Distributed cross-screen display method and system based on digital thread

Abstract

The invention discloses a distributed cross-screen display method and system based on a digital thread, and relates to the field of distributed computing resource management.The method comprises the steps that in response to cross-screen operation of a user, a first device captures and generates an operation context information packet; the digital thread scheduler receives the operation context information packet and creates a digital thread instance corresponding to the screen-crossing task; the digital thread scheduler gathers user interaction event streams from the digital thread instance associated equipment, and models and analyzes the user interaction event streams based on a preset focus analysis rule base; when the residual signal intensity of the node with the highest priority in the attention migration priority list exceeds a preset threshold value, triggering a pre-scheduling decision process; and performing dynamic resource pre-scheduling and preheating operation on the target equipment and the target content area according to the resource state table. According to the invention, the target device can realize instant rendering and response directly based on the pre-heating ready resources, so that real non-perceptual cross-screen experience is realized on the system level.

Description

Technical Field

[0001] This invention relates to the field of distributed computing resource management, and in particular to a distributed cross-screen display method and system based on digital threads. Background Technology

[0002] In multi-device collaboration scenarios, achieving efficient and seamless cross-screen display is key to improving user experience. Currently, a responsive delivery mechanism based on explicit user commands is typically used. When a user performs a cross-screen operation such as dragging, the source device captures the current application state and generates a data packet, which is then transmitted to the target device via the network. After receiving and parsing the data packet, the target device starts the corresponding application instance and rendering process to complete the content display. This technical path is clear and serves as a fundamental solution for achieving cross-device content migration.

[0003] Responsive mechanisms inherently suffer from serial latency in their processing flow. The linear sequence of operation-capture-transmission-initialization-rendering means that the entire process from the completion of a user operation to the presentation of a usable interface on the target device must sequentially experience network transmission latency, target application cold start latency, and rendering latency. Existing technologies improve individual stages by optimizing coding efficiency, increasing network bandwidth, and accelerating local rendering, but they fail to fundamentally change the passive response working mode. Resources are only scheduled after the user operation is completed, failing to address the user's potential intent formation stage or the operation execution process. As a result, even after the focus switches, the user will still perceive a wait due to the lag in resource readiness. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a distributed cross-screen display method based on digital threads to solve the perceptible delay caused by resource readiness lag, and achieve a seamless cross-screen interactive experience.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a distributed cross-screen display method based on digital threads, which includes, in response to a user's cross-screen operation, a first device capturing and generating an operation context information packet; The digital thread scheduler receives the operation context information packet and creates a digital thread instance corresponding to this cross-screen task. The digital thread scheduler aggregates user interaction event streams from devices associated with digital thread instances and models and analyzes these event streams based on a pre-defined focus analysis rule base. When the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold, the pre-scheduling decision process is triggered. Dynamic resource pre-scheduling and preheating operations are performed on the target equipment and target content area based on the resource status table; When the user's actual interaction focus switches to the target device, the target device, based on the result of the preheating operation, obtains content presentation and interaction response without perceptible delay.

[0007] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, in response to a user's cross-screen operation, a first device captures and generates an operation context information packet, including the following steps: By dragging and dropping graphical interface controls, a cross-screen operation is initiated from the first device to the second device. The agent program of the first device captures the cross-screen operation and records the network identifier of the first device, the display content identifier and version in the application, and a snapshot of the display status of the first device. The agent program of the first device obtains the network identifier of the second device specified by the user; The network identifier of the first device, the display content identifier and version, the display status snapshot, and the network identifier of the second device are encapsulated into an operation context information packet.

[0008] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, the digital thread scheduler receives an operation context information packet and creates a digital thread instance corresponding to the current cross-screen task, including the following steps: Based on the operation context information packet received by the digital thread scheduler, a globally unique string is generated as a thread identifier. Using the thread identifier as an index, an empty list of associated devices is initialized. Add the network identifiers of the first device and the second device to the list of associated devices; The digital thread scheduler creates a data structure that combines and encapsulates the thread identifier, the list of associated devices, the display content identifier and version in the operation context information packet, and the display status snapshot of the first device in the operation context information packet to form a digital thread instance corresponding to this cross-screen task.

[0009] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, the digital thread scheduler aggregates user interaction event streams from devices associated with digital thread instances, and models and analyzes the user interaction event streams based on a preset focus analysis rule base, including the following steps: The device and content regions within the digital thread instance are constructed as potential energy nodes in the attention field. Based on the real-time distribution of user interaction event streams, attention potential energy contour maps are drawn. Gradient clustering and time window stability analysis methods are used to determine the regions with stable potential energy peaks as the current semantic focus devices and focus regions. The focus analysis rule base analyzes the disturbance ripples generated by the user interaction event flow in the attention potential field, and performs multi-scale decomposition of the disturbance ripples by applying time-frequency analysis technology that combines wavelet packet transform and Hilbert-Huang transform. When the analysis results show that the power spectral density of the disturbance ripple is concentrated in the low frequency band and the envelope amplitude shows a continuous high energy characteristic, and the instantaneous phase shows high coherence, it is determined to show low frequency and high energy resonance characteristics, indicating a deep coupling between neuronal motion and cognitive load, and determining that the current focus is in a state of deep immersion fine operation. The focus analysis rule base activates the digital meridians associated with the current semantic focus; The focus analysis rule base initiates a virtual attention pulse transmission along the digital meridian starting from the current focus. For other devices or content areas within the digital thread instance, the semantic correlation degree matching algorithm is used to evaluate the residual signal strength when the virtual attention pulse arrives. The focus analysis rule base compares the residual signal strength of each transmission path and selects target nodes with residual signal strength exceeding the threshold as candidate attention transfer points; Based on the residual signal strength, generate an attention transfer priority list, and then proceed according to the attention transfer priority list; Based on the progressive context injection and state consistency verification method, an attention transfer mechanism is triggered to synchronously transmit the operation context, interaction state, and semantic information related to the current focus to high-priority nodes. The focus analysis rule base records the residual signal intensity distribution of this virtual attention impulse transmission. Through a feedback learning mechanism that compares the predicted signal intensity with the actual focus migration results, the transmission of the digital meridian is updated.

[0010] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, when the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold, a pre-scheduling decision process is triggered, including the following steps: The pre-scheduling engine queries the digital meridian transmission efficiency weight map to obtain the digital meridian transmission efficiency value from the current semantic focus device to the pre-scheduling target node; The pre-scheduling engine aggregates the computing resource utilization, memory usage, network bandwidth and latency metrics of each associated device within a digital thread instance to construct a real-time resource status table. The pre-scheduling engine encodes the real-time resource status table into digital physiological state vectors for each device, and inputs the path readiness coefficient and the digital physiological state vector of the pre-scheduling target node into the pre-scheduling decision model. Based on the path readiness coefficient and digital physiological state vector, the required digital metabolic preheating intensity level for the pre-scheduled target node is determined, and the corresponding biological instruction set is generated according to the digital metabolic preheating intensity level.

[0011] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, the dynamic resource pre-scheduling and preheating operation for the target device and target content area according to the resource status table includes the following steps: The digital thread scheduler parses the computational resource tilt instructions in the biological instruction set and extracts the digital signal parameters of the analog preload. The digital thread scheduler injects analog preload digital signal parameters into the operating unit of the target device; The target device's operating unit receives digital signal parameters for simulated preload, inducing the computing resource scheduler to enter a ready state. The digital thread scheduler parses the data preload instructions in the biological instruction set and extracts the preload data identifier and digital digestion path. The digital thread scheduler initiates the digital digestion process along the digital digestion path for the content pointed to by the preloaded data identifier; The digital digestion process transforms the content pointed to by the preloaded data identifier from the storage format into an intermediate format that is close to the rendering state; The digital thread scheduler parses the network bandwidth reservation instruction in the biological instruction set, extracts the immune channel establishment parameters, and establishes the immune channel on the data transmission path based on the immune channel establishment parameters. Once the immune channel is established, background traffic is allowed to pass through, and high-priority forwarding is triggered for specific data patterns belonging to the preheating instruction set. The digital thread scheduler confirms that the target device's computing resource scheduler is in a ready state, the preloaded data has been digitally digested, and the immune channel has been established, thereby obtaining dynamic resource pre-scheduling and preheating operations for the target device and target content area.

[0012] As a preferred embodiment of the distributed cross-screen display method based on digital threads described in this invention, when the user's actual interactive focus switches to the target device, the target device obtains content presentation and interactive response with no perceptible delay based on the result of the warm-up operation, including the following steps: The actual interaction focus is switched to the target device, the target device captures the user's first interaction input, and the operation unit of the target device schedules the execution of the rendering tasks related to the target content area at the real-time level. Read pre-warmed data blocks from the target device's local cache, and composite the read data blocks with the rendering subtask results from the auxiliary computing node; the pixel data generated by the composite rendering is passed through a high-priority network queue. The system reads pixel data from the display frame buffer and refreshes the screen, processes the initial captured interactive input, and generates interactive response commands. Secondly, the present invention provides a distributed cross-screen display system based on digital threads, including a proxy module that, in response to a user's cross-screen operation, captures and generates an operation context information packet by a first device; The module is created by the digital thread scheduler receiving the operation context information packet and creating a digital thread instance corresponding to this cross-screen task. The analysis module, the digital thread scheduler, aggregates user interaction event streams from devices associated with digital thread instances, and models and analyzes the user interaction event streams based on a preset focus analysis rule base; The pre-scheduling module triggers the pre-scheduling decision process when the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold. The preheating operation module performs dynamic resource pre-scheduling and preheating operations on the target device and target content area based on the resource status table. The interaction response module, when the user's actual interaction focus switches to the target device, the target device obtains content presentation and interaction response without perceptible delay based on the result of the preheating operation.

[0013] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the distributed cross-screen display method based on digital threads as described in the first aspect of the present invention.

[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the distributed cross-screen display method based on digital threads as described in the first aspect of the present invention.

[0015] The beneficial effects of this invention are as follows: By constructing an intelligent closed loop of intent prediction and resource preheating, the response paradigm of cross-screen interaction is changed. Based on digital threads, cross-screen tasks are globally coordinated. By utilizing the attention field model and digital meridian transmission mechanism, the user interaction event flow is analyzed in real time, and the potential targets and probabilities of attention migration are accurately predicted. This achieves a leap from event-driven to intent prediction-driven, eliminating decision delay. Based on the prediction results and real-time resource status, multi-dimensional pre-scheduling instructions are generated to perform forward-looking collaborative preheating of the target device's computing resources, data format, and network channels. The unavoidable serial cold start delay in traditional interaction is transformed into a preparatory process executed in parallel in the background. When the user actually switches focus, the target device can directly achieve instant rendering and response based on the preheated and ready resources, thereby achieving a truly seamless cross-screen experience at the system level. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a distributed cross-screen display method based on digital threads.

[0018] Figure 2 This is a schematic diagram of a distributed cross-screen display system based on digital threads. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "example" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the invention. The appearance of an embodiment in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0022] Reference Figures 1-2 This is one embodiment of the present invention, which provides a distributed cross-screen display method based on digital threads, including the following steps: S1. In response to the user's cross-screen operation, the first device captures and generates an operation context information packet.

[0023] S1.1. By dragging and dropping graphical interface controls via touch, a cross-screen operation is initiated from the first device to the second device. The agent program of the first device captures the cross-screen operation and records the network identifier of the first device, the display content identifier and version in the application, and a snapshot of the display status of the first device.

[0024] Furthermore, when a cross-screen operation is initiated by dragging and dropping graphical interface controls, the agent program located on the first device will capture this specific user interaction intent signal in real time. The capture operation is not just a simple recording of a drag-and-drop end event, but also a simultaneous extraction and recording of multiple key metadata closely related to the first device's own state and the current display content, including the first device's unique network identifier in the current network, the display content identifier and version within the application to which the graphical interface control being dragged belongs, and a snapshot of the first device's display state at the moment the dragging action occurs.

[0025] Specifically, for example, when a user drags a specific paragraph of an edited document from a tablet to a smart TV, the agent records not only the document's filename, but also information that constitutes a snapshot of the display state, such as the document's current editing state, cursor position, and applied formatting, as well as the tablet's network address. This refined context capture is the core capability of the first-device agent, providing a precise and reproducible starting point for the entire cross-screen process, ensuring the integrity and continuity of the migrated content, and avoiding the problem of context loss in traditional simple file or screen mirroring transfers. The direct goal of this step is to capture and record the operational context on the first device side.

[0026] S1.2 The agent program of the first device obtains the network identifier of the second device specified by the user.

[0027] Furthermore, after successfully capturing and recording the operational context of the first device, the agent program of the first device needs to clearly define the target endpoint to which the user intends to send the request. The agent program obtains the network identifier of the second device specified by the user by parsing the release point coordinates of the drag-and-drop operation or receiving explicit selection instructions from the user. It then parses a target device name and, more importantly, obtains the network identifier of the second device that allows it to be uniquely addressed and communicated in the current distributed network environment. This identifier includes the second device's IP address and port, unique device code, or logical address in the distributed soft bus. Obtaining the network identifier of the second device establishes a clear path from source to destination.

[0028] Specifically, for example, in a conference room environment containing multiple smart display devices, a user drags content to a large screen on one side of the room. The agent program can then use spatial awareness or device list selection to resolve the network address of the specific large screen device. Identifying the network identifier of the second device is a prerequisite for establishing a cross-device communication link and ensuring that the operation context information packet can be accurately delivered. It transforms cross-screen operation from an abstract intention into a specific task with a clear physical or logical destination. Successfully obtaining the network identifier of the second device specified by the user is a condition for the completion of this step.

[0029] S1.3. Encapsulate the network identifier of the first device, the display content identifier and version, the display status snapshot, and the network identifier of the second device into an operation context information packet.

[0030] Furthermore, after completing the recording of the first device's own context and the target location of the second device, the agent program of the first device will perform a packaging operation. The packaging operation is not simply packaging the recorded data, but rather integrating the four key types of information—the network identifier of the first device, the display content identifier and version, the display status snapshot, and the network identifier of the second device—into a self-contained and self-describing operation context information package according to a predefined or extensible structured format.

[0031] Specifically, the information packet itself carries sufficient information so that the subsequent digital thread scheduler can understand the source, target, content, and initial state of the cross-screen task without repeatedly querying the first device. The format design of the operation context information packet supports efficient serialization and deserialization, facilitating transmission over the network and parsing by the digital thread scheduler. The encapsulation process ensures that the core intent and initial state of the cross-screen task are transmitted completely and unambiguously, providing a unique and sufficient data foundation for creating digital thread instances. The generation of a complete operation context information packet containing all the necessary start-up information of the cross-screen task marks the completion of the first device's capture and encapsulation responsibilities in this cross-screen operation.

[0032] S2. The digital thread scheduler receives the operation context information packet and creates a digital thread instance corresponding to this cross-screen task.

[0033] S2.1 Based on the operation context information packet received by the digital thread scheduler, generate a globally unique string as a thread identifier, and initialize an empty list of associated devices using the thread identifier as an index. Furthermore, the generation of thread identifiers typically combines multiple factors such as timestamps, random numbers, and device identifiers to ensure absolute uniqueness in a distributed environment. After generation, the digital thread scheduler uses this thread identifier as an index to initialize an empty list of associated devices in memory or distributed storage. The purpose of this operation is to establish a logical central control center and namespace for upcoming cross-screen tasks that may involve the collaboration of multiple devices. The thread identifier acts as a unique key to this center throughout its entire lifecycle, while the list of associated devices serves as a dynamic register recording all device members participating in this collaborative task.

[0034] Specifically, when a user initiates a cross-screen operation from their phone to a smartwatch, the digital thread scheduler generates an identifier similar to CrossScreenTask_20231027_ABCD1234 and prepares a list, which is initially empty, waiting to record the identity information of the phone and the smartwatch. It generates a globally unique thread identifier and initializes an empty list of associated devices, completing the first step of creating an independent and traceable logical entity for the cross-screen task.

[0035] It should be noted that after receiving the operation context information packet, the digital thread scheduler parses its structure and extracts core metadata fields, including timestamp, source device network identifier, content identifier, and version. The scheduler inputs these fields along with a high-strength random salt value into a cryptographic hash function for calculation, outputting a collision-resistant fixed-length hash value. This hash value is determined as the globally unique thread identifier for this cross-screen task. The generation strategy ensures that even if the metadata fields are completely identical, the identifier generated at different times will be completely different due to the introduction of the random salt value, thus guaranteeing the uniqueness of task instances in a distributed environment. After generating the thread identifier, the digital thread scheduler immediately uses this identifier as the primary key to create a new record in memory or a distributed key-value store, and initializes an empty, dynamically expandable list under this record. This list is defined as the associated device list. Through the cryptographic hash transformation of the packet metadata and the immediate initialization of structured storage, a unique and reliable index foundation and dynamic member register are established for the entire lifecycle management of the cross-screen task.

[0036] S2.2 Add the network identifier of the first device and the network identifier of the second device to the list of associated devices.

[0037] Furthermore, the digital thread scheduler needs to extract device identity information directly related to the current task from the received operation context information packet. The scheduler parses the operation context information packet to obtain the network identifier of the first device and the network identifier of the user-specified second device, and adds these two network identifiers to the previously associated device list indexed by the thread identifier. This addition operation is not merely a simple list filling; it formally declares that the first and second devices have been included in the management scope of this cross-screen task represented by the thread identifier, marking these two devices as the initial associated members of this digital thread instance.

[0038] Specifically, by adding network identifiers to the list, the digital thread scheduler can address, track the status of, and distribute instructions to the first and second devices based on these identifiers. For example, when the operation context information includes the IP address of the mobile phone and the Bluetooth MAC address of the smartwatch, the digital thread scheduler will add these two address information as entries to the associated device list, thus completing the operation of adding the network identifiers of the first and second devices to the associated device list and establishing the set of devices directly managed by the digital thread instance.

[0039] S2.3 The digital thread scheduler creates a data structure that combines and encapsulates the thread identifier, the list of associated devices, the display content identifier and version in the operation context information packet, and the display status snapshot of the first device in the operation context information packet to form a digital thread instance corresponding to this cross-screen task.

[0040] Furthermore, after establishing the task identifier and initial device list, the digital thread scheduler performs final integration and encapsulation to form a complete digital thread instance. The digital thread scheduler creates a specific data structure that combines and encapsulates four types of information: the thread identifier generated in previous steps, the list of associated devices containing the network identifiers of the first and second devices, the display content identifier and version carried in the operation context packet, and a snapshot of the display state of the first device. This combination and encapsulation is not a simple stacking of elements, but rather the construction of a self-contained, structured task state object—the digital thread instance.

[0041] Specifically, a digital thread instance uses a thread identifier as its unique key, an internal list of associated devices records the task participants, a display content identifier and version clearly define the object of the task operation, and a snapshot of the first device's display state saves the task's initial state. This makes the digital thread instance a complete logical entity containing core information such as who is performing the task, what they are doing, and from what state it starts. The creation of a digital thread instance transforms a one-time cross-screen operation command into a persistent, schedulable, updatable, and manageable dynamic process object, forming a digital thread instance that includes a thread identifier, a list of associated devices, a display content identifier and version, and a snapshot of the first device's display state.

[0042] S3, the digital thread scheduler, aggregates user interaction event streams from devices associated with digital thread instances and models and analyzes these event streams based on a preset focus analysis rule base.

[0043] S3.1 Construct the device and content regions within the digital thread instance into potential energy nodes in the attention field, draw an attention potential energy contour map based on the real-time distribution of user interaction event streams, and use gradient clustering and time window stability analysis methods to determine the regions with stable potential energy peaks as the current semantic focus devices and focus regions.

[0044] Furthermore, the digital thread scheduler continuously collects user interaction event streams from all devices associated with the digital thread instance, including but not limited to raw events such as touch coordinates, mouse movements, keyboard input, gaze focus, and changes in the state of UI controls. To understand the distribution of user attention from these discrete event streams, the digital thread scheduler abstracts each physical device within the digital thread instance and its key content display area as a potential node in the attention field.

[0045] Specifically, user interactions at different locations and of different types are quantified as attention energy injected into corresponding nodes. Based on the real-time distribution of event streams, the digital thread scheduler can dynamically draw an attention potential energy contour map of the entire cross-screen environment. By applying gradient clustering algorithms, the digital thread scheduler can identify peak regions where potential energy accumulates in the map. Combined with time window stability analysis, it can eliminate short-lived, sporadic interaction noise, identifying regions that maintain high and stable potential energy over a sustained period as the current semantic focus device and focus area. This modeling approach unifies dispersed multi-device interactions into a continuous, measurable attention field model, thereby accurately and stably locating the user's true and continuous attention focus in a multi-device environment. For example, when drawing with a pen on a tablet, the drawing area of ​​the tablet forms a high and stable potential energy peak, which is identified as the semantic focus.

[0046] It should be noted that abstracting devices and content areas as potential energy nodes in an attention field draws on the concepts of potential field and potential energy in classical physics. This establishes a unified measurement and synthesis framework for heterogeneous interactive events. Each device or content area becomes a potential well that can accumulate attention energy. Different types of interactive events (such as touch, gaze, and voice) are assigned different energy weights and injected into the corresponding nodes, thereby generating a dynamically evolving virtual scalar field in the space composed of device topology and content layout. This maps the originally scattered, heterogeneous, and difficult-to-compare cross-device interactive data (such as swiping on a mobile phone and staring on a TV) onto the same physical quantity—potential energy, and forms a contour map in a continuous mathematical space. This allows subsequent analysis to use mature field theory mathematical tools (such as gradient and divergence) and image processing methods (such as clustering) to handle interaction problems, realizing a paradigm shift from discrete event analysis to continuous field analysis. This not only achieves global and continuous perception of attention distribution, but more importantly, it makes the definition of attention focus no longer dependent on threshold judgment of a single event type, but based on the structural characteristics of the entire field (such as stable potential energy peaks).

[0047] S3.2 The focus analysis rule base analyzes the disturbance ripples generated by the user interaction event flow in the attention potential field, and performs multi-scale decomposition of the disturbance ripples by applying time-frequency analysis technology combining wavelet packet transform and Hilbert-Huang transform. When the analysis results show that the power spectral density of the disturbance ripple is concentrated in the low frequency band and the envelope amplitude shows a continuous high energy characteristic, and the instantaneous phase shows high coherence, it is determined to show low-frequency, high-energy resonance characteristics, indicating a deep coupling between neuronal motion and cognitive load, and it is determined that the current focus is in a state of deep immersion and fine operation.

[0048] Furthermore, the focus analysis rule base performs signal processing on the user interaction event stream extracted from the current semantic focus device and focus region, transforming the time series of event intensity into a local perturbation ripple signal of the attention potential field at that point. The focus analysis rule base first applies wavelet packet transform to perform multi-scale decomposition of the perturbation ripple signal, decomposing the signal into different frequency sub-bands to simultaneously capture the local features of the signal in both the time and frequency domains, identifying high-frequency components generated by brief, rapid operations and low-frequency components generated by continuous, stable operations. The focus analysis rule base further applies Hilbert-Huang transform to the decomposed signal, especially the low-frequency dominant components, through empirical mode decomposition. The intrinsic mode functions of the signal are obtained, and the Hilbert spectrum of each component is calculated to accurately extract the instantaneous amplitude envelope and instantaneous phase information of the signal. The focus analysis rule base analyzes the characteristics of the processed signal, calculates the power spectral density to confirm whether the energy is concentrated in the low frequency band, observes whether the amplitude envelope is maintained at a high level within the time window, and evaluates the coherence measure of the instantaneous phase sequence. The focus analysis rule base determines that the disturbance ripple exhibits low-frequency, high-energy resonance characteristics if and only if the three conditions of power spectral density being concentrated in the low frequency band, envelope amplitude exhibiting sustained high-energy characteristics, and instantaneous phase exhibiting high coherence are met simultaneously. Based on this, it is determined that the current focus is in a state of deep immersion and fine operation.

[0049] Specifically, through the medium of perturbation ripples, the signal is mapped and deconstructed into a combination of time-frequency domain signal features that reflect the microscopic neurocognitive state. Wavelet packet transform is used as a pre-filter, leveraging its multi-resolution characteristics to adaptively remove high-frequency noise from the interaction signal caused by unconscious jittering, accidental touches, etc., while preserving and enhancing the low-frequency main components dominated by purposeful and coherent fine-grained operations. Hilbert-Huang transform is used as a post-demodulator to perform essential mode decomposition and Hilbert spectrum analysis on the low-frequency main components after high-frequency noise has been filtered out, thereby accurately decoupling the envelope amplitude representing the stability of the operation intensity and the value representing motion. The two independent but related physical quantities, the temporal consistency of cortical output and the instantaneous phase, construct a feature extraction pipeline that progresses from the original interaction event to the purified low-frequency main signal, and then to the amplitude envelope and instantaneous phase. The pipeline can effectively resist the inherent non-stationarity and sudden noise interference in the interaction signal, ensuring that the low-frequency, high-energy, and highly coherent resonance features used to determine the deep immersion state are extracted from real cognitive load signals, rather than being fabricated by accidental and transient operating patterns. This greatly improves the reliability of state determination and the explanatory power of neuroergonomics.

[0050] It should be noted that the focus analysis rule base performs signal transformation on the time series of user interaction event intensity extracted from the current semantic focus region, forming a continuous local perturbation ripple signal. After wavelet packet transformation, the signal is decomposed into a series of sub-band signals covering different frequency ranges through a multi-stage filter bank. This clearly separates the high-frequency transient components and low-frequency persistent components in the original signal in the time-frequency domain. The high-frequency sub-band mainly captures noise generated by accidental touches or rapid browsing, while the low-frequency sub-band retains the core signal components generated by fine and coherent operations. Hilbert-Huang transform is applied to the separated low-frequency dominant signal components, and the signal is adaptively decomposed into several intrinsic mode functions (EMFs) through the empirical mode decomposition algorithm. A Hilbert transform is then performed on each EMF to obtain a result that accurately reflects the signal energy. The instantaneous amplitude envelope sequence, which varies with time, and the instantaneous phase sequence, which can characterize the periodic temporal structure of the signal, are used to calculate the power spectral density of the low-frequency subband signal to quantify the concentration of its energy in the frequency domain. The mean and variance of the instantaneous amplitude envelope within the sliding time window are statistically analyzed to assess its sustained high-energy characteristics. The coherence coefficient of the instantaneous phase sequence within the corresponding time window is calculated to measure its phase stability. When the power spectral density analysis confirms that the energy is concentrated in the low-frequency band, and the instantaneous amplitude envelope statistics show sustained high-level fluctuations, and the instantaneous phase coherence coefficient exceeds the preset stability threshold, the focus analysis rule base determines that the disturbance ripple signal has resonance characteristics of low frequency, high energy, and high phase coherence. Based on this, it is inferred that there is a deep coupling between user operation and cognitive load, thereby determining that the current focus is in a state of deep immersion and fine operation.

[0051] S3.3 The focus analysis rule base activates the digital meridians associated with the current semantic focus.

[0052] Furthermore, based on the determination of the current semantic focus and its deep immersion state, the focus analysis rule base needs to determine the potential paths that user attention may migrate. The focus analysis rule base activates the digital meridians associated with the current semantic focus. The digital meridians are predefined or historically learned logical association channels that connect the current focus with other devices or content areas within the digital thread instance.

[0053] Indeed, activation means that the focus analysis rule base moves these potential migration paths from a dormant state to an evaluation state, ready for signal transmission simulation. The activation of digital networks relies on information such as semantic association graphs, device spatial relationships, and user historical behavior patterns. For example, when the current semantic focus is a design document on a tablet, the associated digital network might point to a smart TV in the living room or a desktop monitor in the study, depending on the document content, device usage, and historical habits.

[0054] It should be noted that, based on the device and content identifiers of the current semantic focus, a multimodal association graph database is queried, including a predefined semantic association graph, a topological graph recording the physical and logical location relationships between devices, and a user-personalized behavior pattern graph mined from historical digital thread instances. The query operation returns a set of target nodes and their associated metadata that are directly or indirectly related to the current semantic focus. For each candidate target node, the focus analysis rule base calculates a comprehensive association strength score, which integrates the content relevance from the semantic association graph, the spatial proximity from the topological graph, and the historical migration probability from the behavior pattern graph. The focus analysis rule base sets an activation threshold based on the comprehensive association strength score and marks the association paths corresponding to candidate target nodes with scores exceeding this threshold as active. Each activated path becomes a digital meridian, whose data structure includes metadata such as the source node, target node, unique identifier of the path, comprehensive association strength score, and historical transmission efficiency of the path. The activation operation is essentially a dynamic and quantitative filtering and instantiation of static and potential associations in the multi-source knowledge base based on the current specific context, generating a set of candidate paths.

[0055] S3.4 The focus analysis rule base initiates a virtual attention pulse transmission along the digital meridian starting from the current focus. For other devices or content areas within the digital thread instance, the semantic correlation degree matching algorithm is used to evaluate the residual signal strength when the virtual attention pulse arrives.

[0056] Furthermore, to predict the target where user attention is most likely to migrate, the focus analysis rule base initiates a virtual attention pulse transmission along the activated digital meridians, originating from the current semantic focus. This transmission is simulated; the focus analysis rule base calculates a virtual pulse signal for each digital meridian path originating from the current focus and leading to other devices or content areas within the digital thread instance. For each potential target node reached by the pulse transmission, i.e., the [missing information]... For each target node, the focus analysis rule base will invoke a semantic relevance matching algorithm to evaluate the residual signal strength when the virtual attention impulse arrives. residual signal strength The calculation follows a specific physical heuristic formula that takes into account the initial attention impulse intensity. Length along the digital meridian path Exponential decay, semantic correlation between the current focus and the target node The modulation ratio relative to the maximum possible semantic relevance Cmax.

[0057] Specifically, path length This may reflect network hop count, logical distance, or interaction cost, as well as semantic relevance. This quantifies the relevance between the focus content and the target node content or function. For example, the impulse transmitted from the focus of the programming IDE to the code documentation help interface has high semantic relevance and low attenuation; while the impulse transmitted to the music player has low relevance and drastic attenuation. The residual signal strength is calculated by formula, providing a comparable and quantifiable migration probability index for each potential attention migration path. The evaluation of the residual signal strength of all target nodes yields a quantitative prediction map of the user's potential intent based on the current context.

[0058] The expression for residual signal strength is: ; in, To transmit to the first Residual signal strength at each target node, The initial attention impulse intensity, The conduction attenuation coefficient, The current focus is on the number 1 to 2. The length of the digital meridian path for each target node As the current focus and the first The semantic relevance of each target node. To maximize the possible semantic relevance, The target node.

[0059] S3.5 The focus analysis rule base compares the residual signal strength of each transmission path and selects the target node whose residual signal strength exceeds the threshold as the candidate attention migration point.

[0060] Furthermore, the focus analysis rule base compares the residual signal strength calculated from all propagation paths and compares it with a preset threshold. This threshold represents the lowest signal strength threshold considered to have a significant migration probability. Target nodes with residual signal strength exceeding this threshold are selected as candidate attention migration points. The comparison and selection process is essentially a coarse screening, filtering out nodes whose predicted signals are extremely weak due to low semantic relevance or high path cost, thereby concentrating computation and resources on the most likely targets.

[0061] Specifically, for example, among multiple peripheral devices, only smart tablets and smartwatches with residual signal strength exceeding a threshold are listed as candidates, while distant smart refrigerators are excluded due to insufficient signal strength. This threshold-based screening mechanism improves the efficiency and targeting of subsequent processing, avoids wasting pre-scheduled resources on low-probability targets, successfully filters out candidate attention migration points with residual signal strength exceeding a preset threshold, and completes the initial filtering of virtual attention pulse transmission results.

[0062] It should be noted that after calculating the residual signal strength of all activated digital meridians, the Focus Analysis rule base obtains a set containing each target node and its corresponding signal strength value. Before performing a threshold-based fast filtering and sorting preprocessing, the Focus Analysis rule base first reads a preset, dynamically adjustable attention migration threshold from the configuration. The attention migration threshold represents the minimum signal strength benchmark required to determine that a migration path has a significant probability. The Focus Analysis rule base traverses the above set and compares the residual signal strength value of each target node with the threshold. For nodes whose residual signal strength value is greater than or equal to the threshold, the Focus Analysis rule base adds its node identifier, corresponding residual signal strength value, and path information of the digital meridian to a candidate intermediate list. This comparison operation is a simple scalar comparison that transforms continuous prediction probabilities (residual signal strength) into binary significant / insignificant decisions through a threshold, achieving dimensionality reduction from the probability space to the decision space. After traversal, the focus analysis rule base outputs this intermediate list, where each entry represents a candidate attention transfer point that has passed the screening. Through a single threshold determination, nodes with weak prediction signals and extremely low migration probability (such as smart refrigerators with signal strength far below the threshold) are efficiently filtered out. This allows subsequent more complex sorting, priority allocation, and resource pre-scheduling operations to be focused on a few high-potential targets (such as smart tablets and smartwatches), greatly optimizing the overall allocation of computing resources.

[0063] S3.6. Based on the residual signal strength, generate an attention transfer priority list and then apply the attention transfer priority list.

[0064] Furthermore, the focus analysis rule base uses the residual signal strength value corresponding to each candidate attention migration point as the unique primary key for sorting. An efficient sorting algorithm is used to arrange all candidate points in descending order, ensuring that the node with the highest value is at the top of the list. When values ​​are the same, a decision is made based on preset secondary rules (such as the historical transmission efficiency of digital meridians) to generate a definite total order. After sorting, the focus analysis rule base sequentially fills a list data structure with node identifiers, residual signal strength values, and other necessary metadata. This list is the attention migration priority list, which losslessly maps the continuous values ​​representing the predicted migration probability generated by virtual attention impulse transmission into a linear, iterative operation sequence. This sequence provides a stable and consistent input for all subsequent modules that rely on priority decisions (such as progressive context injection and pre-scheduling decision models), allowing resource allocation to be executed linearly from the head of the list. This ensures that, with limited resources, the target with the highest predicted migration probability is always warmed up first, thereby maximizing the success rate and efficiency of pre-scheduling operations overall. This achieves an efficient and unambiguous conversion from prediction results to execution strategies.

[0065] Specifically, for example, the residual signal strength of smart tablets is the highest, ranking first on the list; the strength of smartwatches is second, ranking second. This list quantifies the relative probability of different target nodes becoming the next actual focus, generates an attention migration priority list, and transforms the prediction results into a clear and actionable sequence of action guidelines.

[0066] It should be noted that the focus analysis rule base uses the residual signal strength value as the sorting key and applies a stable sorting algorithm with a time complexity of O(n log n), such as merge sort, to the candidate point set to sort all candidate points in descending order, ensuring that the candidate point with the largest residual signal strength value is placed at the beginning of the sequence. During the sorting process, if two or more candidate points have completely equal residual signal strength values, the focus analysis rule base will make a judgment based on preset secondary sorting rules. For example, it will compare the historical transmission efficiency values ​​of the digital meridians corresponding to these candidate points. Candidate points with higher transmission efficiency values ​​will be given higher priority, thus ensuring the generation of a definite, total order sequence. After the sorting algorithm is completed, the focus analysis rule base will traverse the sorted sequence in this order and extract metadata such as node identifier, residual signal strength value, and possible digital meridian path identifiers from the data structure of each candidate point. This information will be added as an entry to a newly created, sequentially accessed list data structure. This newly created list is the attention migration priority list, which transforms the originally unordered set of candidate points that only represents those that have passed the screening into a linear queue that is strictly arranged from high to low according to the predicted migration probability. This makes the priority relationship between smart tablets (intensity 0.85) and smartwatches (intensity 0.72) clear and structured.

[0067] S3.7 Based on the progressive context injection and state consistency verification method, the attention transfer mechanism is triggered to synchronously transmit the operation context, interaction state, and semantic information related to the current focus to high-priority nodes.

[0068] Furthermore, after determining the priority list for attention transfer, it is necessary to prepare the state for potential high-priority transfers. Based on the progressive context injection and state consistency verification method, the focus analysis rule base triggers the attention transfer mechanism. Progressive context injection refers to gradually synchronizing the operation context, interaction state, semantic information, etc., related to the current semantic focus to higher-priority nodes in an incremental and low-overhead manner, according to priority order.

[0069] Specifically, state consistency verification ensures that the state synchronized to the target node is consistent with the source focus state during and after the injection process. This process does not immediately complete the full focus switch, but rather warms up the target node's state environment in advance, allowing it to sense the possible upcoming focus migration and prepare for rapid takeover. For example, when the smart tablet is a high-priority node, context information such as the view position, zoom level, and selected objects of the current design document can be pre-synchronized to the smart tablet, but its main rendering thread is not activated yet. This triggers the attention migration mechanism to start the state pre-synchronization to the high-priority node, aiming to shorten the startup delay of the target node when the actual switch occurs in the future.

[0070] It's important to note that after obtaining the attention migration priority list, the focus analysis rule base initiates a progressive state synchronization process for high-priority nodes. The data processing and analysis sequentially traverses the priority list and performs differentiated context injection. Starting from the head of the list, the focus analysis rule base processes each high-priority node in turn. For the currently processed node, it extracts a subset of data defined as the preheating key context from the current semantic focus state snapshot. This subset includes information such as application view state, selected object identifiers, unsubmitted form data, and session identifiers, rather than the complete application memory image. After extraction, the focus analysis rule base calculates the relationship between this data subset and the target context. The focus analysis rule base packages incremental differences between the target node and its cached older context versions, along with the version number and checksum, into a lightweight synchronization message. Before sending this message to the target node, the focus analysis rule base records the current source focus's state version number as a consistency benchmark. Once the target node receives and applies the synchronization message, it returns an acknowledgment and its updated state version number to the focus analysis rule base. The focus analysis rule base then compares the returned version number with the recorded consistency benchmark. If they match, the node's state injection is marked as successful; otherwise, if they do not match or a timeout occurs, injection failure is recorded, and the node's priority in this task may be lowered. This process is performed node by node in list order, achieving progressive synchronization.

[0071] S3.8 The focus analysis rule base records the residual signal intensity distribution of this virtual attention pulse transmission. Through the feedback learning mechanism of comparing the predicted signal intensity with the actual focus migration result, the transmission efficiency of the digital meridian is updated.

[0072] Furthermore, after completing a virtual attention impulse transmission and state pre-synchronization, the focus analysis rule base records detailed information about this transmission for continuous optimization. The focus analysis rule base updates the transmission efficiency of the digital network through a feedback learning mechanism that compares the predicted signal strength with the actual focus migration results. Specifically, for the path from the source device to the target device, the update of its digital network transmission efficiency follows a feedback learning formula. The new transmission efficiency is jointly determined by the historical transmission efficiency, the strength of the actual attention migration signal, the theoretical prediction value of attention migration to the target node, and the learning rate adjustment factor.

[0073] Specifically, the efficiency inertia coefficient controls the weight of historical experience. This reflects a monitoring signal indicating whether a user has actually migrated to that node, and The learning step size is then dynamically adjusted based on the prediction error. For example, if the residual signal strength of a tablet is predicted to be high, but the user does not ultimately switch to it, the transmission efficiency of the digital meridian leading to that tablet will be reduced. Through this feedback mechanism, the digital meridian can adaptively learn the user's real behavior patterns, making future virtual attention impulse transmission predictions increasingly accurate, recording the transmission results, and updating the transmission efficiency of the digital meridian.

[0074] The expression for the transmission efficiency of digital meridians is: ; in, For source devices To the target device The updated digital meridian transmission efficiency of the attention transfer path For efficiency inertia coefficient, For source devices To the target device The historical performance value of the path, For the actual attention transfer signal strength, For the target node The predicted value of attention transfer theory This is the learning rate adjustment factor. Index the target node. This is the source node index.

[0075] S4. When the residual signal strength of the highest priority node in the attention migration priority list exceeds the preset threshold, the pre-scheduling decision process is triggered.

[0076] S4.1 The pre-scheduling engine queries the digital meridian transmission efficiency weight map to obtain the digital meridian transmission efficiency value from the current semantic focus device to the pre-scheduling target node.

[0077] Furthermore, when the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold, it means that the virtual attention impulse propagation predicts a high probability that the user will shift their focus to that node. The pre-scheduling engine is then triggered. The pre-scheduling engine first needs to evaluate the historical smoothness of migrating from the current state to the target node. The pre-scheduling engine queries the digital meridian propagation efficiency weight graph, which records the success efficiency of attention migration paths between devices during the historical execution of digital thread instances.

[0078] Specifically, the pre-scheduling engine obtains the digital meridian transmission efficiency value from the current semantic focus device to the pre-scheduling target node. This transmission efficiency value is learned based on virtual attention impulse prediction and user's actual migration behavior feedback in similar past contexts, quantifying the historical reliability of this path. For example, in an office scenario, the digital meridian transmission efficiency value from the programming interface of a laptop to an extended display may be high because users frequently perform this operation; while the transmission efficiency value to a smart speaker may be low. Obtaining the digital meridian transmission efficiency value is key to incorporating long-term knowledge of historical behavioral patterns into the current pre-scheduling decision, ensuring that the decision is not only based on the current instantaneous prediction signal but also respects the user's inherent behavioral habits, increasing the long-term rationality and personalized accuracy of the pre-scheduling decision.

[0079] It should be noted that the pre-scheduling engine constructs a query key based on the identifier of the current semantic focus device and the identifier of the pre-scheduling target node. The pre-scheduling engine uses this query key to access a continuously updated digital meridian transmission efficiency weight graph. The digital meridian transmission efficiency weight graph is a graph-structured data storage system with device pairs as edges and historical transmission efficiency values ​​as weights. The query operation locates the specific edge from the source device to the target device in the digital meridian transmission efficiency weight graph and reads the digital meridian transmission efficiency value stored on that edge. This value is a scalar dynamically updated through a historical feedback learning mechanism, reflecting the historical success probability and efficiency of migrating from the current focus to the target node. The process of obtaining the digital meridian transmission efficiency value essentially injects path reliability knowledge based on long-term statistical learning into the real-time decision-making process. This ensures that pre-scheduling decisions not only rely on the instantaneous prediction signals of the current interaction but also incorporate the user's inherent behavioral patterns and habits, thereby enhancing the personalization and long-term rationality of pre-scheduling decisions.

[0080] S4.2 The pre-scheduling engine aggregates the computing resource utilization, memory usage, network bandwidth and latency metrics of each associated device within the digital thread instance to construct a real-time resource status table.

[0081] Furthermore, based on the historical performance data representing the path, the pre-scheduling engine needs to grasp the real-time operating status of all associated devices within the digital thread instance. The pre-scheduling engine actively aggregates real-time performance metrics from each associated device within the digital thread instance, but is not limited to the computing resource utilization, memory usage, available network bandwidth, and network latency of each device. The aggregation process is continuously collected through a lightweight proxy or heartbeat mechanism to ensure the timeliness of the data. The pre-scheduling engine organizes these aggregated multi-dimensional metrics and constructs a real-time resource status table.

[0082] Specifically, this table provides a unified snapshot of resource health across all participating devices. For example, a real-time resource status table can show that a smart TV has low GPU utilization but slightly high network latency, while a tablet has high memory usage but idle CPU. The purpose of building a real-time resource status table is to enable the pre-scheduling engine to clearly understand the current load capacity and bottlenecks of each node in the distributed environment from a global perspective. This is the basis for assessing whether the target device can withstand the preheating load and at what intensity the preheating operation should be performed, avoiding the application of excessive preheating burden to targets with already strained resources, which would lead to a decline in the overall experience.

[0083] It should be noted that the pre-scheduling engine sends a lightweight resource status query request to each device in the list of devices associated with the digital thread instance. Upon receiving the request, each device's local agent instantly collects its own computing resource utilization, memory usage, current available network bandwidth, and network latency metrics to the digital thread scheduler or peer devices, and encapsulates these metrics into a standardized status report for return. The pre-scheduling engine receives and parses asynchronous responses from all associated devices, performs validity checks and timestamp alignment on the multi-dimensional metrics returned by each device, and discards timed-out or invalid data. Using the device identifier as the primary key, the pre-scheduling engine populates a table with a unified architecture, using each device's computing resource utilization, memory usage, network bandwidth, and latency metrics as data fields, thereby constructing a real-time resource status table covering the entire digital thread instance. This table provides an instantaneous snapshot of resource health and network performance across all cooperating devices, enabling the pre-scheduling engine to have a global understanding of the current load and bottlenecks of each node. It provides an objective and quantitative basis for assessing the real-time resource carrying capacity of the pre-scheduling target node and deciding the specific intensity of the preheating operation, avoiding the potential experience degradation caused by high-intensity preheating on devices that are already near resource saturation.

[0084] S4.3 The pre-scheduling engine encodes the real-time resource status table into digital physiological state vectors for each device, and inputs the path readiness coefficient and the digital physiological state vector of the pre-scheduling target node into the pre-scheduling decision model.

[0085] Furthermore, after acquiring historical path efficiency and real-time device status data, the pre-scheduling engine needs to integrate this heterogeneous information into inputs that the pre-scheduling decision model can process. The pre-scheduling engine first converts multiple indicators for each device in the constructed real-time resource status table into a comprehensive digital physiological state vector through specific encoding rules. This vector condenses the device's multi-dimensional health status, including computing, memory, and network. The pre-scheduling engine needs to calculate a path readiness coefficient, which may combine the digital meridian transmission efficiency value and the current attention migration priority information to quantify the comprehensive probability and urgency of migrating from the current focus to the pre-scheduling target node.

[0086] Specifically, the pre-scheduling engine inputs the path readiness coefficient and the digital physiological state vector corresponding to the pre-scheduled target node into the pre-scheduling decision model. By encoding the device state as a vector and combining it with the path readiness, the pre-scheduling decision model can simultaneously weigh the strength of the user's migration intention and the path reliability with the actual current carrying capacity of the target device within a unified mathematical space. This allows it to make decisions that align with both the user's potential intentions and the actual resource constraints. Completing the input preparation for the pre-scheduling decision model creates the conditions for generating the pre-warm-up instruction set.

[0087] S4.4 Based on the path readiness coefficient and digital physiological state vector, determine the required digital metabolic preheating intensity level for the pre-scheduled target node, and generate the corresponding biological instruction set according to the digital metabolic preheating intensity level.

[0088] Furthermore, the pre-scheduling decision model analyzes these two types of inputs to assess the preheating intensity allowed by the target device's current digital physiological state, given the predicted migration probability and path reliability. The pre-scheduling decision model determines a specific digital metabolic preheating intensity level, which represents the degree of resource preparation and state activation applied to the target device in response to predicted attention migration events. The digital metabolic preheating intensity level is a graded instruction, such as mild preheating, standard preheating, and deep preheating. Based on the determined digital metabolic preheating intensity level, the pre-scheduling decision model generates a corresponding set of biological instructions.

[0089] Specifically, the biological instruction set is a set of executable instructions that defines specific preheating actions. Its content matches the preheating intensity level. For example, a deep preheating level might generate a comprehensive instruction set that includes reserving a large amount of computing resources, preloading complete data blocks, and establishing high-bandwidth guaranteed channels. The generation of the digital metabolism preheating intensity level and the biological instruction set marks the transition of pre-scheduling from the analysis and prediction stage to the stage of generating executable preheating plans. It transforms abstract intent predictions and resource states into clear and quantifiable preheating operation guidelines. Successfully determining the digital metabolism preheating intensity level and generating the corresponding biological instruction set signifies that the core output of the pre-scheduling decision-making process has been completed.

[0090] It should be noted that the pre-scheduling decision model first integrates and matches the path readiness coefficient and digital physiological state vector in a predefined feature space. The path readiness coefficient represents the tendency and urgency of migration, while the digital physiological state vector characterizes the current resource health status of the target node. Based on built-in decision rules or a trained classifier, the pre-scheduling decision model analyzes the combined state of these two inputs to assess the preheating load level that the target node's resource status can safely and efficiently bear under a given predicted migration pressure. Based on this analysis, the pre-scheduling decision model determines a specific digital metabolic preheating intensity level from a pre-defined set of discrete levels, such as light, standard, or deep preheating. The level is an abstract label of the intensity, scope, and resource occupancy of the preheating operation. After the decision is made, the pre-scheduling decision model queries a level-instruction template mapping library to obtain a parameterizable biological instruction set template corresponding to that level. The pre-scheduling decision model then fills the template with specific parameters relevant to the current context, instantiating and generating the final executable biological instruction set.

[0091] S5. Perform dynamic resource pre-scheduling and preheating operations on the target equipment and target content area according to the resource status table.

[0092] S5.1 The digital thread scheduler parses the computing resource tilt instructions in the biological instruction set and extracts the digital signal parameters of the analog preload.

[0093] Furthermore, the digital thread scheduler receives the biological instruction set generated by the pre-scheduling engine and first processes the part concerning the pre-allocation of computing resources. The digital thread scheduler parses the biological instruction set, locates and reads the specific content of the computing resource tilt instruction. From the computing resource tilt instruction, the digital thread scheduler extracts digital signal parameters that simulate preload. These parameters do not directly allocate a fixed number of CPU cores or memory size, but rather define how to apply a pressure signal simulating a future high-load state to the computing resource scheduler of the target device, such as specifying an expected computing task type, an expected load change curve, or a priority hint for resource preemption.

[0094] Specifically, the purpose of extracting the digital signal parameters of the simulated preload is to provide precise input for subsequently waking up or preparing the computing power of the target device in a gentle, gradual, and reversible manner, avoiding waste caused by directly allocating exclusive resources when the prediction is inaccurate. For example, the digital signal parameters of the simulated preload can indicate the specific shader units of the GPU that need to be prepared for graphics rendering tasks. Successfully extracting the digital signal parameters of the simulated preload is the preparation of precise control information for performing computing resource warm-up.

[0095] It should be noted that the digital thread scheduler scans and identifies the computational resource slack instruction field within the predefined format of the biological instruction set. These instructions, written in a declarative or parameterized description language, specify the intention to preheat the target device's computational resources, but do not directly specify a fixed amount of resources. The digital thread scheduler parses this instruction and uses instruction decoding logic to extract key control parameters, collectively referred to as the digital signal parameters for simulated preload. The extraction process includes parsing the expected computational task type, load change curve profile, target CPU / GPU core wake-up strategy, and priority indications for computational resource preemption, among other metadata. The digital signal parameters for simulated preload do not immediately allocate physical cores or memory; rather, they define a strategy for applying simulated load signals to the target device's computational resource scheduler.

[0096] Furthermore, after acquiring the digital signal parameters of the simulated preload, the digital thread scheduler needs to transmit this control information to the local execution unit of the target device. The digital thread scheduler then injects the extracted digital signal parameters of the simulated preload into the operation unit of the target device through a cross-device communication mechanism. The injection process ensures that the preload command can be accurately received and understood by the entity responsible for resource management on the target device. Injection is a command issuance and parameter transmission, rather than the immediate execution of the computation task itself.

[0097] Specifically, the digital thread scheduler injects digital signal parameters simulating preload into the target device's operating unit. This is a key communication step that transforms global pre-scheduling intentions into locally executable actions on the target device. It establishes a command link from central scheduling to edge execution, enabling the target device to sense the impending computing demands and begin internal preparations.

[0098] It should be noted that, based on the target device's network identifier, a low-latency, high-reliability command transmission session is constructed on the established communication channel. The digital thread scheduler extracts the analog preload digital signal parameters and serializes and encapsulates them according to the protocol format agreed upon with the target device's operating unit, forming a command data packet. This command data packet contains not only the parameters themselves but also the sender identifier, command type, sequence number, and integrity checksum. The digital thread scheduler sends this command data packet to the target device's network endpoint via point-to-point messaging or a publish-subscribe mechanism. The target device's operating unit continuously monitors the command channel. Upon receiving the data packet, it first performs verification and deserialization to reconstruct the analog preload digital signal parameters issued by the digital thread scheduler. This ensures that the global pre-scheduling intent can be accurately and securely transmitted to the target device's local execution entity, establishing a specific command link for computing resource preheating from the central scheduler to the edge device's operating unit. This provides the necessary and accurate input for the target device's operating unit to subsequently guide the local computing resource scheduler into a ready state based on these parameters.

[0099] S5.3 The target device's operating unit receives the digital signal parameters of the simulated preload, inducing the computing resource scheduler to enter the standby state. The digital thread scheduler parses the data preload instructions in the biological instruction set and extracts the preload data identifier and digital digestion path.

[0100] Furthermore, after receiving the analog preload digital signal parameters injected by the digital thread scheduler, the target device's operating unit begins to perform preparatory work on its local computing resources. The target device's operating unit receives these digital signal parameters and interprets them as induction signals to the local computing resource scheduler. Based on these parameters, the target device's operating unit induces the computing resource scheduler to enter a preparatory state. This preparatory state may include increasing the clock frequency of relevant processing units, waking some cores from deep sleep, preloading frequently used instructions or data into the cache, or adjusting the task queue scheduling strategy to prioritize the response to upcoming specific task types. Inducing the computing resource scheduler to enter a preparatory state essentially allows the computing units to warm up from an idle state to a working state in advance, so that when the real task arrives in the future, it can skip the time-consuming initialization and frequency increase process and immediately engage in full-speed computation. Meanwhile, the digital thread scheduler continues to parse other instructions in the biological instruction set at the other end.

[0101] Specifically, the digital thread scheduler parses the data preloading instructions in the biological instruction set, extracting the preloaded data identifier and digital digestion path. The preloaded data identifier indicates which specific data content needs to be prepared in advance, while the digital digestion path describes the process of how this data should be acquired, transformed, and delivered. The target device's operation unit successfully receives and responds to the simulated preload parameters to induce the computing resource scheduler to enter the preparation state, and the digital thread scheduler successfully parses the key information of the data preloading instructions, thus advancing the warm-up operation in two parallel directions: computing resource preparation and data content preparation.

[0102] S5.4 The digital thread scheduler initiates the digital digestion process for the content pointed to by the preloaded data identifier along the digital digestion path.

[0103] Furthermore, after obtaining the preloaded data identifier and the digital digestion path, the digital thread scheduler initiates the data content preparation process. Based on the extracted digital digestion path, the digital thread scheduler initiates the digital digestion process for the content pointed to by the preloaded data identifier. The digital digestion path may specify the data source, such as from the cache of the first device, cloud storage, or content delivery network, as well as the protocol and order of data transmission.

[0104] Specifically, initiating the digital digestion process means that the digital thread scheduler will, according to the path indication, initiate the acquisition, verification, and initial transmission of the target data content. However, the destination at this point is the warm-up buffer of the target device, not the video memory directly used for real-time rendering. Initiating the digital digestion process transforms the static identifier of what data needs to be preloaded into a dynamic process of how to acquire and begin transmitting this data. It marks the transition of data warm-up from the planning stage to the execution stage. Completing the initiation of the digital digestion process ensures that the target data content begins to flow to the target device.

[0105] It's important to note that the parsing of the digital digestion path is typically described using structured data, specifying the location of the data source, the acquisition protocol, necessary transformation steps, and the target cache location. Based on the path indication, the digital thread scheduler initiates a data acquisition request to the designated data source, carrying a preloaded data identifier to clarify the required content. Simultaneously or subsequently, the digital thread scheduler coordinates or initiates the corresponding digital digestion process according to the transformation steps defined in the path. The digital digestion process is a background, distributed data processing pipeline. Its task is to perform a series of preprocessing operations on the acquired raw data content, such as decoding, parsing, format conversion, or feature extraction. The aim is to transform the data from a stored state into an intermediate state closer to direct consumption by the rendering pipeline. Initiating this process signifies that data preheating has moved from the planning stage to the active execution stage; the data begins to flow along the predetermined path and is gradually digested, performing crucial pre-calculations and format preparations for ultimately achieving latency-free rendering on the target device.

[0106] S5.5 The digital digestion process transforms the content pointed to by the preloaded data identifier from the storage format to an intermediate format close to the rendering state.

[0107] Furthermore, the raw data is preprocessed to reduce latency in the final rendering. The digital digestion process processes the content pointed to by the preloaded data identifiers, transforming this content from its original format in the storage medium, such as compressed image files, database records, or serialized document structures, into an intermediate format close to the rendering state. This intermediate format is a form that the rendering pipeline can consume more quickly and directly, such as decompressed bitmaps, parsed document object models, or compiled shader programs. It pre-compiles most of the computationally intensive work required for future rendering, such as decoding, parsing, and compilation, so that rendering is only needed when the user actually switches focus and requires it.

[0108] Specifically, the target device can directly use the pre-digested intermediate data for rapid synthesis and rendering, avoiding stuttering caused by format conversion at critical moments. For example, a video file is decapsulated and decoded into an uncompressed frame sequence during the digital digestion process and stored in fast storage.

[0109] S5.6 The digital thread scheduler parses the network bandwidth reservation instruction in the biological instruction set, extracts the immune channel establishment parameters, and establishes the immune channel on the data transmission path based on the immune channel establishment parameters.

[0110] Furthermore, the digital thread scheduler continues to execute the network transmission guarantee instructions in the biological instruction set. The digital thread scheduler parses the network bandwidth reservation instructions in the biological instruction set and extracts the immune channel establishment parameters from them. The immune channel establishment parameters define the attributes of the dedicated or high-priority network channel required for this preheating operation, such as target bandwidth, maximum allowed latency, source and destination addresses, and pattern characteristics used to identify preheating-related data packets.

[0111] Specifically, based on the extracted immune channel establishment parameters, the digital thread scheduler initiates a request to establish an immune channel in the network infrastructure, establishes an immune channel on the data transmission path, and marks a protected, quality-of-service-guaranteed transmission sub-path for subsequent data transmissions related to this preheating at the physical or logical network layer. Establishing an immune channel provides a definite network performance guarantee for the preheating data stream, ensuring that the data preloading process is not affected by sudden interference from other background traffic in the network and can be completed stably and with low latency. This is the key network foundation for achieving overall imperceptible latency.

[0112] S5.7 After the immune channel is established, background traffic is allowed to pass through and high-priority forwarding is triggered for specific data patterns belonging to the preheating instruction set.

[0113] Furthermore, after an immune channel is established, its operating rules need to be defined to achieve intelligent utilization of network resources. Once established, an immune channel does not completely block other network traffic. The immune channel's operating mechanism allows regular background traffic to continue passing through the same physical link, but the traffic scheduler in the network device or operating system kernel identifies the flowing data packets. When a data packet is detected to belong to a specific data pattern defined by a preheating instruction set, such as matching a specific protocol header, port number, or content identifier, the immune channel mechanism triggers high-priority forwarding.

[0114] Specifically, high-priority forwarding means that these data packets will be inserted at the front of the sending queue or given a smaller queuing delay in the routing, ensuring that the preheating data stream has priority to meet its low latency requirements, while not excessively crowding out the bandwidth of other network applications. This achieves differentiated quality of service management and efficient sharing of network resources. For example, regular web browsing traffic and data streams preloaded from the cloud share the link, but the model data stream gets priority forwarding because it matches the preheating pattern. The immune channel is successfully established and begins to perform high-priority forwarding based on pattern recognition, which means that the network preheating is ready.

[0115] S5.8 The digital thread scheduler confirms that the target device's computing resource scheduler is in a ready state, the preloaded data has been digitally digested, and the immune channel has been established, thereby obtaining dynamic resource pre-scheduling and preheating operations for the target device and target content area.

[0116] Furthermore, after all the warm-up operations across all dimensions are initiated and executed as instructed, the digital thread scheduler needs to perform a final status confirmation. The digital thread scheduler comprehensively confirms the completion of the warm-up operations by querying the status feedback of the target device's operating units, checking the completion report of the digital digestion process, and verifying the activity status of the immune channel. The digital thread scheduler confirms that the target device's computing resource scheduler is in a ready state, indicating that the computing unit has completed its warm-up. The digital thread scheduler confirms that the preloaded data has completed digital digestion, indicating that the target data is ready in the target device's local cache in an intermediate format. The digital thread scheduler confirms that the immune channel has been established, indicating that the high-priority network path is unobstructed.

[0117] Specifically, the digital thread scheduler considers that the dynamic resource pre-scheduling and warm-up operations for the target device and target content area have been successfully obtained. Obtaining the warm-up operation means that the target device is ready to respond immediately for potential user focus migration in the three key resource dimensions of computing, data, and network. The digital thread scheduler has successfully confirmed and obtained the dynamic resource pre-scheduling and warm-up operations for the target device and target content area.

[0118] S6. When the user's actual interaction focus switches to the target device, the target device obtains content presentation and interaction response without perceptible delay based on the result of the preheating operation.

[0119] S6.1 Switch the actual interaction focus to the target device. The target device captures the user's first interaction input. The operation unit of the target device schedules the execution of the rendering tasks related to the target content area at the real-time level.

[0120] Furthermore, when a user actually switches the focus to the target device—for example, by looking at the screen, touching the device with a finger, or using a voice command—the target device immediately captures this focus switch event and the subsequent initial interactive input, such as a click or swipe. Simultaneously, the target device's operating unit receives the focus switch signal and immediately schedules the rendering tasks related to the target content area. Because the target device's computing resource scheduler has already been induced into a ready state during the warm-up phase.

[0121] Specifically, the target device's operating unit can elevate the rendering task process to real-time level and allocate pre-prepared computing resources with extremely short scheduling latency. The target device's operating unit schedules the rendering process at the real-time level, ensuring that the rendering task immediately obtains CPU and GPU time slices, skipping the conventional delays of process wake-up, resource contention, and scheduler decisions. This allows the visual content generation process to start immediately; for example, when a user turns to look at the pre-warmed smart TV screen and presses the confirmation button on the remote control, the smart TV's operating unit immediately schedules the video player's rendering thread with the highest priority, thus completing real-time scheduling of the rendering task process.

[0122] It should be noted that the target device's operation unit receives and processes the focus switching signal. The operation unit queries its local status to confirm that the rendering task process related to the target content area has been created or marked during the warm-up phase, but may be in a suspended or low-priority state. Based on the high-priority trigger of the focus switching signal, the target device's operation unit immediately sends a real-time scheduling request to the local compute resource scheduler. This request carries the identifier of the target content area rendering task process and requests that its scheduling level be raised to real-time. When processing this request, the compute resource scheduler, having been induced into a ready state during the warm-up phase, can immediately place the specified rendering task process in the real-time run queue with extremely short context switching and decision latency, and allocate the prepared CPU time slices, GPU computing units, and memory bandwidth to it.

[0123] S6.2 Read the pre-warmed data block from the local cache of the target device, and perform composite rendering with the read data block and the rendering subtask result from the auxiliary computing node; the pixel data generated by composite rendering is passed through a high-priority network queue.

[0124] Furthermore, after the rendering task process is scheduled and executed, it needs to quickly obtain the data required for rendering and perform pixel compositing. The rendering task process directly reads data blocks that have already been digitally digested during the warm-up phase from the local cache of the target device. These data blocks are already in an intermediate format close to the rendering state, avoiding the overhead of on-site decoding or parsing. After reading the warmed-up data blocks, the rendering task process may combine this data with the rendering subtask results from the auxiliary computing nodes for rendering. The auxiliary computing nodes may be other devices in the digital thread instance, which may also have been allocated some distributed rendering tasks during the warm-up phase.

[0125] Specifically, the compositing rendering process efficiently integrates locally preprocessed data with the results of remote computation to generate the final pixel data. The pixel data generated by compositing rendering does not go through the conventional network queue, but is transmitted through a high-priority network queue specially established in the pre-warming stage. This ensures that the rendering sub-results returned from the auxiliary computing nodes can arrive with minimal latency. The pre-warming data is read from the local cache and combined with the results of the auxiliary nodes for compositing rendering, making full use of the pre-warming results, bringing data preparation and some computation work forward, and optimizing and integrating network transmission into the rendering pipeline, so that complex distributed rendering can proceed smoothly.

[0126] S6.3 Read pixel data from the display frame buffer and refresh the screen. Process the captured first interactive input and generate interactive response instructions.

[0127] Furthermore, once the pixel data is ready, the target device needs to complete the final image presentation and provide real-time feedback to the user's initial interaction. The pixel data generated by the composite rendering is sent to the target device's display frame buffer. The display controller reads this latest pixel data from the display frame buffer and drives the screen to refresh the image, thereby presenting the content to the user.

[0128] Specifically, because the rendering data is already prepared, the refresh latency is extremely low. Simultaneously or almost simultaneously with the screen refresh, the target device processes the initial user interaction input captured at the start of the process. Since computing resources are already in a ready state, the logic for processing the interaction input can be executed rapidly—for example, parsing click coordinates, updating application state, or triggering corresponding operations to generate appropriate interaction response instructions. These instructions may trigger new rendering tasks, network requests, or device controls, read pixel data from the frame buffer to complete the screen refresh, and process the initial interaction input to generate response instructions. This ensures that the user is visually and tactilely unaware of any waiting caused by device switching or content migration. The completion of the screen refresh and the generation of interaction response instructions marks the final achievement of imperceptible latency content presentation and interaction response based on the pre-warming operation.

[0129] This embodiment also provides a distributed cross-screen display system based on digital threads, including: a proxy module, which, in response to a user's cross-screen operation, captures and generates an operation context information packet by a first device; The module is created by the digital thread scheduler receiving the operation context information packet and creating a digital thread instance corresponding to this cross-screen task. The analysis module, the digital thread scheduler, aggregates user interaction event streams from devices associated with digital thread instances, and models and analyzes the user interaction event streams based on a preset focus analysis rule base; The pre-scheduling module triggers the pre-scheduling decision process when the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold. The preheating operation module performs dynamic resource pre-scheduling and preheating operations on the target device and target content area based on the resource status table. The interaction response module, when the user's actual interaction focus switches to the target device, the target device obtains content presentation and interaction response without perceptible delay based on the result of the preheating operation.

[0130] This embodiment also provides a computer device applicable to the distributed cross-screen display method based on digital threads, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the distributed cross-screen display method based on digital threads as proposed in the above embodiment.

[0131] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0132] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the distributed cross-screen display method based on digital threads as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0133] In summary, this invention changes the response paradigm of cross-screen interaction by constructing an intelligent closed loop of intent prediction and resource preheating. It coordinates cross-screen tasks globally based on digital threads and uses attention field models and digital meridian transmission mechanisms to analyze user interaction event flows in real time, accurately predicting the potential targets and probabilities of attention migration. This achieves a leap from event-driven to intent prediction-driven, eliminating decision delays. Based on the prediction results and real-time resource status, it generates multi-dimensional pre-scheduling instructions to proactively and collaboratively preheat the computing resources, data formats, and network channels of the target device. This transforms the unavoidable serial cold start delay in traditional interaction into a background parallel execution preparation process. When the user actually switches focus, the target device can directly achieve instant rendering and response based on the preheated and ready resources, thus realizing a truly seamless cross-screen experience at the system level.

[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A distributed cross-screen display method based on digital threads, characterized in that: This includes, in response to a user's cross-screen actions, the first device capturing and generating an operation context information packet; The digital thread scheduler receives the operation context information packet and creates a digital thread instance corresponding to this cross-screen task. The digital thread scheduler aggregates user interaction event streams from devices associated with digital thread instances and models and analyzes these event streams based on a pre-defined focus analysis rule base. When the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold, the pre-scheduling decision process is triggered. Dynamic resource pre-scheduling and preheating operations are performed on the target equipment and target content area based on the resource status table; When the user's actual interaction focus switches to the target device, the target device, based on the result of the preheating operation, obtains content presentation and interaction response without perceptible delay.

2. The digital thread based distributed cross-screen display method of claim 1, wherein: In response to a user's cross-screen action, the first device captures and generates an operation context information packet, including the following steps: By dragging and dropping graphical interface controls, a cross-screen operation is initiated from the first device to the second device. The agent program of the first device captures the cross-screen operation and records the network identifier of the first device, the display content identifier and version in the application, and a snapshot of the display status of the first device. The agent program of the first device obtains the network identifier of the second device specified by the user; The network identifier of the first device, the display content identifier and version, the display status snapshot, and the network identifier of the second device are encapsulated into an operation context information packet.

3. The digital thread based distributed cross-screen display method of claim 2, wherein: The digital thread scheduler receives the operation context information packet and creates a digital thread instance corresponding to this cross-screen task, including the following steps: Based on the operation context information packet received by the digital thread scheduler, a globally unique string is generated as a thread identifier. Using the thread identifier as an index, an empty list of associated devices is initialized. Add the network identifiers of the first device and the second device to the list of associated devices; The digital thread scheduler creates a data structure that combines and encapsulates the thread identifier, the list of associated devices, the display content identifier and version in the operation context information packet, and the display status snapshot of the first device in the operation context information packet to form a digital thread instance corresponding to this cross-screen task.

4. The digital thread based distributed cross-screen display method of claim 3, wherein: The digital thread scheduler aggregates user interaction event streams from devices associated with digital thread instances and models and analyzes these streams based on a pre-defined focus analysis rule base, including the following steps: The device and content regions within the digital thread instance are constructed as potential energy nodes in the attention field. Based on the real-time distribution of user interaction event streams, attention potential energy contour maps are drawn. Gradient clustering and time window stability analysis methods are used to determine the regions with stable potential energy peaks as the current semantic focus devices and focus regions. The focus analysis rule base analyzes the disturbance ripples generated by the user interaction event flow in the attention potential field, and performs multi-scale decomposition of the disturbance ripples by applying time-frequency analysis technology that combines wavelet packet transform and Hilbert-Huang transform. When the analysis results show that the power spectral density of the disturbance ripple is concentrated in the low frequency band and the envelope amplitude shows a continuous high energy characteristic, and the instantaneous phase shows high coherence, it is determined to show low frequency and high energy resonance characteristics, indicating a deep coupling between neuronal motion and cognitive load, and determining that the current focus is in a state of deep immersion fine operation. The focus analysis rule base activates the digital meridians associated with the current semantic focus; The focus analysis rule base initiates a virtual attention pulse transmission along the digital meridian starting from the current focus. For other devices or content areas within the digital thread instance, the semantic correlation degree matching algorithm based on graph neural network evaluates the residual signal strength when the virtual attention pulse arrives. The focus analysis rule base compares the residual signal strength of each transmission path and selects target nodes with residual signal strength exceeding the threshold as candidate attention transfer points; Based on the residual signal strength, generate an attention transfer priority list, and then proceed according to the attention transfer priority list; Based on the progressive context injection and state consistency verification method, an attention transfer mechanism is triggered to synchronously transmit the operation context, interaction state, and semantic information related to the current focus to high-priority nodes. The focus analysis rule base records the residual signal intensity distribution of this virtual attention impulse transmission. By comparing the predicted signal intensity with the actual focus migration results through a feedback learning mechanism, the transmission efficiency of the digital meridian is updated.

5. The digital thread based distributed cross-screen display method of claim 4, wherein: When the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold, a pre-scheduling decision process is triggered, including the following steps: The pre-scheduling engine queries the digital meridian transmission efficiency weight map to obtain the digital meridian transmission efficiency value from the current semantic focus device to the pre-scheduling target node; The pre-scheduling engine aggregates the computing resource utilization, memory usage, network bandwidth, and latency metrics of each associated device within a digital thread instance to construct a real-time resource status table; The pre-scheduling engine encodes the real-time resource status table into digital physiological state vectors for each device, and inputs the path readiness coefficient and the digital physiological state vector of the pre-scheduling target node into the pre-scheduling decision model. Based on the path readiness coefficient and digital physiological state vector, the required digital metabolic preheating intensity level for the pre-scheduled target node is determined, and the corresponding biological instruction set is generated according to the digital metabolic preheating intensity level.

6. The digital thread based distributed cross-screen display method of claim 5, wherein: Based on the resource status table, dynamic resource pre-scheduling and preheating operations are performed on the target device and target content area, including the following steps: The digital thread scheduler parses the computational resource tilt instructions in the biological instruction set and extracts the digital signal parameters of the analog preload. The digital thread scheduler injects analog preload digital signal parameters into the operating unit of the target device; The target device's operating unit receives digital signal parameters for simulated preload, inducing the computing resource scheduler to enter a ready state. The digital thread scheduler parses the data preload instructions in the biological instruction set and extracts the preload data identifier and digital digestion path. The digital thread scheduler initiates the digital digestion process along the digital digestion path for the content pointed to by the preloaded data identifier; The digital digestion process transforms the content pointed to by the preloaded data identifier from the storage format into an intermediate format that is close to the rendering state; The digital thread scheduler parses the network bandwidth reservation instruction in the biological instruction set, extracts the immune channel establishment parameters, and establishes the immune channel on the data transmission path based on the immune channel establishment parameters. Once the immune channel is established, background traffic is allowed to pass through, and high-priority forwarding is triggered for specific data patterns belonging to the preheating instruction set. The digital thread scheduler confirms that the target device's computing resource scheduler is in a ready state, the preloaded data has been digitally digested, and the immune channel has been established, thereby obtaining dynamic resource pre-scheduling and preheating operations for the target device and target content area.

7. The digital thread based distributed cross-screen display method of claim 6, wherein: When the user's actual interaction focus switches to the target device, the target device, based on the results of the warm-up operation, obtains content presentation and interaction response without perceptible delay, including the following steps: The actual interaction focus is switched to the target device, the target device captures the user's first interaction input, and the operation unit of the target device schedules the execution of the rendering tasks related to the target content area at the real-time level. Read pre-warmed data blocks from the target device's local cache, and composite the read data blocks with the rendering subtask results from the auxiliary computing node; the pixel data generated by the composite rendering is passed through a high-priority network queue. The system reads pixel data from the display frame buffer and refreshes the screen, processes the captured initial interactive input, and generates interactive response commands.

8. A distributed cross-screen display system based on digital threads, based on the distributed cross-screen display method based on digital threads according to any one of claims 1 to 7, characterized in that: include, The proxy module responds to the user's cross-screen operations by capturing and generating an operation context information packet from the first device; The module is created by the digital thread scheduler receiving the operation context information packet and creating a digital thread instance corresponding to this cross-screen task. The analysis module, the digital thread scheduler, aggregates user interaction event streams from devices associated with digital thread instances, and models and analyzes the user interaction event streams based on a preset focus analysis rule base; The pre-scheduling module triggers the pre-scheduling decision process when the residual signal strength of the highest priority node in the attention migration priority list exceeds a preset threshold. The preheating operation module performs dynamic resource pre-scheduling and preheating operations on the target device and target content area based on the resource status table. The interaction response module, when the user's actual interaction focus switches to the target device, the target device, based on the result of the preheating operation, obtains content presentation and interaction response without perceptible delay. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: When the processor executes the computer program, it implements the steps of the distributed cross-screen display method based on digital threads as described in any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: When the computer program is executed by the processor, it implements the steps of the distributed cross-screen display method based on digital threads as described in any one of claims 1 to 7.

Images