Data processing method and device and electronic equipment

Abstract

The invention discloses a data processing method and device and electronic equipment, and the method comprises the steps: responding to a triggering operation for first information, and outputting multiple pieces of alternative information; wherein the alternative information comprises at least one first content and at least one second content; the first content is determined based on a first attribute of the first information; the second content is the content determined based on the second attribute of the first information; the second attribute is at least related to the information content of the first information and is different from the first attribute; in response to a trigger operation for the alternative information, obtaining processing content according to the first information and target content corresponding to the trigger operation; the target content comprises second content in the alternative information; inputting the processing content into the target model; receiving at least one target instruction output by the target model; and executing the corresponding target task according to the target instruction.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, device and electronic device. Background Art

[0002] When there is text output, the user can select part of the text and right-click to trigger the right-click menu.

[0003] Currently, the menu options in the right-click menu are all fixed settings of the operating system based on the application where the text is located. Summary of the Invention

[0004] In view of this, the present application provides a data processing method, device, and electronic device as follows:

[0005] A data processing method, comprising:

[0006] In response to a triggering operation on the first information, outputting a plurality of candidate information;

[0007] The candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute;

[0008] In response to a trigger operation on the candidate information, obtaining processing content according to the first information and target content corresponding to the trigger operation; the target content includes the second content in the candidate information;

[0009] inputting the processed content into a target model;

[0010] receiving at least one target instruction output by the target model;

[0011] According to the target instructions, the corresponding target tasks are executed.

[0012] In the above method, preferably, the target model is the first model, and the method further includes:

[0013] The information content of the first information is processed using a second model to obtain the second content; the second content is text type content.

[0014] The above method, preferably, further comprises:

[0015] In response to a setting operation on target information in the candidate list, obtaining the second content;

[0016] The candidate list is output in response to the trigger operation, and the candidate information is also displayed in the candidate list.

[0017] In the above method, preferably, the target model is the first model, and the method further includes:

[0018] Optimizing the second model according to the second content corresponding to the setting operation and the information content of the first information;

[0019] The second model is used to process the information content of the first information to obtain the second content.

[0020] The above method, preferably, further comprises:

[0021] Constructing second content according to the information content of the first information and the application corresponding to the first information.

[0022] The above method, preferably, further comprises:

[0023] constructing second content according to the information content of the first information and the location information of the electronic device;

[0024] The electronic device is a device that outputs the first information.

[0025] In the above method, preferably, the alternative information is presented in a right-click menu corresponding to the first information;

[0026] The second content is a secondary menu option in the right-click menu.

[0027] Preferably, the above method further comprises, before executing the corresponding target task according to the target instruction:

[0028] Determine the application programs required to achieve the target tasks;

[0029] Transmitting the target instruction to an execution device where the application is deployed; the execution device is at least one of the following: the electronic device or another device interconnected with the electronic device;

[0030] The execution device is used to execute the corresponding target task according to the target instruction.

[0031] A data processing device, comprising:

[0032] an alternative output unit, configured to output a plurality of alternative information in response to a triggering operation on the first information;

[0033] The candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute;

[0034] a processing obtaining unit, configured to obtain processing content according to the first information and target content corresponding to the triggering operation in response to a triggering operation on the candidate information; the target content includes the second content in the candidate information;

[0035] a processing input unit, configured to input the processing content into a target model;

[0036] an instruction obtaining unit, configured to receive at least one target instruction output by the target model;

[0037] The task execution unit is used to execute the corresponding target task according to the target instruction.

[0038] An electronic device, comprising:

[0039] monitor;

[0040] a processor, configured to output, via the display, a plurality of candidate information in response to a triggering operation on the first information; wherein the candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute;

[0041] The processor is also used to respond to a trigger operation for the alternative information, obtain processing content based on the first information and the target content corresponding to the trigger operation; the target content includes the second content in the alternative information; input the processing content into the target model; receive at least one target instruction output by the target model; and execute the corresponding target task according to the target instruction.

[0042] It can be seen from the above technical solution that in a data processing method, device and electronic device disclosed in the present application, after receiving a trigger operation for the first information, alternative information containing two kinds of content can be output, one of which is content determined based on attributes related to the information content of the first information, and the other is content determined based on other attributes. Therefore, after receiving a trigger operation for the alternative information, the processing content input to the target model can be obtained based on the first information and the content determined based on attributes related to the information content of the first information in the alternative information, so that after receiving the target instruction output by the target model, the corresponding target task can be executed according to the target instruction. It can be seen that in this embodiment, alternative information related to the information content of the first information can be provided, which can enrich the prompt content provided to the target model, thereby making the target task executed according to the target instruction output by the target model more meet the user's usage needs, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0045] Figure 2 This is an example diagram of alternative information in the embodiments of the present application;

[0046] Figure 3 This is an example diagram of obtaining processing content in an embodiment of the present application;

[0047] Figure 4 This is an example diagram of executing a target instruction to complete a target task of ordering roast duck takeout in an embodiment of the present application;

[0048] Figure 5 This is an example diagram of a user-defined second content in an embodiment of the present application;

[0049] Figure 6 This is an example diagram of achieving the target task of making a lunch appointment based on the new second content in an embodiment of the present application;

[0050] Figure 7 This is an example diagram of completing the target task of making a lunch appointment based on an application in an embodiment of the present application;

[0051] Figure 8This is another example diagram of completing the target task of ordering roast duck takeout based on an application in an embodiment of the present application;

[0052] Figure 9 This is an example diagram of completing the target task of ordering fast food takeout based on the location information of the electronic device in an embodiment of the present application;

[0053] Figure 10 This is another example diagram of completing the target task of making a lunch appointment based on the location information of the electronic device in an embodiment of the present application;

[0054] Figure 11 Another flow chart of a data processing method provided in an embodiment of the present application;

[0055] Figure 12 This is an example diagram of a laptop sending a target instruction to a mobile phone to complete a target task of ordering fast food takeout in an embodiment of the present application;

[0056] Figure 13 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0057] Figure 14 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] refer to Figure 1 FIG2 is a flowchart of a data processing method according to an embodiment of the present application, which can be applied to electronic devices capable of data processing, such as notebooks or tablet devices. The technical solution in this embodiment is mainly used to improve the user experience of electronic devices.

[0060] Specifically, the method in this embodiment may include the following steps:

[0061] Step 101: In response to a triggering operation on first information, output a plurality of candidate information.

[0062] The first information may be text, images, audio, or other information selected by the user. The first information may include characters in text, objects or characters in images, or text recognized by audio.

[0063] For example, Figure 2As shown in , when the user is editing a document, he selects the characters "It's time for lunch" in the text and right-clicks the mouse on the selected information. At this time, the first information is "It's time for lunch". The triggering operation may include: a selection operation and a right-click operation on the first information. In response to the triggering operation, multiple menu options, i.e., alternative information, are output in the right-click menu.

[0064] It should be noted that the candidate information includes at least one first content and at least one second content. The first content is determined based on the first attribute of the first information. The second content is determined based on the second attribute of the first information. The second attribute is at least related to the information content of the first information and is different from the first attribute.

[0065] In one implementation, the first attribute may be an attribute corresponding to the application to which the first information belongs, or an attribute corresponding to the information type of the first information, while the second attribute is different from the first attribute and is related to the information content of the first information.

[0066] For example, Figure 2 As shown in , the right-click menu of the first information "It's time for lunch" includes first content such as "Cut", "Copy", and "Font" determined based on the text attributes of the first information, and also includes second content such as "I want to eat roast duck" and "Restaurant A" determined based on "lunch time". The first content and the second content are provided to the user as alternative information for triggering operations, such as left clicking.

[0067] Step 102: In response to a trigger operation on candidate information, processing content is obtained according to the first information and the target content corresponding to the trigger operation.

[0068] The target content includes the second content in the candidate information.

[0069] In a specific implementation, in this embodiment, processing content may be generated based on the information content of the first information and the second content in the candidate information selected by the triggering operation.

[0070] In one implementation, in this embodiment, the information content of the first information may be spliced with the second content in the candidate information selected by the triggering operation to obtain the processed content.

[0071] In another implementation, in this embodiment, content extraction and content merging may be performed on the information content of the first information and the second content in the candidate information selected by the triggering operation to obtain processed content.

[0072] In another implementation, in this embodiment, the information content of the first information and the second content in the candidate information selected by the trigger operation may be spliced together, and then a screenshot image of the interface where the candidate information is located may be integrated to obtain the processed content.

[0073] For example, Figure 2 As shown in , the user's selection of "craving roast duck" in the candidate information and the first information "it's time for lunch" can be combined to generate processing content corresponding to "craving roast duck for lunch" or "it's time for lunch, I want roast duck." The processing content can be prompt information obtained based on the first information, the target content, and a preset prompt word. This prompt information can guide the target model to perform reasoning.

[0074] For example, Figure 3 As shown in , the user's selected "I want to eat roast duck" in the alternative information and the first information "It's time for lunch" can be integrated with the applications installed on the notebook identified in the notebook desktop screenshot image to generate the processed content of "I want to eat roast duck for lunch" and the application identification.

[0075] Step 103: Input the processed content into the target model.

[0076] This embodiment is based on a Large Action Model (LAM), a target application built based on the capabilities of a target model. The target model can reason about processing content to output at least one corresponding target instruction. The target model can be a local model of the target application or a remote model called by the target application. The target model is a machine learning model that can recognize natural language and / or other inputs (such as audio, video, images, tables, etc.) input to the target model and perform comprehensive language processing tasks such as semantic analysis and question answering, thereby generating output related to the input and / or responding to the input. The target model learns the characteristics and patterns of natural language by training on large amounts of diverse data, thereby enabling it to understand and generate natural language. It typically has model parameters (model parameters are variables that control the behavior of the target model) in the hundreds of millions to hundreds of billions, capable of capturing complex relationships and patterns in natural language. The target model can be a generative model or a generative language model (GLM). For example, it can include large language models (LLMs) and GPT (Generative Pre-trained Transformer). The target model has more than 100 million weight parameters; the target model generates output information based on its own weight parameters; and the target model's output is obtained by concatenating the characteristic information generated by the target model one by one. The models involved in the embodiments of this application can be general large models or expert large models obtained by fine-tuning based on needs, and the embodiments of this application are not limited to this.

[0077] For example, in this embodiment, after generating the processing content of "I want to eat roast duck for lunch" and the application identification, these processing contents are sent to the target model. The target model outputs at least one target instruction through model reasoning, such as the target instructions of clicking on the "takeout application", finding the roast duck menu, and ordering roast duck.

[0078] Step 104: Receive at least one target instruction output by the target model.

[0079] For example, in this embodiment, the corresponding mouse, touch, content input, etc. instructions output by the LAM-based functional model are received, such as opening the "takeout application", finding the roast duck menu, and ordering roast duck.

[0080] Step 105: Execute the corresponding target task according to the target instruction.

[0081] For example, Figure 4As shown in , in this embodiment, according to the target instructions of clicking on the "takeout application", finding the roast duck menu, and ordering roast duck, first move the mouse to the application icon of the takeout application, double-click the application icon, and after the application interface of the takeout application is expanded, search for the roast duck menu. After searching for the roast duck menu, order roast duck to complete the target task of ordering roast duck takeout.

[0082] It can be seen from the above technical solution that in a data processing method provided by an embodiment of the present application, after receiving a trigger operation for the first information, alternative information containing two kinds of content can be output, one of which is content determined based on attributes related to the information content of the first information, and the other is content determined based on other attributes. Therefore, after receiving a trigger operation for the alternative information, the processing content input to the target model can be obtained based on the first information and the content determined based on attributes related to the information content of the first information in the alternative information. Therefore, after receiving the target instruction output by the target model, the corresponding target task can be executed according to the target instruction. It can be seen that in this embodiment, alternative information related to the information content of the first information can be provided, which can enrich the prompt content provided to the target model, thereby making the target task executed according to the target instruction output by the target model more meet the user's usage needs, thereby improving the user experience.

[0083] In one implementation, the target model may be a first model. In this embodiment, a second model is also deployed. Based on this, in this embodiment, the second model may be used to process the information content of the first information to obtain the second content. The second model may be different from the first model, or the second model may be a partial functional module of the first model.

[0084] The second content is text-type content.

[0085] In a specific implementation, the second model can be an intelligent model for intent recognition, which can process the information content of the first information to obtain the second content, and the second content can represent any behavioral intention expressed by the information content of the first information as described in this article.

[0086] For example, in this embodiment, the first information "Have a meeting to discuss at 3 pm" can be identified through the intelligent model of intent recognition to determine possible behavioral intentions, such as "issuing meeting invitations", "booking a meeting room" and "notifying relevant people by email".

[0087] Based on the above implementation, in this embodiment, the intelligent model for intent recognition can be trained through user history data. For example, user history data includes: previously obtained information content and historical operations performed by the user after the information content is obtained.

[0088] For example, the previously obtained information content may be text content X received by a user via a chat application, and the corresponding historical operations may be the historical operations performed by the user after receiving text content X. The operation descriptions of these historical operations serve as the second content corresponding to the first information X, such as opening a food delivery application or switching to a friend dialog box. In this embodiment, the intelligent model is trained based on this user historical data so that the intelligent model can output the corresponding second content based on the first information selected by the user, such as X.

[0089] In one implementation, the second content in the candidate information can also be customized by the user. Specifically, in this embodiment, the second content can also be obtained in response to a setting operation on the target information in the candidate list. The second content is processed together with the information content of the first information as the target content, and the target model outputs the target instruction, thereby executing the corresponding target task.

[0090] The candidate list is output in response to the trigger operation for the first information, and the candidate list also displays the candidate information. That is, in this embodiment, in response to the trigger operation for the first information, the candidate information and the target information are output in the form of the candidate list.

[0091] In a specific implementation, the candidate information and the target information are presented in the right-click menu corresponding to the first information, while the second content and the target information can be secondary menu options in the right-click menu, and the first content can be a primary menu option in the right-click menu. The secondary menu options can be output through the link option in the primary menu option.

[0092] For example, Figure 5As shown in the figure, after the user selects the first information "It's time for lunch" and right-clicks, the right-click menu contains first content such as "Cut", "Copy", and "Font", and also contains "Extended Options". The "Extended Options" points to the second-level menu options. The second-level menu options include second content based on "Lunch Time", such as "Want to Eat Roast Duck" and "Restaurant A". The user can select any first content in the first-level menu options or any second content in the second-level menu options. Furthermore, the second-level menu options can also include a "Customize" option as the target information. If the user feels that the behavioral intention expressed by the second content in the secondary menu option does not meet the needs, then the user can customize the settings. That is, the user clicks the "Customize" option and enters custom content such as "Invite a dinner buddy out for dinner" in the pop-up input box. The processing content generated by this second content and the information content of the first message is provided to the target model, and the target model generates target instructions such as "Open the chat application", "Search for dinner buddies in the friend group", and "Send a dinner invitation message in the dinner buddy group". According to these target instructions, the corresponding target tasks are performed. For example, first move the mouse to the application icon of the chat application and double-click the application icon. After the application interface of the chat application is expanded, search for the dinner buddy group in the friend list. After searching for the dinner buddy group, send a message "Let's go for lunch" in the dinner buddy group to complete the target task of making a lunch appointment.

[0093] It can be seen that in this embodiment, through the output of target information, a service of customizing the second content for the first content is provided to the user, so that the executed target task can better meet the user's needs.

[0094] Based on the above implementation, the target model can be the first model. In this embodiment, a second model is also deployed. Based on this, in this embodiment, the second model can also be optimized according to the second content corresponding to the setting operation and the information content of the first information, so that the second model can learn that the information content of the first information will generate the behavioral intention corresponding to the second content. Therefore, the next time the first information is triggered, the output alternative information includes the second content obtained through the setting operation on the target information.

[0095] For example, Figure 6As shown in , after a user selects the first message "It's time for lunch" and right-clicks, the right-click menu contains first items such as "Cut," "Copy," and "Font," as well as "Extended Options." The "Extended Options" point to a second-level menu, which includes options based on second items such as "Want to eat roast duck," "Restaurant A," and "Let's go out for lunch." The user can select any first item from the first-level menu or any second item from the second-level menu. If the user selects "Let's go out for lunch," the processed content generated based on this second item and the information content of the first message is provided to the target model, which generates target instructions such as "Open a chat app," "Search for friends in the friend group," and "Send a lunch invitation message to the friend group." These target instructions execute the corresponding target tasks. For example, first move the mouse to the chat app icon and double-click the icon. After the chat app interface is expanded, search for the friend group. After finding the friend group, send the message "Let's go for lunch" to the friend group, completing the target task of making a lunch invitation.

[0096] It can be seen that in this embodiment, the second model can be optimized by setting the operation and the corresponding second content, so that the second content in the alternative information can better represent the user's behavioral intention to operate the first information, thereby making the target task performed better meet user needs.

[0097] In one implementation, in this embodiment, the second content may also be constructed according to the information content of the first information and the application corresponding to the first information.

[0098] The application corresponding to the first information may be a document editing application, a chat application, or the like.

[0099] For example, Figure 7 As shown in , in this embodiment, the second content "Invite friends to have lunch" can be constructed based on the information content of the first message "It's time for lunch" and the chat application where the first message is located, and then the processing content "Invite friends to have lunch" is generated based on "It's time for lunch" and the user's selection of "Invite friends to have lunch". The target model processes and outputs target instructions such as "Open the chat application", "Search for the meal group", and "Send a meal invitation message in the meal group". According to these target instructions, the corresponding target tasks are executed, such as first moving the mouse to the application icon of the chat application and double-clicking the application icon. After the application interface of the chat application is expanded, search for the meal group. After searching the meal group, send a message "Lunch, let's go" in the meal group to complete the target task of making a lunch appointment.

[0100] For example, Figure 8As shown in , in this embodiment, the information content of the first message "It's time for lunch" and the text editing application where the first message is located can be used to construct the second content "I want to eat roast duck". Then, based on "It's time for lunch" and the user's selection of "I want to eat roast duck", the processing content "Eat roast duck at noon" is generated, and the target model processes and outputs the target instructions of clicking on the "takeout application", finding the roast duck menu, and ordering roast duck. Then, according to the target instructions of clicking on the "takeout application", finding the roast duck menu, and ordering roast duck, first move the mouse to the application icon of the takeout application and double-click the application icon. After the application interface of the takeout application is expanded, search for the roast duck menu. After searching for the roast duck menu, order roast duck and complete the target task of ordering roast duck takeout.

[0101] Therefore, in this embodiment, target content can be further filtered from the second content determined by the information content of the first information according to the application corresponding to the first information, so that the target task achieved can more accurately meet user needs.

[0102] In one implementation, this embodiment may further construct the second content based on the information content of the first information and the location information of the electronic device. The electronic device may be a device that outputs the first information, such as a laptop or mobile phone. The location information of the electronic device may be the location of the electronic device in a city or an indoor or outdoor location, such as the ** office building in city A or street C in area B in city A.

[0103] For example, Figure 9 As shown in , in this embodiment, based on the first message's content "It's lunch time" and the electronic device's location in the ** office building, the second content "Eat fast food" can be constructed. Based on "It's lunch time" and the user's selection of "Eat fast food," the processed content "Eat fast food at noon" is generated. The target model processes this and outputs the target instructions of opening the "takeout app," searching for the fast food menu, and placing the fast food order. Then, following the target instructions of opening the "takeout app," searching for the fast food menu, and placing the fast food order, the user first moves the mouse to the takeout app's app icon and double-clicks it. After the takeout app's interface expands, the user searches for the fast food menu. Once the menu is found, the user places the order, completing the target task of ordering fast food.

[0104] For example, Figure 10As shown in FIG, in this embodiment, the second content "Lunchtime" can be constructed based on the first message content "It's time for lunch" and the electronic device being located in City A, Area B, Street C. Then, based on "It's time for lunch" and the user's selection of "Lunchtime," the processing content "Meet a nearby friend for lunch at Restaurant D on Street C" is generated. The target model processes and outputs target instructions such as "Open a chat app," "Search for pinned friends," and "Send a lunchtime message to the pinned friend's message box." These target instructions are then used to execute the corresponding target tasks. For example, the user first moves the mouse to the chat app icon and double-clicks the icon. After the chat app interface is expanded, the user searches for pinned friends. After finding the pinned friends, the user then sends the message "Lunchtime, come to Restaurant D on Street C" in the pinned friend's message box, completing the lunchtime target task.

[0105] Therefore, in this embodiment, target content can be further filtered from the second content determined by the information content of the first information according to the location information of the electronic device, so that the achieved target task can more accurately meet user needs.

[0106] In one implementation, before step 105 in this embodiment executes the corresponding target task, the following processing may be performed first, such as Figure 11 As shown in:

[0107] Step 106: Determine the application program required to achieve the target task.

[0108] Specifically, in this embodiment, the task type and task function of the target task may be analyzed to determine an application program that can implement the target task.

[0109] For example, the target task of ordering roast duck takeout requires a takeout application, and the target task of making a dinner appointment requires a chat application.

[0110] Step 107: Transmit the target instructions to the execution device where the application is deployed.

[0111] The execution device is at least one of the following: an electronic device, or another device interconnected with the electronic device. The execution device is used to execute the corresponding target task according to the target instruction.

[0112] In one implementation, the execution device can be an electronic device. In this case, the target instruction can be transmitted to the processor of the electronic device on the electronic device, and the processor of the electronic device starts the application required to achieve the target task, such as a chat application, according to the target instruction, thereby achieving the target task.

[0113] In another implementation, the execution device may be another device interconnected with the electronic device. In this case, the target instruction may be transmitted to the execution device through the data connection between the electronic device and the execution device. The execution device may then start the application required to implement the target task, such as a food delivery application, in accordance with the target instruction, thereby achieving the target task.

[0114] For example, Figure 12 As shown in , on a notebook, the user selects the first message "It's time for lunch." The notebook can output alternative messages based on the first message's content, "It's time for lunch." After the user selects the second content, "Eat fast food," the notebook generates the processing content "Eat fast food at noon" based on "It's time for lunch" and the user's selection of "Eat fast food." The target model processes and outputs target instructions for opening the "takeout app," finding the fast food menu, and placing an order. The takeout app is then on the phone, and the target instructions are sent to the phone via the WiFi connection between the notebook and the phone. Then, on the phone, according to the target instructions for opening the "takeout app," finding the fast food menu, and placing an order, the user first clicks the takeout app's icon. After the takeout app's interface is expanded, the user searches for the fast food menu. After finding the fast food menu, the user places an order, completing the target task of ordering fast food.

[0115] refer to Figure 13 , is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application. The device can be deployed in an electronic device capable of data processing, such as a notebook or tablet device. The technical solution in this embodiment is mainly used to improve the user experience of electronic devices.

[0116] Specifically, the device in this embodiment may include the following units:

[0117] The alternative output unit 1301 is configured to output a plurality of alternative information in response to a triggering operation on the first information;

[0118] The candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute;

[0119] The processing obtaining unit 1302 is configured to obtain processing content according to the first information and the target content corresponding to the triggering operation in response to the triggering operation on the candidate information; the target content includes the second content in the candidate information;

[0120] A processing input unit 1303, configured to input the processing content into a target model;

[0121] An instruction obtaining unit 1304 is configured to receive at least one target instruction output by the target model;

[0122] The task execution unit 1305 is used to execute the corresponding target task according to the target instruction.

[0123] It can be seen from the above technical solution that in a data processing device provided by an embodiment of the present application, after receiving a trigger operation for the first information, alternative information containing two kinds of content can be output, one of which is content determined based on attributes related to the information content of the first information, and the other is content determined based on other attributes. Therefore, after receiving a trigger operation for the alternative information, the processing content input to the target model can be obtained based on the first information and the content determined based on attributes related to the information content of the first information in the alternative information, so that after receiving the target instruction output by the target model, the corresponding target task can be executed according to the target instruction. It can be seen that in this embodiment, alternative information related to the information content of the first information can be provided, which can enrich the prompt content provided to the target model, thereby making the target task executed according to the target instruction output by the target model more meet the user's usage needs, thereby improving the user experience.

[0124] In one implementation, the target model is a first model, and the alternative output unit 1301 is further configured to: process the information content of the first information using a second model to obtain the second content; the second content is text-type content.

[0125] In one implementation, the alternative output unit 1301 is further configured to: obtain the second content in response to a setting operation on target information in the alternative list; wherein the alternative list is output in response to the trigger operation, and the alternative information is also displayed in the alternative list.

[0126] In one implementation, the target model is the first model, and the alternative output unit 1301 is further used to: optimize the second model according to the second content corresponding to the setting operation and the information content of the first information; wherein the second model is used to process the information content of the first information to obtain the second content.

[0127] In one implementation, the alternative output unit 1301 is further configured to construct second content according to the information content of the first information and the application corresponding to the first information.

[0128] In one implementation, the alternative output unit 1301 is further configured to construct second content based on the information content of the first information and location information of an electronic device, wherein the electronic device is a device that outputs the first information.

[0129] In one implementation, the alternative information is presented in a right-click menu corresponding to the first information; wherein the second content is a secondary menu option in the right-click menu.

[0130] In one implementation, before the task execution unit 1305 executes the corresponding target task according to the target instruction, the instruction acquisition unit 1304 is also used to: determine the application required to implement the target task; transmit the target instruction to the execution device where the application is deployed; the execution device is at least one of the following: the electronic device or other device interconnected with the electronic device; wherein, the execution device is used to execute the corresponding target task according to the target instruction.

[0131] It should be noted that the specific implementation of each unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0132] refer to Figure 14 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, and the electronic device may include the following structure:

[0133] Display 1401;

[0134] Processor 1402 is configured to, in response to a triggering operation on first information, output, via the display, a plurality of candidate information; wherein the candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to information content of the first information, and the second attribute is different from the first attribute;

[0135] The processor 1402 is also used to respond to a trigger operation for the alternative information, obtain processing content according to the first information and the target content corresponding to the trigger operation; the target content includes the second content in the alternative information; input the processing content into the target model; receive at least one target instruction output by the target model; and execute the corresponding target task according to the target instruction.

[0136] It can be seen from the above technical solution that in an electronic device provided by an embodiment of the present application, after receiving a trigger operation for a first information, alternative information containing two kinds of content can be output, one of which is content determined based on attributes related to the information content of the first information, and the other is content determined based on other attributes. Therefore, after receiving a trigger operation for the alternative information, the processing content input to the target model can be obtained based on the first information and the content determined based on attributes related to the information content of the first information in the alternative information, so that after receiving the target instruction output by the target model, the corresponding target task can be executed according to the target instruction. It can be seen that in this embodiment, alternative information related to the information content of the first information can be provided, which can enrich the prompt content provided to the target model, thereby making the target task executed according to the target instruction output by the target model more meet the user's usage needs, thereby improving the user experience.

[0137] Taking the scenario where a user selects text in a document editing application in a notebook as an example, the technical solution of this application is illustrated below:

[0138] In the right-click menu output when the user selects text, a secondary menu is added. The link option in the primary menu is "AILAM", indicating that the secondary menu option it links to contains a second content determined based on the text content of the selected text.

[0139] Among them, in the secondary menu, according to the selected text content, the second content analyzed by AI (ie, the second model) can be one or more.

[0140] For example, if the selected text is: "Meeting at 3 pm to discuss the spec", then the secondary menu options can be "Send meeting invitations", "Book a meeting room", or "Notify relevant people by email".

[0141] For example, if the selected text is: "After get off work, pick up the package at the express locker at the community gate", then the secondary menu option can be "Set reminder";

[0142] Based on this, after the user clicks on a secondary menu option, the option name (ie, the second content) and the selected text content of the secondary menu option are given as input to the LAM for automatic execution.

[0143] It should be noted that the title of the secondary menu option in the right-click menu can be determined by calling a large language model or other intelligent model for analysis; it can also be determined by training pairs based on user historical data such as "the content of a received message" and "the next action" to obtain a small model, namely the intelligent model for intent recognition mentioned above, and use this small model for reasoning.

[0144] In addition, the secondary menu of AI LAM can add an "other" item, namely the "custom" mentioned above, for users to input what they need LAM to do, such as "book a meeting room" and "send meeting invitations". By learning the user's input, a very personalized model is trained to calculate what the user should do next for a piece of text and provide it in the right-click menu.

[0145] It can be seen that the technical solution in this embodiment can shorten the user operation process, reduce the complexity of user operations, and thus improve the user experience.

[0146] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0147] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0148] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0149] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, comprising: In response to a triggering operation on the first information, outputting a plurality of candidate information; The candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute; In response to a trigger operation on the candidate information, obtaining processing content according to the first information and target content corresponding to the trigger operation; the target content includes the second content in the candidate information; inputting the processed content into a target model; receiving at least one target instruction output by the target model; According to the target instructions, the corresponding target tasks are executed.

2. The method according to claim 1, wherein the target model is a first model, and the method further comprises: Processing the information content of the first information using a second model to obtain the second content; The second content is text-type content.

3. The method according to claim 1, further comprising: In response to a setting operation on target information in the candidate list, obtaining the second content; The candidate list is output in response to the trigger operation, and the candidate information is also displayed in the candidate list.

4. The method according to claim 3, wherein the target model is a first model, and the method further comprises: Optimizing the second model according to the second content corresponding to the setting operation and the information content of the first information; The second model is used to process the information content of the first information to obtain the second content.

5. The method according to claim 1, further comprising: Constructing second content according to the information content of the first information and the application corresponding to the first information.

6. The method according to claim 1, further comprising: constructing second content according to the information content of the first information and the location information of the electronic device; The electronic device is a device that outputs the first information.

7. The method according to claim 1, wherein the candidate information is presented in a right-click menu corresponding to the first information; in, The second content is a secondary menu option in the right-click menu.

8. The method according to claim 1, before executing the corresponding target task according to the target instruction, the method further comprises: Determine the application programs required to achieve the target tasks; Transmitting the target instruction to an execution device where the application is deployed; the execution device is at least one of the following: an electronic device or another device interconnected with the electronic device; The execution device is used to execute the corresponding target task according to the target instruction.

9. A data processing device comprising: an alternative output unit, configured to output a plurality of alternative information in response to a triggering operation on the first information; The candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute; a processing obtaining unit, configured to obtain processing content according to the first information and target content corresponding to the triggering operation in response to a triggering operation on the candidate information; the target content includes the second content in the candidate information; a processing input unit, configured to input the processing content into a target model; an instruction obtaining unit, configured to receive at least one target instruction output by the target model; The task execution unit is used to execute the corresponding target task according to the target instruction.

10. An electronic device comprising: monitor; a processor, configured to output, via the display, a plurality of candidate information in response to a triggering operation on the first information; wherein the candidate information includes at least one first content and at least one second content; the first content is content determined based on a first attribute of the first information; the second content is content determined based on a second attribute of the first information; the second attribute is at least related to the information content of the first information, and the second attribute is different from the first attribute; The processor is also used to respond to a trigger operation for the alternative information, obtain processing content based on the first information and the target content corresponding to the trigger operation; the target content includes the second content in the alternative information; input the processing content into the target model; receive at least one target instruction output by the target model; and execute the corresponding target task according to the target instruction.

Images