A display device and a schedule making method

Abstract

This application provides a display device and a method for planning. The display device, responding to a user's instruction to formulate a first plan, can analyze the content of the first instruction to accurately obtain the user's intent, first user information, and the user's first requirements for the first plan. The display device can first filter out a first historical task set matching the first instruction from a historical task set, and then adjust the first historical task set according to the user's intent, first user information, and first requirements to quickly obtain a target task set that matches the current plan. This reduces the workload and time consumption of planning tasks, improves the efficiency of obtaining the target task set, and thus improves the efficiency of formulating the first plan.

Description

Technical Field

[0001] This application relates to the field of display device technology, and more particularly to a display device and a method for planning. Background Technology

[0002] Display devices refer to terminal devices capable of outputting specific display images, such as smart TVs, mobile terminals, smart advertising screens, and projectors. Taking smart TVs as an example, smart TVs are television products based on Internet application technologies, possessing open operating systems and chips, and having open application platforms. They enable two-way human-computer interaction and integrate multiple functions such as audio-visual, entertainment, and data to meet diverse and personalized user needs.

[0003] Display devices can be configured with a planning function. Based on this function, when a user wants to create a plan, they can input their requirements for the plan into the display device. The display device then plans and executes the tasks according to these requirements. The display device summarizes the execution results of each task to obtain the corresponding plan.

[0004] Based on the above planning process, it is clear that the more requests users make, the more complex and time-consuming the process of the display device planning the tasks to be executed becomes. Furthermore, the more tasks are planned, the longer the execution time becomes. Therefore, the display device's planning efficiency is low, leading to longer waiting times for users from inputting their requests to receiving the plan, resulting in a poor user experience. Summary of the Invention

[0005] This application provides a display device and a method for planning, which can quickly obtain a target task set that matches the current plan by adjusting the historical task set, thereby improving the efficiency of planning.

[0006] In a first aspect, this application provides a display device, comprising: a controller configured to: respond to a first instruction from a user to formulate a first plan; obtain, based on the instruction content of the first instruction, a user intent, first user information, and at least one first requirement of the user for the first plan; obtain at least one historical task set, the historical task set corresponding to historical instructions from the user to formulate the corresponding plan; filter out a first historical task set matching the first instruction from the at least one historical task set; adjust the tasks in the first historical task set according to the user intent, the first user information, and the at least one first requirement to obtain a target task set; invoke a target tool corresponding to each task in the target task set, and execute the corresponding task through the target tool to obtain the first plan; and display the first plan.

[0007] The above technical solution has the following beneficial effects or advantages:

[0008] The display device, responding to a user's instruction to formulate a first plan, can analyze the content of the first instruction to accurately obtain the user's intent, first user information, and the user's first requirements for the first plan. The display device can first filter out a first set of historical tasks matching the first instruction from a historical task set, and then adjust this first set of historical tasks according to the user's intent, first user information, and first requirements to quickly obtain a target set of tasks that match the first plan. This reduces the workload and time spent on planning tasks, improves the efficiency of obtaining the target task set, and consequently improves the efficiency of formulating the first plan.

[0009] In some embodiments of this application, the controller executes a first instruction in response to a user instruction to formulate a first plan, and obtains user intent, user information, and at least one first requirement of the user for the first plan based on the instruction content of the first instruction. Specifically, it is configured to: obtain the user intent based on the instruction content of the first instruction; and extract the first user information and the at least one first requirement from the first text based on the user intent.

[0010] The above technical solution has the following beneficial effects or advantages:

[0011] By extracting first user information and first requirements corresponding to the user's intent from the instruction content of the first instruction, the display device can ensure that the extracted first user information and first requirements conform to the user's intent, thereby ensuring that the target task set subsequently obtained based on the first user information and first requirements also conforms to the user's intent. Furthermore, by extracting the first user information and first requirements according to the user's intent, the display device can effectively filter out other information in the first text, reducing the amount of data extracted. This improves the data processing efficiency of subsequently obtaining the target task set based on the first user information and first requirements, and further enhances the efficiency of formulating the first plan.

[0012] In some embodiments of this application, the controller executes a first instruction in response to a user instruction to formulate a first plan, and obtains user intent, first user information, and at least one first requirement of the user for the first plan based on the instruction content of the first instruction. Specifically, it is configured to: if the instruction content of the first instruction does not include the first user information, when the first instruction is a voice instruction, obtain the voice features corresponding to the first instruction; and obtain the first user information based on the voice features.

[0013] The above technical solution has the following beneficial effects or advantages:

[0014] When the content of the first instruction does not contain the first user information and the first instruction is a voice instruction, the display device can combine sound analysis technology to obtain the first user information based on the voice features of the first instruction, thereby ensuring the integrity of the information used to obtain the target task set and thus ensuring the accuracy of the target task set.

[0015] In some embodiments of this application, the controller executes a first instruction in response to a user instruction to formulate a first plan, and obtains user intent, first user information, and at least one first requirement of the user for the first plan based on the instruction content of the first instruction. It is further configured to: obtain summary information corresponding to the historical instruction, the summary information being used to characterize a specified dimension of the historical instruction; filter out target summary information from the summary information that matches the instruction content of the first instruction; and update the first user information based on the target summary information.

[0016] The above technical solution has the following beneficial effects or advantages:

[0017] After acquiring the initial user information, the display device can use the summary information corresponding to historical instructions as auxiliary information to update the initial user information. Since the summary information can characterize the user's historical interactions with the display device, and these interactions can reflect the user's preferences, habits, and needs in certain dimensions, the updated initial user information can more accurately reflect the user's preferences, habits, and needs, further improving the accuracy of the target task set subsequently obtained based on the updated initial user information.

[0018] In some embodiments of this application, the controller performs the function of filtering a first historical task set that matches the first instruction from the at least one historical task set. Specifically, it is configured to: obtain the historical instruction corresponding to each historical task set in the at least one historical task set; match the first instruction with each historical instruction, and / or match the first instruction with the tasks in each historical task set to obtain a matching result; and filter the first historical task set from the at least one historical task set according to the matching result, wherein the matching result corresponding to the first historical task set satisfies a first matching result and / or a second matching result, the first matching result being that the first instruction matches the historical instruction corresponding to the first historical task set, and the second matching result being that the task in the first historical task set matches the at least one first requirement corresponding to the first instruction.

[0019] The above technical solution has the following beneficial effects or advantages:

[0020] The display device can accurately filter out a first historical task set that can be matched with the first instruction by matching the first instruction with historical instructions and / or matching the first instruction with tasks in the historical task set. The first historical task set has relatively few tasks that need to be adjusted, which can effectively improve the efficiency of obtaining the target task set in the future, and thus improve the efficiency of formulating the first plan.

[0021] In some embodiments of this application, the controller performs the following actions: adjusting tasks in the first historical task set according to the user intent, the first user information, and the at least one first requirement to obtain the target task set. Specifically, the controller is configured to: filter out a first task from the tasks included in the first historical task set, wherein the first task does not match at least one of the user intent, the first user information, and the at least one first requirement; filter out a requirement to be planned from the at least one first requirement, wherein the requirement to be planned does not match any of the tasks in the first historical task set; adjust the first task according to the mismatch information in the user intent, the first user information, and the at least one first requirement; and add a second task corresponding to the requirement to be planned to the first historical task set to obtain the target task set.

[0022] The above technical solution has the following beneficial effects or advantages:

[0023] The display device can obtain tasks that accurately match the user intent, first user information, and each first requirement by adjusting first tasks in the first historical task set that do not match the user intent, first user information, and first requirements, and by adding second tasks corresponding to the requirements to be planned to the first historical task set. The first user information can include user information directly extracted from the instruction content of the first instruction, user information obtained based on the voice features of the first instruction, and user information updated according to the summary information corresponding to the historical instructions. Therefore, the target task set formed by these tasks can accurately match the user intent, first user information, and each first requirement.

[0024] In some embodiments of this application, the controller performs tasks in the first historical task set according to the user intent, the first user information, and the at least one first requirement to obtain a target task set, and is further configured to: obtain tool information of available tools; and add a third task to the first historical task set according to the tool information of the available tools, wherein the third task has a corresponding available tool.

[0025] The above technical solution has the following beneficial effects or advantages:

[0026] Display devices can be configured with tools for performing corresponding tasks. When planning a task, the available tools can be used to ensure planning efficiency, enhance the richness of the planned tasks, and ensure the feasibility of the planned tasks.

[0027] In some embodiments of this application, the controller executes adjustments to the tasks in the first historical task set based on the user intent, the first user information, and the at least one first requirement to obtain the target task set. It is also configured to: obtain the associated tasks of the user intent; obtain a fourth task from the associated tasks that is different from the tasks in the first historical task set; and add the fourth task to the first historical task set to obtain the target task set.

[0028] The above technical solution has the following beneficial effects or advantages:

[0029] The display device can directly add user-intended related tasks to the first historical task set to automatically expand the content that the user may need and create a richer first plan.

[0030] In some embodiments of this application, the controller executes the invocation of the target tools corresponding to each task in the target task set, and executes the corresponding tasks through the target tools to obtain the first plan. Specifically, it is configured to: obtain a first type of task and a second type of task in the target task set, wherein the first type of task corresponds to the unadjusted tasks in the first historical task set, and the second type of task is the task in the target task set other than the first type of task; if the first historical task set includes the execution results corresponding to each task, obtain the execution results corresponding to the first type of task from the first historical task set; invoke the target tool corresponding to the second type of task, and execute the corresponding second type of task through the target tool to obtain the execution result of the second type of task; and form the first plan by combining the execution results corresponding to the first type of task and the execution results of the second type of task.

[0031] The above technical solution has the following beneficial effects or advantages:

[0032] When a display device executes tasks in a target task set, it can directly use the execution results of the first type of tasks and only need to execute the second type of tasks. This can effectively reduce the number of tasks that actually need to be executed and improve the overall efficiency of task execution.

[0033] Secondly, this application also provides a method for formulating a plan, applied to any of the display devices described in the first aspect, the method comprising: responding to a user instruction to formulate a first plan; obtaining, based on the instruction content of the first instruction, a user intent, first user information, and at least one first requirement of the user for the first plan; obtaining at least one historical task set, the historical task set corresponding to a historical instruction from the user to formulate a corresponding plan; filtering out a first historical task set matching the first instruction from the at least one historical task set; adjusting the tasks in the first historical task set according to the user intent, the first user information, and the at least one first requirement to obtain a target task set; invoking a target tool corresponding to each task in the target task set, and executing the corresponding task through the target tool to obtain the first plan; and displaying the first plan.

[0034] The above technical solution has the following advantages or beneficial effects:

[0035] The display device, responding to a user's instruction to formulate a first plan, can analyze the content of the first instruction to accurately obtain the user's intent, first user information, and the user's first requirements for the first plan. The display device can first filter out a first set of historical tasks matching the first instruction from a historical task set, and then adjust this first set of historical tasks according to the user's intent, first user information, and first requirements to quickly obtain a target set of tasks that match the first plan. This reduces the workload and time spent on planning tasks, improves the efficiency of obtaining the target task set, and consequently improves the efficiency of formulating the first plan. Attached Figure Description

[0036] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a schematic diagram illustrating the operation scenario between the display device 200 and the control device 100 in an embodiment of this application;

[0038] Figure 2 This is a hardware configuration block diagram of the display device 200 in this embodiment of the application;

[0039] Figure 3 This is a diagram showing the operating system configuration of the display device 200 in this embodiment of the application;

[0040] Figure 4 A flowchart illustrating the first plan for the display device 200 in this application embodiment;

[0041] Figure 5 This is a schematic diagram of the architecture to be developed in the embodiments of this application;

[0042] Figure 6 A timing diagram for a first plan is provided for the display device 200 in this embodiment of the application;

[0043] Figure 7 This is a flowchart illustrating how the display device 200 acquires user intent, first user information, and first request in an embodiment of this application.

[0044] Figure 8 This is a flowchart illustrating the process of display device 200 updating first user information in an embodiment of this application;

[0045] Figure 9 This is a flowchart illustrating the process of display device 200 filtering the first historical task set in an embodiment of this application;

[0046] Figure 10 This is a flowchart illustrating how the display device 200 adjusts the first historical task set in this embodiment of the application.

[0047] Figure 11 A schematic diagram of the structure of the tool library provided in the embodiments of this application;

[0048] Figure 12 This is a flowchart illustrating the task planning process of the display device 200 according to the tool library in this embodiment of the application.

[0049] Figure 13 This is a flowchart illustrating how the display device 200 plans tasks based on associated tasks in an embodiment of this application.

[0050] Figure 14 This is a flowchart illustrating the task execution of the display device 200 in this embodiment of the application;

[0051] Figure 15 This is an interactive schematic diagram of the display device 200 creating a fitness plan for a user in an embodiment of this application. Detailed Implementation

[0052] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0053] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0054] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0055] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0056] In this application embodiment, "display device" refers to a device with screen display and data processing capabilities. For example, display devices include, but are not limited to, smart TVs, mobile terminals, computers, monitors, advertising screens, wearable devices, virtual reality devices, and augmented reality devices.

[0057] Figure 1 This is a schematic diagram illustrating an operational scenario between a display device and a control device provided in some embodiments of this application. For example... Figure 1 As shown, users can operate the display device 200 via touch, voice, mobile terminal 300, and control device 100. For example, control device 100 can be a remote control, stylus, gamepad, etc.

[0058] like Figure 1 The diagram also shows that the display device 200 communicates with the server 400 (which may also be referred to as the cloud or cloud server) via various communication methods. The display device 200 can communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0059] Display device 200 can provide broadcast television reception function, and can also be equipped with intelligent network television function that provides computer support, including but not limited to network television, smart television, Internet Protocol television (IPTV), etc.

[0060] Figure 2 Provided for some embodiments of this application Figure 1 Hardware configuration block diagram of display device 200.

[0061] In some embodiments, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a user input interface 280, a memory, and a power supply.

[0062] In some embodiments, the communication device 220 is a component for communicating with external devices or the server 400 according to various communication protocol types. The display device 200 may be equipped with multiple communication devices 220 depending on the supported communication methods. The communication devices 220 can enable the display device 200 to communicate with the external devices or the server 400 via wireless or wired connections.

[0063] In some embodiments, detector 230 is used to acquire signals from the external environment or to interact with the outside world. For example, detector 230 includes a light receiver, a sensor for acquiring ambient light intensity; or, detector 230 includes an image acquisition device, such as a camera, which can be used to acquire external environmental scenes, user attributes, or user interaction gestures; or, detector 230 includes a sound acquisition device, such as a microphone, for receiving external sounds.

[0064] In some embodiments, device interface 240 is used to connect to an external device.

[0065] In some embodiments, the controller 250 is used to control the overall operation of the display device 200. The controller 250 may include at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processing unit (GPU), and a power processor, and a first to an nth interface for input / output. The controller 250 controls the operation of the display device 200 and responds to user operations through various software control programs stored in memory.

[0066] In some embodiments, the controller 250 and the tuner 210 may be located in different separate devices, that is, the tuner 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0067] In some embodiments, the display 260 is used to receive and display image signals output from the controller 250. The display 260 may include display function components for presenting images and driving components for driving image display.

[0068] In some embodiments, a user can input user commands on a graphical user interface (GUI) displayed on a display 260, and a user input interface 280 can receive user commands through the GUI.

[0069] In some embodiments, the audio output device 270 may be a built-in speaker of the display device 200 or an external audio output device connected to the display device 200.

[0070] In some embodiments, the user input interface 280 can be used to receive instructions from user input.

[0071] In some embodiments, to enable user interaction, the display device 200 may run an operating system. An operating system is a computer program that manages and controls the hardware and software resources of the display device 200. The operating system can control the display device to provide a user interface; for example, the operating system can directly control the display device to provide a user interface, or it can provide a user interface by running applications. The operating system also allows users to interact with the display device 200.

[0072] The operating system can be a native operating system based on a specific operating platform, a third-party operating system that is deeply customized based on a specific operating platform, or an independent operating system specifically developed for display devices 200.

[0073] An operating system can be divided into different modules or levels based on the functions it implements, for example... Figure 3 As shown, in some embodiments, the system can be divided into four layers, from top to bottom: the Applications layer (referred to as the "Application Layer"), the Application Framework layer (referred to as the "Framework Layer"), the System Runtime Library layer, and the Kernel Layer.

[0074] In some embodiments, the application layer provides services and interfaces for applications, enabling the display device 200 to run applications and interact with users based on the applications. For example, the application layer may include a voice assistant, which provides voice interaction functionality, allowing users to interact with the display device via voice.

[0075] The framework layer provides application programming interfaces (APIs) and programming frameworks for applications. The application framework layer includes predefined functions. It acts as a central processing unit, determining the actions taken by applications within the application layer. Through the API, applications can access system resources and obtain system services during execution.

[0076] In some embodiments, the system runtime library layer can provide support for the framework layer. When the framework layer is used, the operating system runs the instruction library contained in the system runtime library layer, such as the C / C++ instruction library, to implement the functions to be performed by the framework layer.

[0077] In some embodiments, the kernel layer is a functional layer situated between the hardware and software of the display device 200. The kernel layer can implement functions such as hardware abstraction, multitasking, and memory management.

[0078] It should be noted that the above examples are merely a simple division of operating system functions and do not limit the specific form of the operating system of the display device 200 in this application embodiment. Depending on the function of the display device, the type of operating system, and other factors, the number of levels and the specific level type of the operating system may be expressed in other forms.

[0079] The display device 200 can be configured with a planning function. Based on this function, when a user wants to create a plan, they can input their requirements for the plan into the display device 200. The display device 200 needs to plan the tasks to be performed according to these requirements and execute these tasks. The display device 200 summarizes the execution results of each task to obtain the corresponding plan.

[0080] Based on the above planning process, it is clear that the more requests users make, the more complex and time-consuming the process of the display device 200 in planning the tasks to be executed becomes. Furthermore, the number of planned tasks also increases, and consequently, the execution time takes longer. Therefore, the display device 200's planning efficiency is low, leading to a longer waiting time for users from inputting their requests to receiving the plan, resulting in a poor user experience.

[0081] To address the aforementioned issues, the display device 200 provided in this application embodiment can be configured to quickly obtain a target task set that matches the current plan by adjusting the historical task set, thereby improving the efficiency of plan formulation.

[0082] In this embodiment, the plan-making function configured on the display device 200 can be used to create various types of plans, thus it is a universally applicable function. Alternatively, the plan-making function configured on the display device 200 can be used to create plans of a specific type, thus it is a personalized function configured for a particular application. For example, the plan-making function configured on the display device 200 could be a function configured for a fitness application, used to create fitness-related plans.

[0083] In some embodiments, the display device 200 may have an agent application (also known as a smart agent application) installed, and the agent application provides the function of creating plans. Taking the function of creating plans as an example, which is configured for a fitness application, the agent application can be the fitness application. The agent application can provide one or more agent services (also known as smart agent services).

[0084] Figure 4A flowchart for formulating a first plan for the display device 200 in this application embodiment is shown below, with the specific steps as follows:

[0085] Step S401: In response to a first instruction to formulate a first plan by a user, obtain the user intent, first user information, and at least one first requirement of the user for the first plan according to the instruction content of the first instruction.

[0086] When a user wants to make a plan, they can give a first instruction to the display device 200 to make a first plan, where the first plan is the plan that the user wants to make this time.

[0087] In some embodiments, the first instruction may be a non-voice instruction. In one example, the display device 200 may display a planning page in response to a user's control instruction. This planning page may include one or more of the following: input boxes, selection items, scrolling items, etc. The input boxes may be used to input the content of the first instruction; the content corresponding to the selection items and scrolling items may also serve as instruction content. The display device 200 may, in response to a first instruction input by the user based on a generated item on the planning page or a confirmation key on the control device 100, determine that the first instruction is used to instruct the formulation of a first plan, and acquire the information corresponding to the input boxes, selection items, scrolling items, etc., and use this information as the instruction content of the first instruction.

[0088] In some embodiments, the first instruction may be a voice instruction. In one example, the display device 200 may support far-field voice functionality. The display device 200 may switch to a wake-up state in response to a wake-up word input by the user. In the wake-up state, the display device 200 may interact with the user via voice through an assistant application. In the wake-up state, the display device 200 may respond to a first instruction spoken by the user and may convert the first instruction into text data, which is the instruction content of the first instruction.

[0089] In this embodiment of the application, after receiving the first instruction, the display device 200 can execute the planned task through the large model.

[0090] In some embodiments, the large model can be integrated on the display device 200 side, that is, the large model is a local model, and the display device 200 can perform the planned tasks locally.

[0091] Combination Figure 3 The operating system shown allows for the configuration of assistant applications at the application layer for interaction with users; the configuration of an assistant framework at the framework layer, which provides the infrastructure and runtime environment, such as supporting assistant services; and the configuration of large models at the system runtime layer. These large models interact with components / modules / services supported by the assistant framework to execute planned tasks.

[0092] In some embodiments, the large model can be integrated on the server 400 side, that is, the large model is a cloud model, and the display device 200 needs to transmit the first instruction to the cloud model and receive the result of the task to be executed according to the plan returned by the cloud model.

[0093] Combination Figure 5 The illustrated architecture diagram shows that the display device 200 can be configured with an assistant application, and the server 400 can be configured with an assistant framework and a large model. The assistant application has the function of transmitting the user's initial input command to the server 400; for example, it can invoke the communication device 220 of the display device 200 to send the initial command to the server 400. The assistant framework and large model in the server 400 are similar to those described above for the assistant framework and large model integrated into the operating system, and will not be repeated here.

[0094] The display device 200 can input the instruction content of the first instruction into a large model, and the large model can analyze the instruction content and output the user intent, the first user information, and the user's first requirements for the first plan. In other words, the display device 200 uses the large model to obtain the user intent, the first user information, and the user's first requirements for the first plan.

[0095] If the first instruction is a voice instruction, the voice recognition module configured in the display device 200 can convert the first instruction into text data, and then input the text data into the large model. Alternatively, if the large model integrates Automatic Speech Recognition (ASR) functionality, the first instruction can be directly input into the large model, which will automatically convert it into text data.

[0096] The large model integrates Natural Language Processing (NLP) capabilities, which can perform semantic understanding of the instruction content of the first instruction, determine the user intent reflected by the instruction content, the first user information contained in the instruction content, and the first requirement.

[0097] In this context, user intent can indicate the type of plan the user wants to create, i.e., the type of the first plan. For example, if the user intent is fitness intent, it means that the first plan is a fitness plan.

[0098] The first user information may include the user's basic information, such as age, gender, height, weight, and health status.

[0099] The user's first requirement for the first plan is the basic requirement that the first plan must meet, such as time, purpose, and location.

[0100] The instruction content of the first instruction may include one or more first requirements. If it includes one first requirement, or the number of first requirements is less than or equal to n (n is a positive integer greater than 1), the instruction content of the first instruction is relatively simple; if it includes multiple first requirements, or the number of first requirements is greater than n, the instruction content of the first instruction is relatively complex. It is understandable that the display device 200 can formulate corresponding first plans for both simple and complex first instructions.

[0101] Figure 6 A timing diagram for a first plan is provided for the display device 200 in the embodiments of this application.

[0102] Combination Figure 6 The display device 200 interacts with the user through an assistant application. After receiving the first instruction input by the user through the assistant application, the display device 200 sends / transmits the first instruction to the assistant service in the assistant framework, and the assistant service inputs the instruction content of the first instruction into the large model. The large model outputs the user intent, the first user information, and the first request.

[0103] Figure 7 This is a flowchart illustrating how the display device 200 acquires user intent, first user information, and a first request in an embodiment of this application. The specific steps include:

[0104] Step S701: Obtain the user intent based on the instruction content of the first instruction.

[0105] Display device 200 can use large models to obtain user intent.

[0106] Step S702: Based on the user's intent, extract first user information and at least one first request from the first text.

[0107] The instruction content of the first instruction may contain information unrelated to the user's intent, such as user information and requirements unrelated to the user's intent. The display device 200 can utilize a large model to extract first user information and at least one first requirement related to the user's intent from the instruction content of the first instruction. This ensures that the extracted first user information and first requirement conform to the user's intent, thereby ensuring that the target task set subsequently obtained based on the first user information and first requirement conforms to the user's intent. Furthermore, it can effectively filter out other information in the first text, reducing the amount of extracted data, thereby improving the data processing efficiency of subsequently obtaining the target task set based on the first user information and first requirement, and further improving the efficiency of formulating the first plan.

[0108] The initial user information affects the degree to which the subsequently generated target task set matches the user's basic information, thus impacting the accuracy of the target task set. Specifically, the higher the completeness of the initial user information, the higher the accuracy of the generated target task set; conversely, the lower the completeness of the initial user information, or the absence of initial user information, the lower the accuracy of the generated target task set. For example, if the initial user information includes gender, tasks matching that gender can be planned. For instance, if the gender is female, when planning a task to find fitness styles, tasks suitable for women can be planned, such as low-intensity workouts or flexibility workouts. If the instruction information does not include gender information, it will be impossible to accurately plan tasks matching the user's actual gender. For instance, if the user's actual gender is male, when planning a task to find fitness styles, without knowing the user's gender information, it is impossible to accurately plan tasks matching the user's actual gender. This could result in planning flexibility workouts or other fitness styles unsuitable for men, leading to inaccurate task planning.

[0109] If the instruction content of the first instruction does not include the first user information, in order to improve the accuracy of the subsequent generation of the target task set, the display device 200 actively obtains the first user information.

[0110] In some embodiments, if the first instruction is a voice instruction, the display device 200 obtains the voice features corresponding to the first instruction and obtains the first user information based on the voice features.

[0111] In one example, the display device 200 may integrate a sound analysis / processing module, which can be used to acquire the speech features corresponding to the speech data. Thus, the display device 200 can acquire the speech features corresponding to voice commands through this module.

[0112] In one example, the large model can integrate sound analysis / processing functions to obtain the speech features corresponding to the speech data. Alternatively, the assistant framework can support sound analysis / processing services, and the large model can obtain the speech features corresponding to the speech data by calling these services. Thus, the display device 200 can utilize the large model to obtain the speech features corresponding to voice commands.

[0113] In some embodiments, speech features can be used to analyze the first user information of the corresponding user. Speech features may include one or a combination of several of the following: voiceprint features, frequency features, timbre features, intonation features, energy features, etc. It is understood that speech features are not limited to the features disclosed above.

[0114] Voice features can be used to analyze a user's primary information, such as determining the user's gender, mood, and health status.

[0115] In other embodiments, the display device 200 may display query information to prompt the user to input corresponding user information based on the query information, and the display device 200 shall determine the user information input by the user as the first user information.

[0116] The first user information extracted from the instruction content of the first instruction, or the first user information obtained based on the query information, has certain limitations and can easily affect the accuracy of the subsequently obtained target task set. To solve the above problems, the display device 200 can actively acquire some auxiliary information to update the first user information, thereby improving the richness and accuracy of the first user information.

[0117] In some embodiments, if the display device 200 is equipped with a positioning function, for example, if the display device 200 is equipped with a positioning module, the display device 200 can obtain the current positioning information in response to the first instruction, and can update the first user information based on the positioning information, for example, by adding the positioning information to the first user information. In this way, when planning tasks based on the updated first user information, the planning can be performed based on the positioning information therein.

[0118] In some embodiments, the display device 200 may be configured to record historical interaction information between the user and the display device 200 when the user uses the planning function of the display device 200. This historical interaction information may reflect the user's habits, preferences, interests, and other information. More specifically, this historical interaction information may reflect the user's habits, preferences, interests, and other information when making different types of plans.

[0119] Prior to the formulation of the first plan, the historical interaction information generated between the user's plan formulation and the display device 200 can also be referred to as historical instructions. For an explanation of historical instructions, please refer to the explanation of the first instruction above; it will not be repeated here.

[0120] Display device 200 can utilize relevant information extraction models, classification models, and tagging models to obtain summary information corresponding to each historical instruction. The summary information is used to characterize a specified dimension of the corresponding historical instruction. This specified dimension can include a summary of the historical instruction, key information, the user's personality, interests, etc. Accordingly, the summary information can include a summary of the historical instruction, key information of the historical instruction, the theme of the historical instruction, the personality tags corresponding to the historical instruction, and the interest tags corresponding to the historical instruction. In other words, the summary information can reflect the key points and outlines of the specific dialogue data when the user made a plan in the past, the theme (or type) of the plan, the user's personality, and the user's interests.

[0121] The display device 200 can store summary information, key events, topics, etc., from the summary information into a vector library, and store personality tags, interest tags, etc., into a tag library. Specifically, after receiving a user input instruction to formulate a plan, the display device 200 stores the summary information corresponding to that instruction (also called new summary information). When storing new summary information, the display device 200 updates the already stored summary information with the new summary information. For example, it can directly add new summary information, merge new summary information with already stored summary information, or delete new summary information.

[0122] In some embodiments, combined with Figure 5 The assistant framework can also support a memory module, which performs the task of storing summary information of historical instructions.

[0123] In some embodiments, the display device 200 may use summary information as supplementary information to update the first user information.

[0124] Figure 8 This is a flowchart illustrating the process of the display device 200 updating the first user information in this embodiment of the application. The specific steps are as follows:

[0125] Step S801: Obtain summary information corresponding to historical instructions.

[0126] The display device 200 can obtain summary information corresponding to each historical instruction from the corresponding library.

[0127] Step S802: Filter out the target summary information that matches the instruction content of the first instruction from the summary information.

[0128] Since each historical instruction indicates a different type of plan, the display device 200 needs to filter out target summary information from the summary information that matches the content of the first instruction. For example, the corresponding historical instruction indicates that the type of plan to be formulated is the same as the type of the first plan. The filtered target summary information can improve the matching degree with the user's current plan formulation needs and can also effectively reduce the amount of data that needs to be processed subsequently.

[0129] Step S803: Update the first user information based on the target summary information.

[0130] If the target summary information does not conflict with the first user information, the target summary information can be added to the first user information.

[0131] If the target summary information conflicts with the first user information, the conflicting target summary information can be deleted based on the first user information, or a conflict prompt can be displayed to prompt the user to confirm the user information to be used, and the user information confirmed by the user can be updated to the first user information.

[0132] Display device 200 can utilize the large model to execute steps S801-S803. Combined with... Figure 6 The large model can invoke the memory module supported by the assistant framework. For example, it can send a request to the memory module to retrieve summary information through the corresponding interface. This request can include relevant information such as the instruction content of the first instruction, which is used to filter the summary information. The memory module responds to the request, filters the target summary information, and feeds the target summary information back to the large model.

[0133] Therefore, the updated first user information can more accurately reflect the user's preferences, habits, and needs, and can further improve the accuracy of the target task set obtained subsequently based on the updated first user information.

[0134] In some embodiments, the display device 200 can utilize a large model to plan each task for realizing the user's intent based on each first requirement and first user information. It is evident that planning tasks involves a significant workload and requires a considerable amount of time.

[0135] In other embodiments, the display device 200 may utilize a historical task set to assist in planning tasks to achieve user intent, thereby reducing the workload of task planning and shortening the time required for task planning.

[0136] The historical task set corresponds to the historical instructions of the user to formulate the corresponding plan. In other words, the tasks contained in each historical task set are used to realize the user intent indicated by the historical instructions corresponding to the historical task set, that is, to formulate the plan indicated by the historical instructions.

[0137] In some embodiments, the display device 200 may be configured to store a set of historical tasks corresponding to each historical instruction.

[0138] In some embodiments, the display device 200 may be configured to process the historical task set corresponding to each historical instruction and store the processed historical task set.

[0139] In one example, the display device 200 filters successful tasks from the tasks contained in the historical task set. For example, a reflection assistant (also known as a reflection agent) can be built, and the reflection assistant filters successful tasks based on the historical instructions corresponding to the historical task set, the trajectory of each task execution, the execution results of each task, and the user's feedback on success or failure.

[0140] The display device 200 can group and cluster successful tasks according to historical instructions, and filter out high-quality successful tasks from each group that contain a number of subtasks less than or equal to a specified number.

[0141] The display device 200 can generate corresponding prompts for high-quality successful tasks in the historical task set. These prompts may include relevant content from the historical instructions, the thought process of the reflection assistant, and information about the tools used to execute the task.

[0142] Successful tasks in the historical task set, excluding high-quality successful tasks, are considered non-high-quality successful tasks. The display device 200 can generate corresponding prompt information for non-high-quality successful tasks. This prompt information may include the corresponding content in the instruction content of the historical instructions, the thought process of the reflection assistant, information about the tools called to execute the task, the call result returned by the called tools, rules for removing invalid / erroneous subtasks, etc.

[0143] The tasks in the historical task set that are not successful tasks are considered failed tasks. The display device 200 can generate corresponding prompt information for non-high-quality successful tasks and failed tasks. This prompt information is negative prompt information. This negative prompt information may include the corresponding content in the instruction content of the historical instruction, the thought process of the reflection assistant, the information of the tools called to execute the task, the call result returned by the called tools, and subtasks that have no positive effect on the instruction content.

[0144] In some embodiments, combined with Figure 5 The assistant framework also supports a task module, also known as a task decision-making and task retrieval module. This task module can perform the processing and storage of the aforementioned historical task sets.

[0145] Step S402: Obtain at least one set of historical tasks.

[0146] Display device 200 can retrieve at least one stored set of historical tasks.

[0147] Step S403: Select a first historical task set that matches the first instruction from at least one historical task set.

[0148] Figure 9 This is a flowchart of the display device 200 filtering the first historical task set in this embodiment of the application. The specific steps are as follows:

[0149] Step S901: Obtain the historical instructions corresponding to each historical task set in at least one historical task set.

[0150] The historical instructions may include the corresponding text data, and may also include the corresponding user intent, summary information, etc.

[0151] Step S902: Match the first instruction with each historical instruction, and / or match the first instruction with each task in each historical task set to obtain the matching result.

[0152] The matching result between the first instruction and the historical instructions can represent the degree of matching between the user intent corresponding to the first instruction and the historical instructions, the degree of semantic matching between the text data corresponding to the first instruction and the historical instructions, or the degree of information matching between the summary information corresponding to the first instruction and the historical instructions.

[0153] The matching result between the first instruction and the tasks in the historical task set can represent the degree of matching between the first requirement corresponding to the first instruction and the requirements satisfied by the tasks in the historical task set.

[0154] Step S903: Based on the matching results, select the first historical task set from at least one historical task set.

[0155] If the first instruction matches a historical instruction, it means that the first instruction matches the user intent, text data, and summary information corresponding to the historical instruction. The plan formulated based on the historical task set corresponding to the historical instruction has a high probability of meeting the user's needs for formulating the first plan.

[0156] If the first requirement corresponding to the first instruction matches the requirements met by the tasks in the historical task set, it means that the plan formulated based on the historical task set corresponding to the historical instruction can better meet the user's requirements for the first plan.

[0157] The matching results corresponding to the first historical task set filtered by the display device 200 can satisfy the first matching result and / or the second matching result. Specifically, the first matching result is that the first instruction matches the historical instruction corresponding to the first historical task set, and the second matching result is that the task in the first historical task set matches at least one first requirement corresponding to the first instruction.

[0158] The first historical task set includes prompts for various tasks, which are used to optimize and adjust the first historical task set in the future.

[0159] In some embodiments, it can be by Figure 5 The task module shown performs the task of filtering the first set of historical tasks.

[0160] Combination Figure 6 The large model can call the task modules supported by the assistant framework. For example, it can send a request to the task module to retrieve the historical task set through the corresponding interface. This request can include relevant information such as the instruction content of the first instruction, which is used to match it with the historical task set. The task module responds to the request, filters out the first historical task set, and feeds it back to the large model.

[0161] Step S404: Based on the user intent, the first user information, and at least one first requirement, adjust the tasks in the first historical task set to obtain the target task set.

[0162] Based on the first historical task set, the display device 200 adjusts the tasks according to user intent, first user information, and at least one first requirement, so as to quickly and accurately obtain the target task set that conforms to the user intent, user information, and user requirements of the first plan formulated this time.

[0163] Figure 10 This is a flowchart illustrating how the display device 200 adjusts the first historical task set in this embodiment of the application. The specific steps are as follows:

[0164] Step S1001: Select the first task from the tasks included in the first historical task set.

[0165] The first task is one that requires adjustment, such as deleting or adjusting parameters. Specifically, the first task does not match at least one of the following: user intent, first user information, and at least one first requirement.

[0166] Step S1002: Select the requirements to be planned from at least one primary requirement.

[0167] The requirements to be planned do not match the tasks in the first set of historical tasks, meaning that none of the tasks in the first set of historical tasks can meet or achieve the requirements to be planned.

[0168] Step S1003: Based on the user intent, the first user information, and at least one mismatched information in the first requirement, adjust the first task and add the second task corresponding to the requirement to be planned to the first historical task set to obtain the target task set.

[0169] The first task is adjusted so that it matches information that was not originally matched. For example, if the first task did not match the first user information before adjustment, the adjusted first task will match the first user information.

[0170] Add a second task corresponding to the planning requirement to the first set of historical tasks, and let the second task satisfy / realize the planning requirement.

[0171] Therefore, the target task set can accurately match user intent, primary user information, and tasks according to primary requirements.

[0172] In some embodiments, the large model can be configured to invoke tools that perform large model planning tasks. Figure 5 The assistant framework can also support tool libraries, which can include at least one toolset. Different toolsets can correspond to different scenarios. For example, the same toolset can correspond to different scenarios, and different toolsets can correspond to the same scenario. Each toolset can include at least one tool.

[0173] Figure 11 This is a schematic diagram of the tool library provided in an embodiment of this application. The tool library includes toolsets corresponding to scenarios such as movie-watching, education, gaming, and fitness. Specifically, the toolsets corresponding to the movie-watching scenario may include toolsets for watching TV series, and the toolsets corresponding to the fitness scenario may include fitness recommendation toolsets. Fitness recommendation toolsets may include weather forecast tools, fitness video search tools, fitness venue search tools, food management tools, recipe search tools, tourist attraction search tools, and memo tools.

[0174] When adjusting the first historical task set, the display device 200 can also plan tasks based on the tool library.

[0175] Figure 12 This is a flowchart illustrating the task planning process of the display device 200 according to the tool library in this embodiment of the application. The specific steps are as follows:

[0176] Step S1201: Obtain tool information for available tools.

[0177] In some embodiments, the scenarios corresponding to the toolset are related to user intents, wherein a user intent may correspond to at least one scenario. For example, a fitness intent may correspond to a fitness scenario; an entertainment intent may correspond to a movie-watching scenario and a game scenario.

[0178] Based on the correspondence between user intent and scenario, the display device 200 can determine the scenario corresponding to the current user intent and identify the toolset corresponding to that scenario. The tools in this toolset are the available tools for this planning. The tool information of the available tools may include the interface description information, such as the interface name, interface details, and the interface's input and output parameters.

[0179] Step S1202: Based on the tool information of the available tools, add a third task to the first historical task set. The third task has a corresponding available tool.

[0180] There is a correspondence between tools and tasks; that is, a tool is used to perform a corresponding task. Based on this correspondence, we can determine the third task corresponding to the available tools, which is the task corresponding to the current user intent, and thus the task required to achieve the current user intent.

[0181] Combination Figure 6 The large model can invoke a tool library, for example, by sending a request to the tool library to retrieve available tools. This request can include the user's intent. The tool library responds to the request, filters out available tools that match the user's intent, and feeds back the tool information of the available tools to the large model. The large model then adds a third task based on the tool information of the available tools.

[0182] In this way, when planning this task, we can use the tools available among these tools to ensure planning efficiency, improve the richness of the planned tasks, and ensure the feasibility of the planned tasks.

[0183] In some embodiments, the display device 200 may pre-establish a correspondence between user intents and associated tasks. The associated tasks of the user intents can be obtained through iterative learning of historical instructions using a large model. Based on the associated tasks of the user intents, the required tasks can be quickly planned.

[0184] Figure 13 This is a flowchart illustrating the task planning process of the display device 200 according to associated tasks in this embodiment of the application. The specific steps are as follows:

[0185] Step S1301: Obtain the associated task of the user intent.

[0186] The display device 200 can obtain the associated tasks corresponding to the current user intent, and these associated tasks can be used to enrich the planned tasks.

[0187] Step S1302: Obtain the fourth task in the associated tasks that is different from the task in the first historical task set.

[0188] Select a fourth task from the associated tasks that is different from all tasks in the first historical task set, in order to avoid adding associated tasks that are duplicated with tasks in the first historical task set.

[0189] Step S1303: Add the fourth task to the first historical task set to obtain the target task set.

[0190] Adding a fourth mission to the first historical mission set will give you the target mission set.

[0191] By directly adding user-intended related tasks to the first historical task set, the display device 200 can automatically expand the content that the user may need and formulate a richer first plan.

[0192] Combination Figure 6 The large model adjusts the first historical task set based on the information from each input, such as user intent, first user information, first requirement, first historical task set (including each prompt information), and tool information of available tools, to obtain the target task set.

[0193] Step S405: Call the target tools corresponding to each task in the target task set, and execute the corresponding tasks through the target tools to obtain the first plan.

[0194] The display device 200 determines the target tools corresponding to each task in the target task set, and executes the corresponding tasks by calling each target tool. The execution results constitute the first plan.

[0195] Figure 14 This is a flowchart of the task execution process of the display device 200 in this embodiment of the application. The specific steps are as follows:

[0196] Step S1401: Obtain the first type of tasks and the second type of tasks in the target task set.

[0197] The first type of task corresponds to the tasks in the first historical task set that have not been adjusted. That is, the first type of task is the original task in the first historical task set, which is a task that has been executed before. Therefore, the first type of task has a corresponding execution result.

[0198] The second category of tasks consists of tasks in the target task set other than those in the first category. In other words, tasks in the second category are not originally in the first historical task set and cannot be considered as tasks that have been executed before. Therefore, tasks in the second category do not have corresponding execution results.

[0199] Step S1402: If the first historical task set includes the execution results of each task, obtain the execution results of the first type of task from the first historical task set.

[0200] The execution results of the first type of task can be obtained directly from the first historical task set, thus eliminating the need to re-execute the first type of task and saving the time required to execute the first type of task.

[0201] Step S1403: Call the target tool corresponding to the second type of task, and execute the corresponding second type of task through the target tool to obtain the execution result of the second type of task.

[0202] Combination Figure 6 The large model calls the target tool corresponding to the second type of task. After executing the second type of task, the target tool feeds back the execution result to the large model.

[0203] Step S1404: The first plan is composed of the execution results of the first type of task and the execution results of the second type of task.

[0204] When the display device 200 executes tasks in the target task set, it can directly use the execution results of the first type of tasks and only need to execute the second type of tasks, thereby effectively reducing the number of tasks that actually need to be executed and improving the overall efficiency of task execution.

[0205] Step S406: Present the first plan.

[0206] Combination Figure 6 The large model returns the first plan to the assistant app, which then displays the first plan.

[0207] In some embodiments, the display device 200 may display the first plan in a manner that includes displaying the first plan in an assistant interaction interface or playing the first plan by voice.

[0208] The following example illustrates the process by which display device 200 formulates a first plan for a user through voice interaction.

[0209] Figure 15 This is an interactive schematic diagram illustrating how the display device 200 creates a fitness plan for a user, as shown in this embodiment of the application. Figure 15 As shown in Figure ①, after entering the fitness application, the display device 200 can respond to the wake word spoken by the user and display an assistant interaction interface. This assistant interaction interface can display the interaction between the fitness assistant and the user in the form of a dialogue. For example, the fitness assistant may first ask the user, "Please state your fitness needs."

[0210] Users can give their initial instructions, such as, "I want to work out. I enjoy outdoor sports like hiking, running, and swimming. Please help me create a fitness plan. I'm usually free on weekends, but I work overtime on weekdays and get home around 9 pm." Figure 15 As shown in Figure ②, the display device 200 can convert the first instruction into text data and display it in the assistant interaction interface. Simultaneously, the display device 200 will formulate a first plan based on the first instruction.

[0211] Display device 200 can use a large model to identify user intent as fitness intent and extract the first requirement, including a preference for outdoor activities such as hiking, running, and swimming, with the time scheduled after 9 PM on weekdays and weekends. The large model can obtain first user information based on the voice characteristics of the first command, and additionally obtain location information and target summary information by calling the memory module. The large model can call the task module to obtain the first historical task set and the tool library to obtain tool information for available tools. Combining the above information, the large model adjusts the first historical task set to obtain the target task set, which may include querying the weather, searching for attractions, searching for swimming pools, searching for ingredients, searching for recipes, and setting memos. The large model obtains the execution results of each task by calling the target tools corresponding to each task in the target task set and summarizes them into a first plan. This first plan could be: "On weekdays, you can go swimming at swimming pool A; on weekends, you can go hiking at mountain B and running at attraction C; design recipe D based on the ingredients in your refrigerator; a fitness memo has been set for you." Figure 15 As shown in ③, the display device 200 displays the first plan on the assistant interaction interface and can broadcast it via voice.

[0212] In some embodiments, a method for formulating a plan is also provided, which can be applied to the display device 200 provided in the embodiments of this application. The method includes: responding to a first instruction from a user to formulate a first plan; obtaining a user intent, first user information, and at least one first requirement of the user for the first plan based on the instruction content of the first instruction; obtaining at least one historical task set, the historical task set corresponding to a historical instruction from the user to formulate a corresponding plan; filtering out a first historical task set that matches the first instruction from the at least one historical task set; adjusting the tasks in the first historical task set according to the user intent, the first user information, and at least one first requirement to obtain a target task set; invoking the target tool corresponding to each task in the target task set, and executing the corresponding task through the target tool to obtain the first plan; and displaying the first plan.

[0213] The above technical solution has the following advantages or beneficial effects: In response to a user's instruction to formulate a first plan, the display device 200 can analyze the instruction content of the first instruction to accurately obtain the user's intent, first user information, and the user's first requirements for the first plan. The display device 200 can first filter out a first historical task set that matches the first instruction from the historical task set, and adjust the first historical task set according to the user's intent, first user information, and first requirements to quickly obtain a target task set that matches the first plan. This reduces the workload and time consumption of planning tasks, improves the efficiency of obtaining the target task set, and thus improves the efficiency of formulating the first plan.

[0214] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the discussion in some embodiments is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the contents of this disclosure, thereby enabling those skilled in the art to better utilize the embodiments.

Claims

1. A display device, characterized by comprising: include: The controller is configured as follows: In response to a first instruction from a user to formulate a first plan, the system obtains user intent, first user information, and at least one first requirement of the user for the first plan, based on the content of the first instruction; wherein the user intent indicates the type of the first plan. Obtain at least one set of historical tasks, the set of historical tasks corresponding to historical instructions from the user to formulate a corresponding plan; wherein, the tasks contained in the set of historical tasks are used to implement the historical plan formulated by the historical instructions; A first set of historical tasks that matches the first instruction is selected from the at least one set of historical tasks. Based on the user intent, the first user information, and the at least one first requirement, adjust the tasks in the first historical task set to obtain the target task set; The first plan is obtained by calling the target tools corresponding to each task in the target task set and executing the corresponding tasks through the target tools. Show the first plan; Specifically, the controller executes adjustments to the tasks in the first historical task set based on the user intent, the first user information, and the at least one first request to obtain the target task set, and is configured as follows: A first task is selected from the tasks included in the first historical task set, wherein the first task does not match at least one of the user intent, the first user information, and the at least one first request; From the at least one first requirement, a requirement to be planned is selected, wherein the requirement to be planned does not match any of the tasks in the first historical task set; Based on the user intent, the first user information, and the mismatch information in at least one first requirement, the first task is adjusted, and a second task corresponding to the requirement to be planned is added to the first historical task set to obtain the target task set.

2. The display device according to claim 1, characterized in that, The controller executes a first instruction in response to a user instruction to formulate a first plan, and based on the content of the first instruction, obtains the user's intent, user information, and at least one first requirement of the user for the first plan, specifically configured as follows: Based on the instruction content of the first instruction, obtain the user intent; Based on the user intent, the first user information and the at least one first request are extracted from the first text, where the first text refers to the text data corresponding to the instruction content of the first instruction.

3. The display device according to claim 1 or 2, characterized in that, The controller executes a first instruction in response to a user instruction to formulate a first plan, and based on the content of the first instruction, obtains the user's intent, first user information, and at least one first requirement of the user for the first plan, specifically configured as follows: If the instruction content of the first instruction does not include the first user information, when the first instruction is a voice instruction, the voice feature corresponding to the first instruction is obtained; Based on the voice features, the first user information is obtained.

4. The display device according to claim 3, characterized in that, The controller executes a first instruction in response to a user instruction to formulate a first plan, and, based on the content of the first instruction, obtains the user's intent, first user information, and at least one first requirement of the user for the first plan, and is further configured to: Obtain summary information corresponding to the historical instructions, wherein the summary information is used to characterize a specified dimension of the historical instructions; Target summary information that matches the instruction content of the first instruction is selected from the summary information; Update the first user information based on the target summary information.

5. The display device according to claim 1, characterized in that, The controller is configured to select a first set of historical tasks that matches the first instruction from the at least one set of historical tasks, specifically as follows: Obtain the historical instructions corresponding to each of the at least one historical task sets; The first instruction is matched with each of the historical instructions, and / or the first instruction is matched with the tasks in each of the historical task sets to obtain a matching result; Based on the matching result, the first historical task set is selected from the at least one historical task set, wherein the matching result corresponding to the first historical task set is a first matching result and / or a second matching result, the first matching result is that the first instruction matches the historical instruction corresponding to the first historical task set, and the second matching result is that the task in the first historical task set matches the at least one first requirement corresponding to the first instruction.

6. The display device according to claim 1, characterized in that, The controller executes adjustments to the tasks in the first historical task set based on the user intent, the first user information, and the at least one first request to obtain a target task set, and is further configured to: Obtain tool information for available tools; Based on the tool information of the available tools, a third task is added to the first historical task set, and the third task has a corresponding available tool.

7. The display device according to claim 1, characterized in that, The controller executes adjustments to the tasks in the first historical task set based on the user intent, the first user information, and the at least one first request to obtain the target task set, and is further configured to: Obtain the associated task of the user intent; Obtain the fourth task from the associated tasks that is different from the task in the first historical task set; The fourth task is added to the first historical task set to obtain the target task set.

8. The display device according to claim 1, characterized in that, The controller invokes the target tools corresponding to each task in the target task set, and executes the corresponding tasks through the target tools to obtain the first plan, which is specifically configured as follows: Obtain a first type of task and a second type of task from the target task set. The first type of task is the task that has not been adjusted in the first historical task set, and the second type of task is the task in the target task set other than the first type of task. If the first historical task set includes the execution results corresponding to each task, obtain the execution results corresponding to the first type of task from the first historical task set; Invoke the target tool corresponding to the second type of task, and execute the corresponding second type of task through the target tool to obtain the execution result of the second type of task; The first plan is composed of the execution results of the first type of task and the execution results of the second type of task.

9. A method for formulating a plan, characterized in that, Applied to a display device, the method includes: In response to a first instruction from a user to formulate a first plan, the system obtains user intent, first user information, and at least one first requirement of the user for the first plan, based on the content of the first instruction; wherein the user intent indicates the type of the first plan. Obtain at least one set of historical tasks, the set of historical tasks corresponding to historical instructions from the user to formulate a corresponding plan; wherein, the tasks contained in the set of historical tasks are used to implement the historical plan formulated by the historical instructions; A first set of historical tasks that matches the first instruction is selected from the at least one set of historical tasks. Based on the user intent, the first user information, and the at least one first requirement, adjust the tasks in the first historical task set to obtain the target task set; The first plan is obtained by calling the target tools corresponding to each task in the target task set and executing the corresponding tasks through the target tools. Show the first plan; The step of adjusting the tasks in the first historical task set according to the user intent, the first user information, and the at least one first requirement to obtain the target task set includes: A first task is selected from the tasks included in the first historical task set, wherein the first task does not match at least one of the user intent, the first user information, and the at least one first request; From the at least one first requirement, a requirement to be planned is selected, wherein the requirement to be planned does not match any of the tasks in the first historical task set; Based on the user intent, the first user information, and the mismatch information in at least one first requirement, the first task is adjusted, and a second task corresponding to the requirement to be planned is added to the first historical task set to obtain the target task set.

Images