Function recommendation method and device, equipment, program and medium

Abstract

The invention discloses a function recommendation method and device, equipment, a program and a medium. The method comprises the steps of obtaining target input information input by a user during operation of a first application; performing semantic analysis on the target input information to obtain target control information; determining at least one second application meeting a recommendation condition based on the target control information; and displaying a shortcut instruction control corresponding to the second application on a display interface of the terminal equipment.

Description

Function recommendation method, device, equipment, program and medium Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more specifically, to a function recommendation method, apparatus, device, program, and medium. Background Art

[0002] During the application process of the terminal device, the user can interact with the terminal device by clicking instructions, calling the application program currently required by the user and the functional modules of the application program in the terminal device to implement the corresponding functions.

[0003] However, frequently clicking commands (mouse clicks or touchscreen clicks, etc.) to access multiple levels of functionality is cumbersome, and interaction with the terminal device requires the user's dedicated attention, disrupting the user's current operating environment and resulting in a poor user experience. Therefore, achieving seamless interaction and improving the user experience has become a pressing technical challenge for those skilled in the art.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure provide a function recommendation method, apparatus, device, program, and medium, aiming to solve the problem of how to complete function recommendation without disrupting the current operating environment and achieve seamless interaction.

[0006] A first aspect of an embodiment of the present disclosure provides a function recommendation method, the method comprising:

[0007] During the execution of the first application, obtaining target input information input by the user;

[0008] Performing semantic analysis on the target input information to obtain target control information;

[0009] determining, based on the target control information, at least one second application that meets a recommendation condition;

[0010] Display the shortcut command control corresponding to the second application on the display interface of the terminal device.

[0011] In an optional implementation, after displaying the shortcut command control corresponding to the second application on the display interface of the terminal device, the method further includes:

[0012] In response to a user operation on the first shortcut command control, opening an application interface of the second application;

[0013] Receive first configuration information input by a user, and switch the application interface of the second application to a functional interface for executing the first configuration information.

[0014] In an optional implementation, after determining the second application that meets the recommendation condition, the method further includes:

[0015] Performing configuration information identification on the target input information to obtain second configuration information;

[0016] Determine a target application based on the second application and the second configuration information, where the target application is the second application that can execute the target control information according to the second configuration information;

[0017] determining a target function, where the target function is to control the target application to execute an instruction corresponding to the target control information, and the target function is set based on the second configuration information;

[0018] Display the shortcut command control corresponding to the target function on the display interface of the terminal device.

[0019] In an optional implementation, the target input information includes third input information, and the method includes:

[0020] Performing configuration information identification on the third input information to obtain second configuration information;

[0021] In response to a user operation on the first shortcut command control, opening an application interface of the second application;

[0022] Based on the second configuration information, the second application is configured so that the application interface of the second application is switched to a functional interface for executing the second configuration information.

[0023] In an optional implementation, the second application is a countdown application.

[0024] In an optional embodiment,

[0025] The target input information includes first input information and second input information. The target input information is semantically parsed to obtain target control information, including:

[0026] Performing semantic parsing on the first input information to obtain first target control information;

[0027] performing semantic parsing on the second input information to obtain second target control information;

[0028] Determining, based on the target control information, at least one second application that meets a recommendation condition includes:

[0029] determining, based on the first target control information, at least one second application for the first input information that meets the recommendation condition;

[0030] determining, based on the second target control information, at least one second application for the second input information that meets the recommendation condition;

[0031] Displaying the shortcut command control corresponding to the second application on the display interface of the terminal device includes:

[0032] The shortcut command control corresponding to the second application for the second input information and the shortcut command control corresponding to the second application for the first input information are simultaneously displayed on the display interface of the terminal device.

[0033] In an optional implementation, the target input information includes first input information and second input information, and displaying a shortcut command control corresponding to the second application on a display interface of the terminal device includes:

[0034] In response to a user operation on the first shortcut command control, opening an application interface of a second application corresponding to the first input information on the display interface;

[0035] In response to the user's operation on the second shortcut command control, the application interface of the second application for the first input information is closed, and the application interface of the second application for the second input information is opened on the display interface.

[0036] In an optional implementation, after determining the second application that meets the recommendation condition, the method further includes:

[0037] When the terminal device is in a network connection state, determining a third application that meets a recommendation condition based on the target control information, where the third application is a cloud platform application;

[0038] The shortcut command control corresponding to the second application and the shortcut command control corresponding to the third application are displayed simultaneously on the display interface of the terminal device.

[0039] In an optional embodiment, the method further includes:

[0040] When the terminal device is in a state of no network connection, a prompt message is displayed on the display interface of the terminal device, and the prompt message is used to prompt the user to check the network status of the terminal device;

[0041] Generating a network setting icon on the display interface of the terminal device;

[0042] In response to the user's interactive operation with the network setting icon, a network setting interface is displayed on the display interface of the terminal device.

[0043] In an optional implementation, determining the second application that meets the recommendation condition based on the target control information includes:

[0044] Matching the target control information with multiple applications in the terminal device to obtain a first matching degree;

[0045] Based on the first matching degree, the second application that meets the recommendation condition is obtained.

[0046] In an optional implementation, after obtaining the target control information, the method further includes:

[0047] Matching the target control information with multiple applications in the terminal device to obtain a first matching degree;

[0048] Based on the first matching degree, obtaining at least one candidate second application that meets the recommendation condition, where the recommendation condition is that the first matching degree is greater than a first matching threshold;

[0049] In order of the first matching degrees of the candidate second applications, shortcut command controls corresponding to the candidate second applications are displayed in sequence on the display interface of the terminal device.

[0050] In an optional embodiment, the method further includes:

[0051] During the running of the first application, the target input information input by the user is obtained, where the first application is a handwriting application, the target input information is handwriting input information, and the handwriting input information is text information obtained by performing text recognition on handwriting trajectory point information;

[0052] Performing semantic analysis on the handwriting input information to obtain the target control information;

[0053] determining, based on the target control information, at least one second application that meets the recommendation condition;

[0054] Display the shortcut command control corresponding to the second application on the application interface of the handwriting application.

[0055] In an optional implementation, the handwriting input information is obtained as follows:

[0056] Acquire the handwriting track point information input by the user, where the handwriting track point information includes at least one of the following: track point coordinate value, track point timestamp, and track point status;

[0057] Based on the handwriting trajectory point information, obtaining a handwriting trajectory connection diagram;

[0058] Inputting the handwriting trajectory point information into a first branch of a text recognition network to obtain a first input feature, where the first input feature includes trajectory point time information of the handwriting trajectory point information;

[0059] Inputting the handwriting trajectory connection diagram into the second branch of the character recognition network to obtain a second input feature, where the second input feature does not include the trajectory point time information of the handwriting trajectory point information;

[0060] The first input feature and the second input feature are combined to obtain the handwriting input information.

[0061] In an optional implementation, the target input information is voice input information, and the voice input information is obtained as follows:

[0062] Get the voice information input by the user;

[0063] Performing feature extraction on the voice information to obtain voice features;

[0064] Based on a speech recognition model, the speech features are decoded to obtain the speech input information.

[0065] In an optional implementation, performing semantic parsing on the target input information to obtain target control information includes:

[0066] Based on the target input information, obtaining at least one sentence;

[0067] Performing word segmentation processing on the sentences in the target input information to obtain multiple word segments;

[0068] Matching each word segment with the candidate control information to obtain a second matching degree;

[0069] The candidate control information whose second matching degree is greater than a second matching threshold is used as the target control information.

[0070] In an optional implementation manner, the candidate control information is obtained as follows:

[0071] Obtaining a function type of each application in the terminal device;

[0072] grouping all applications in the terminal device according to the functional type of each application in the terminal device to obtain at least one application cluster, wherein the functional types of applications in each application cluster are the same;

[0073] The function type corresponding to each application cluster is used as the candidate control information.

[0074] In an optional implementation, after obtaining a plurality of segmented words, the method further includes:

[0075] The left-hand side participle and the right-hand side participle corresponding to each participle in the sentence are used as classification input data to obtain a classification input data set;

[0076] The classified input data set is input into a classification model, and semantic parsing is performed on the classified input data set based on the classification model to obtain the target control information.

[0077] According to a second aspect of the present disclosure, a function recommendation device is provided, comprising:

[0078] A target input information acquisition module, configured to acquire target input information input by a user during the execution of the first application;

[0079] A semantic parsing module, configured to perform semantic parsing on the target input information to obtain target control information;

[0080] a recommended application module, configured to determine, based on the target control information, a second application that meets a recommendation condition;

[0081] A display module is used to display the shortcut command control corresponding to the second application on the display interface of the terminal device.

[0082] In an optional embodiment, the device further includes:

[0083] an application opening module, configured to open an application interface of the second application in response to a user operation on the first shortcut command control;

[0084] The interface switching module is used to receive first configuration information input by a user and switch the application interface of the second application to a functional interface for executing the first configuration information.

[0085] In an optional embodiment, the device further includes:

[0086] a configuration information acquisition module, configured to perform configuration information identification on the target input information to obtain second configuration information;

[0087] a target application module, configured to determine a target application based on the second application and the second configuration information, wherein the target application is the second application that can execute the target control information according to the second configuration information;

[0088] a target function module, configured to determine a target function, wherein the target function is to control the target application to execute an instruction corresponding to the target control information, and the target function is set based on the second configuration information;

[0089] The second display module is used to display the shortcut command control corresponding to the target function on the display interface of the terminal device.

[0090] In an optional embodiment, the device further includes:

[0091] a configuration acquisition module, configured to perform configuration information identification on the third input information to obtain second configuration information;

[0092] An opening module, configured to open an application interface of the second application in response to a user operation on the first shortcut command control;

[0093] An application configuration module is used to configure the second application based on the second configuration information so that the application interface of the second application is switched to a functional interface for executing the second configuration information.

[0094] In an optional embodiment, the semantic parsing module includes:

[0095] A first parsing submodule, configured to perform semantic parsing on the first input information to obtain first target control information;

[0096] A second parsing submodule, configured to perform semantic parsing on the second input information to obtain second target control information;

[0097] The recommended application module includes:

[0098] A first recommended application submodule, configured to determine, based on the first target control information, at least one second application for the first input information that meets the recommendation condition;

[0099] a second recommended application submodule, configured to determine, based on the second target control information, at least one second application for the second input information that meets the recommendation condition;

[0100] The display module includes:

[0101] The third display submodule is used to simultaneously display the shortcut command control corresponding to the second application for the second input information and the shortcut command control corresponding to the second application for the first input information on the display interface of the terminal device.

[0102] In an optional embodiment, the display module includes:

[0103] a first control submodule, configured to open, on the display interface, an application interface of a second application corresponding to the first input information in response to a user operation on the first shortcut command control;

[0104] The second control submodule is used to close the application interface of the second application for the first input information in response to the user's operation on the second shortcut command control, and open the application interface of the second application for the second input information on the display interface.

[0105] In an optional embodiment, the device further includes:

[0106] a network recommendation application module, configured to determine, when the terminal device is in a network connection state, based on the target control information, a third application that meets the recommendation condition, wherein the third application is a cloud platform application;

[0107] The fourth display module is used to simultaneously display the shortcut command control corresponding to the second application and the shortcut command control corresponding to the third application on the display interface of the terminal device.

[0108] In an optional embodiment, the device further includes:

[0109] a prompt module, configured to display a prompt message on a display interface of the terminal device when the terminal device is in a state of no network connection, wherein the prompt message is used to prompt a user to check the network status of the terminal device;

[0110] A network setting display module, configured to generate a network setting icon on the display interface of the terminal device;

[0111] The fifth display module is used to display a network setting interface on the display interface of the terminal device in response to the user's interactive operation with the network setting icon.

[0112] In an optional implementation, the application recommendation module includes:

[0113] a first matching submodule, configured to match the target control information with a plurality of applications in the terminal device to obtain a first matching degree;

[0114] The recommended application submodule is configured to obtain the second application that meets the recommendation condition based on the first matching degree.

[0115] In an optional embodiment, the device further includes:

[0116] a first matching module, configured to match the target control information with a plurality of applications in the terminal device to obtain a first matching degree;

[0117] a candidate second application acquisition module, configured to acquire, based on the first matching degree, at least one candidate second application that meets the recommendation condition, wherein the recommendation condition is that the first matching degree is greater than a first matching threshold;

[0118] A fifth display module is used to display the shortcut command controls corresponding to the candidate second applications in sequence on the display interface of the terminal device in the order of the first matching degrees of the candidate second applications.

[0119] In an optional embodiment, the device further includes:

[0120] a handwriting input information acquisition module, configured to acquire the target input information input by the user during the running of the first application, wherein the first application is a handwriting application, the target input information is handwriting input information, and the handwriting input information is text information obtained by performing text recognition on handwriting trajectory point information;

[0121] a second semantic parsing module, configured to perform semantic parsing on the handwriting input information to obtain the target control information;

[0122] a third application recommendation module, configured to determine, based on the target control information, at least one of the second applications that meets the recommendation condition;

[0123] A sixth display module is used to display the shortcut command control corresponding to the second application on the application interface of the handwriting application.

[0124] In an optional implementation, the handwriting input information acquisition module includes:

[0125] A handwriting information acquisition submodule, configured to acquire the handwriting track point information input by the user, wherein the handwriting track point information includes at least one of the following: track point coordinate value, track point timestamp, and track point status;

[0126] A connection diagram acquisition submodule, configured to acquire a handwriting trajectory connection diagram based on the handwriting trajectory point information;

[0127] A first input feature submodule, configured to input the handwriting trajectory point information into a first branch of a text recognition network to obtain a first input feature, wherein the first input feature includes trajectory point time information of the handwriting trajectory point information;

[0128] A second input feature submodule, configured to input the handwriting trajectory connection diagram into a second branch of the character recognition network to obtain a second input feature, wherein the second input feature does not include trajectory point time information of the handwriting trajectory point information;

[0129] A combining submodule is configured to combine the first input feature with the second input feature to obtain the handwriting input information.

[0130] In an optional implementation, the target input information acquisition module further includes:

[0131] The voice information acquisition submodule is used to acquire the voice information input by the user;

[0132] A feature extraction submodule, configured to extract features from the speech information to obtain speech features;

[0133] The decoding submodule is used to decode the speech features based on a speech recognition model to obtain the speech input information.

[0134] In an optional embodiment, the semantic parsing module includes:

[0135] A sentence segmentation module, configured to obtain at least one sentence based on the target input information;

[0136] A word segmentation submodule, configured to perform word segmentation processing on the sentences in the target input information to obtain a plurality of word segments;

[0137] A second matching submodule is used to match each word segment with the candidate control information to obtain a second matching degree;

[0138] The target control information acquisition submodule is configured to use the candidate control information for which the second matching degree is greater than a second matching threshold as the target control information.

[0139] In an optional implementation, the second matching submodule includes:

[0140] An application acquisition subunit, configured to acquire all applications in the terminal device, wherein the labels are used to characterize the functional types of the applications in the terminal device;

[0141] an application clustering subunit, configured to group all applications in the terminal device according to a function type of each application in the terminal device to obtain at least one application cluster, wherein the functions of the applications in each application cluster are the same;

[0142] The candidate control information acquisition subunit is configured to take the function type corresponding to each application cluster as a candidate control information.

[0143] In an optional embodiment, the semantic parsing module further includes:

[0144] A classification input data acquisition submodule is used to take the left-hand side segmentation and the right-hand side segmentation corresponding to each segmentation in the sentence as classification input data to obtain a classification input data set;

[0145] The semantic parsing submodule is used to input the classified input data set into the classification model, perform semantic parsing on the classified input data set based on the classification model, and obtain the target control information.

[0146] A third aspect of the present disclosure provides a computing and processing device, including:

[0147] a memory having computer readable code stored therein; and

[0148] One or more processors, when the computer-readable code is executed by the one or more processors, the computing processing device performs the function recommendation method as described in any one of the first aspects.

[0149] A fourth aspect of an embodiment of the present disclosure provides a computer program, comprising a computer-readable code, which, when executed on a computing and processing device, causes the computing and processing device to execute the function recommendation method according to any one of the first aspects.

[0150] A fifth aspect of the embodiments of the present disclosure provides a computer-readable medium, in which the computer program described in the fourth aspect is stored. Beneficial effects:

[0151] The embodiments of the present disclosure provide a function recommendation method, apparatus, device, program and medium, the method comprising: obtaining target input information input by a user during the operation of a first application; performing semantic parsing on the target input information to obtain target control information; determining at least one second application that meets the recommendation conditions based on the target control information; and displaying a shortcut command control corresponding to the second application on a display interface of the terminal device.

[0152] The disclosed embodiment determines the target control information of the user based on the target input information during the user's operation of the first application, and intelligently and real-time recommends related applications corresponding to the target input information on the display interface. This process does not require the user to specifically input input information for the recommended application, thereby ensuring that the user's operation of the first application will not be interrupted, and completing function recommendations without disrupting the current operating environment, achieving seamless interaction, thereby enhancing the user's sense of immersion, and improving the user's operating efficiency and usage experience.

[0153] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0154] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0155] FIG1 schematically shows a process flow for executing a function recommendation method according to the present disclosure;

[0156] FIG2 schematically illustrates an example of handwriting trajectory points used to perform the method according to the present disclosure;

[0157] FIG3 schematically shows an example of a handwriting trajectory point connection diagram for executing the method according to the present disclosure;

[0158] FIG4 schematically shows a second application display example in which the target control information for executing the method according to the present disclosure is “countdown”;

[0159] FIG5 schematically shows a second application display example in which the target control information for executing the method according to the present disclosure is “progress”;

[0160] FIG6 schematically shows an example of a display interface recommendation target function for executing the method according to the present disclosure;

[0161] FIG7 schematically illustrates prompt information and network setting icon examples for executing the method according to the present disclosure;

[0162] FIG8 schematically shows an example of a function recommendation minimization icon for executing the method according to the present disclosure;

[0163] FIG9 schematically shows a function recommendation device for executing the method according to the present disclosure;

[0164] FIG10 schematically shows a computing processing device for executing the method according to the present disclosure. Specific embodiments

[0165] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0166] In related technologies, the process of users running related applications usually requires users to interact with terminal devices through clicking instructions, calling the applications currently required by users and the functional modules of the applications in the terminal devices to implement corresponding functions. However, the user's frequent clicking instructions (mouse clicks or touch screen clicks, etc.) make the calling steps of multi-level functions cumbersome and the user experience is poor.

[0167] With the rapid development of terminal devices, it is now possible to automatically recommend functions to users through terminal devices and display the applications they need to users. For example, the user opens the voice pickup interface for function recommendation and enters a detailed description of the currently required application in the form of voice. The terminal device generates an application that meets the description characteristics based on the detailed description and displays it to the user. This method avoids the user's active and frequent click interactions with the terminal device.

[0168] However, the voice-controlled function recommendation method requires users to enter clear voice operation instructions in a specific interface in order to recommend specific applications or perform specific functions. In some usage scenarios, users need to interrupt the current operation to perform voice input to achieve function recommendations, which makes users lack immersion and reduces user experience; users may even give up using this function recommendation method in order not to disrupt the current operating environment.

[0169] In view of this, an embodiment of the present disclosure provides a function recommendation method. FIG1 schematically shows a process for performing a function recommendation method according to the present disclosure. As shown in FIG1 , the method includes the following steps:

[0170] S101: While running a first application, obtain target input information input by a user.

[0171] During the running of a first application, target input information input by a user is obtained, where the first application includes at least one of the following: a home application and a third-party application.

[0172] S102: Perform semantic analysis on the target input information to obtain target control information.

[0173] S103: Determine at least one second application that meets a recommendation condition based on the target control information.

[0174] S104: Display the shortcut command control corresponding to the second application on the display interface of the terminal device.

[0175] In an embodiment of the present application, the function recommendation method is applied to a terminal device, which includes multiple applications, wherein the first application is an application that can obtain the user's target input information, and the first application at least includes the terminal device's local home application (such as an application that displays the terminal device's homepage) and a third-party application; the target input information includes the user's intended target control information, and the target control information can be realized by running the function of the second application in the terminal device. Specifically, the first application is the application that the user is running, and the first application can obtain the information source through the information collection unit of the terminal device and generate corresponding text information as the target input information. The information collection unit can be a functional unit of the terminal device itself. For example, when the terminal device is a mobile terminal, the information collection unit can be a touch screen or a built-in camera of the mobile terminal; the information collection unit can also be an external collection device that establishes a wired connection or a wireless connection with the terminal device. For example, the information collection unit can be a handwriting tablet that establishes a wired connection with the terminal device or an external camera that establishes a wireless connection with the terminal device.

[0176] When a user needs to use a second application while running a first application, since the first application is running, directly calling the second application or specifically inputting voice description information for calling the second application through the voice pickup interface will interrupt the user's use of the first application and reduce the user's immersion in the use. The embodiment of the present application directly processes the target input information when the user runs the first application, intelligently obtains the second application required by the user and recommends it to the user. This can avoid disrupting the user's current usage environment while achieving function recommendations for the user's target control information, thereby improving the user's usage experience.

[0177] In the embodiment of the present disclosure, the target input information is text information corresponding to the information that the terminal device can obtain through a local unit or an external device. For example, the target input information can be text information corresponding to the information source in the form of voice information, handwriting trajectory point information, video information, text information, etc. It should be noted that the form of the information source of the specific target input information can be determined according to actual conditions, and this application does not impose any restrictions on this.

[0178] In the disclosed embodiment, the semantic parsing is used to intelligently identify the semantics of the target input information based on the target input information input by the user, and generate target control information that can characterize the user needs in the target input information based on the semantics of the target input information. The target control information is used to characterize the user needs contained in the target input information. For example, for the target input information "exam time 100 minutes", the corresponding target control information is "countdown"; for the target input information "calculate the average value", the corresponding target control information is "calculation". The second application recommended to the user is determined by the target control information corresponding to the target input information, without obtaining the input information for the second application. The application currently required by the user is recommended to the user without the user's perception, thereby maximizing the user's usage experience.

[0179] For example, the first application is a video conference. During the video conference, the user enters the voice message "Exam time 100 minutes". The text message corresponding to this voice message "Exam time 100 minutes" is used as the target input information, which contains the user's target control information "Countdown". This target control information can be implemented through the second application "Timer" on the terminal device. However, during the video conference, whether the user opens the "Timer" application by clicking or opening the voice recommendation interface and specifically entering the detailed voice recommendation information "Open timer", the video conference process will be interrupted. In this embodiment of the application, the text message "Exam time 100 minutes" corresponding to the voice message entered by the user during the "Video Conference" application is obtained, and the text message is semantically parsed to obtain the target control information "Countdown". Based on this target control information, the "Timer" application is automatically displayed on the display interface, without interrupting the video conference process, and the user's current required "Timer application" is provided in real time. It should be noted that the above example is only an optional situation proposed to enable those skilled in the art to better understand the present disclosure. Those skilled in the art may apply other first and second applications as the function recommendation method of the present disclosure without creative work.

[0180] In order to enable those skilled in the art to better understand the technical solution of the embodiment of the present disclosure, a function recommendation method provided by the embodiment of the present disclosure is described in detail below:

[0181] When step S101 is specifically implemented, the information collection unit based on the terminal device obtains the target input information for the first application input by the user during the operation of the first application. First, the information collection unit collects the original information input during the operation of the first application. The first application controls the information collection unit to obtain the original information in the information form corresponding to the first application based on its own processing capabilities and needs. For example, when the first application is a "voice conference", the original information is voice information or audio information; when the first application is a "handwriting input method", the original information is handwriting trajectory point information. Since the information form of the original information may be different, it is necessary to unify the original information of different information forms into text information for semantic analysis. Therefore, after obtaining the original information input by the user during the operation of the first application, text recognition is performed on the original information to obtain text information as the target input information.

[0182] In an optional embodiment, when the first application is a handwriting application and the original information is handwriting trajectory point information, the target input information corresponding to the handwriting trajectory point information is obtained according to the following process: first, the handwriting trajectory point information input by the user is obtained. Figure 2 schematically shows an example of handwriting trajectory points for executing the method according to the present disclosure. As shown in Figure 2, during the running of the first application, the user inputs handwriting trajectory point information through a handwriting device. The handwriting trajectory point information consists of a trajectory point diagram drawn by the user on the handwriting device in chronological order, and is composed of multiple handwriting trajectory points. The handwriting trajectory point information includes at least one of the following: trajectory point coordinate value, trajectory point timestamp, and trajectory point status (pen down or pen up).

[0183] When the user inputs the handwriting trajectory point information, the input timestamp of each point has a sequence, that is, the handwriting trajectory point information contains time information, and when the user inputs the handwriting trajectory point information, there is a situation where the input is not in accordance with the normal stroke order, that is, the "inverted pen" phenomenon. When the handwriting trajectory point information has the "inverted pen" phenomenon, the time information of the handwriting trajectory point information becomes a negative feature for the process of obtaining the corresponding text information, resulting in a decrease in the accuracy of the text information directly obtained based on the handwriting trajectory point information.

[0184] Therefore, in order to avoid the negative impact of the time feature of the handwriting trajectory point information, the trajectory points in the handwriting trajectory point information are connected, the time information in the handwriting trajectory point information is eliminated, and a handwriting trajectory connection diagram that does not contain the time feature is obtained. Figure 3 schematically shows an example of a handwriting trajectory point connection diagram for executing the method according to the present disclosure. As shown in Figure 3, the handwriting trajectory points in Figure 2 are connected to obtain the handwriting trajectory point connection diagram. Since each handwriting trajectory point is connected to form a whole text, the time information of each handwriting trajectory point is annihilated. Therefore, the handwriting trajectory point connection diagram, as the original information without time information, can reduce the problem of decreased accuracy caused by using only the handwriting trajectory point information as the original information for text recognition.

[0185] Subsequently, the handwriting trajectory point information and the handwriting trajectory point connection diagram are input into the text recognition network, and the text recognition network includes a first branch and a second branch. Specifically, the handwriting trajectory point information is input as the first original information into the first branch of the text recognition network, and the handwriting trajectory point information (trajectory point coordinate value, trajectory point timestamp, trajectory point status) is subjected to feature extraction and text recognition based on the first branch to obtain a first input feature, and the first input feature includes the trajectory point time information of the handwriting trajectory point information. The handwriting trajectory connection diagram is input as the second original information into the second branch of the text recognition network, and the handwriting trajectory point connection diagram is subjected to feature extraction and text recognition based on the second branch to obtain a second input feature, and the second input feature does not include the trajectory point time information of the handwriting trajectory point information; finally, the first input feature is combined with the second input feature to obtain the combined text information as the handwriting input information (i.e., the target input information when the first application is a handwriting application). The disclosed embodiment obtains a first input feature containing time information through a first branch, and obtains a second input feature without time information through a second branch, thereby reducing the negative impact of time information as the output text recognition result, and obtaining text information with a higher accuracy after combination. This text information characterizes the textual meaning of the input handwriting trajectory point, and uses this text information as handwriting input information for the subsequent semantic recognition process. After semantic parsing based on the handwriting input information, at least one second application that meets the recommendation conditions is determined, and the shortcut command control corresponding to the second application is displayed on the application interface of the handwriting application. For the specific semantic parsing and the process of determining the second application, please refer to the specific implementation process of subsequent S102-S103.

[0186] Exemplarily, the first branch of the text recognition network is an RNN network structure, including a combination of a multi-layer bidirectional long short-term memory network (BiLSTM) and a dropout layer arranged in sequence, and a fully connected layer. The first original information is feature extracted through multiple BiLSTM layers, and a dropout layer is set after each BiLSTM layer to improve the model recognition rate. Finally, the first input feature is obtained through the fully connected layer; the second branch of the text recognition network is a CNN network structure, including multiple downsampling layers and a fully connected layer. The second original information is feature extracted through multiple downsampling layers, and the second input feature is obtained through the fully connected layer; finally, the first input feature and the second input feature are combined to obtain the text information corresponding to the original information. It should be noted that the above example is only an optional implementation method proposed to enable those skilled in the art to better understand the solution of the present disclosure. The specific text recognition network can be determined according to actual conditions, and the present disclosure is not limited here.

[0187] In an optional embodiment, when the original information is voice information, the target input information corresponding to the voice information is obtained according to the following process: first, the voice information input by the user based on the audio acquisition device connected to the terminal device is obtained; then, feature extraction is performed on the voice information, the part of the voice signal that is helpful for understanding the language content is extracted, and the part that is not helpful for understanding the voice content is removed, and the voice information is converted into corresponding voice features, and the voice features are decoded based on the voice recognition model, and the voice features are enhanced and represented through text to obtain text information corresponding to the voice information, and the text information is used as the voice input information (that is, the target input information when the first application is a voice application).

[0188] Exemplarily, Mel-scale Frequency Cepstral Coefficients (MFCC) feature extraction is performed on the speech information to obtain the MFCC features corresponding to the speech information; the MFCC features are then input into a decoder, such as an acoustic model (traditional acoustic model GMM+HMM), a pronunciation dictionary, and a language model to decode the speech features, perform feature enhancement on the speech features, and represent them through text to obtain text information corresponding to the speech information, and use the text information as the target input information. It should be noted that the above example is only an optional implementation method proposed to enable those skilled in the art to better understand the scheme of the present disclosure. The specific speech recognition model can be determined according to actual conditions, such as traditional acoustic models (dynamic time warping, hidden Markov model, etc.), deep learning algorithms based on artificial neural networks (such as time-delay neural networks TDNN, Transformer models based on convolutional enhancement), etc., and the present disclosure does not limit this.

[0189] Specifically, when step S102 is implemented, after obtaining the target input information in the form of text information, semantic analysis is performed based on the target input information to obtain target control information represented by the target input information, and the target control information reflects the user's needs in inputting the target input information.

[0190] In an optional embodiment, the target control information corresponding to the target input information is obtained by matching with the candidate control information. Since the target input information is the text information corresponding to the original information collected during the target time period, the target input information contains at least one sentence, and the target control information corresponding to each sentence may be different. For example, the target input information is "A certain project will be reported on September 15, and in addition, a certain matter requires everyone to vote on it." The target input information contains two sentences, "A certain project will be reported on September 15," and "In addition, a certain matter requires everyone to vote on it." The target control information of the first sentence and the second sentence are different. The user demand of the first sentence is "schedule," while the user demand of the second sentence is "voting." Therefore, in order to accurately obtain the target control information of the target input information, it is necessary to sentence-process the target input information and then perform semantic analysis on each sentence.

[0191] Specifically, the target input information is firstly processed into sentences to obtain at least one sentence; then each sentence corresponding to the target input information is processed into words to obtain multiple words. Since each sentence is composed of multiple words, the meaning of the words is easier to parse semantically than the entire sentence, and the user's target control information can also be represented by words, so each sentence is processed into words to obtain multiple words. A set of candidate control information is preset in the terminal device, and the candidate control information is the word corresponding to each application cluster. All applications in the terminal device are grouped according to the functional type of the application to obtain at least one application cluster. All applications in each application cluster correspond to a word of the same functional type, and the word (that is, the functional type corresponding to each application cluster) is used as a candidate control information. Each segmentation in the target input information is matched with the candidate control information to obtain a second matching degree. The second matching degree represents the degree of overlap between each segmentation and each candidate control information. The larger the second matching degree, the more similar the segmentation is to the candidate control information, and the more likely the segmentation is to represent the target control information of the corresponding sentence. The larger the second matching degree, the more similar the segmentation is to the candidate control information, and the more likely the segmentation is to represent the target control information of the corresponding sentence. Conversely, the smaller the second matching degree, the greater the difference between the segmentation and the candidate control information, and the less likely the segmentation is to represent the target control information of the corresponding sentence. After obtaining the second matching degree of each segmentation and all candidate control information, the candidate control information with the second matching degree greater than the second matching threshold is used as the target control information of the sentence to which the segmentation belongs. In addition, if the second matching degree of the segmentation and all candidate control information is less than the second matching threshold, it means that the segmentation cannot be used as the target control information of the sentence. It should be noted that the second matching threshold and the candidate control information can be determined according to actual conditions, and this disclosure does not limit this.

[0192] For example, the word segmentation is "vote" and the first candidate control information is "video playback." The application cluster corresponding to the first candidate control information includes multiple applications that can play videos. If the second matching degree between the word segmentation and the first candidate control information is far less than the second matching threshold, the word segmentation and the first candidate control information fail to match. The second candidate control information is "vote." The application cluster corresponding to the second candidate control information includes multiple voting device applications. If the second matching degree between the word segmentation and the second candidate control information is greater than the second matching threshold, the word segmentation and the first candidate control information are successfully matched, and the second candidate control information serves as the target control information for the sentence.

[0193] In another optional embodiment, the target control information corresponding to the target input information is obtained through a classification model. First, the target input information is processed into sentences and words to obtain multiple word segments corresponding to each sentence. Since each word segment in the sentence has a front-to-back order, the word segmentation order information is captured when obtaining the semantic features of the sentence, so the classification input data containing the word segmentation order is first constructed. Specifically, the left-hand word segment and the right-hand word segment corresponding to each word segment in the sentence are used as classification input data to obtain a classification input data set; the classification input data set is input into the classification model, and the classification input data set is semantically parsed based on the classification model to obtain the target control information. The embodiment of the present disclosure captures the sequential feature information of the word segmentation, and uses each word segmentation and its preceding word (left-hand word segmentation) and following word (right-hand word segmentation) as input data to obtain the target control information, thereby improving the accuracy of the target control information. It should be noted that the classification model selected in the embodiment of the present disclosure can be determined according to actual conditions. For example, the classification model can be a common text classification model such as a random forest model (RF), an SVM classification model, or a TextCNN classification model, and the present disclosure does not limit this.

[0194] When step S103 is specifically implemented, since the first application is an application currently running on the terminal device, the first application does not need to be opened through the function recommendation method provided by the present disclosure. Therefore, in order to reduce the recommendation delay of the function recommendation method provided in the embodiment of the present disclosure, the first application is excluded from the applications that need to be recommended. First, the target control information is matched with multiple applications in the terminal device to obtain a first matching degree. Exemplarily, the target control information is matched with the application names of multiple applications in the terminal device to obtain the degree of overlap between the target control information and the application name as the first matching degree. The first matching degree characterizes the degree of overlap between the target control information and the application. The larger the first matching degree, the more similar the application name is to the target control information, and the greater the possibility that the application is the application that executes the target control information; conversely, the smaller the first matching degree, the greater the difference between the application name and the target control information, and the less likely the application is the application that executes the target control information. It should be noted that the above example is only an optional implementation method provided to enable those skilled in the art to better understand the solution of the present disclosure. The specific method of obtaining the first matching degree can be determined according to actual conditions. For example, the first matching degree can be the degree of overlap between the target control information and the name, function type or other information of the application. The present disclosure does not impose any restrictions on this.

[0195] After obtaining a first degree of match between the target control information and multiple applications in the terminal device, a second application that meets the recommendation condition is obtained based on the first degree of match. The recommendation condition may be that the first degree of match is greater than a first matching threshold, or may be another matching method. It should be noted that the first recommendation threshold can be determined based on actual circumstances and is not limited in this disclosure.

[0196] In an optional embodiment, when the target control information is obtained in an allocation-based manner, if candidate control information with a second degree of match greater than a second matching threshold with the target control information has been determined during the process of obtaining the target control information, there is no need to match the target control information with multiple applications in the terminal device. Instead, the target control information only needs to be matched with the applications in the application cluster corresponding to the candidate control information to obtain the first degree of match. Since the second degree of match between the candidate control information and the word segmentation is greater than the second matching threshold, it indicates that the applications in the application cluster corresponding to the candidate control information have a high degree of overlap. In this case, the second application can be determined by re-matching the applications in the application cluster using the first matching threshold, which can greatly reduce matching time and improve recommendation accuracy.

[0197] For example, if a second degree of match between a word in a sentence of the target input information and candidate control information exceeds a second matching threshold of 60%, the candidate control information is used as target control information corresponding to the sentence. The application cluster corresponding to the candidate control information contains multiple applications. The target control information is then matched against all applications in the application cluster to obtain an application with a matching degree exceeding the first matching threshold of 80% as the second application that meets the recommendation criteria.

[0198] Specifically, when implementing step S104, the application is displayed on the display interface of the terminal device as a shortcut control corresponding to the second application, wherein the shortcut control corresponding to the second application can be an icon or link corresponding to the launch control of the second application, and the shortcut control corresponding to the second application is displayed within a target area on the display interface. The target area can be around or within the display area of ​​the first application's functional interface when the user executes the first application. It should be noted that the display area of ​​the second application on the display interface of the terminal device can be determined according to actual circumstances and is not limited in this application.

[0199] In an optional embodiment, after the target control information is matched with multiple applications in the terminal device, there may be multiple applications that meet the recommendation conditions. At this time, all applications that meet the recommendation conditions (the first matching degree is greater than the first matching threshold) are regarded as candidate second applications. These candidate second applications are more likely to meet user needs and execute the target control information. They are then sorted according to the first matching degree corresponding to each candidate second application, and the shortcut command controls corresponding to the candidate second applications are displayed in sequence on the display interface of the terminal device in descending order of the first matching degrees of the candidate second applications.

[0200] For example, FIG4 schematically illustrates a second application display example for executing the method according to the present disclosure, where the target control information is "countdown." As shown in FIG4 , the target input information is "exam time 100 minutes." The target control information corresponding to the target input information obtained through semantic parsing is "countdown." Based on the target control information "countdown," a second application "timer" and other second applications "application 2," "application 3," ..., "application 6" whose first matching degree with "countdown" exceeds a first matching threshold are obtained, with their first matching degrees decreasing in sequence. The application icons for "timer" and the other second applications "application 2," "application 3," ..., "application 6" are sequentially displayed on the display interface of the terminal device. While the first application is running, the user can directly start the timer by clicking the "timer" icon on the display interface.

[0201] For example, FIG5 schematically illustrates an example of a second application display for executing the method according to the present disclosure, wherein the target control information is "progress". As shown in FIG5 , the target input information is "progress", and the target control information corresponding to the target input information obtained through semantic parsing is "progress". Based on the target control information "progress", a second application "Gantt chart" and other second applications "Application 2", "Application 3" ... "Application 6" whose first matching degree with "progress" is greater than a first matching threshold are obtained, and their first matching degrees decrease in sequence; the application icons of "Gantt chart" and other second applications "Application 2", "Application 3" ... "Application 6" are sequentially displayed on the display interface of the terminal device. While the first application is running, the user can directly open the functional interface of the Gantt chart application by clicking the "Gantt chart" icon on the display interface.

[0202] It should be noted that the above-mentioned multiple examples are specific implementation examples given to enable those skilled in the art to better understand the solutions of the present disclosure. The specific second application can be determined according to different target control information, for example, it can be an intelligent chart, an intelligent formula, a SWOT chart, a pyramid chart, a KANO model and other applications, and the present disclosure does not impose any restrictions on this.

[0203] In an optional embodiment, after the second application for the target input information is displayed on the display interface of the terminal device, the user can operate the first shortcut command control by interacting with the terminal device while running the first application to input the target input information, so as to open the second application for the target input information. In response to the operation on the first shortcut command control, the terminal device opens the application interface of the second application for the target input information on the display interface. The user then inputs the first configuration information for controlling the second application to execute the target control information. The terminal device receives the first configuration information input by the user and switches the application interface of the second application to a functional interface for executing the first configuration information.

[0204] In an optional embodiment, the target input information input by the user during the operation of the first application includes first input information and second input information, and the second input information is the information input by the user after the first input information during the operation of the first application. After the first input information is input, the second input information is input, and the terminal device performs semantic analysis on the first input information to obtain first target control information, and based on the first target control information, determines at least one second application for the first input information that meets the recommendation condition; the terminal device performs semantic analysis on the second input information to obtain second target control information, and based on the second target control information, determines at least one second application for the second input information that meets the recommendation condition; the specific process of generating the second application for the first input information based on the first input information, and the process of generating the second application for the second input information based on the second input information are the same as the above-mentioned process of generating the second application for the target input information based on the target input information. The detailed process can be found in the above-mentioned steps S101-S104, and this disclosure will not repeat them here.

[0205] After the application interface of the second application for the first input information is displayed on the display interface of the terminal device in response to the user's operation on the first shortcut command control, when the second application for the second input information and the second application for the first input information are different applications, the user can operate the second shortcut command control by interacting with the terminal device while the first application is running to input the second input information, and the terminal device responds to the user's operation on the second shortcut command control to open the second application for the second input information. In response to the user's operation on the second shortcut command control, the terminal device closes the second application for the first input information and opens the second application for the second input information on the display interface, completing the switch from executing the target control information corresponding to the first input information to executing the target control information corresponding to the second input information.

[0206] In an optional embodiment, after the user opens the second application recommended by the display interface, the user still needs to enter the first configuration information in the application interface of the second application to set the function, which will still disrupt the user's current usage environment to a certain extent. In order to further improve the user's experience, after determining the second application that meets the recommendation conditions, the user's second configuration information can be directly determined through the target input information, and the target function can be automatically generated and recommended to the user through the second information, thereby avoiding the user from manually entering the configuration information (i.e., the first configuration information). Specifically, the target input information entered by the user during the operation of the first application is firstly identified to obtain the second configuration information. The second configuration information is an entity segmentation with a specific meaning in the target input information (text information). For example, the second configuration information can be a segmentation of a person's name, place name, organization name, proper noun, numerical value and unit in the target input information. The second configuration information represents the specific standard or execution object when executing the target control information. In the embodiment of the present disclosure, the specific method for identifying the configuration information of the target input information can be determined according to the actual situation. For example, common recognition algorithms such as conditional random field (CRF), LSTM+CRF, BERT+LSTM+CRF can be used, and this application does not impose any restrictions on this.

[0207] Subsequently, a second application that meets the recommendation conditions is obtained. For detailed processes, please refer to the description of S101-S104 above. The second application is screened, and a second application that can execute the target control information according to the entity information is obtained as the target application that can execute the entity information. Since there may be multiple second applications that meet the recommendation conditions, some of which cannot execute functions according to the entity information and need to be screened and removed, and the target application that can execute functions according to the entity information is retained. After obtaining the target application, the terminal device determines the target function, and the target function is to control the target application to execute instructions corresponding to the target control information, and the target function is set based on the second configuration information. Through the target function, the user can directly run the target application according to the entity information without the user having to make additional function settings. This improves the user experience and increases the user's immersion. Finally, a shortcut command control corresponding to the target function is generated, and the shortcut command control corresponding to the target function is displayed on the display interface of the terminal device.

[0208] Exemplarily, the target application (the second application that can execute the target control information according to the second configuration information) is a countdown application. Figure 6 schematically shows an example of a display interface recommended target function for executing the method according to the present disclosure. As shown in Figure 6, the target input information is "exam time 100 minutes", and the target control information corresponding to the target input information obtained through semantic parsing is "countdown". Two second applications "timer" and "stopwatch" that meet the recommendation conditions are obtained; the second configuration information obtained by performing configuration information identification on the target input information is "100 minutes", and the two second applications "timer" and "stopwatch" are screened to determine that the "timer" can perform the "countdown" operation according to the specific setting of "100 minutes", while the "stopwatch" application cannot perform the "countdown" operation according to the specific setting of "100 minutes". Then, the "timer" is used as the target application, and the target function of "timing for 100 minutes" is generated, and the target function icon of "timing for 100 minutes" is displayed on the display interface of the terminal device. During the operation of the first application, the user can directly open the timer to execute the countdown function for 100 minutes by clicking the target function icon of "timing for 100 minutes" on the display interface.

[0209] In an optional embodiment, after the target function for the target input information is displayed on the display interface of the terminal device, the user can, while running the first application and inputting the target input information, interact with the terminal device and operate the third shortcut command control to open the target application and execute the target function for the target input information. In response to the user's operation on the third shortcut command control, the terminal device opens the target function interface of the target application on the display interface and executes the target function for the target input information.

[0210] In an optional embodiment, the target input information includes third input information. To further enhance the user experience, after determining a second application that meets the recommendation criteria based on the third input information, the configuration information of the third input information is identified to obtain the second configuration information. The user operates the first shortcut control to open the second application corresponding to the third input information. In response to the user's operation on the first shortcut control, the terminal device opens the application interface of the second application corresponding to the target input information on the display interface, and configures the second application based on the second configuration information, so that the application interface of the second application switches to a functional interface for executing the second configuration information.

[0211] For example, the second application for the third input information is a countdown application, and the third input information is "exam time 10 minutes." The target control information corresponding to the third input information obtained through semantic parsing is "countdown," and a countdown application "timer" that meets the recommendation criteria is obtained; the second configuration information obtained by performing configuration information identification on the third input information is "10 minutes." The user operates the first shortcut control, and the terminal device opens the "timer" application interface in response to the user's operation on the first shortcut control. Based on the second configuration information "10 minutes," the terminal device automatically switches the display interface of the countdown application "timer" to the functional interface of "10-minute countdown."

[0212] Because the input target input information includes first input information and second input information, when the user enters the second input information after entering the first input information while running the first application, the terminal device generates a second target function for the second input information based on the second input information. The specific process of generating the second target function based on the second input information is the same as the process of generating the target function for the target input information based on the target input information described above, and is not further described in this disclosure. After the second target function is displayed on the display interface of the terminal device, it is determined whether the second target function and the application corresponding to the target function are the same.

[0213] When the application corresponding to the second target function for the second input information is the target application, it indicates that the target function and the second target function can be executed through the same target application. While the user is running the first application and inputting the second input information, the user interacts with the terminal device and operates the fourth shortcut command control to control the execution of the second target function. In response to the user's operation on the fourth shortcut command control, the terminal device switches the target application to the second target function interface and executes the second target function.

[0214] When the application corresponding to the second target function for the second input information is different from the target application, it means that the target function and the second target function need to be executed by different applications. While the user is running the first application to input the second input information, the user operates the fourth shortcut command control by interacting with the terminal device. In response to the user's operation on the fourth shortcut command control, the target application is closed, and the second target application for the second input information is opened on the display interface to execute the second target function.

[0215] In an optional embodiment, while the user is running the first application, after inputting the first input information, the user continues to input the second input information, and the terminal device generates a second application for the second input information based on the second input information. Since the user inputs the first input information and the second input information continuously while running the first application, the second application for the first input information is displayed on the display interface during the input of the first input information, and the second application for the second input information is displayed on the display interface during the input of the second input information. When the input interval between the first input information and the second input information is small, the user operates the shortcut command control to control the execution of the second application for the first input information. The executable time period is short, which affects the user's usage experience to a certain extent.

[0216] After obtaining the second application for the second input information, the shortcut command control corresponding to the second application for the first input information is retained on the display interface of the terminal device. Specifically, the shortcut command control corresponding to the second application for the second input information is placed before the shortcut command control corresponding to the second application for the first input information, and the shortcut command control corresponding to the second application for the second input information and the shortcut command control corresponding to the second application for the first input information are displayed simultaneously on the display interface of the terminal device. Preferably, considering the limitation on the number of shortcut command controls corresponding to applications that can be displayed on the display interface, a preset number of shortcut command controls corresponding to the second application for the first input information are retained and displayed on the display interface in the order of the first matching degree of the second application, and the shortcut command control corresponding to the second application for the second input information and a preset number of shortcut command controls corresponding to the second application for the first input information are sequentially displayed on the display interface of the terminal device. Exemplarily, the display interface displays all shortcut command controls corresponding to the second application for the second input information, and retains one shortcut command control corresponding to the second application for the first input information and arranges it after the second application for the second input information. It should be noted that the above example is only to enable those skilled in the art to better understand an optional implementation provided by this application. The preset number can be determined according to actual conditions and is not limited by this disclosure.

[0217] In an optional embodiment, the second application is a local application of the terminal device, and the terminal device includes a cloud platform application that runs through a network in addition to the first application and the second application. The present disclosure can determine a third application to recommend to the user based on matching the target control information with the cloud platform application. Specifically, after determining the second application that meets the recommendation conditions, the network status of the terminal device is judged, where the network status includes a network connection status and a no network connection status, and the network connection can be a wired connection or a wireless connection. When the terminal device is in a network connection state, based on the target control information corresponding to the target input information, the first matching degree between the target control information and the cloud platform application is judged. When the first matching degree between the target control information and the cloud platform application is greater than the first matching threshold, the cloud platform application that meets the recommendation conditions is determined as the third application. Finally, the shortcut command control corresponding to the second application and the shortcut command control corresponding to the third application are simultaneously displayed on the display interface of the terminal device.

[0218] When the terminal device is in a state of no network connection, a prompt message is displayed on the display interface of the terminal device, and the prompt message is used to prompt the user to check the network status of the terminal device. Figure 7 schematically shows an example of prompt information and a network setting icon for executing the method according to the present disclosure. As shown in Figure 7, a prompt message is displayed on the display interface ("The network is not connected, please check the network!" in Figure 7), and a network setting icon ("Check the network" in Figure 7) is generated on the display interface of the terminal device. The network device icon is used to jump to the network setting interface of the terminal device in response to user instructions (such as click operations, etc.). When the user interacts with the network setting icon, the network setting interface is displayed on the display interface of the terminal device in response to the user's interaction with the network setting icon.

[0219] In an optional embodiment, a function recommendation minimization icon is configured on the display interface of the terminal device. Figure 8 schematically shows an example of a function recommendation minimization icon for executing the method according to the present disclosure. As shown in Figure 8, during the execution of the first application, the user controls the terminal device display interface to minimize the function recommendation area by interacting with the function recommendation minimization icon on the display interface. An extension icon is configured in the minimized function recommendation area, and the user controls the terminal device display interface to restore the function recommendation area to normal display mode by interacting with the extension icon of the minimized function recommendation area.

[0220] An embodiment of the present disclosure provides a function recommendation method, which includes: obtaining target input information input by a user during the operation of a first application, where the first application includes at least one of the following: a home application and a third-party application; performing semantic parsing on the target input information to obtain target control information; based on the target control information, determining at least one second application that meets the recommendation conditions; and displaying a shortcut command control corresponding to the second application on the display interface of the terminal device.

[0221] The disclosed embodiment determines the target control information of the user through the target input information during the user's operation of the first application, and intelligently and real-time recommends the relevant applications corresponding to the target input information on the display interface. This process does not require the user to specifically input input information for the recommended application, and can ensure that the process of the user running the first application will not be interrupted, and the function recommendation can be completed without disrupting the current operating environment, realizing seamless interaction, thereby enhancing the user's sense of immersion, and improving the user's operating efficiency and usage experience.

[0222] Based on the same inventive concept, an embodiment of the present disclosure provides a function recommendation device. FIG9 schematically shows a function recommendation device for executing the method according to the present disclosure. As shown in FIG9 , the device includes:

[0223] A target input information acquisition module, configured to acquire target input information input by a user during the execution of the first application;

[0224] A semantic parsing module, configured to perform semantic parsing on the target input information to obtain target control information;

[0225] a recommended application module, configured to determine, based on the target control information, a second application that meets a recommendation condition;

[0226] A display module is used to display the shortcut command control corresponding to the second application on the display interface of the terminal device.

[0227] In an optional embodiment, the device further includes:

[0228] an application opening module, configured to open an application interface of the second application in response to a user operation on the first shortcut command control;

[0229] The interface switching module is used to receive first configuration information input by a user and switch the application interface of the second application to a functional interface for executing the first configuration information.

[0230] In an optional embodiment, the device further includes:

[0231] a configuration information acquisition module, configured to perform configuration information identification on the target input information to obtain second configuration information;

[0232] a target application module, configured to determine a target application based on the second application and the second configuration information, wherein the target application is the second application that can execute the target control information according to the second configuration information;

[0233] a target function module, configured to determine a target function, wherein the target function is to control the target application to execute an instruction corresponding to the target control information, and the target function is set based on the second configuration information;

[0234] The second display module is used to display the shortcut command control corresponding to the target function on the display interface of the terminal device.

[0235] In an optional embodiment, the device further includes:

[0236] a configuration acquisition module, configured to perform configuration information identification on the third input information to obtain second configuration information;

[0237] An opening module, configured to open an application interface of the second application in response to a user operation on the first shortcut command control;

[0238] An application configuration module is used to configure the second application based on the second configuration information so that the application interface of the second application is switched to a functional interface for executing the second configuration information.

[0239] In an optional embodiment, the semantic parsing module includes:

[0240] A first parsing submodule, configured to perform semantic parsing on the first input information to obtain first target control information;

[0241] A second parsing submodule, configured to perform semantic parsing on the second input information to obtain second target control information;

[0242] The recommended application module includes:

[0243] A first recommended application submodule, configured to determine, based on the first target control information, at least one second application for the first input information that meets the recommendation condition;

[0244] a second recommended application submodule, configured to determine, based on the second target control information, at least one second application for the second input information that meets the recommendation condition;

[0245] The display module includes:

[0246] The third display submodule is used to simultaneously display the shortcut command control corresponding to the second application for the second input information and the shortcut command control corresponding to the second application for the first input information on the display interface of the terminal device.

[0247] In an optional embodiment, the display module includes:

[0248] a first control submodule, configured to open, on the display interface, an application interface of a second application corresponding to the first input information in response to a user operation on the first shortcut command control;

[0249] The second control submodule is used to close the application interface of the second application for the first input information in response to the user's operation on the second shortcut command control, and open the application interface of the second application for the second input information on the display interface.

[0250] In an optional embodiment, the device further includes:

[0251] a network recommendation application module, configured to determine, when the terminal device is in a network connection state, based on the target control information, a third application that meets the recommendation condition, wherein the third application is a cloud platform application;

[0252] The fourth display module is used to simultaneously display the shortcut command control corresponding to the second application and the shortcut command control corresponding to the third application on the display interface of the terminal device.

[0253] In an optional embodiment, the device further includes:

[0254] a prompt module, configured to display a prompt message on a display interface of the terminal device when the terminal device is in a state of no network connection, wherein the prompt message is used to prompt a user to check the network status of the terminal device;

[0255] A network setting display module, configured to generate a network setting icon on the display interface of the terminal device;

[0256] The fifth display module is used to display a network setting interface on the display interface of the terminal device in response to the user's interactive operation with the network setting icon.

[0257] In an optional implementation, the application recommendation module includes:

[0258] a first matching submodule, configured to match the target control information with a plurality of applications in the terminal device to obtain a first matching degree;

[0259] The recommended application submodule is configured to obtain the second application that meets the recommendation condition based on the first matching degree.

[0260] In an optional embodiment, the device further includes:

[0261] a first matching module, configured to match the target control information with a plurality of applications in the terminal device to obtain a first matching degree;

[0262] a candidate second application acquisition module, configured to acquire, based on the first matching degree, at least one candidate second application that meets the recommendation condition, wherein the recommendation condition is that the first matching degree is greater than a first matching threshold;

[0263] A fifth display module is used to display the shortcut command controls corresponding to the candidate second applications in sequence on the display interface of the terminal device in the order of the first matching degrees of the candidate second applications.

[0264] In an optional embodiment, the device further includes:

[0265] a handwriting input information acquisition module, configured to acquire the target input information input by the user during the running of the first application, wherein the first application is a handwriting application, the target input information is handwriting input information, and the handwriting input information is text information obtained by performing text recognition on handwriting trajectory point information;

[0266] a second semantic parsing module, configured to perform semantic parsing on the handwriting input information to obtain the target control information;

[0267] a third application recommendation module, configured to determine, based on the target control information, at least one of the second applications that meets the recommendation condition;

[0268] A sixth display module is used to display the shortcut command control corresponding to the second application on the application interface of the handwriting application.

[0269] In an optional implementation, the handwriting input information acquisition module includes:

[0270] A handwriting information acquisition submodule, configured to acquire the handwriting track point information input by the user, wherein the handwriting track point information includes at least one of the following: track point coordinate value, track point timestamp, and track point status;

[0271] A connection diagram acquisition submodule, configured to acquire a handwriting trajectory connection diagram based on the handwriting trajectory point information;

[0272] A first input feature submodule, configured to input the handwriting trajectory point information into a first branch of a text recognition network to obtain a first input feature, wherein the first input feature includes trajectory point time information of the handwriting trajectory point information;

[0273] A second input feature submodule, configured to input the handwriting trajectory connection diagram into a second branch of the character recognition network to obtain a second input feature, wherein the second input feature does not include trajectory point time information of the handwriting trajectory point information;

[0274] A combining submodule is configured to combine the first input feature with the second input feature to obtain the handwriting input information.

[0275] In an optional implementation, the target input information acquisition module further includes:

[0276] The voice information acquisition submodule is used to acquire the voice information input by the user;

[0277] A feature extraction submodule, configured to extract features from the speech information to obtain speech features;

[0278] The decoding submodule is used to decode the speech features based on a speech recognition model to obtain the speech input information.

[0279] In an optional embodiment, the semantic parsing module includes:

[0280] A sentence segmentation module, configured to obtain at least one sentence based on the target input information;

[0281] A word segmentation submodule, configured to perform word segmentation processing on the sentences in the target input information to obtain a plurality of word segments;

[0282] A second matching submodule is used to match each word segment with the candidate control information to obtain a second matching degree;

[0283] The target control information acquisition submodule is configured to use the candidate control information for which the second matching degree is greater than a second matching threshold as the target control information.

[0284] In an optional implementation, the second matching submodule includes:

[0285] An application acquisition subunit, configured to acquire all applications in the terminal device, wherein the labels are used to characterize the functional types of the applications in the terminal device;

[0286] an application clustering subunit, configured to group all applications in the terminal device according to a function type of each application in the terminal device to obtain at least one application cluster, wherein the functions of the applications in each application cluster are the same;

[0287] The candidate control information acquisition subunit is configured to take the function type corresponding to each application cluster as a candidate control information.

[0288] In an optional embodiment, the semantic parsing module further includes:

[0289] A classification input data acquisition submodule is used to take the left-hand side segmentation and the right-hand side segmentation corresponding to each segmentation in the sentence as classification input data to obtain a classification input data set;

[0290] The semantic parsing submodule is used to input the classified input data set into the classification model, perform semantic parsing on the classified input data set based on the classification model, and obtain the target control information.

[0291] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0292] The various component embodiments of the present disclosure can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the computing processing equipment according to the embodiments of the present disclosure. The present disclosure can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present disclosure can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0293] For example, FIG10 illustrates a computing and processing device that can implement the methods of the present disclosure. The computing and processing device 100 conventionally includes a processor 120 and a computer program product or computer-readable medium in the form of a memory 110. The memory 110 can be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, a hard disk, or ROM. The memory 110 has storage space for program code for executing any of the method steps described above. For example, the storage space for program code can include individual program codes for implementing various steps in the above method. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. Such computer program products are typically portable or fixed storage units. The storage unit can have storage segments, storage space, etc. arranged similarly to the memory 110 in the computing and processing device of FIG10. The program code can, for example, be compressed in a suitable form. Typically, the storage unit includes computer-readable codes, ie, codes that can be read by a processor such as 120 , which, when executed by a computing processing device, cause the computing processing device to perform the steps of the method described above.

[0294] References herein to "one embodiment," "an embodiment," or "one or more embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Furthermore, please note that instances of the phrase "in one embodiment" do not necessarily all refer to the same embodiment.

[0295] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0296] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present disclosure may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0297] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure.

Claims

1. A feature recommendation method, It is characterized in that The method comprises: During the running of the first application, obtaining target input information input by a user; Performing semantic analysis on the target input information to obtain target control information; Based on the target control information, determining at least one second application that meets the recommendation condition; Display the shortcut command control corresponding to the second application on the display interface of the terminal device.

2. The function recommendation method according to claim 1, It is characterized in that After displaying the shortcut command control corresponding to the second application on the display interface of the terminal device, the method further includes: In response to a user operation on the first shortcut command control, opening an application interface of the second application; Receive first configuration information input by a user, and switch the application interface of the second application to a function interface for executing the first configuration information.

3. The function recommendation method according to claim 1, It is characterized in that After determining the second application that meets the recommendation condition, the method further includes: Performing configuration information identification on the target input information to obtain second configuration information; Determine a target application based on the second application and the second configuration information, where the target application is the second application that can execute the target control information according to the second configuration information; Determine a target function, where the target function is to control the target application to execute an instruction corresponding to the target control information, and the target function is set based on the second configuration information; The shortcut command control corresponding to the target function is displayed on the display interface of the terminal device.

4. The function recommendation method according to claim 1, It is characterized in that The target input information includes third input information, and the method includes: Performing configuration information identification on the third input information to obtain second configuration information; In response to a user operation on the first shortcut command control, opening an application interface of the second application; Based on the second configuration information, the second application is configured so that the second application The application interface is switched to a function interface for executing the second configuration information.

5. The function recommendation method according to claim 3 or 4, It is characterized in that The second application is a countdown application.

6. The function recommendation method according to claim 1, It is characterized in that The target input information includes first input information and second input information. The target input information is semantically parsed to obtain target control information, including: Performing semantic analysis on the first input information to obtain first target control information; Performing semantic analysis on the second input information to obtain second target control information; Determining at least one second application that meets a recommendation condition based on the target control information includes: Determining, based on the first target control information, at least one second application for the first input information that meets the recommendation condition; determining, based on the second target control information, at least one second application for the second input information that meets the recommendation condition; Displaying the shortcut command control corresponding to the second application on the display interface of the terminal device includes: The shortcut command control corresponding to the second application for the second input information and the shortcut command control corresponding to the second application for the first input information are simultaneously displayed on the display interface of the terminal device.

7. The function recommendation method according to claim 6, It is characterized in that The target input information includes first input information and second input information, and displaying the shortcut command control corresponding to the second application on the display interface of the terminal device includes: In response to a user operation on the first shortcut command control, opening an application interface of a second application corresponding to the first input information on the display interface; In response to the user's operation on the second shortcut command control, the application interface of the second application for the first input information is closed, and the application interface of the second application for the second input information is opened on the display interface.

8. The function recommendation method according to claim 1, It is characterized in that After determining the second application that meets the recommendation condition, the method further includes: When the terminal device is in a network connection state, determining a third application that meets a recommendation condition based on the target control information, wherein the third application is a cloud platform application; The shortcut command control corresponding to the second application and the shortcut command control corresponding to the third application are simultaneously displayed on the display interface of the terminal device.

9. The function recommendation method according to claim 1, It is characterized in that The method further comprises: When the terminal device is in a state of no network connection, a prompt message is displayed on the display interface of the terminal device, and the prompt message is used to prompt the user to check the network status of the terminal device; Generating a network setting icon on a display interface of the terminal device; In response to the user's interactive operation with the network setting icon, a network setting interface is displayed on the display interface of the terminal device.

10. The function recommendation method according to claim 1, It is characterized in that Determining the second application that meets the recommendation condition based on the target control information includes: Matching the target control information with a plurality of applications in the terminal device to obtain a first matching degree; Based on the first matching degree, the second application that meets the recommendation condition is obtained.

11. The function recommendation method according to claim 1, It is characterized in that After obtaining the target control information, the method further includes: Matching the target control information with a plurality of applications in the terminal device to obtain a first matching degree; Based on the first matching degree, acquiring at least one candidate second application that meets the recommendation condition, where the recommendation condition is that the first matching degree is greater than a first matching threshold; In the order of the first matching degrees of the candidate second applications, the shortcut command controls corresponding to the candidate second applications are displayed in sequence on the display interface of the terminal device.

12. The function recommendation method according to claim 1, It is characterized in that The method further comprises: During the running of the first application, the target input information input by the user is obtained, the first application is a handwriting application, the target input information is handwriting input information, and the handwriting input information is text information obtained by performing text recognition on handwriting track point information; Performing semantic analysis on the handwriting input information to obtain the target control information; Based on the target control information, determining at least one of the second applications that meets the recommendation condition; Display the shortcut command control corresponding to the second application on the application interface of the handwriting application.

13. The function recommendation method according to claim 12, It is characterized in that The handwriting input information is obtained in the following manner: Acquire the handwriting track point information input by the user, wherein the handwriting track point information includes at least one of the following: track point coordinate value, track point timestamp, and track point status; Based on the handwriting trajectory point information, obtaining a handwriting trajectory connection diagram; Inputting the handwriting trajectory point information into a first branch of a text recognition network to obtain a first input feature, wherein the first input feature includes trajectory point time information of the handwriting trajectory point information; Inputting the handwriting trajectory connection diagram into the second branch of the text recognition network to obtain a second input feature, where the second input feature does not include trajectory point time information of the handwriting trajectory point information; The first input feature and the second input feature are combined to obtain the handwriting input information.

14. The function recommendation method according to claim 1, It is characterized in that The target input information is voice input information, and the voice input information is obtained in the following manner: Get the voice information input by the user; Extracting features from the voice information to obtain voice features; Based on a speech recognition model, the speech feature is decoded to obtain the speech input information.

15. The function recommendation method according to claim 1, It is characterized in that Perform semantic parsing on the target input information to obtain target control information, including: Based on the target input information, obtaining at least one sentence; Performing word segmentation processing on the sentences in the target input information to obtain a plurality of word segments; Match each word segment with the candidate control information to obtain a second matching degree; The candidate control information for which the second matching degree is greater than a second matching threshold is used as the target control information.

16. The function recommendation method according to claim 15, It is characterized in that The candidate control information is obtained in the following manner: Obtaining a function type of each application in the terminal device; According to the function type of each application in the terminal device, all applications in the terminal device are grouped to obtain at least one application cluster, wherein the functions of applications in each application cluster are the same; The function type corresponding to each application cluster is used as the candidate control information.

17. The function recommendation method according to claim 15, It is characterized in that After obtaining a plurality of participles, the method further includes: The left participle and the right participle corresponding to each participle in the sentence are used as classification input data to obtain a classification input data set; The classified input data set is input into a classification model, and semantic parsing is performed on the classified input data set based on the classification model to obtain the target control information.

18. A function recommendation device, It is characterized in that include: A target input information acquisition module, used to acquire target input information input by a user during the running of the first application; A semantic parsing module, used for performing semantic parsing on the target input information to obtain target control information; A recommended application module, configured to determine at least one second application satisfying a recommendation condition based on the target control information; A display module is used to display the shortcut command control corresponding to the second application on the display interface of the terminal device.

19. A computing device, It is characterized in that include: a memory having computer readable code stored therein; as well as One or more processors, when the computer readable code is executed by the one or more processors, the computing processing device performs the function recommendation method according to any one of claims 1-17.

20. A computer program, It is characterized in that The method comprises a computer-readable code, which, when executed on a computing and processing device, causes the computing and processing device to execute the function recommendation method according to any one of claims 1 to 17.

21. A computer readable medium, It is characterized in that A computer program as claimed in claim 20 is stored therein.

Images