Starting method and device and electronic equipment

Abstract

The invention discloses a starting method and device and electronic device.The starting method comprises the steps that in response to a target interaction operation, at least one function corresponding to a target application is obtained; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application; determining a target function from the at least one function based on target data corresponding to the target object; and starting the target function to process the target data based on the target starting parameter corresponding to the target function.

Description

Technical Field

[0001] The present application relates to but is not limited to the field of computer technology, and in particular to a startup method, device and electronic device. Background Art

[0002] The drag operation allows users to transfer data between applications or within an application through gestures, a mouse, or other operating tools. Since the drag operation has the advantages of being intuitive and efficient, it is widely used in various applications and / or systems.

[0003] However, in the related art, the drag operation is only used to implement simple data transmission functions such as copy and paste, and has low flexibility and intelligence. Therefore, how to expand the use of the drag operation has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present application at least provides a startup method, device and electronic device.

[0005] The technical solution of this application is implemented as follows:

[0006] In one aspect, the present application provides a startup method, the method comprising:

[0007] In response to a target interaction operation, obtaining at least one function corresponding to the target application; the target interaction operation is an interaction operation of dragging the target object to a response area corresponding to the target application;

[0008] determining a target function from at least one function based on the target data corresponding to the target object;

[0009] Based on the target startup parameters corresponding to the target function, the target function is started to process the target data.

[0010] In some embodiments, the response area corresponding to the target application includes one of the following:

[0011] The display area occupied by the application icon of the target application;

[0012] The display area occupied by the target application's application window.

[0013] In some embodiments, based on the target object, determining the target function from at least one function includes at least one of the following:

[0014] Based on the attribute information of the target data, determining a target function matching the attribute information from at least one function;

[0015] Based on the first semantic information of the target data, a target function having the highest correlation with the semantic information is determined from the at least one function.

[0016] In some embodiments, based on the target object, determining the target function from at least one function includes:

[0017] Inputting the target data and the description information of at least one function into the target model, so as to determine the target function matching the target object from the at least one function using the target model;

[0018] The number of weight parameters in the target model is greater than 100 million.

[0019] In some embodiments, the target startup parameters include a first startup parameter and a second startup parameter;

[0020] The first startup parameter is used to start the target function of the target application, and the second startup parameter is used to enable the target function to process target data.

[0021] In some embodiments, the method further comprises:

[0022] In response to the target data satisfying a second startup parameter condition corresponding to the target function, using the target data as a second startup parameter;

[0023] In response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data and using the first data as the second startup parameter;

[0024] The first data satisfies a second startup parameter condition corresponding to the target function.

[0025] In some embodiments, the target data does not satisfy the second startup parameter condition corresponding to the target function, indicating that the data type of the target data is not the target data type;

[0026] In response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data, and using the first data as the second startup parameter, includes:

[0027] Acquiring second semantic information of target data;

[0028] Based on the second semantic information, generate first data of the target data type;

[0029] The first data is used as the second startup parameter.

[0030] In some embodiments, the method further comprises:

[0031] Inputting the first startup parameter, the second startup parameter condition and the target data of the target function into the target model to obtain the target startup parameter;

[0032] The number of weight parameters in the target model is greater than 100 million.

[0033] On the other hand, the present application also proposes a starting device, comprising:

[0034] An acquisition module, configured to acquire at least one function corresponding to a target application in response to a target interaction operation; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application;

[0035] A first determination module, configured to determine a target function from at least one function based on target data corresponding to the target object;

[0036] The startup module is used to start the target function to process the target data based on the target startup parameters corresponding to the target function.

[0037] On the other hand, the present application also proposes an electronic device, comprising:

[0038] A first application program running on an electronic device, the first application program is used to determine at least one task based on a user interaction operation, and for each task, the first application program is used to at least:

[0039] In response to a target interaction operation corresponding to the task, obtaining at least one function corresponding to the target application; the target interaction operation is an interaction operation of dragging the target object to a response area corresponding to the target application;

[0040] Inputting target data corresponding to the target object and description information of at least one function into a target model, so as to determine a target function matching the target object from the at least one function using the target model;

[0041] Based on the target start parameter corresponding to the target function, start the target function to process the target data;

[0042] Among them, the number of weight parameters in the target model is greater than 100 million.

[0043] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0045] Figure 1 A schematic diagram of the implementation flow of a startup method provided in this application;

[0046] Figure 2 A schematic diagram of an implementation flow of an embodiment of the startup method provided by the present application;

[0047] Figure 3A schematic diagram of the composition structure of a starting device provided in this application;

[0048] Figure 4 A schematic diagram of an electronic device provided for this application;

[0049] Figure 5 A hardware entity schematic diagram of an electronic device provided in this application;

[0050] Figure 6 A hardware entity schematic diagram of an electronic device provided in this application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0052] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0053] The terms "first / second / third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first / second / third" can be interchanged with a specific order or sequence where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing this application and are not intended to limit this application.

[0055] The present application provides a startup method, which can be executed by a processor of an electronic device. The electronic device may refer to a server, a laptop, a tablet computer, a desktop computer, a smart TV, a set-top box, a mobile device (such as a mobile phone, a portable video player, a personal digital assistant, a dedicated messaging device, a portable gaming device) and other devices with data processing capabilities.

[0056] Figure 1 A schematic diagram of the implementation flow of a startup method provided in this application, such as Figure 1 As shown, the method includes the following steps S101 to S103:

[0057] Step S101, in response to a target interaction operation, obtaining at least one function corresponding to a target application; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application.

[0058] Here, the target application refers to any application installed on the electronic device.

[0059] In some embodiments, the target application may be an application currently in operation in the electronic device, or may be an application currently in non-operation in the electronic device.

[0060] In some embodiments, the response area corresponding to the target application may refer to any area corresponding to the target application displayed on the display screen of the electronic device.

[0061] For example, when the target application is currently in a running state, the response area corresponding to the target application may be an area on the display screen of the electronic device where the application icon of the target application is displayed, or it may be an area on the display screen of the electronic device where the running interface of the target application is displayed; when the target application is currently in a non-running state, the response area corresponding to the target application may be an area on the display screen of the electronic device where the application icon of the target application is displayed.

[0062] In some embodiments, the response area of ​​the target application may be a preset area for receiving the target interactive operation, or may be an area for receiving the target interactive operation determined according to user settings.

[0063] In this way, the target interaction operation is to drag the target object to an area on the display screen of the electronic device where an application icon of the target application is displayed, or to drag the target object to an area on the display screen of the electronic device where an operating interface of the target application is displayed.

[0064] Here, dragging can be an interactive operation performed by a user using a gesture, a mouse, or other operating tools. For example, a user long presses a target object with a finger and drags it to a response area of ​​a target application; another example, a user long presses a target object with a mouse and drags it to a response area of ​​a target application; another example, a user long presses a target object with a touchpad and drags it to a response area of ​​a target application.

[0065] The target object may be an object to be processed displayed on a display screen of an electronic device.

[0066] In some embodiments, the target object may be an icon displayed on the desktop or in a folder of the electronic device. For example, the target object may be an icon corresponding to a document (e.g., an icon of an office file), an icon corresponding to a device (e.g., an icon of a hard disk installed in the electronic device), an icon of another application (e.g., an icon of a conference application, an icon of an instant messaging application), an icon of an audio file (e.g., an icon of a music file, an icon of a recording file), and the like.

[0067] In some embodiments, the target object may be an image thumbnail displayed on the desktop or in a folder of the electronic device. For example, the target object may be a thumbnail of a picture taken by a user or a picture downloaded from a network.

[0068] In some embodiments, the target object may be data such as text, picture, or audio selected in a document or a running application. For example, when a user has opened an office document, a text, picture, or audio selected by the user in the office document may be used as the target object; for another example, when a user uses an instant messaging application to communicate with an interactive party, a text, picture, or audio selected by the user in the instant messaging application may be used as the target object; and so on.

[0069] In this way, the target interactive operation is an interactive operation of dragging an icon, thumbnail, text, picture or audio displayed on the display screen of the electronic device to a response area corresponding to the target application.

[0070] Acquiring at least one function corresponding to the target application refers to reading at least one application function that can be implemented by the target application corresponding to the target interaction operation when the target interaction operation is detected.

[0071] For example, when the target application is a conference application, you can obtain the conference application's conference schedule management function, audio conference function, video conference function, data sharing function, meeting record function, etc.; for another example, when the target application is WeChat, you can obtain WeChat's corresponding instant messaging function, address book function, circle of friends function in the discovery page, scan function, search function, and life service function, etc.

[0072] In some embodiments, at least one function corresponding to the target application may be acquired through configuration information of the target application.

[0073] In some embodiments, at least one function corresponding to the target application may be obtained by referring to the developer documentation of the target application.

[0074] In some embodiments, at least one function of the target application can be obtained through an agent running on the electronic device.

[0075] In some embodiments, at least one function of the target application has corresponding startup parameter information and function description information, wherein the startup parameter information refers to the configuration parameters required to start the corresponding function; and the function description information refers to the detailed description of the corresponding function.

[0076] Step S102: determining a target function from the at least one function based on the target data corresponding to the target object.

[0077] Here, the target data corresponding to the target object refers to the relevant data pointed to by the target object.

[0078] For example, when the target object is an icon, the target data may be the document content, device information, application, audio file or video file corresponding to the icon, etc.; for another example, when the target object is an image thumbnail, the target data may be the original image corresponding to the image thumbnail; for another example, when the target object is text, picture, audio or other data selected by the user from a document or interactive application, the target object is the target data.

[0079] A target function is determined from the at least one function based on the target data, that is, a function having a high correlation with the target data is determined from the at least one function as the target function.

[0080] For example, when the target application is WeChat and the target data is an image, the WeChat Moments sharing function can be determined as the target function; for another example, when the target application is a conference application and the target data is an office document, the conference application's information sharing function can be determined as the target function; for another example, when the target application is a conference application and the target data is a piece of text selected by the user from the body of an email, the conference schedule management function of the conference application can be determined as the target application by identifying the semantic information of the text.

[0081] Step S103: based on the target start-up parameters corresponding to the target function, start the target function to process the target data.

[0082] Here, after the target function is determined, the target function is started based on the target start parameter corresponding to the target function, so as to process the target data using the target function.

[0083] In some embodiments, when the target application is currently in a running state, the target startup parameters include function startup parameters corresponding to the target function.

[0084] In some embodiments, when the target application is currently in a non-running state, the target startup parameters include application startup parameters corresponding to the target application and function startup parameters corresponding to the target function.

[0085] In this way, the target function is started, and the target data is used as input data of the target application so that the target data is processed by the target function.

[0086] As can be seen from the above, in the startup method provided by the present application, first, in response to the target interaction operation of dragging the target object to the response area corresponding to the target application, at least one function corresponding to the target application is obtained; then, based on the target data corresponding to the target object, the target function is determined from at least one function; finally, based on the target startup parameter corresponding to the target function, the target function is started to process the target data. In this way, on the one hand, the target function that the user expects to start is determined by combining the target object dragged by the user and the target application that receives the target object, that is, the user's intention is identified, the effect of the enhanced drag gesture is achieved, and the startup efficiency of the target application and the target function is improved, thereby improving the interaction efficiency between the user and the electronic device; on the other hand, compared with the screen content recognition scheme in the prior art, the present application uses the drag operation as a trigger point to identify the user's intention, and only recognizes the data related to the drag, so the content of the screen recognition can be controlled within the range that the user considers safe, thereby reducing the risk of user privacy leakage.

[0087] In some embodiments, the response area corresponding to the target application may include a display area occupied by an application icon of the target application.

[0088] Here, the display area occupied by the application icon may be the display area occupied by the application icon on the desktop of the electronic device, or may be the display area occupied by the application image in a folder when the folder where the application icon is located is opened.

[0089] In this way, the target object is dragged to the response area corresponding to the target application, that is, the target object is dragged to the display area occupied by the application icon of the target application.

[0090] In some embodiments, the response area corresponding to the target application may also include a display area occupied by an application window of the target application.

[0091] Here, when the target application is currently in a running state, the running interface of the target application can be displayed using the application window, so that the display area occupied by the application window can be used as the response area corresponding to the target application.

[0092] In some embodiments, the application window may include a main window or at least one sub-window corresponding to the target application.

[0093] In this way, the target object is dragged to the response area corresponding to the target application, that is, the target object is dragged to the main window or any sub-window corresponding to the target application.

[0094] In some embodiments, when the response area corresponding to the target application is the display area occupied by the application icon of the target application, or the display area occupied by the main window of the target application, the acquisition of at least one function corresponding to the target application in step S101 may include acquiring all functions corresponding to the target application. For example, when the target application is WeChat and the response area corresponding to the target application is the display area occupied by the WeChat icon, all function information of WeChat is acquired.

[0095] In some embodiments, when the response area corresponding to the target application is the display area occupied by the sub-window of the target application, the acquisition of at least one function corresponding to the target application in the above step S101 may include acquiring all functions corresponding to the sub-window. For example, when the target application is WeChat and the response area corresponding to the target application is the display area occupied by the discovery window of WeChat, all function information corresponding to the discovery window of WeChat is acquired, such as the Moments function, the video account function, the scan function, etc.

[0096] In the above embodiment, by dividing the response area corresponding to the target application into different types of response areas, the function information to be obtained can be determined based on the response area corresponding to the drag operation, thereby improving the recognition accuracy of the user's intention.

[0097] In some embodiments, the target function is determined from the at least one function based on the target data corresponding to the target object, that is, the above step S102 can be implemented as at least one of the following steps S1021 to S1022:

[0098] Step S1021: Based on the attribute information of the target data, determine a target function matching the attribute information from the at least one function.

[0099] The attribute information of the target data may include type information, size information or precision information of the target data, etc.

[0100] In some embodiments, the type information of the target data may include text type, image type, audio type, video type, and the like.

[0101] The size information of the target data may include the overall data volume size information of the target data.

[0102] In the case where the target data is of a digital type or a vector representation type, the precision information of the target data may include the digital precision of the target data, the precision of the vector representation, and so on.

[0103] Thus, determining a target function matching the attribute information from at least one function based on the attribute information of the target data may refer to determining a target function capable of processing the target data having the attribute from at least one function based on the attribute information of the target data and the functional description information of at least one function. For example:

[0104] Based on the type of target data, a function in at least one function of the target application that can process the target data of that type is determined as the target function. For example, when the target application is WeChat and the target data is of audio type, since the WeChat friend circle function, scan function, search function, etc. do not support audio processing, while WeChat's instant messaging function supports audio processing, WeChat's instant messaging function can be determined as the target function;

[0105] Based on the size information and precision information of the target data, a function in at least one function of the target application that can handle the size or precision is determined as the target function. For example, when the target application is an email application and the target data is an office file with a large amount of data, the large attachment function in the email application that can handle large attachments can be determined as the target function; for another example, when the target application is a mathematical calculation application and the target data is a number with a high precision, the function used to process high-precision digital calculations in the mathematical calculation application can be determined as the target function.

[0106] Step S1022: Based on the first semantic information of the target data, determine, from the at least one function, a target function that has the highest correlation with the semantic information.

[0107] Here, the first semantic information of the target data refers to the actual meaning represented by the target data. For example, when the target data is an image, the first semantic information refers to the association information between pixels in the image; when the target data is text, the first semantic information refers to the meaning of the text information; and so on.

[0108] In some embodiments, the first semantic information of the target data may be acquired by using natural language processing (NLP), knowledge graphs and semantic networks, context awareness, machine learning, and deep learning.

[0109] In some embodiments, the model may be used to extract features from the target data, and first semantic information of the target data may be determined based on the extracted features.

[0110] In this way, the function with the highest correlation with the first semantic information of the target data among the at least one function of the target application is determined as the target function.

[0111] In some embodiments, the relevance between the first semantic information of the target data and each function is determined based on the first semantic information of the target data and the functional description information of each function.

[0112] In some embodiments, for each function, semantic information of the function description information of the function may be extracted, and then the correlation between the first semantic information of the target data and the semantic information of the function description information may be determined.

[0113] In the above embodiments, determining the target function from at least one function of the target application based on the attribute information of the target data can improve the efficiency of determining the target function; determining the target function from at least one function of the target application based on the first semantic information of the target data can achieve the determination of the target function according to the actual meaning of the target data, context information, etc., so that the determined target function is more in line with the actual intention of the user, thereby improving the user's usage experience; similarly, when determining the target function from at least one function of the target application based on the attribute information of the target data and the first semantic information at the same time, at least one function of the target application can be screened based on the attribute information of the target data and the first semantic information respectively, and the final target function can be obtained by combining the two screening results, or at least one function of the target application can be screened based on the attribute information of the target data and the first semantic information in turn to determine the target function, which can not only improve the recognition accuracy of the target function, but also make up for the problem that multiple target functions may appear when the target function is determined using attribute information alone.

[0114] In some embodiments, the determining of the target function from the at least one function based on the target data corresponding to the target object, that is, the above step S102, can be implemented as the following step S1023:

[0115] Step S1023, inputting the target data and the description information of the at least one function into the target model, so as to use the target model to determine the target function matching the target object from the at least one function; the number of weight parameters in the target model is greater than 100 million.

[0116] Here, the target model is a large model used to determine the target function, and the number of weight parameters is greater than 100 million.

[0117] In some embodiments, the target model may be a large language model, such as a Gemini model, a GPT series model, a BERT (Bidirectional Encoder Representations from Transformers) model, and the like.

[0118] In this way, prompt information is determined based on the target data and the functional description information corresponding to at least one function of the target application, and the prompt information is input into the target model, so that the target model can determine the target function based on the prompt information.

[0119] The number of weight parameters of the target model is greater than 100 million, that is, the target model has a higher model capacity and can capture complex features and data distribution. Therefore, the target model can achieve higher model inference accuracy.

[0120] In the above embodiment, the target function that matches the target object is determined using the target model, which can improve the efficiency and intelligence of determining the target function; in addition, since the number of weight parameters of the target model is greater than 100 million, the target model has a higher reasoning accuracy, which can further improve the accuracy of determining the target function and achieve accurate identification of user intentions.

[0121] In some embodiments, the target startup parameters corresponding to the target function include a first startup parameter and a second startup parameter; wherein the first startup parameter is used to start the target function of the target application, and the second startup parameter is used to enable the target function to process the target data.

[0122] Here, the target startup parameters corresponding to the target function refer to a set of parameter values ​​passed to the target application or the operating environment on which the target application depends when starting the target function of the target application. The parameter values ​​can be used to configure and adjust the behavior of the target application when executing the target function, including memory allocation, garbage collection, logging, system property settings, etc.

[0123] The first start parameter in the target start parameters is used to start the target function of the target application, that is, to switch the target application to the running state of the target function.

[0124] The second startup parameter in the target startup parameter is used to enable the target function to process the target data, that is, the second startup parameter is determined based on the target data so that the target function can process the target data based on the second startup parameter.

[0125] In some embodiments, before the above step S103, the startup method provided by the present application further includes the following step S104 or step S105:

[0126] Step S104, in response to the target data satisfying the second startup parameter condition corresponding to the target function, using the target data as the second startup parameter;

[0127] Step S105, in response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data, and using the first data as the second startup parameter; wherein the first data satisfies the second startup parameter condition corresponding to the target function.

[0128] Here, the second startup parameter condition corresponding to the target function refers to a parameter input condition corresponding to the second startup parameter for enabling the target function to process target data.

[0129] In some embodiments, the second startup parameter condition may include conditions such as parameter size and parameter type.

[0130] When the target data meets the second startup parameter condition, the target data is used as the second startup parameter, that is, the target data is directly used as the object data to be processed using the target function; when the target data does not meet the second startup parameter condition, the target data is converted to obtain the first data that meets the second startup parameter condition, so that the first data is used as the object data to be processed using the target function.

[0131] In some embodiments, when the target data does not satisfy the parameter size condition in the second startup parameter condition, the target data may be converted into first data satisfying the parameter size condition in the second startup parameter condition by reducing or increasing the precision of the target data, data clipping, etc. For example, when the data precision that the target application can process is 16-bit floating point numbers, and the data precision of the target data is 32-bit floating point numbers, the target data with 32-bit precision may be converted into first data with 16-bit precision by reducing the data precision.

[0132] In some embodiments, when the target data does not satisfy the parameter type condition in the second startup parameter condition, the data type of the target data can be converted into first data that satisfies the parameter type condition in the second startup parameter condition by data type conversion. For example, when the data type that can be processed by the target function is text type, and the target data is image type, the target data of image type can be converted into first data of text type by data type conversion; and so on.

[0133] In the above embodiment, when determining the second startup parameter for enabling the target function to process the target data, if the target data does not meet the second startup parameter condition, the target data is converted into the first data to achieve the target data being processed by the target function. In this way, after determining the target function matching the target data, the target data can be adaptively adjusted according to the second startup parameter condition corresponding to the target function, thereby improving the intelligence of processing the target data by the target function.

[0134] In some embodiments, the target data does not satisfy the second startup parameter condition corresponding to the target function, indicating that the data type of the target data is not the target data type.

[0135] For example, when the target data type in the second startup parameter condition is text and the target data data type is image type, the target data does not satisfy the second startup parameter condition corresponding to the target function; for another example, when the target data type in the second startup parameter condition is text type and the target data data type is audio type, the target data does not satisfy the second startup parameter condition corresponding to the target function.

[0136] In this way, in response to the target data not satisfying the second startup parameter condition corresponding to the target function, the target data is converted into first data, and the first data is used as the second startup parameter, that is, the above step S105 can be implemented as the following steps S1051 to S1053:

[0137] Step S1051, obtaining second semantic information of the target data.

[0138] Here, the second semantic information of the target data is information used to represent the actual meaning represented by the target data.

[0139] In some embodiments, the second semantic information of the target data can be acquired by using natural language processing (NLP), knowledge graphs and semantic networks, context awareness, machine learning and deep learning.

[0140] In some embodiments, the model may be used to extract features from the target data, and the second semantic information of the target data may be determined based on the extracted features.

[0141] Step S1052: Generate first data of the target data type based on the second semantic information.

[0142] Here, after the second semantic information of the target data is determined, data conversion is performed on the second semantic information according to the target data type to obtain the first data.

[0143] It can be seen that the first data has a target data type that meets the second startup parameter condition and has the second semantic information of the target data.

[0144] Step S1053: use the first data as the second startup parameter.

[0145] Since the first data has the target data type and the second semantic information of the target data, the first data is used as the second startup parameter of the target function to enable the target function to process the target data.

[0146] In the above embodiment, by acquiring the second semantic information of the target data and generating the first data corresponding to the target data based on the target data type in the second startup parameter condition, the effect of enabling the target function to process the target data using the first data is achieved, thereby improving the intelligence of data processing in the process of starting the target function of the target application.

[0147] In some embodiments, before the above step S103, the startup method provided by the present application further includes the following step S106:

[0148] Step S106, inputting the first startup parameter, the second startup parameter condition and the target data of the target function into the target model to obtain the target startup parameter; wherein the number of weight parameters in the target model is greater than 100 million.

[0149] Here, the first startup parameter, the second startup parameter condition and the target data are input into the target model as prompt information, so as to generate the target startup parameter using the target model.

[0150] In some embodiments, first, a first prompt message is generated based on function description information and target data corresponding to at least one function of the target application, and the first prompt message is input into a target model so as to determine a target function from at least one function using the target model; then, based on the startup parameters of the target function, that is, based on the first startup parameters, the second startup parameter conditions and the target data, a second prompt message is generated, and the second prompt message is input into the target model so as to generate the target startup parameters using the target model.

[0151] In some embodiments, first, a first prompt message is generated based on function description information and target data corresponding to at least one function of the target application, and a third prompt message is generated based on the startup parameters of each function of the target application, that is, based on the first startup parameter, the second startup parameter condition and the target data of each function; then, the first prompt message and the third prompt message are sent to the target model at the same time, so as to use the target model to determine the target function based on the first prompt message, and generate the target startup parameter based on the third prompt message and the target function.

[0152] In some embodiments, in the process of generating the target startup parameters based on the first startup parameter, the second startup parameter condition and the target data using the target model, if the target data does not meet the second startup parameter condition, the above steps S1051 to S1053 are performed using the target model, and the specific implementation method is not repeated here.

[0153] Here, the number of weight parameters in the target model is greater than 100 million, that is, the target model is a large model. In this way, since the target model has a higher number of weight parameters and model capacity, it can capture complex features and data distribution, so the target model can achieve a higher model inference accuracy.

[0154] Next, combine Figure 2 , the implementation process of an embodiment of the startup method provided by this application is described. Figure 2 As shown, this embodiment includes the following steps S201 to S205:

[0155] Step S201, in response to the user dragging the target content to the application, multiple functions that can be implemented by the application and functional description information and startup parameters of each function are obtained; then, step S202 is executed;

[0156] Step S202, generating fourth prompt information based on the target content and the function description information of each function, generating fifth prompt information based on the target content and the startup parameters of each function, and inputting the fourth prompt information and the fifth prompt information into the large language model; thereafter, executing step S203;

[0157] Step S203, based on the fourth prompt information, using the large language model to determine the best function that can process the target content from multiple functions of the application; then, executing step S204;

[0158] Step S204, based on the fifth prompt information, using the large language model to generate startup parameters corresponding to the optimal function; then, executing step S205;

[0159] Step S205 : sending the activation parameters corresponding to the best function to the application, so as to activate the best function of the application and process the target content using the best function.

[0160] Based on the foregoing embodiments, the present application provides a starting device, which includes the units included and the modules included in the units, and can be implemented by a processor in an electronic device; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0161] Figure 3 A schematic diagram of the composition structure of a starting device provided in this application, such as Figure 3As shown, the starting device 300 includes: an acquisition module 310, a first determination module 320 and a starting module 330, wherein:

[0162] The acquisition module 310 is used to acquire at least one function corresponding to the target application in response to a target interaction operation; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application;

[0163] A first determining module 320, configured to determine a target function from the at least one function based on the target data corresponding to the target object;

[0164] The starting module 330 is used to start the target function to process the target data based on the target starting parameters corresponding to the target function.

[0165] In some embodiments, the response area corresponding to the target application includes one of the following:

[0166] The display area occupied by the application icon of the target application;

[0167] The display area occupied by the application window of the target application.

[0168] In some embodiments, the first determining module 320 is configured to perform at least one of the following:

[0169] Based on the attribute information of the target data, determining a target function matching the attribute information from the at least one function;

[0170] Based on the first semantic information of the target data, a target function having the highest correlation with the semantic information is determined from the at least one function.

[0171] In some embodiments, the first determination module 320 is used to input the target data and the description information of the at least one function into the target model, so as to use the target model to determine the target function that matches the target object from the at least one function; wherein the number of weight parameters in the target model is greater than 100 million.

[0172] In some embodiments, the target startup parameter includes a first startup parameter and a second startup parameter; wherein the first startup parameter is used to start the target function of the target application, and the second startup parameter is used to enable the target function to process the target data.

[0173] In some embodiments, the apparatus 300 further includes a second determining module 340; the second determining module 340 is configured to:

[0174] In response to the target data satisfying a second startup parameter condition corresponding to the target function, using the target data as the second startup parameter;

[0175] In response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data, and using the first data as the second startup parameter;

[0176] The first data satisfies a second startup parameter condition corresponding to the target function.

[0177] In some embodiments, the target data does not satisfy the second startup parameter condition corresponding to the target function, indicating that the data type of the target data is not the target data type;

[0178] The second determining module 340 is configured to:

[0179] Acquiring second semantic information of the target data;

[0180] Based on the second semantic information, generate first data of the target data type;

[0181] The first data is used as the second startup parameter.

[0182] In some embodiments, the second determination module 340 is used to input the first startup parameter, the second startup parameter condition and the target data of the target function into the target model to obtain the target startup parameter; wherein the number of weight parameters in the target model is greater than 100 million.

[0183] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0184] Based on the above embodiments, the present application provides an electronic device. Figure 4 As shown, a first application 410 is running on the electronic device 400; wherein,

[0185] The first application 410 is used to determine at least one task based on a user interaction operation, and for each task, the first application 410 is used to:

[0186] In response to a target interaction operation corresponding to the task, obtaining at least one function corresponding to the target application; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application;

[0187] Inputting target data corresponding to the target object and description information of the at least one function into a target model, so as to determine a target function matching the target object from the at least one function using the target model;

[0188] Based on the target startup parameter corresponding to the target function, start the target function to process the target data;

[0189] Among them, the number of weight parameters in the target model is greater than 100 million.

[0190] Here, the first application 410 refers to an application with higher permissions that runs at the operating system level of the electronic device 400. In this way, the first application 410 can obtain more system resources in the electronic device 400 to manage multiple applications installed on the electronic device 400 using the obtained system resources.

[0191] In some embodiments, the first application 410 may obtain a variety of interactive operations performed by the user on the electronic device 400 to automatically determine at least one task based on the user interactive operations.

[0192] In some embodiments, the first application 410 may read the running status information of multiple applications installed on the electronic device 400 to determine the control information for at least one application based on the running status information of the multiple applications.

[0193] In some embodiments, the first application 410 can read the function information of multiple applications installed on the electronic device 400, and the function description information and startup parameter information corresponding to each function. For example, the first application 410 can read the function description information, the first startup parameter and the second startup parameter condition corresponding to each function of the application.

[0194] In some embodiments, the first application 410 may be an intelligent agent running on the electronic device 400, such as Lenovo Xiaotian.

[0195] In this way, the first application 410 can detect the interactive operation performed by the user on the electronic device 400, and automatically determine at least one task related to the user interactive operation. For example, based on the user dragging text to the audio application, determine the task of searching the audio file corresponding to the text using the audio application.

[0196] Afterwards, for each task, the first application may determine the target function of the target application based on the target interaction operation corresponding to the task and call the target model, and start the target function based on the target start parameter of the target function to process the target data corresponding to the target interaction operation.

[0197] In some embodiments, the target model may be a model running on the electronic device 400 , or a model running on a cloud device, an edge device, a cluster device, etc.

[0198] Based on the above embodiments, the present application also provides an electronic device. Here, the electronic device may refer to a server, a laptop, a tablet computer, a desktop computer, a smart TV, a set-top box, a mobile device (such as a mobile phone, a portable video player, a personal digital assistant, a dedicated messaging device, a portable gaming device) and other devices with data processing capabilities.

[0199] like Figure 5 As shown, the electronic device 500 includes a processor 510 and a display screen 520; wherein,

[0200] The processor 510, in response to a target interaction operation, obtains at least one function corresponding to a target application; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application; based on target data corresponding to the target object, determines a target function from the at least one function; based on a target startup parameter corresponding to the target function, starts the target function to process the target data;

[0201] The display screen 520 is used to display and output the running interface corresponding to the target application.

[0202] It should be noted that the description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0203] It should be noted that in the embodiment of the present application, if the above-mentioned startup method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.

[0204] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.

[0205] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.

[0206] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code is run in an electronic device, a processor in the electronic device executes some or all of the steps for implementing the above method.

[0207] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0208] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.

[0209] It should be noted that Figure 6 A schematic diagram of a hardware entity of an electronic device in this application, such as Figure 6 As shown, the hardware entity of the electronic device 600 includes: a processor 601, a communication interface 602 and a memory 603, wherein:

[0210] The processor 601 generally controls the overall operation of the electronic device 600 .

[0211] The communication interface 602 enables the electronic device to communicate with other terminals or servers through a network.

[0212] The memory 603 is configured to store instructions and applications executable by the processor 601, and can also cache data to be processed or processed by the processor 601 and each module in the electronic device 600 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission can be performed between the processor 601, the communication interface 602, and the memory 603 through the bus 604.

[0213] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.

[0214] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0215] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0216] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0217] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0218] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0219] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0220] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A startup method, comprising: In response to the target interaction operation, obtaining at least one function corresponding to the target application; The target interaction operation is an interaction operation of dragging the target object to a response area corresponding to the target application; determining a target function from the at least one function based on the target data corresponding to the target object; Based on the target startup parameter corresponding to the target function, the target function is started to process the target data.

2. According to the method of claim 1, the response area corresponding to the target application includes one of the following: The display area occupied by the application icon of the target application; The display area occupied by the application window of the target application.

3. The method according to claim 1, wherein determining a target function from the at least one function based on the target object comprises at least one of the following: Based on the attribute information of the target data, determining a target function matching the attribute information from the at least one function; Based on the first semantic information of the target data, a target function having the highest correlation with the semantic information is determined from the at least one function.

4. The method according to any one of claims 1 to 2, wherein determining a target function from the at least one function based on the target object comprises: Inputting the target data and the description information of the at least one function into a target model, so as to determine a target function matching the target object from the at least one function using the target model; The number of weight parameters in the target model is greater than 100 million.

5. The method according to any one of claims 1 to 2, wherein: The target startup parameters include a first startup parameter and a second startup parameter; The first startup parameter is used to start the target function of the target application, and the second startup parameter is used to enable the target function to process the target data.

6. The method according to claim 5, further comprising: In response to the target data satisfying a second startup parameter condition corresponding to the target function, using the target data as the second startup parameter; In response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data, and using the first data as the second startup parameter; The first data satisfies a second startup parameter condition corresponding to the target function.

7. The method according to claim 6, the target data not satisfying the second startup parameter condition corresponding to the target function indicates that the data type of the target data is not the target data type; In response to the target data not satisfying the second startup parameter condition corresponding to the target function, converting the target data into first data and using the first data as the second startup parameter includes: Acquiring second semantic information of the target data; Based on the second semantic information, generate first data of the target data type; The first data is used as the second startup parameter.

8. The method according to claim 5, further comprising: Inputting the first startup parameter, the second startup parameter condition and the target data of the target function into the target model to obtain the target startup parameter; The number of weight parameters in the target model is greater than 100 million.

9. A starting device, comprising: An acquisition module, configured to acquire at least one function corresponding to a target application in response to a target interaction operation; The target interaction operation is an interaction operation of dragging the target object to a response area corresponding to the target application; A first determining module, configured to determine a target function from the at least one function based on target data corresponding to the target object; A startup module is used to start the target function to process the target data based on the target startup parameter corresponding to the target function.

10. An electronic device comprising: A first application program running on the electronic device, the first application program being used to determine at least one task based on a user interaction operation, and for each task, the first application program being used at least to: In response to a target interaction operation corresponding to the task, obtaining at least one function corresponding to the target application; the target interaction operation is an interaction operation of dragging a target object to a response area corresponding to the target application; Inputting target data corresponding to the target object and description information of the at least one function into a target model, so as to determine a target function matching the target object from the at least one function using the target model; Based on the target startup parameter corresponding to the target function, start the target function to process the target data; Among them, the number of weight parameters in the target model is greater than 100 million.

Images