Input method, device and equipment

Abstract

The embodiment of the present invention discloses an input method, device and equipment. After receiving the first information input by the user, the terminal first selects the input method wake-up condition corresponding to the first information according to the first input type. If the first information satisfies the input method wake-up condition, the input information is started to be received. When receiving the second information input by the user, the terminal selects the input end condition corresponding to the second input type of the second information. If the second information satisfies the input end condition, the input information is received and the input result is obtained according to the received input information. In this way, by providing a variety of input method system wake-up and input end methods, the user can input the first information and the second information according to different needs using an input type that is convenient for the user, thereby overcoming the problem that the user cannot conveniently complete the input under the single input type requirement, providing input convenience for the user, and thus improving the user's input experience.

Description

Technical Field

[0001] The present invention relates to the technical field of input methods, and in particular to an input method, device and equipment. Background Art

[0002] When using various applications, users basically need to input information by calling the input method system. For example, after opening an instant messaging client, the user needs to call out the input method system first and input information through the input interface of the input method system to realize instant messaging between the user and other users.

[0003] At present, when a user calls an input method system for input, he needs to perform some operations in a fixed way (for example, clicking a specific location on his terminal or through voice control), such as waking up the input method system, ending the input operation, etc. In this way, in some cases, for example, assuming that the user needs to click on his terminal to input, but the user's hands are occupied or the user's fingers are injured, it is inconvenient for the user to click a specific location on the terminal, resulting in the user being unable to complete the input; in other cases, for example, assuming that the user needs to use voice control to input, but the user is not convenient to input voice information, resulting in the user being unable to complete the input, thereby reducing the user's input experience. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present invention provide an input method, apparatus and device, so that even if the user is not convenient to use a certain input method, it is possible to complete the input on the application installed on the terminal by selecting a more convenient method (such as voice input or image input) from a variety of other optional methods, thereby improving the user's input experience.

[0005] In a first aspect, an embodiment of the present invention provides an input method, which may specifically include:

[0006] receiving first information, wherein the first information is at least one of multiple input types;

[0007] selecting an input method wake-up condition corresponding to the first input type according to the first input type of the first information;

[0008] If the first information satisfies the input method wake-up condition, then, starting to receive input information;

[0009] receiving second information, wherein the second information is at least one of a plurality of input types;

[0010] selecting an input end condition corresponding to the second input type according to the second input type of the second information;

[0011] If the second information satisfies the input termination condition, the receiving of the input information is terminated, and the input result is obtained according to the received input information.

[0012] Optionally, the first input type includes at least one of the following input types:

[0013] Touch screen key input type, voice input type and image input type;

[0014] The second input type includes at least one of the following input types:

[0015] Touch screen key input type, voice input type and image input type.

[0016] Optionally, if the first information is first voice information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0017] Identify that the input type of the first voice information is a voice input type;

[0018] Selecting a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition;

[0019] If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics;

[0020] If the second information is second voice information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0021] Identify that the input type of the second voice information is a voice input type;

[0022] Selecting a preset ending semantic corresponding to the voice input type as the input ending condition;

[0023] If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

[0024] Optionally, if the first information is first image information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0025] collecting the first image information;

[0026] Identify that the input type of the first image information is an image input type;

[0027] Selecting a preset wake-up image corresponding to the image input type as the input method wake-up condition;

[0028] If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image;

[0029] If the second information is second image information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0030] collecting the second image information;

[0031] Identify the input type of the second image information as an image input type;

[0032] Selecting a preset end image corresponding to the image input type as the input end condition;

[0033] If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

[0034] Optionally, if the first information satisfies an input method wake-up condition, then starting to receive input information includes:

[0035] If the first information satisfies the input method wake-up condition corresponding to the target input mode, then the input information starts to be received in the target input mode.

[0036] Optionally, the target input mode includes: a voice input mode, a lip reading input mode or an air writing input mode;

[0037] Wherein, in the voice input mode, the input information is voice information;

[0038] In the lip reading input mode, the input information is a lip reading image;

[0039] In the air handwriting input mode, the input information is a handwritten image.

[0040] Optionally, the method further comprises:

[0041] receiving third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type;

[0042] If the priority of the third input type is higher than the priority of the fourth input type, the third input type is determined to be the target input mode, and the process of starting to receive the input information in the target input mode is triggered.

[0043] Optionally, the method further comprises:

[0044] receiving fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition;

[0045] If the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, the step of starting to receive input information is triggered.

[0046] Optionally, after obtaining the input result, the method further includes:

[0047] The input result is sent.

[0048] In a second aspect, an embodiment of the present invention further provides an input device, which may specifically include:

[0049] A first receiving unit, configured to receive first information, where the first information is at least one of multiple input types;

[0050] A first selection unit, configured to select an input method wake-up condition corresponding to a first input type according to the first input type of the first information;

[0051] A second receiving unit, configured to start receiving input information if the first information satisfies the input method wake-up condition;

[0052] A third receiving unit, configured to receive second information, where the second information is at least one of multiple input types;

[0053] a second selection unit, configured to select an input end condition corresponding to a second input type according to a second input type of the second information;

[0054] The acquiring unit is configured to terminate the reception of the input information if the second information satisfies the input termination condition, and obtain the input result according to the received input information.

[0055] Optionally, the first input type includes at least one of the following input types:

[0056] Touch screen key input type, voice input type and image input type;

[0057] The second input type includes at least one of the following input types:

[0058] Touch screen key input type, voice input type and image input type.

[0059] Optionally, if the first information is first voice information, the first selection unit includes:

[0060] A first recognition subunit, used to recognize that the input type of the first voice information is a voice input type;

[0061] A second selection subunit, configured to select a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition;

[0062] If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics;

[0063] If the second information is second voice information, the second selection unit includes:

[0064] A second identification subunit, used for identifying that the input type of the second voice information is a voice input type;

[0065] A second selection subunit, configured to select a preset end semantic corresponding to the speech input type as the input end condition;

[0066] If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

[0067] Optionally, if the first information is first image information, the first selection unit includes:

[0068] A first acquisition subunit, used for acquiring the first image information;

[0069] A third identification subunit, used to identify that the input type of the first image information is an image input type;

[0070] A third selection subunit, configured to select a preset wake-up image corresponding to the image input type as the input method wake-up condition;

[0071] If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image;

[0072] If the second information is second image information, the second selection unit includes:

[0073] A second acquisition subunit, used for acquiring the second image information;

[0074] A fourth identification subunit, used to identify that the input type of the second image information is an image input type;

[0075] a fourth selection subunit, configured to select a preset end image corresponding to the image input type as the input end condition;

[0076] If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

[0077] Optionally, the second receiving unit is specifically configured to:

[0078] If the first information satisfies the input method wake-up condition corresponding to the target input mode, then the input information starts to be received in the target input mode.

[0079] Optionally, the target input mode includes: a voice input mode, a lip reading input mode or an air writing input mode;

[0080] Wherein, in the voice input mode, the input information is voice information;

[0081] In the lip reading input mode, the input information is a lip reading image;

[0082] In the air handwriting input mode, the input information is a handwritten image.

[0083] Optionally, the device further comprises:

[0084] a fourth receiving unit, configured to receive third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type;

[0085] A determining unit is configured to determine, if the priority of the third input type is higher than the priority of the fourth input type, that the third input type is the target input mode, and trigger the execution of starting to receive the input information in the target input mode.

[0086] Optionally, the device further comprises:

[0087] a fifth receiving unit, configured to receive fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition;

[0088] A triggering unit is used to trigger the start of receiving input information if the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information.

[0089] Optionally, the device further comprises:

[0090] A sending unit is used to send the input result after obtaining the input result.

[0091] In a third aspect, an embodiment of the present invention further provides an input device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including for executing the method provided in the first aspect above.

[0092] In a fourth aspect, an embodiment of the present invention further provides a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an input device, enables the input device to execute the method provided in the first aspect described above.

[0093] In an embodiment of the present invention, if a user needs to call an input method system on a terminal for input, the user can input first information to the terminal in at least one of multiple input types. After receiving the first information, the terminal firstly selects an input method wake-up condition corresponding to the first input type according to the first input type of the first information, and then determines whether the first information satisfies the input method wake-up condition. If so, the input method system is awakened and starts to receive input information. Then, when the user inputs second information to the terminal in at least one of multiple input types, the input method system receives the second information and can select an input end condition corresponding to the second input type according to the second input type of the second information. Finally, it determines whether the second information satisfies the input end condition. If so, the input information is received and the input result is obtained according to the received input information. In this way, the embodiment of the present invention provides multiple ways to wake up the input method system and end the input operation. The user can use at least one of multiple input types to input the first information and the second information according to their different needs, thereby overcoming the problem that a single input type cannot meet the user's input needs, resulting in inconvenience for the user's input, and realizing the diversification of the input method system wake-up and end operations, providing convenience for the user, thereby improving the user's input experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0095] Figure 1 A schematic diagram of a flow chart of an input method in an embodiment of the present invention;

[0096] Figure 2A schematic diagram of an example of an input method according to an embodiment of the present invention;

[0097] Figure 3 A flowchart of another example of an input method in an embodiment of the present invention;

[0098] Figure 4 is a schematic structural diagram of an input device in an embodiment of the present invention;

[0099] Figure 5 is a schematic diagram of the structure of an input device in an embodiment of the present invention;

[0100] Figure 6 Schematic diagram of the structure of the server in the embodiment of the present invention. DETAILED DESCRIPTION

[0101] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0102] With the development of science and technology, various applications have appeared on terminals, providing convenient services for people's clothing, food, housing, transportation, etc. The input method system is an indispensable tool for users to interact with various applications, and can allow users to express their needs in various applications.

[0103] At present, when performing input operations in applications, in some cases, users are often required to click on a specific location on the terminal. For example, when user A needs to chat with friend B through WeChat, he first needs to click on the input box on the terminal to wake up the input method system, and then on the input interface, input the content by clicking the corresponding button, and finally end the input operation by clicking the return function key. However, for example, when the user's hands are occupied, or when the user's fingers are injured, the user cannot perform accurate click operations on the terminal. In this way, the user cannot complete the input by clicking on a specific location on the terminal interface, which reduces the user's input experience. In other cases, the user can also wake up the input method system by inputting voice control, and then continue to input specific content by voice input, and finally end the voice input operation by inputting voice control. However, for example, when the user is in a public place or other quiet place where it is inconvenient to input voice information, the user cannot input voice information to the terminal. In this way, the user cannot complete the input through voice control, which reduces the user's input experience.

[0104] Based on this, in an embodiment of the present invention, a more convenient input method is provided. If a user needs to call an input method system on a terminal for input, a specific implementation method includes: a user can input first information to the terminal in at least one of multiple input types. After receiving the first information, the terminal first selects an input method wake-up condition corresponding to the first input type according to the first input type of the first information, and then determines whether the first information satisfies the input method wake-up condition. If so, the input method system is woken up to start receiving input information; then, when the user inputs second information to the terminal in at least one of multiple input types, the input method system receives the second information and can select an input end condition corresponding to the second input type according to the second input type of the second information. Finally, it determines whether the second information satisfies the input end condition. If so, the input information is received and the input result is obtained based on the received input information.

[0105] In this way, the embodiments of the present invention provide multiple ways to wake up the input method system and end the input operation. The user can use at least one of the multiple input types to input the first information and the second information according to their different needs. This overcomes the problem that a single input type cannot meet the user's input needs, resulting in inconvenience for the user's input. The input method system wakes up and ends operations in a diversified manner, which provides convenience for the user and improves the user's input experience.

[0106] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0107] Exemplary Methods

[0108] Figure 1 A schematic diagram of a flow chart of an input method provided by an embodiment of the present invention. Figure 1 In this embodiment, the method may specifically include the following steps 101 to 106:

[0109] Step 101: Receive first information, where the first information is at least one of multiple input types.

[0110] In specific implementation, when a user uses an application and wants to perform operations such as content search, chat interaction, etc., he needs to first call out the input method system and input the user's needs in the current application through the input method system. Then, the user must first request to wake up the input method system. In order to provide more wake-up methods, the user can use at least one of the multiple input types; for example: in order to free the user's hands, the user can input the first information without touching the terminal with both hands, and initiate a wake-up request for the input method system. Then, the input type of the first information can be a voice input type or an image input type; for another example: the user can also input the first information by touch and initiate a wake-up request for the input method system. Then, the input type of the first information can also be a touch screen key input type.

[0111] It is understandable that the first information may be used to convey to the input method system the user's intention to use the input method system, and may be regarded as a request message to wake up the input method system. The first information may be information that can be collected without touching the terminal, and its input type may include: voice input type and image input type; the first information may also be information that can be collected only after touching the terminal, and its input type may also include: touch screen key input type.

[0112] As an example, if the input type of the first information is a voice input type, then the first information can be the first voice information. Then, step 101 can be specifically: when the user wants to call the input method system to perform an input operation, the input method system needs to be awakened first. At this time, the user can speak a voice to the terminal, and the sound collection module of the terminal can collect the voice and use it as the first voice information (i.e., the first information) as a request message for subsequently waking up the input method system. For example: the received first voice information can be the voice information collected by the microphone of the terminal after the user speaks voice segments such as "start input", "start input" or "start reply" to the terminal.

[0113] As another example, if the input type of the first information is an image input type, then the first information may be first image information, which may be a gesture image, a lip reading image, or the like. Then, step 101 may specifically be: when the user wants to call the input method system to perform an input operation, the input method system must be awakened first. At this time, the user may pose a specific pose in front of the terminal when the image acquisition module is turned on. The image acquisition module of the terminal may capture the image corresponding to the specific pose and use it as the first image information (i.e., the first information) as a request message for subsequently waking up the input method system. For example, the first image information received may be the image information captured by the camera after the user poses a gesture representing "OK", "Yeah" or "Six" in front of the camera of the terminal.

[0114] As another example, if the input type of the first message is a touch screen key input type, the first information may be the first typing information. Then, step 101 may specifically be: when the user wants to call the input method system to perform an input operation, the input method system must be woken up first. At this time, the user may click on the input box in the application on the terminal interface, and the terminal may receive the first typing information (i.e., the first information) corresponding to the click operation as a request message for subsequently waking up the input method system.

[0115] Step 102: Select an input method wake-up condition corresponding to the first input type according to the first input type of the first information.

[0116] Step 103: If the first information meets the input method wake-up condition, then start receiving input information.

[0117] It is understandable that each input type is provided with a corresponding input method wake-up condition, which is used to determine whether the first information of the input type can wake up the input method system according to the input method wake-up condition corresponding to the input type after receiving the first information of the input type.

[0118] As an example, if the first information is the first voice information, then step 102 may specifically be: S11, identifying that the input type of the first voice information is a voice input type (ie, the first input type); S12, selecting a preset wake-up semantic corresponding to the voice input type as an input method wake-up condition.

[0119] As another example, if the first information is the first image information, then step 102 may specifically be: S21, collecting the first image information; S22, identifying that the input type of the first image information is an image input type (i.e., the first input type); S23, selecting a preset wake-up image corresponding to the image input type as an input method wake-up condition.

[0120] As another example, if the first information is the first typing information, then step 102 may specifically be: S31, collecting the first typing information; S32, identifying that the input type of the first typing information is a touch screen button input type (ie, the first input type); S33, selecting a preset wake-up position corresponding to the touch screen button input type as an input method wake-up condition.

[0121] It is understandable that the input method wake-up condition may include at least one of a preset wake-up semantics, a preset wake-up image, and a preset wake-up position that are pre-set and stored for waking up the input method system. The first information satisfies the input method wake-up condition, which means that the first information matches the preset wake-up semantics included in the input method wake-up condition, or the first information matches the preset wake-up image included in the input method wake-up condition, or the first information matches the preset wake-up position included in the input method wake-up condition; the first information does not satisfy the input method wake-up condition, which means that the first information does not match the preset wake-up semantics, preset wake-up image, and preset wake-up position included in the input method wake-up condition.

[0122] In a specific implementation, in one case, if the first information received meets the input method wake-up condition, it means that the input method system is allowed to be awakened by the currently received first information. In this case, the input method system is awakened. At this time, the awakened input method system can start to receive input information, that is, the user can start to input the content to be input, and the content to be input can be received by the input method system as input information.

[0123] In another case, if the received first information does not meet the input method wake-up condition, it means that the input method system is not allowed to be woken up by the currently received first information, then the first information is ignored and the input method system is not woken up. In this case, in order to improve the user's input experience, the user can also be informed that the first information input does not meet the input method wake-up condition, and the user is prompted to input the first information again. In this way, the incorrect wake-up of the input method system caused by misoperation can be avoided, and the accuracy of the input method can be improved.

[0124] As an example, when the first information is the first voice information, then, in step 103, analyzing whether the first information meets the input method wake-up condition may specifically include the following S41 to S42:

[0125] S41, identifying the first voice information, and obtaining first semantics corresponding to the first voice information.

[0126] In a specific implementation, when the first voice information is collected by a voice collection module (e.g., a microphone), semantic recognition can be performed on the first voice information to obtain the first semantics corresponding to the first voice information. In one case, the received first voice information can be converted into the corresponding first text information, and then the semantics corresponding to the first text information can be recognized, and the semantics corresponding to the first text information can be used as the first semantics corresponding to the first voice information; in another case, the semantics corresponding to the first voice information can also be directly recognized as the first semantics.

[0127] As an example, assuming that the user inputs "I will start replying to messages now" as the first voice information, then by recognizing the first voice information, the first semantics corresponding to "I will start replying to messages now" can be obtained as: start replying.

[0128] S42, matching the first semantics with preset wake-up semantics; wherein, the first semantics matches the preset wake-up semantics, indicating that the first voice information satisfies the input method wake-up condition.

[0129] In specific implementation, after receiving the first voice information and identifying the first semantics corresponding to the first voice information, in order to determine whether the first voice information meets the input method wake-up condition, the first semantics can be matched with the preset wake-up semantics included in the preset input method wake-up condition. If the first semantics matches the preset wake-up semantics, it means that the first voice information is allowed to wake up the input method system, that is, the first voice information meets the input method wake-up condition. Otherwise, if the preset wake-up semantics matching the first semantics cannot be found, it means that the first voice information has not been set to wake up the input method system, that is, the first voice information does not meet the input method wake-up condition.

[0130] For example: Assume that the input method wake-up condition includes two preset wake-up semantics, namely: preset wake-up semantic A-start input, preset wake-up semantic B-start reply. If the first voice message is "Start replying to messages now", the corresponding first semantic is: start replying, then the first semantic matches the preset wake-up semantic B, and it can be determined that the first voice message meets the input method wake-up condition. If the first voice message is "Start eating now", the corresponding first semantic is: start eating, then the first semantic does not match either the preset wake-up semantic A or the preset wake-up semantic B, and it can be determined that the first voice message does not meet the input method wake-up condition.

[0131] It should be noted that in the process of matching the first semantics and the preset wake-up semantics, since the preset wake-up semantics may not include all expressions that meet the input method wake-up conditions, when it is found that the first semantics and the preset wake-up semantics are not exactly the same, it is also possible to analyze whether the first semantics and the preset wake-up semantics express the same semantics, such as: including synonyms. If so, the first semantics is also regarded as matching the preset wake-up semantics.

[0132] As another example, when the first information is the first image information, then, analyzing whether the first information meets the input method wake-up condition in step 103 may specifically include: matching the first image information with a preset wake-up image; wherein, the first image information matches the preset wake-up image, indicating that the first image information meets the input method wake-up condition.

[0133] In a specific implementation, after receiving the first image information, in order to determine whether the first image information meets the input method wake-up condition, the first image information can be matched with a preset wake-up image included in the preset input method wake-up condition. If the first image information matches the preset wake-up image, it means that the first image information is allowed to be used to wake up the input method system, that is, the first image information meets the input method wake-up condition. Otherwise, if no preset wake-up image matching the first image information is found, it means that the first image information has not been set to wake up the input method system, that is, the first image information does not meet the input method wake-up condition.

[0134] For example: Assume that the input method wake-up condition includes three preset wake-up images, namely: preset wake-up image C-a scissors hand gesture image representing "yeah", preset wake-up image D-a gesture image representing "OK", and preset wake-up image E-a gesture image representing "six". If the first image information is a gesture image in which the index finger and the middle finger are straight and the other fingers are bent, that is, the first image information is a scissors hand gesture image representing "yeah", then the first image information matches the preset wake-up image C, and it can be determined that the first image information meets the input method wake-up condition. If the first image information is a gesture image in which all five fingers are straight, then the first image information does not match the preset wake-up image C, the preset wake-up image D, and the preset wake-up image E, and it can be determined that the first image information does not meet the input method wake-up condition.

[0135] It is understandable that the preset wake-up image can be flexibly set, and the matching condition that the first image information needs to meet with each preset wake-up image can also be flexibly set. The matching of the first image information and the preset wake-up image can mean that the similarity between the first image information and the preset wake-up image is greater than a preset similarity threshold, or that the form represented by the first image information is consistent with the form represented by the preset wake-up image, or that the first image information and the preset wake-up image information are symmetrical, and so on.

[0136] It should be noted that in order to improve the input experience and free the user's hands, the above introduces an implementation method in which the user enters the first information to wake up the input method system without touching the terminal in an embodiment of the present invention. However, the embodiment of the present invention also includes an implementation method for waking up the input method system by clicking a specific position of the terminal (for example: clicking an input box on the touch screen of the terminal).

[0137] In some implementations, when it is analyzed that the first information satisfies the input method wake-up condition, the input method system can be awakened and start receiving input information. The input method system generally has multiple input modes, such as contact input mode, voice input mode, lip reading input mode and air handwriting input mode, wherein the contact input mode is the conventional input by clicking on the input interface presented on the terminal, such as: input by clicking on the buttons in the input interface or by handwriting on the input interface; in the voice input mode, the user inputs voice information in the form of voice; in the lip reading input mode, the user inputs the lip reading image through the terminal's image acquisition module; in the air handwriting input mode, the user inputs the handwriting image through the terminal's image acquisition module.

[0138] Generally, for the convenience of user input, in addition to the part requesting to wake up the input method system, the first information may also include the part requesting the input mode of the input information. Then, if the first information satisfies the input method wake-up condition in step 103, then, starting to receive the input information includes: if the first information satisfies the input method wake-up condition corresponding to the target input mode, then, starting to receive the input information in the target input mode.

[0139] It is understandable that each preset wake-up semantics in the input method wake-up condition corresponds to an input mode, and similarly, each preset wake-up image in the input method wake-up condition also corresponds to an input mode. However, an input mode can correspond to at least one preset wake-up semantics and / or at least one preset wake-up image.

[0140] In one case, if the first information is the first voice information, and it is determined that the first semantics corresponding to the first voice information matches the preset wake-up semantics, the input mode corresponding to the preset wake-up semantics matching the first semantics can be further determined, recorded as the target input mode, and after waking up the input method system, the user starts to input information in the target input mode, and the input method system also receives the user's input information in the target input mode. For example: Assume that the preset wake-up semantics a "start voice reply" and "start voice input" both correspond to the voice input mode, the preset wake-up semantics b "start lip reading reply" and "start lip reading input" both correspond to the lip reading input mode, and the preset wake-up semantics c "start air handwriting reply" and "start air handwriting input" both correspond to the air handwriting input mode. When the first semantics matches the preset wake-up semantics a, then the input information can be received in the voice input mode; when the first semantics matches the preset wake-up semantics b, then the input information can be received in the lip reading input mode; when the first semantics matches the preset wake-up semantics c, then the input information can be received in the air handwriting input mode.

[0141] In another case, if the first information is the first image information, and it is determined that the first image information matches the preset wake-up image, the input mode corresponding to the preset wake-up image matching the first image information can be further determined, recorded as the target input mode, and after waking up the input method system, the user starts to input information in the target input mode, and the input method system also receives the user's input information in the target input mode. For example: Assume that the preset wake-up image d "a scissors hand gesture image representing 'yeah'" corresponds to the voice input mode, the preset wake-up image e "a gesture image representing 'OK'" corresponds to the lip reading input mode, and the preset wake-up image f "a gesture image representing 'six'" corresponds to the air handwriting input mode. When the first image information matches the preset wake-up image d, then the input information can be received in the voice input mode; when the first image information matches the preset wake-up image e, then the input information can be received in the lip reading input mode; when the first image information matches the preset wake-up image f, then the input information can be received in the air handwriting input mode.

[0142] It should be noted that, in some instances, the input mode portion of the requested input information may not be included in the first information, but is information for indicating the input mode that is received separately after determining that the first information requesting to wake up the input method system satisfies the input method wake-up condition. In this implementation, after determining that the first information satisfies the input method wake-up condition and waking up the input method system, the user may be prompted to "select a target input mode". After the user enters the indication information for indicating the input mode according to the prompt, the target input mode may be obtained by parsing the indication information, and input information may be received in the target input mode.

[0143] It should be noted that in order to improve the user's input experience and allow the user to input the content to be input in the correct input mode as soon as possible after waking up the input method system, after waking up the input method system and determining the target input mode, the user can be prompted to input in the target input mode. For example: after determining that the target input mode is the voice input mode, a prompt "Please start inputting in the form of voice" can be given on the terminal in the form of text, or a prompt "Please start inputting in the form of voice" can be given in the form of voice.

[0144] It should be noted that in order to free up both hands, the user can enter the content to be input as input content through voice input mode, lip reading input mode or air handwriting input mode without touching the terminal. However, in order to apply to more application scenarios, the embodiment of the present invention also includes an implementation method in which the user enters the content to be input through a contact input mode (such as clicking a button in the input interface). Moreover, after determining the target input mode, during the input process, the user can also flexibly switch to other input modes for input according to actual needs.

[0145] In some specific scenarios, considering that two first messages may be received almost at the same time, both of which meet the input method wake-up condition, but the two first messages correspond to different input types, in order for the input method to be effectively and conveniently used by the user, the embodiment of the present invention may also set different priorities for multiple first messages of different input types. For example, different first information types may be, in descending order of pre-set priorities, contact, voice, gesture image, and lip reading image.

[0146] When implementing it specifically, Figure 2 As shown, the embodiment of the present invention may further include:

[0147] Step 201, receiving third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type.

[0148] It is understandable that in order to distinguish different first information received, the two first information received almost simultaneously are recorded as the third information and the fourth information respectively, and the third information and the fourth information are analyzed respectively through the above steps 102 to 103 to determine that the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input mode. The input type corresponding to the third information can be a touch screen button input type, a voice input type, a gesture image input type, or a lip reading image input type; the input type corresponding to the fourth information can also be a touch screen button input type, a voice input type, a gesture image input type, or a lip reading image input type.

[0149] Step 202: If the priority of the third input type is higher than the priority of the fourth input type, then the first input type is determined to be the target input mode, and the process of starting to receive the input information in the target input mode is triggered.

[0150] In specific implementation, the priority of the third information corresponding to the third input type and the priority of the fourth information corresponding to the fourth input type can be determined respectively, and the priority of the third input type can be compared to see whether it is higher than that of the fourth input type. In one case, if the priority of the third input type is higher than that of the fourth input type, it means that the third input type corresponding to the input method wake-up condition satisfied by the third information needs to be the target input mode, then, "start receiving input information" in step 103 can be specifically "ignore the fourth information, and start receiving input information with the first input type (i.e., target input mode)". In another case, if the priority of the third input type is lower than that of the fourth input type, it means that the fourth input type corresponding to the input method wake-up condition satisfied by the fourth information needs to be the target input mode, then, "start receiving input information" in step 103 can be specifically "ignore the third information, and start receiving input information with the fourth input type (i.e., target input mode)".

[0151] It should be noted that if the third input type and the fourth input type are the same or their corresponding priorities are the same, the information received slightly later can be ignored and the earlier received information shall prevail. If the earlier received information between the third and fourth information meets the input method wake-up condition, the input type corresponding to the earlier received information between the third and fourth information shall be used as the target input mode, and input information shall continue to be received according to the determined target input mode.

[0152] For example: Assume that the first information types may be, in descending order of the preset priorities, touch screen key input type, voice input type, gesture image input type or lip reading image input type, and the third information received corresponds to the third input type of voice input type, and the fourth information corresponds to the input type of gesture image input type, and the third information satisfies the preset wake-up semantic a "start voice reply" in the input method wake-up condition; the fourth information satisfies the preset wake-up image e "gesture image indicating 'OK'" in the input method wake-up condition. Since the priority of the input type "voice input type" corresponding to the third information is higher than the priority of the input type "gesture image input type" corresponding to the fourth information, the third input type (i.e., voice input type) is used as the target input mode to start receiving voice input information.

[0153] In this way, the problem of input confusion caused by receiving multiple first messages almost at the same time can be effectively solved. By setting different priorities for each corresponding type of first information, users can complete input conveniently and effectively, thereby improving the user's input experience.

[0154] It is understandable that from the moment when the input information starts to be received, the user can continuously input the content he wants to input through the target input mode, that is, the input information increases as the user inputs more content and as time goes by.

[0155] Step 104: Receive second information, where the second information is at least one of multiple input types.

[0156] It is understandable that the second information may be used to convey to the input method system the user's intention to end the input operation, and may be regarded as a request message to end the input operation. The second information may be information that can be collected without contacting the terminal, and its input type may include: voice input type and image input type.

[0157] As an example, if the input type of the second information is a voice input type, then the second information may be a second voice information, and step 104 may specifically be: when the user wants to end the current input operation, the user may speak a voice segment to the terminal, and the sound collection module of the terminal may collect the voice segment and use it as the second voice information (i.e., the second information), as a request message for the subsequent end of the input operation. For example, the received second voice information may be the voice information collected by the microphone of the terminal after the user speaks a voice segment such as "end input" or "complete input" to the terminal.

[0158] As another example, if the input type of the second information is an image input type, then the second information may be second image information, specifically a gesture image, a lip reading image, etc. Then, step 104 may specifically be: when the user wants to end this input operation, the user can pose a specific pose in front of the terminal when the image acquisition module is turned on, and the image acquisition module of the terminal can capture the image corresponding to the specific pose and use it as the second image information (i.e., the second information), as a request message for the subsequent end of the input operation. For example: the received second image information may be the image information captured by the camera after the user poses a gesture representing "five" or "eight" in front of the camera of the terminal.

[0159] As another example, if the input type of the second message is a touch screen button input type, the second information may be second typing information. Then, step 104 may specifically be: when the user wants to end this input operation, the user may click the send button in the application on the terminal interface, and the terminal may receive the second typing information (i.e., the second information) corresponding to the click operation as a request message for subsequently ending the input operation.

[0160] Step 105: Select an input end condition corresponding to the second input type according to the second input type of the second information.

[0161] Step 106: If the second information satisfies the input end condition, then the receiving of the input information is ended, and an input result is obtained according to the received input information.

[0162] It can be understood that each input type is provided with a corresponding input end condition, which is used to determine whether the second information of the input type can end the current input according to the input end condition corresponding to the input type after receiving the second information of the input type.

[0163] As an example, if the second information is the second voice information, then step 105 may specifically be: S51, identifying that the input type of the second voice information is a voice input type (ie, the second input type); S52, selecting a preset end semantic corresponding to the voice input type as an input end condition.

[0164] As another example, if the second information is second image information, then step 105 may specifically be: S61, collecting the second image information; S62, identifying that the input type of the second image information is an image input type (i.e., the second input type); S63, selecting a preset end image corresponding to the image input type as an input end condition.

[0165] As another example, if the second information is the second typing information, then step 105 may specifically be: S71, collecting the second typing information; S72, identifying that the input type of the second typing information is a touch screen button input type (i.e., the second input type); S73, selecting a preset end position corresponding to the touch screen button input type as the input end condition.

[0166] It is understandable that the input end condition may include at least one of a preset end semantics, a preset end image, and a preset end position that are preset and stored to end the current input operation. The second information satisfies the input end condition, which means that the second information matches the preset end semantics included in the input end condition, or the second information matches the preset end image included in the input end condition, or the second information matches the preset end position included in the input end condition; the second information does not satisfy the input end condition, which means that the second information does not match the preset end semantics, the preset end image, and the preset end position included in the input end condition.

[0167] In specific implementation, in one case, if the received second information meets the input end condition, it means that the input operation is allowed to be ended with the currently received second information. In this case, the reception of the input information is ended. At this time, the input result can be obtained based on the received input information, that is, all the input information entered by the user from "start receiving input information" in step 103 to "end receiving input information" in step 106 is used as the input result.

[0168] In another case, if the received second information does not meet the input end condition, it means that the current input operation is not allowed to be ended with the currently received second information, then the second information is ignored and the reception of the input information is not ended. In this case, in order to improve the user's input experience, the user can also be informed that the second information input does not meet the input end condition, and the user is prompted: if you want to end this input, you can enter the second information again. In this way, the wrong end of the input operation caused by the wrong operation can be avoided, and the accuracy of the input method is improved.

[0169] As an example, when the second information is the second voice information, then, in step 106, analyzing whether the second information meets the input end condition may specifically include the following S81 to S82:

[0170] S81, identifying the second voice information, and obtaining second semantics corresponding to the second voice information.

[0171] In a specific implementation, when the second voice information is collected by a voice collection module (e.g., a microphone), semantic recognition can be performed on the second voice information to obtain the second semantics corresponding to the second voice information. In one case, the received second voice information can be first converted into the corresponding second text information, and then the semantics corresponding to the second text information can be recognized and recorded as the second semantics corresponding to the second voice information; in another case, the semantics corresponding to the second voice information can also be directly recognized as the second semantics.

[0172] As an example, assuming that the user inputs "complete this input" as the second voice information through voice, then by recognizing the second voice information, the second semantics corresponding to "complete this input" can be obtained as: complete the input.

[0173] S82, matching the second semantics with the preset end semantics; wherein, the second semantics matches the preset end semantics, indicating that the second voice information satisfies the input end condition.

[0174] In specific implementation, after receiving the second voice information and identifying the second semantics corresponding to the second voice information, in order to determine whether the second voice information meets the input end condition, the second semantics can be matched with the preset end semantics included in the preset input end condition. If the second semantics matches the preset end semantics, it means that the second voice information is allowed to end the current input operation, that is, the second voice information meets the input end condition. Otherwise, if the preset end semantics matching the second semantics are not found, it means that the second voice information has not been set to end the input operation, that is, the second voice information does not meet the input end condition.

[0175] For example: Assume that the input end condition includes two preset end semantics, namely: preset end semantic I-complete input, preset end semantic J-end reply. If the second voice message is "complete input now", the corresponding second semantic is: complete input, then the second semantic matches the preset wake-up semantic I, and it can be determined that the second voice message meets the input end condition. If the second voice message is "I'm done eating", the corresponding second semantic is: end eating, then the second semantic does not match either the preset end semantic I or the preset end semantic J, and it can be determined that the second voice message does not meet the input end wake-up condition.

[0176] It should be noted that in the process of matching the second semantics with the preset end semantics, since the preset end semantics may not include all expressions that meet the input end conditions, when it is found that the second semantics and the preset end semantics are not exactly the same, it is also possible to analyze whether the second semantics and the preset end semantics express the same semantics, such as: including synonyms. If so, the second semantics is also regarded as matching the preset end semantics.

[0177] As another example, when the second information is second image information, then, analyzing whether the second information satisfies the input end condition in step 106 may specifically include: matching the second image information with a preset end image; wherein, the second image information matches the preset end image, indicating that the second image information satisfies the input end condition.

[0178] In specific implementation, after receiving the second image information, in order to determine whether the second image information meets the input end condition, the second image information can be matched with the preset end image included in the preset input end condition. If the second image information matches the preset end image, it means that the second image information is allowed to end the current input operation, that is, the second image information meets the input end condition. Otherwise, if the preset end image matching the second image information is not found, it means that the second image information has not been set to end the input operation, that is, the second image information does not meet the input end condition.

[0179] For example: Assume that the input end condition includes three preset end images, namely: preset end image L-gesture image representing "eight", preset end image M-gesture image representing "five", and preset end image N-gesture image representing "great". If the second image information is a gesture image with the thumb straight and other fingers bent, that is, the second image information is a gesture image representing "great", then the second image information matches the preset end image N, and it can be determined that the second image information meets the input end condition. If the second image information is a gesture image with all five fingers bent, then the second image information does not match the preset end image L, the preset end image M, and the preset end image N, and it can be determined that the second image information does not meet the input end condition.

[0180] It is understandable that the preset end image can be flexibly set, and the matching condition that the second image information needs to meet with each preset end image can also be flexibly set. The matching of the second image information and the preset end image can mean that the similarity between the second image information and the preset end image is greater than a preset similarity threshold, or that the form represented by the second image information is consistent with the form represented by the preset end image, or that the second image information and the preset end image information are symmetrical, and so on.

[0181] It should be noted that in order to improve the input experience and free the user's hands, the above-mentioned embodiment of the present invention introduces an implementation method in which the user enters the second information without touching the terminal to end the input operation. However, the embodiment of the present invention also includes an implementation method for ending the input operation by clicking a specific position of the terminal (for example: clicking the return key on the terminal touch screen).

[0182] In some specific scenarios, considering that the fifth information and the sixth information may be received almost at the same time, wherein the fifth information meets the input method wake-up condition and the sixth information meets the input end condition, then, in order for the input method to be effectively and conveniently used by the user, the embodiment of the present invention may also set different priorities for different types of information. For example, different information types may be, in descending order of pre-set priorities, touch screen key input type, voice input type, gesture image input type, or lip reading image input type.

[0183] When implementing it specifically, Figure 3 As shown, the embodiment of the present invention may further include:

[0184] Step 301, receiving fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition.

[0185] It is understandable that in order to distinguish Figure 1In the embodiment shown, the first information, the second information and Figure 2 Corresponding to the third information and the fourth information in the embodiment, the two information received almost simultaneously are recorded as the fifth information and the sixth information respectively, and the fifth information and the sixth information are analyzed respectively through the above steps 103 and 106 to determine that the fifth information satisfies the input method wake-up condition and the sixth information satisfies the input end condition. The input type corresponding to the fifth information may be a touch screen key input type, a voice input type, a gesture image input type or a lip reading image input type; the input type corresponding to the sixth information may also be a touch screen key input type, a voice input type, a gesture image input type or a lip reading image input type.

[0186] Step 302: If the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, the process of starting to receive input information is triggered.

[0187] In specific implementation, the priority of the input type corresponding to the fifth information and the input type corresponding to the sixth information can be determined respectively, and a comparison can be made as to whether the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information. In one case, if the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, it means that the input method wake-up condition satisfied by the fifth information needs to be used as the basis, that is, "start receiving input information" in step 103 that should be executed after the input method wake-up condition is satisfied. In another case, if the priority of the input type corresponding to the fifth information is lower than the priority of the input type corresponding to the sixth information, it means that the input end condition satisfied by the sixth information needs to be used as the basis, that is, "end receiving input information and obtain input results based on the received input information" in step 106 that should be executed after the input end condition is satisfied.

[0188] It should be noted that if the input type corresponding to the fifth information is the same as the input type corresponding to the sixth information or their corresponding priorities are the same, the information received slightly later can be ignored, and the information received earlier can be used as the basis. The conditions satisfied by the information received earlier between the fifth information and the sixth information can be used to determine whether to execute "start receiving input information" in step 103 or "end receiving input information and obtain input results based on the received input information" in step 106.

[0189] For example: Assume that the input types corresponding to each information can be, in descending order of the preset priority, touch screen key input type, voice input type, gesture image input type or lip reading image input type, the received fifth information corresponding to the input type is the voice input type, the sixth information corresponding to the input type is the gesture image input type, and the fifth information satisfies the preset wake-up semantics a "start voice reply" in the input method wake-up condition; the sixth information satisfies the preset end image M-gesture image representing "five" in the input end condition. Since the priority of the fifth information corresponding to the input type "voice input type" is higher than the priority of the sixth information corresponding to the input type "gesture image input type", then the input method wake-up condition satisfied by the fifth information shall prevail, and the input information shall be received.

[0190] In this way, the problem of input confusion caused by receiving information for waking up the input method system and for ending the input operation almost at the same time can be effectively solved. By setting different priorities for different types of information, users can complete input conveniently and effectively, thereby improving the user's input experience.

[0191] It should be noted that, when a plurality of second information of different corresponding types for ending the input operation are received almost simultaneously, any one of the received second information may be used as a basis for ending the reception of the input information.

[0192] It should be noted that after obtaining the received input result, different operations can be performed on the input result according to different settings. For example: after obtaining the input result, the input result is stored in the space corresponding to the target address according to the user setting, and the input result is sent only after receiving the user's preset sending instruction (such as: voice sending instruction, gesture image corresponding sending instruction, or specific action of the operating terminal corresponding sending instruction); for example: after obtaining the input result, the input result is directly sent according to the user setting; for example: after obtaining the input result, the user is prompted to set according to the user setting, the input result is converted into a text result, and the user is prompted to confirm or modify it, and the input result is sent after the user confirms that it is correct, or the text result corresponding to the input result, or the correct text result after modification.

[0193] It can be seen that in the embodiment of the present invention, when the user needs to call the input method system on the terminal for input, the user can input the first information to the terminal in at least one of the multiple input types. After receiving the first information, the terminal firstly selects the input method wake-up condition corresponding to the first input type according to the first input type of the first information, and then determines whether the first information satisfies the input method wake-up condition. If so, the input method system is awakened and starts to receive input information. Then, when the user inputs the second information to the terminal in at least one of the multiple input types, the input method system receives the second information and can select the input end condition corresponding to the second input type according to the second input type of the second information. Finally, it determines whether the second information satisfies the input end condition. If so, the input information is received and the input result is obtained according to the received input information. In this way, the present embodiment provides multiple ways to wake up the input method system and end the input operation. The user can use at least one of the multiple input types to input the first information and the second information according to their different needs, thereby overcoming the problem that the user input needs cannot be met under a single input type, resulting in inconvenience for the user input, and realizing the diversification of the input method system wake-up and end operations, providing convenience for the user, thereby improving the user input experience.

[0194] Exemplary Devices

[0195] Figure 4 A schematic diagram of the structure of an input device provided by an embodiment of the present invention. Figure 4 In this embodiment, the device may specifically include:

[0196] A first receiving unit 401 is configured to receive first information, where the first information is at least one of multiple input types;

[0197] A first selection unit 402, configured to select an input method wake-up condition corresponding to a first input type according to the first input type of the first information;

[0198] The second receiving unit 403 is configured to start receiving input information if the first information satisfies the input method wake-up condition;

[0199] A third receiving unit 404 is configured to receive second information, where the second information is at least one of multiple input types;

[0200] A second selection unit 405, configured to select an input end condition corresponding to the second input type according to the second input type of the second information;

[0201] The acquisition unit 406 is configured to terminate the reception of the input information if the second information satisfies the input termination condition, and obtain an input result according to the received input information.

[0202] Optionally, the first input type includes at least one of the following input types:

[0203] Touch screen key input type, voice input type and image input type;

[0204] The second input type includes at least one of the following input types:

[0205] Touch screen key input type, voice input type and image input type.

[0206] Optionally, if the first information is first voice information, the first selection unit 402 includes:

[0207] A first recognition subunit, used to recognize that the input type of the first voice information is a voice input type;

[0208] A second selection subunit, configured to select a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition;

[0209] If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics;

[0210] If the second information is second voice information, the second selection unit 405 includes:

[0211] A second identification subunit, used for identifying that the input type of the second voice information is a voice input type;

[0212] A second selection subunit, configured to select a preset end semantic corresponding to the speech input type as the input end condition;

[0213] If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

[0214] Optionally, if the first information is first image information, the first selection unit 402 includes:

[0215] A first acquisition subunit, used for acquiring the first image information;

[0216] A third identification subunit, used to identify that the input type of the first image information is an image input type;

[0217] A third selection subunit, configured to select a preset wake-up image corresponding to the image input type as the input method wake-up condition;

[0218] If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image;

[0219] If the second information is second image information, the second selection unit 405 includes:

[0220] A second acquisition subunit, used for acquiring the second image information;

[0221] A fourth identification subunit, used to identify that the input type of the second image information is an image input type;

[0222] a fourth selection subunit, configured to select a preset end image corresponding to the image input type as the input end condition;

[0223] If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

[0224] Optionally, the second receiving unit 403 is specifically configured to:

[0225] If the first information satisfies the input method wake-up condition corresponding to the target input mode, then the input information starts to be received in the target input mode.

[0226] Optionally, the target input mode includes: a voice input mode, a lip reading input mode or an air writing input mode;

[0227] Wherein, in the voice input mode, the input information is voice information;

[0228] In the lip reading input mode, the input information is a lip reading image;

[0229] In the air handwriting input mode, the input information is a handwritten image.

[0230] Optionally, the device further comprises:

[0231] a fourth receiving unit, configured to receive third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type;

[0232] A determining unit is configured to determine, if the priority of the third input type is higher than the priority of the fourth input type, that the third input type is the target input mode, and trigger the execution of starting to receive the input information in the target input mode.

[0233] Optionally, the device further comprises:

[0234] a fifth receiving unit, configured to receive fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition;

[0235] A triggering unit is used to trigger the start of receiving input information if the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information.

[0236] Optionally, the device further comprises:

[0237] A sending unit is used to send the input result after obtaining the input result.

[0238] Figure 4 The device shown is with Figure 1 The device corresponding to the method shown, the specific implementation method and the effect achieved are Figure 1 Similar to the method shown, refer to Figure 1 The description of the method shown in the figure will not be repeated here.

[0239] Reference Figure 5 , the input device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 506 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0240] The processing component 502 generally controls the overall operation of the device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 506 and the processing component 502.

[0241] The memory 504 is configured to store various types of data to support operations on the input device 500. Examples of such data include instructions for any application or method operating on the input device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0242] The power supply component 506 provides power to the various components of the input device 500. The power supply component 506 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the input device 500.

[0243] The multimedia component 506 includes a screen that provides an output interface between the input device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 506 includes a front camera and / or a rear camera. When the input device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0244] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the input device 500 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0245] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0246] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the input device 500. For example, the sensor assembly 514 can detect the open / closed state of the input device 500, the relative positioning of components, such as the display and keypad of the device 500, and the sensor assembly 514 can also detect the position change of the input device 500 or a component of the input device 500, the presence or absence of user contact with the input device 500, the orientation or acceleration / deceleration of the input device 500, and the temperature change of the input device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0247] The communication component 516 is configured to facilitate wired or wireless communication between the input device 500 and other devices. The input device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0248] In an exemplary embodiment, the input device 500 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0249] Specifically, an embodiment of the present invention provides an input device, which may be specifically an input device 500, including a memory 504 and one or more programs, wherein the one or more programs are stored in the memory 504 and are configured to be executed by one or more processors 520. The one or more programs include instructions for performing the following operations:

[0250] receiving first information, wherein the first information is at least one of multiple input types;

[0251] selecting an input method wake-up condition corresponding to the first input type according to the first input type of the first information;

[0252] If the first information satisfies the input method wake-up condition, then, starting to receive input information;

[0253] receiving second information, wherein the second information is at least one of a plurality of input types;

[0254] selecting an input end condition corresponding to the second input type according to the second input type of the second information;

[0255] If the second information satisfies the input termination condition, the receiving of the input information is terminated, and the input result is obtained according to the received input information.

[0256] Optionally, the first input type includes at least one of the following input types:

[0257] Touch screen key input type, voice input type and image input type;

[0258] The second input type includes at least one of the following input types:

[0259] Touch screen key input type, voice input type and image input type.

[0260] Optionally, if the first information is first voice information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0261] Identify that the input type of the first voice information is a voice input type;

[0262] Selecting a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition;

[0263] If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics;

[0264] If the second information is second voice information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0265] Identify that the input type of the second voice information is a voice input type;

[0266] Selecting a preset ending semantic corresponding to the voice input type as the input ending condition;

[0267] If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

[0268] Optionally, if the first information is first image information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0269] collecting the first image information;

[0270] Identify that the input type of the first image information is an image input type;

[0271] Selecting a preset wake-up image corresponding to the image input type as the input method wake-up condition;

[0272] If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image;

[0273] If the second information is second image information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0274] collecting the second image information;

[0275] Identify the input type of the second image information as an image input type;

[0276] Selecting a preset end image corresponding to the image input type as the input end condition;

[0277] If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

[0278] Optionally, if the first information satisfies an input method wake-up condition, then starting to receive input information includes:

[0279] If the first information satisfies the input method wake-up condition corresponding to the target input mode, then the input information starts to be received in the target input mode.

[0280] Optionally, the target input mode includes: a voice input mode, a lip reading input mode or an air writing input mode;

[0281] Wherein, in the voice input mode, the input information is voice information;

[0282] In the lip reading input mode, the input information is a lip reading image;

[0283] In the air handwriting input mode, the input information is a handwritten image.

[0284] Optionally, the processor 520 is further configured to execute the one or more programs including instructions for performing the following operations:

[0285] receiving third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type;

[0286] If the priority of the third input type is higher than the priority of the fourth input type, the third input type is determined to be the target input mode, and the process of starting to receive the input information in the target input mode is triggered.

[0287] Optionally, the processor 520 is further configured to execute the one or more programs including instructions for performing the following operations:

[0288] receiving fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition;

[0289] If the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, the step of starting to receive input information is triggered.

[0290] Optionally, after obtaining the input result, the processor 520 is further configured to execute the one or more programs including instructions for performing the following operations:

[0291] The input result is sent.

[0292] In addition, the embodiment of the present invention further provides a non-transitory computer-readable storage medium including instructions, such as a memory 504 including instructions, and the instructions can be executed by the processor 520 of the input device 500 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0293] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an input device, enables the input device to perform an input method, the method comprising:

[0294] receiving first information, wherein the first information is at least one of multiple input types;

[0295] selecting an input method wake-up condition corresponding to the first input type according to the first input type of the first information;

[0296] If the first information satisfies the input method wake-up condition, then, starting to receive input information;

[0297] receiving second information, wherein the second information is at least one of a plurality of input types;

[0298] selecting an input end condition corresponding to the second input type according to the second input type of the second information;

[0299] If the second information satisfies the input termination condition, the receiving of the input information is terminated, and the input result is obtained according to the received input information.

[0300] Optionally, the first input type includes at least one of the following input types:

[0301] Touch screen key input type, voice input type and image input type;

[0302] The second input type includes at least one of the following input types:

[0303] Touch screen key input type, voice input type and image input type.

[0304] Optionally, if the first information is first voice information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0305] Identify that the input type of the first voice information is a voice input type;

[0306] Selecting a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition;

[0307] If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics;

[0308] If the second information is second voice information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0309] Identify that the input type of the second voice information is a voice input type;

[0310] Selecting a preset ending semantic corresponding to the voice input type as the input ending condition;

[0311] If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

[0312] Optionally, if the first information is first image information, then the selecting, according to the first input type of the first information, an input method wake-up condition corresponding to the first input type includes:

[0313] collecting the first image information;

[0314] Identify that the input type of the first image information is an image input type;

[0315] Selecting a preset wake-up image corresponding to the image input type as the input method wake-up condition;

[0316] If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image;

[0317] If the second information is second image information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes:

[0318] collecting the second image information;

[0319] Identify the input type of the second image information as an image input type;

[0320] Selecting a preset end image corresponding to the image input type as the input end condition;

[0321] If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

[0322] Optionally, if the first information satisfies an input method wake-up condition, then starting to receive input information includes:

[0323] If the first information satisfies the input method wake-up condition corresponding to the target input mode, then the input information starts to be received in the target input mode.

[0324] Optionally, the target input mode includes: a voice input mode, a lip reading input mode or an air writing input mode;

[0325] Wherein, in the voice input mode, the input information is voice information;

[0326] In the lip reading input mode, the input information is a lip reading image;

[0327] In the air handwriting input mode, the input information is a handwritten image.

[0328] Optionally, the method further comprises:

[0329] receiving third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type;

[0330] If the priority of the third input type is higher than the priority of the fourth input type, the third input type is determined to be the target input mode, and the process of starting to receive the input information in the target input mode is triggered.

[0331] Optionally, the method further comprises:

[0332] receiving fifth information and sixth information, wherein the fifth information satisfies the input method system wake-up condition, and the sixth information satisfies the input end condition;

[0333] If the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, the step of starting to receive input information is triggered.

[0334] Optionally, after obtaining the input result, the method further includes:

[0335] The input result is sent.

[0336] Figure 6 6 is a schematic diagram of the structure of the server in an embodiment of the present invention. The server 600 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 622 (for example, one or more processors) and a memory 632, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 642 or data 644. Among them, the memory 632 and the storage medium 630 can be short-term storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 622 can be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the server 600.

[0337] The server 600 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input and output interfaces 658, one or more keyboards 656, and / or one or more operating systems 641, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0338] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0339] It should be understood that the present invention is not limited to the precise structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0340] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An input method, It is characterized in that include: receiving first information, wherein the first information is at least one of multiple input types; Selecting an input method wake-up condition corresponding to a first input type according to the first information; the first input type includes at least one of the following input types: a touch screen key input type, a voice input type, and an image input type; When the first information includes multiple input types, and the multiple input types all meet the corresponding input wake-up conditions, the input mode corresponding to the input type with the highest priority is determined as the target input mode according to the priority corresponding to the input type, and input information is started to be received in the target input mode; wherein the target input mode includes: voice input mode, lip reading input mode or air handwriting input mode; in the voice input mode, the input information is voice information; in the lip reading input mode, the input information is a lip reading image; in the air handwriting input mode, the input information is a handwriting image; receiving second information, wherein the second information is at least one of a plurality of input types; Selecting an input end condition corresponding to a second input type according to the second information; the second input type includes at least one of the following input types: a touch screen key input type, a voice input type, and an image input type; When the second information includes multiple input types, and the multiple input types all meet the corresponding input end conditions, the input end condition corresponding to the input type with the highest priority is determined as the target input end condition, and the reception of the input information is terminated according to the target input end condition, and the input result is obtained based on the received input information.

2. The method according to claim 1, It is characterized in that If the first information is the first voice information, then the step of selecting the input method wake-up condition corresponding to the first input type according to the first input type of the first information includes: Identify that the input type of the first voice information is a voice input type; Selecting a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition; If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics; If the second information is second voice information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes: Identify that the input type of the second voice information is a voice input type; Selecting a preset ending semantic corresponding to the voice input type as the input ending condition; If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

3. The method according to claim 1, It is characterized in that If the first information is first image information, then the step of selecting an input method wake-up condition corresponding to the first input type according to the first input type of the first information includes: collecting the first image information; Identify that the input type of the first image information is an image input type; Selecting a preset wake-up image corresponding to the image input type as the input method wake-up condition; If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image; If the second information is second image information, then the step of selecting an input end condition corresponding to the second input type according to the second input type of the second information includes: collecting the second image information; Identify the input type of the second image information as an image input type; Selecting a preset end image corresponding to the image input type as the input end condition; If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

4. The method according to claim 1, It is characterized in that When the first information includes multiple input types, and the multiple input types all meet the corresponding input wake-up conditions, the input mode corresponding to the input type with the highest priority is determined as the target input mode according to the priorities of the input types, and input information is started to be received in the target input mode, including: receiving third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type; If the priority of the third input type is higher than the priority of the fourth input type, then the input mode corresponding to the third input type is determined to be the target input mode, and the process of starting to receive the input information in the target input mode is triggered.

5. The method according to claim 1, It is characterized in that When the second information includes multiple input types, and the multiple input types all meet corresponding input end conditions, the input end condition corresponding to the input type with the highest priority is determined as the target input end condition according to the priorities corresponding to the input types, and the reception of the input information is ended according to the target input end condition, and an input result is obtained according to the received input information, including: receiving fifth information and sixth information, wherein the fifth information satisfies the input end condition, and the sixth information satisfies the input end condition; If the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, the reception of the input information is terminated according to the input termination condition corresponding to the fifth information, and the input result is obtained according to the received input information.

6. The method according to any one of claims 1 to 5, It is characterized in that After obtaining the input result, the method further includes: The input result is sent.

7. An input device, It is characterized in that include: A first receiving unit, configured to receive first information, where the first information is at least one of multiple input types; A first selection unit, configured to select an input method wake-up condition corresponding to a first input type according to the first input type of the first information; The first input type includes at least one of the following input types: a touch screen key input type, a voice input type, and an image input type; A second receiving unit is used for, when the first information includes multiple input types and the multiple input types all meet the corresponding input wake-up conditions, determining the input mode corresponding to the input type with the highest priority as the target input mode according to the priority corresponding to the input type, and starting to receive input information in the target input mode; wherein the target input mode includes: voice input mode, lip reading input mode or air handwriting input mode; in the voice input mode, the input information is voice information; in the lip reading input mode, the input information is a lip reading image; in the air handwriting input mode, the input information is a handwriting image; A third receiving unit, configured to receive second information, where the second information is at least one of multiple input types; A second selection unit is used to select an input end condition corresponding to a second input type according to the second input type of the second information; the second input type includes at least one of the following multiple input types: a touch screen key input type, a voice input type, and an image input type; An acquisition unit is used to, when the second information includes multiple input types and the multiple input types all meet corresponding input end conditions, determine the input end condition corresponding to the input type with the highest priority as the target input end condition according to the priorities corresponding to the input types, end the reception of the input information according to the target input end condition, and obtain the input result based on the received input information.

8. The device according to claim 7, It is characterized in that If the first information is first voice information, the first selection unit includes: A first recognition subunit, used to recognize that the input type of the first voice information is a voice input type; A second selection subunit, configured to select a preset wake-up semantic corresponding to the voice input type as the input method wake-up condition; If the first information satisfies the input method wake-up condition, specifically: the first semantics corresponding to the first voice information matches the preset wake-up semantics; If the second information is second voice information, the second selection unit includes: A second identification subunit, used for identifying that the input type of the second voice information is a voice input type; A second selection subunit, configured to select a preset end semantic corresponding to the speech input type as the input end condition; If the second information satisfies the input end condition, specifically: the second semantics corresponding to the second voice information matches the preset end semantics.

9. The device according to claim 7, It is characterized in that If the first information is first image information, the first selection unit includes: A first acquisition subunit, used for acquiring the first image information; A third identification subunit, used to identify that the input type of the first image information is an image input type; A third selection subunit, configured to select a preset wake-up image corresponding to the image input type as the input method wake-up condition; If the first information satisfies the input method wake-up condition, specifically: the first image information matches the preset wake-up image; If the second information is second image information, the second selection unit includes: A second acquisition subunit, used for acquiring the second image information; A fourth identification subunit, used to identify that the input type of the second image information is an image input type; a fourth selection subunit, configured to select a preset end image corresponding to the image input type as the input end condition; If the second information satisfies the input end condition, specifically: the second image information matches the preset end image.

10. The device according to claim 7, It is characterized in that The first receiving unit comprises: a fourth receiving unit, configured to receive third information and fourth information, wherein the third information satisfies the input method wake-up condition corresponding to the third input type, and the fourth information satisfies the input method wake-up condition corresponding to the fourth input type; A determination unit is used to determine that the input mode corresponding to the third input type is the target input mode if the priority of the third input type is higher than the priority of the fourth input type, and trigger the execution of starting to receive the input information in the target input mode.

11. The device according to claim 7, It is characterized in that The acquisition unit comprises: a fifth receiving unit, configured to receive fifth information and sixth information, wherein the fifth information satisfies the input end condition, and the sixth information satisfies the input end condition; A trigger unit is used to terminate the reception of the input information according to the input termination condition corresponding to the fifth information if the priority of the input type corresponding to the fifth information is higher than the priority of the input type corresponding to the sixth information, and obtain the input result according to the received input information.

12. The device according to any one of claims 7 to 11, It is characterized in that The device also includes: A sending unit is used to send the input result after obtaining the input result.

13. An input device, It is characterized in that The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include being used to execute the method as claimed in any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an input device, the input device is enabled to perform the method as claimed in any one of claims 1 to 6.

Images