponding gesture may be set, and the gesture of the meaningless character is different from the gestures of other characters. For example, when the characters defined by the smart watch only include 26 letters and meaningless characters, the 26 characters correspond to Figure 4 The gestures shown correspond to meaningless characters Figure 4 Other gestures. Figure 4If the five-fingers-opening gesture is not shown, the meaningless character may correspond to the five-fingers-opening gesture. When the user wants to input the pinyin "hh", the user may first make a gesture corresponding to "H", then make a five-fingers-opening gesture, i.e., a gesture corresponding to the meaningless character, and finally make a gesture corresponding to "H". If the smartwatch captures the first gesture image by timed shooting or voice control, the smartwatch captures the corresponding first gesture image when the user makes the gesture corresponding to "H" for the first time, captures the corresponding first gesture image when the user makes the five-fingers-opening gesture, and captures the corresponding first gesture image when the user makes the gesture corresponding to "H" for the second time. If the smartwatch obtains the first gesture image by recording a video, the smartwatch may determine from the video captured by the camera that the number of image frames of the three groups of continuous image frames, including the first time the user makes the gesture corresponding to "H", the continuous image frames of the user making the five-fingers-opening gesture, and the continuous image frames of the second time the user makes the gesture corresponding to "H", all reach a preset number. By taking any image frame from the three groups of continuous image frames as a first gesture image, we can obtain the first gesture image including the user's first gesture corresponding to "H", the first gesture image including the user's gesture with five fingers open, and the first gesture image including the user's second gesture corresponding to "H".

[0047] S120: Compare the first gesture image with pre-stored second gesture images corresponding to respective characters to determine a target character corresponding to the first gesture image.

[0048] In this embodiment, the mapping relationship between characters and gestures can be set uniformly by the watch manufacturer or the input method manufacturer, or it can be set by the user according to personal habits. For example, when the smart watch leaves the factory, a set of mapping relationships between 26 letters and gestures is configured. After the user gets it, he is not used to it, so he changes the factory-set mapping relationship to Figure 4 The mapping relationship between the 26 characters and gestures shown. The second gesture image in this embodiment refers to a sample image of a gesture containing the corresponding character. For the mapping relationship configured at the factory, the manufacturer prepares in advance to shoot a second gesture image containing the gesture corresponding to the character, and associates the character with the second gesture image containing the corresponding gesture and saves it in the memory of the smart watch. When the user modifies the mapping relationship configured at the factory to the mapping relationship of personal habit, the second gesture image can be re-shot through the camera, the second gesture image can be associated with the corresponding character and saved in the memory of the smart watch, and the original mapping relationship can be deleted.

[0049] Figure 5 is a flow chart of determining the target character corresponding to the first gesture image provided by an embodiment of the present application. Figure 5 As shown, the step of determining the target character corresponding to the first gesture image specifically includes S1201-S1202:

[0050] S1201: Determine similarity between a first gesture image and each second gesture image.

[0051] S1202: If there is a second gesture image whose similarity to the first gesture image is greater than a preset similarity threshold, determine the character corresponding to the second gesture image with the highest similarity as the target character of the first gesture image.

[0052] For example, it is assumed that the second gesture image stored in the smartwatch includes Figure 4 The gesture shown and the gesture with five fingers open, Figure 4 The gestures shown correspond to Figure 4 The letters in the image, and the gesture with five fingers open correspond to meaningless characters. The first feature point is extracted from the first gesture image and the second feature point is extracted from the second gesture image by the SIFI operator, and the similarity between the first gesture image and the second gesture image is determined by the second feature point and the first feature point. In this embodiment, the preset similarity threshold is the minimum similarity between two images containing the same gesture set in this embodiment. When the similarity between the first gesture image and the second gesture image is greater than or equal to the preset similarity threshold, it is determined that the first gesture image and the second gesture image contain the same gesture. When the similarity between the first gesture image and the second gesture image is less than the preset similarity threshold, it is determined that the first gesture image and the second gesture image contain different gestures.

[0053] It should be noted that if the first gesture image contains Figure 4 If a certain gesture is selected in the image, the first gesture image will only have a similarity with the second gesture image corresponding to the gesture that is greater than or equal to a preset similarity threshold. However, it is not ruled out that the gesture made by the user is not standard enough to cause a mismatch. At this time, if the similarity between the first gesture image and multiple second gesture images is greater than or equal to the preset similarity threshold, it is determined that the second gesture image with the highest similarity contains the same gesture as the first gesture image, and then the character corresponding to the second gesture image with the highest similarity is determined as the target character that the user wants to input.

[0054] In another embodiment, the gesture corresponding to the meaningless character can be a gesture specially set by the user, such as the five-fingered gesture mentioned in the above embodiment, or any gesture other than the gesture corresponding to the meaningful character. For example, when the character set only includes 26 letters, the 26 characters correspond to Figure 4 The gesture shown, when the user makes Figure 4 When a gesture other than the 26 gestures shown is made, the camera captures a first gesture image containing the gesture. Since the gesture in the first gesture image does not belong to Figure 4When the smartwatch calculates the similarity between the first gesture image and each second gesture image, it will determine that there is no second gesture image whose similarity with the first gesture image is greater than a preset similarity threshold among all the second gesture images stored locally. At this time, it can be determined that the target character corresponding to the first gesture image is a meaningless character. Compared with setting a specific gesture as a meaningless character, the user does not need to remember the gesture corresponding to the meaningless character, which reduces the complexity of interaction.

[0055] S130: Generate currently input text content according to the shooting order of the first gesture images and the corresponding target characters.

[0056] For example, the target characters corresponding to the first gesture image are sorted in the order in which they were taken to obtain a corresponding character sequence. If the current input method is English, the character sequence can be used as text content; if the current input method is Chinese, the character sequence can be used as pinyin to generate one or more Chinese contents and display them on the screen, and the user can click on a Chinese character as the input text content.

[0057] When there are a large number of characters, the user may confuse the gestures corresponding to the characters, and the target character corresponding to the first gesture image is not the character the user wants, resulting in the generated text content not being the text content the user wants to input. Therefore, an input method with a character correction function can be installed on the smart watch, and the mis-input characters in the character sequence can be corrected by the preset input method, and the currently input text content is generated according to the corrected character sequence. Exemplarily, the input method can query the dictionary to see whether the corresponding character sequence is the correct character sequence. For example, when the character sequence is "applh", the English input method queries the English dictionary to determine that "apple" is the correct English word, and then the character sequence "applh" is modified to "apple" and entered as text content in the text box. In addition, the input method also has an expansion function, that is, when partial characters are entered, the input method can automatically expand the complete text content, greatly improving the text input speed.

[0058] In one embodiment, the smartwatch stores teaching videos and practice games that guide users to perform gestures corresponding to various characters, so that users can quickly learn the gestures corresponding to various characters by watching the teaching videos or practicing games. It should be noted that the teaching videos and practice games are videos recorded and games designed by the manufacturer, and they guide users to learn the mapping relationship between characters and gestures set by the manufacturer.

[0059] In summary, the text input method provided by the embodiment of the present application confirms that the user is currently preparing to input text through gestures when receiving an input start operation, then turns on the camera and captures the user's gestures to obtain a first gesture image; compares the first gesture image with a plurality of pre-stored second gesture images, determines a second gesture image that is the same as the gesture in the first gesture image, and determines the character associated with the second gesture image as the target character corresponding to the gesture in the first gesture image; sorts the corresponding target characters according to the shooting order of the first gesture image, so as to generate the text content currently input by the user according to the sorted character sequence. Through the above technical means, the user inputs characters by making gestures instead of the user clicking on the watch keyboard to input characters, and accurately inputs the characters the user wants to input by recognizing the user's gestures, thereby improving the accuracy of character input, solving the problem of frequent mis-inputs caused by easy mis-touch of keyboard input in the prior art, and helping to improve the speed of text input.

[0060] Based on the above embodiments, Figure 6 A structural diagram of a text input device provided in an embodiment of the present application. Figure 6 The text input device provided in this embodiment specifically includes: an image acquisition module 21, a character determination module 22 and a text input module 23.

[0061] The image acquisition module is configured to receive an input start operation, and acquire at least one first gesture image in response to the input start operation;

[0062] a character determination module, configured to compare the first gesture image with pre-stored second gesture images corresponding to respective characters, and determine a target character corresponding to the first gesture image;

[0063] The text input module is configured to generate the currently input text content according to the shooting order of the first gesture images and the corresponding target characters.

[0064] Based on the above embodiment, the first gesture image is obtained by taking pictures with an infrared thermal camera.

[0065] Based on the above embodiment, the image acquisition module 21 includes: a video recording unit, configured to respond to the input start operation to shoot a video through a camera; an image frame comparison unit, configured to compare adjacent image frames in the captured video to determine continuous image frames containing the same gesture; a first image acquisition unit, configured to determine any image frame in the continuous image frames as a first gesture image when the number of image frames of the continuous image frames reaches a preset number.

[0066] Based on the above embodiment, the image acquisition module 21 also includes: a second image acquisition unit, which is configured to determine any two image frames in the corresponding continuous image frames as the first gesture image if the gesture image area of ​​any image frame in the continuous image frames whose number of image frames is greater than or equal to a preset number is less than a preset area threshold.

[0067] Based on the above embodiment, the character determination module 22 includes: a similarity determination unit, configured to determine the similarity between the first gesture image and each second gesture image; a first character determination unit, configured to determine the character corresponding to the second gesture image with the highest similarity as the target character of the first gesture image if there is a second gesture image whose similarity with the first gesture image is greater than a preset similarity threshold.

[0068] Based on the above embodiment, the character determination module 22 also includes: a second character determination unit, configured to determine that the target character corresponding to the first gesture image is a meaningless character if there is no second gesture image whose similarity with the first gesture image is greater than a preset similarity threshold.

[0069] Based on the above embodiment, the text input module 23 includes: a character arrangement unit, configured to arrange the corresponding target characters according to the shooting order of the first gesture image to obtain a character sequence; a text input unit, configured to correct the mis-input characters in the character sequence through a preset input method, and generate the currently input text content according to the corrected character sequence.

[0070] As mentioned above, the text input device provided by the embodiment of the present application confirms that the user is currently preparing to input text through gestures when receiving an input start operation, then turns on the camera and captures the user's gestures to obtain a first gesture image; compares the first gesture image with a plurality of pre-stored second gesture images, determines a second gesture image that is the same as the gesture in the first gesture image, and determines the character associated with the second gesture image as the target character corresponding to the gesture in the first gesture image; sorts the corresponding target characters according to the shooting order of the first gesture image, so as to generate the text content input by the current user according to the sorted character sequence. Through the above technical means, the user inputs characters by making gestures instead of the user clicking on the watch keyboard to input characters, and accurately inputs the characters the user wants to input by recognizing the user's gestures, thereby improving the accuracy of character input, solving the problem of frequent mis-inputs caused by easy mis-touch of keyboard input in the prior art, and helping to improve the speed of text input.

[0071] The text input device provided in the embodiment of the present application can be used to execute the text input method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0072] Figure 7is a schematic diagram of a device provided in an embodiment of the present application, with reference to Figure 7 The device includes: a processor 31, a memory 32, a communication device 33, an input device 34 and an output device 35. The number of processors 31 in the text input device can be one or more, and the number of memories 32 in the text input device can be one or more. The processor 31, memory 32, communication device 33, input device 34 and output device 35 of the text input device can be connected via a bus or other means.

[0073] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the text input method of any embodiment of the present application (for example, the image acquisition module 21, the character determination module 22 and the text input module 23 in the text input device). The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0074] The communication device 33 is used for data transmission.

[0075] The processor 31 executes the software programs, instructions and modules stored in the memory 32 to execute various functional applications and data processing of the device, that is, to implement the above-mentioned text input method.

[0076] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0077] The above-provided device can be used to execute the text input method provided in the above-mentioned embodiment, and has corresponding functions and beneficial effects.

[0078] An embodiment of the present application also provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to execute a text input method. The text input method includes: receiving an input start operation, and obtaining at least one first gesture image in response to the input start operation; comparing the first gesture image with second gesture images corresponding to each character stored in advance to determine the target character corresponding to the first gesture image; and generating the text content of the current input according to the shooting order of the first gesture images and the corresponding target characters.

[0079] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0080] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application, whose computer executable instructions are not limited to the above text input method, can also execute related operations in the text input method provided in any embodiment of the present application.

[0081] The text input device, storage medium and equipment provided in the above embodiments can execute the text input method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the text input method provided in any embodiment of the present application.

[0082] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A text input method, characterized in that: include: receiving an input start operation, and acquiring at least one first gesture image in response to the input start operation; Comparing the first gesture image with pre-stored second gesture images corresponding to respective characters, and determining a target character corresponding to the first gesture image; The currently input text content is generated according to the shooting order of the first gesture images and the corresponding target characters.

2. The text input method according to claim 1, characterized in that: The first gesture image is obtained by taking pictures with an infrared thermal camera.

3. The text input method according to claim 1, characterized in that: The initiating operation in response to the input to obtain at least one first gesture image comprises: initiating an operation to capture a video via a camera in response to the input; Comparing adjacent image frames in the captured video to determine consecutive image frames containing the same gesture; When the number of the continuous image frames reaches a preset number, any image frame in the continuous image frames is determined as a first gesture image.

4. The text input method according to claim 3, characterized in that: The method further comprises: If the area of ​​the gesture image of any image frame in the continuous image frames whose number is greater than or equal to the preset number is smaller than the preset area threshold, any two image frames in the corresponding continuous image frames are determined as the first gesture image.

5. The text input method according to any one of claims 1 to 4, characterized in that: The comparing the first gesture image with pre-stored second gesture images corresponding to respective characters to determine the target character corresponding to the first gesture image includes: determining a similarity between the first gesture image and each second gesture image; If there is a second gesture image whose similarity to the first gesture image is greater than a preset similarity threshold, the character corresponding to the second gesture image with the highest similarity is determined as the target character of the first gesture image.

6. The text input method according to claim 5, characterized in that: After determining the similarity between the first gesture image and each second gesture image, the method further includes: If there is no second gesture image whose similarity with the first gesture image is greater than a preset similarity threshold, it is determined that the target character corresponding to the first gesture image is a meaningless character.

7. The text input method according to claim 1, characterized in that: The step of generating the currently input text content according to the collection order of the first gesture images and the corresponding target characters includes: Arrange the corresponding target characters according to the shooting order of the first gesture images to obtain a character sequence; The mis-input characters in the character sequence are corrected by a preset input method, and the currently input text content is generated according to the corrected character sequence.

8. A text input device, characterized in that: include: An image acquisition module, configured to receive an input start operation, and acquire at least one first gesture image in response to the input start operation; a character determination module, configured to compare the first gesture image with pre-stored second gesture images corresponding to respective characters, and determine a target character corresponding to the first gesture image; The text input module is configured to generate the currently input text content according to the shooting order of the first gesture images and the corresponding target characters.

9. A text input device, characterized in that: include: one or more processors; The memory stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the text input method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the text input method as described in any one of claims 1-7 when executed by a computer processor.

Images