A spatiotemporal task intelligent scheduling method and system for multiple executors

Abstract

This disclosure provides a method and system for intelligent orchestration of spatiotemporal tasks with multiple executors. The method includes: acquiring profile information of executors corresponding to multiple different spatial elements within a target digital intelligence space; acquiring a target spatiotemporal task to be executed within the target digital intelligence space, performing multi-dimensional data analysis on the target spatiotemporal task, and decomposing the target spatiotemporal task into multiple sub-tasks based on the analysis results; matching each sub-task with the profile information corresponding to different executors, assigning a corresponding executor to each sub-task, and generating an initial orchestration result for the target spatiotemporal task; identifying the collaborative relationships between the executors based on the initial orchestration result, and coordinating and adjusting the scheduling of each executor based on the collaborative relationships, thereby generating a target orchestration result for the target spatiotemporal task. This enables reasonable task allocation in scenarios with multiple executors and improves the collaborative efficiency among multiple executors.

Description

Technical Field

[0001] This disclosure relates to the field of collaborative scheduling and control technology, and in particular to a method and system for intelligent orchestration of spatiotemporal tasks by multiple executors. Background Technology

[0002] Digital spaces, as intelligent carriers integrating digital technology and physical space, are widely used in various scenarios such as intelligent exhibition halls, digital twins, and intelligent interaction. Spatiotemporal tasks are performed by executors within the digital space, and the needs of different scenarios can be met by executing these tasks. However, current technologies in digital spaces can only orchestrate tasks for a single type of executor. With the development of technology and services, more and more digital spaces are beginning to feature multiple types of executors, making it difficult for current systems to reasonably allocate tasks in scenarios with multiple executors and reducing the collaborative efficiency among them. Summary of the Invention

[0003] The main objective of this disclosure is to propose a spatiotemporal task intelligent orchestration method and system for multiple executors, which can reasonably allocate tasks in scenarios with multiple executors and improve the collaborative efficiency among multiple executors.

[0004] To achieve the above objectives, a first aspect of this disclosure proposes a spatiotemporal task intelligent orchestration method with multiple executors, comprising: For the executors of multiple different spatial elements within the target digital intelligence space, obtain corresponding profile information for each. Obtain the target spatiotemporal task to be executed in the target data space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results; Each subtask is matched with the profile information corresponding to different executors to obtain the matching score of different executors under each subtask, and the corresponding executor is assigned to each subtask based on the size of the matching score to generate the initial arrangement result corresponding to the target spatiotemporal task; Based on the initial orchestration result, the collaborative relationship between each executor is identified, and based on the collaborative relationship, the executors are coordinated and adjusted to generate the target orchestration result corresponding to the target spatiotemporal task.

[0005] In some embodiments, the executors of the different spatial elements include biological human executors, digital human executors, and robotic executors; acquiring corresponding profile information for each executor of multiple different spatial elements within the target digital space includes: For the biological human executor, the digital human executor, and the robot executor, corresponding position data, status data, and historical performance data are collected respectively to obtain general dimension data for each type of executor; Differentiated capability dimension data are collected for the execution characteristics of the biological human executor, the digital human executor, and the robot executor, respectively. By integrating the general dimension data and the capability dimension data, profile information corresponding to each of the executors is generated.

[0006] In some embodiments, the step of performing multi-dimensional data analysis on the target spatiotemporal task and decomposing the target spatiotemporal task into multiple different sub-tasks based on the analysis results includes: The task description of the target spatiotemporal task is analyzed, and analytical data are extracted from the dimensions of task capability requirements, time requirements, and space requirements. Based on the task type of the target spatiotemporal task, a preset task decomposition template is matched to identify the execution stage and independent sub-task units of the target spatiotemporal task; A standardized task description is generated for each subtask unit, and based on the analysis data of the target spatiotemporal task, adaptive capability requirements, time requirements, and space requirements are configured for each subtask to obtain multiple different subtasks.

[0007] In some embodiments, the analysis data based on the target spatiotemporal task is used to configure suitable capability requirements, time requirements, and space requirements for each subtask, resulting in multiple different subtasks, including: Based on the analysis data of the target spatiotemporal task, the capability requirements, time requirements and space requirements of each subtask are configured to obtain multiple different initial subtasks; Perform time-series dependency analysis, resource dependency analysis, data dependency analysis and logical dependency analysis on each of the initial subtasks to obtain the multi-dimensional dependency relationships corresponding to each of the initial subtasks; Based on the multi-dimensional dependencies of each initial subtask, a dependency graph is constructed between the subtasks, and the dependency graph is subjected to cyclic dependency verification and execution reachability verification. Based on the verified dependency graph, the initial subtasks are topologically sorted to obtain multiple sorted subtasks.

[0008] In some embodiments, the step of matching each subtask with the profile information corresponding to different executors to obtain matching scores for different executors under each subtask, and assigning corresponding executors to each subtask based on the matching scores to generate the initial orchestration result corresponding to the target spatiotemporal task includes: For a single subtask and a single executor, based on the capability requirements of the subtask and the profile information of the executor, the capability coverage and capability level of the executor are evaluated from multiple capability dimensions, including professional knowledge, emotional interaction, persistence and stability, personalized service, and physical interaction, and the corresponding capability matching score is calculated. Calculate the location matching score, time matching score, and historical performance matching score corresponding to the executor and the subtask. Then, calculate the capability matching score, location matching score, time matching score, and historical performance matching score by weighting them according to preset weights to obtain the corresponding comprehensive matching score. For multiple sorted subtasks, filter available executors that meet the execution requirements based on their status, location, and load; The executor with the highest comprehensive matching score is selected from the available executors and assigned to the corresponding subtask. The status information of the corresponding executor is updated synchronously. After all subtasks are traversed and the assignment is completed, the initial arrangement result corresponding to the target spatiotemporal task is generated.

[0009] In some embodiments, the step of identifying the collaborative relationships between the executors based on the initial orchestration result, and adjusting the collaborative scheduling of the executors based on the collaborative relationships to generate the target orchestration result corresponding to the target spatiotemporal task includes: Based on the initial arrangement results, complementary, substitutive, and collaborative relationships among the executors are identified as the collaborative relationships among the executors. By combining time, space, and execution resource constraints, and based on the collaborative relationship, the executor combination and task allocation in the initial orchestration result are coordinated and adjusted to generate the target orchestration result corresponding to the target spatiotemporal task.

[0010] In some embodiments, after generating the target orchestration result corresponding to the target spatiotemporal task, the multi-actor spatiotemporal task intelligent orchestration method further includes: Real-time detection of whether resource conflicts, time conflicts, or spatial conflicts occur during the execution of the target spatiotemporal task; wherein, the resource conflict is multiple subtasks competing for the same execution resource, the time conflict is multiple tasks of the same executor with overlapping time windows, and the spatial conflict is multiple executors having conflicting execution spaces; When multiple conflicts are detected, the priority order for conflict handling is determined based on pre-configured task priorities and executor priorities. Each conflict is processed sequentially according to the priority order, and the corresponding conflict is resolved during the processing by at least one of the following: time window adjustment, execution space reallocation, execution resource reallocation, or executor rematch. The target orchestration result corresponding to the target spatiotemporal task is updated synchronously.

[0011] To achieve the above objectives, a second aspect of this disclosure proposes a spatiotemporal task intelligent orchestration system with multiple executors, comprising: The profile information acquisition module is used to acquire corresponding profile information for executors of multiple different spatial elements within the target digital space. The task decomposition module is used to acquire the target spatiotemporal task to be executed in the target digital space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results. The task and executor matching module is used to match each of the sub-tasks with the profile information corresponding to different executors, obtain the matching score of different executors under each sub-task, and assign a corresponding executor to each sub-task based on the size of the matching score, and generate the initial arrangement result corresponding to the target spatiotemporal task. The collaborative scheduling module is used to identify the collaborative relationships between the executors based on the initial orchestration results, and to perform collaborative scheduling adjustments on the executors based on the collaborative relationships, thereby generating the target orchestration results corresponding to the target spatiotemporal task.

[0012] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the multi-actor spatiotemporal task intelligent orchestration method described in the first aspect embodiment.

[0013] To achieve the above objectives, a fourth aspect of the present disclosure provides a storage medium, which is a computer-readable storage medium storing a computer program that, when executed by a processor, implements the multi-actor spatiotemporal task intelligent orchestration method described in the first aspect embodiment.

[0014] The beneficial effects of the embodiments disclosed herein include: This embodiment first comprehensively acquires the unique profile information of various executors within the target digital space, accurately grasps the characteristics of each type of executor, then conducts multi-dimensional in-depth analysis of the target spatiotemporal task and breaks it down into multiple sub-tasks adapted to different execution needs. Based on the matching score between the sub-tasks and the executor profiles, suitable executors are accurately assigned to each sub-task according to the matching degree, forming an initial task arrangement result that fits the scenario of multiple executors. Furthermore, based on the initial arrangement result, the collaborative relationships between each executor are identified and targeted collaborative scheduling optimizations are carried out to streamline the task connection and cooperation logic of multiple executors, solve the problem of unreasonable task allocation, and finally achieve rational task allocation for scenarios of multiple executors, effectively improving the collaborative efficiency among multiple executors. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the spatiotemporal task intelligent orchestration method for multiple executors provided in this embodiment of the disclosure; Figure 2 yes Figure 1 A flowchart further includes step S101; Figure 3 yes Figure 1 A flowchart further includes step S102; Figure 4 yes Figure 3 A flowchart further included in step S303; Figure 5 yes Figure 1 A flowchart further includes step S103; Figure 6 yes Figure 1 A flowchart further includes step S104; Figure 7 yes Figure 1 A flowchart illustrating the further steps following step S104; Figure 8 This is a schematic diagram of the functional modules of the spatiotemporal task intelligent orchestration system with multiple executors provided in this embodiment of the disclosure; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this disclosure. Detailed Implementation

[0016] The accompanying drawings in the embodiments clearly and completely describe the technical solutions in the embodiments of this disclosure. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0017] It is understood that in the specific embodiments of this disclosure, which involve retrieving portrait information, target spatiotemporal tasks and related data, when the above embodiments of this disclosure are applied to specific products or technologies, permission or consent from the target is required, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0018] Furthermore, when this embodiment of the disclosure needs to retrieve portrait information, target spatiotemporal tasks, and related data, it will obtain separate permission or separate consent for the portrait information, target spatiotemporal tasks, and related data through pop-up windows or redirection to a confirmation page. After clearly obtaining separate permission or separate consent for the portrait information, target spatiotemporal tasks, and related data, it will then obtain the necessary portrait information, target spatiotemporal tasks, and related data to enable the embodiments of this disclosure to operate normally.

[0019] In this disclosure, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0020] Please see Figure 1 , Figure 1 This is a flowchart illustrating the spatiotemporal task intelligent orchestration method for multiple executors provided in this embodiment. This spatiotemporal task intelligent orchestration method for multiple executors can be applied to a server or to a spatiotemporal task intelligent orchestration system for multiple executors (hereinafter referred to as the system). The spatiotemporal task intelligent orchestration method for multiple executors includes steps S101 to S104: Step S101: For the executors of multiple different spatial elements within the target digital space, obtain corresponding profile information for each. Step S102: Obtain the target spatiotemporal task to be executed in the target digital space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results. Step S103: Match each subtask with the profile information corresponding to different executors to obtain the matching score of different executors under each subtask, and assign the corresponding executor to each subtask based on the size of the matching score to generate the initial arrangement result corresponding to the target spatiotemporal task. Step S104: Identify the collaborative relationships between each executor based on the initial orchestration results, and perform collaborative scheduling adjustments on each executor based on the collaborative relationships to generate the target orchestration results corresponding to the target spatiotemporal task.

[0021] Regarding step S101 above, the target digital intelligent space is an intelligent carrier that integrates digital technology and physical space, such as intelligent exhibition halls, digital twin scenarios, and intelligent interactive spaces. The programmable objects within the target digital intelligent space are primarily core spatial element executors with independent task execution capabilities, while also encompassing spatial supporting execution elements that can be linked and collaboratively arranged. Among these, the core spatial element executors are categorized into three types: biological human executors, digital human executors, and robotic executors. They are the core execution subjects of spatiotemporal tasks. Spatial supporting execution elements include, but are not limited to, basic spatial units such as lighting systems, background sound systems, scene display screens, and environmental special effects devices. These elements can be incorporated into the overall spatiotemporal task arrangement system, cooperating with the core executors to achieve synchronous scheduling and coordinated control.

[0022] In one embodiment, the three types of spatial element executors, serving as the core execution entities, each possess differentiated execution characteristics and capability boundaries, adaptable to different types of task requirements. Biological human executors possess judgment, communication abilities, and flexibility, making them suitable for tasks requiring complex decision-making and emotional interaction; digital human executors are AI-based virtual assistants, capable of, but not limited to, speech synthesis, image generation, and multilingual interaction, suitable for tasks such as information broadcasting and virtual explanation; and robotic executors possess, but not limited to, physical capabilities such as movement, grasping, navigation, flight, and voice dialogue, suitable for tasks requiring physical movement such as goods transportation and site guidance.

[0023] The aforementioned spatial support elements such as lighting and background sound do not independently undertake the main execution of the core task. Instead, they mainly serve as supporting units for the core executor, coordinating with the task execution rhythm to achieve scenario-based linkage. For example, they can adjust the brightness, color, and background sound atmosphere of the exhibition area in sync with the content and rhythm of the digital human's explanation, switch the scene lighting and prompts along the path guided by the robot, and adapt the corresponding environmental effects to the interactive links of the bio-human, thereby achieving a deep integration of the core executor's task execution with the spatial environment.

[0024] Profile information is a data set describing the characteristics of each executor, including but not limited to common dimensions such as location, status, and historical performance, as well as differentiated dimensions such as capability indicators specific to various executors. Profile information can be obtained in various ways, such as reading static profiles from a database, collecting status data in real time through sensors, and statistically analyzing performance data from historical execution records.

[0025] It should be noted that, by obtaining the exclusive profile information of various executors in the target digital intelligence space, this embodiment of the disclosure accurately grasps the characteristics of each type of executor, providing a comprehensive and quantitative data foundation for subsequent task allocation and collaborative scheduling, and avoiding the problem of unreasonable allocation caused by insufficient understanding of the executor's capabilities in traditional methods.

[0026] Regarding step S102 above, the target spatiotemporal task is a specific task that needs to be completed within the digital space, such as providing guided tours for visitors or organizing exhibits in the exhibition hall. Multi-dimensional data analysis involves analyzing the task across at least two of the three dimensions: capability requirements, time requirements, and spatial requirements. Capability requirement analysis extracts the types and levels of capabilities required for the task; for example, a guided tour requires language skills, communication skills, and navigation skills. Time requirement analysis extracts the expected duration, deadline, and time window of the task. Spatial requirement analysis extracts the execution location, movement path, and spatial range of the task. Task decomposition breaks down a complex task into multiple independent sub-task units. For example, a guided tour service can be decomposed into sub-tasks such as welcoming visitors, explaining exhibit A, explaining exhibit B, interactive experiences, and bidding farewell. This can be further decomposed into sub-tasks that can be performed by each executor based on the actual scenario. Furthermore, the decomposition process needs to consider the dependencies between sub-tasks, such as temporal dependencies, resource dependencies, data dependencies, and logical dependencies. This embodiment of the present disclosure does not impose specific limitations on these dependencies.

[0027] It should be noted that the embodiments disclosed herein conduct multi-dimensional in-depth analysis of the target spatiotemporal task and decompose it into multiple sub-tasks adapted to different execution needs, thereby structuring and modularizing the complex overall task, reducing the difficulty of task allocation, improving the accuracy of subsequent matching, and providing a clear execution unit for the collaborative work of multiple executors.

[0028] Regarding step S103 above, the matching score is a quantitative indicator that measures the suitability between the subtask and the executor. The matching score can be a comprehensive score calculated and estimated using a neural network model or matching algorithm, or it can be a weighted score obtained by summing the scores of multiple sub-items. For example, it can be calculated separately for ability matching score, location matching score, time matching score, and historical performance matching score, and then weighted and summed according to preset weights. Specifically, the ability matching score assesses whether the executor possesses the necessary ability to complete the task and whether their ability level meets the standard; the location matching score calculates the distance between the executor's current location and the task execution location; the time matching score assesses whether the executor's available time window matches the task time requirements; and the historical performance score is evaluated based on historical data such as the executor's past task completion rate, response time, and error rate. The initial orchestration result is a preliminary task allocation scheme formed by assigning each subtask to the available executor with the highest matching score.

[0029] It should be noted that, based on the matching and scoring of sub-tasks and executor profiles, this embodiment accurately assigns suitable executors to each sub-task according to the degree of matching, forming an initial task arrangement result that fits the diverse executor scenarios, ensuring that each sub-task can find the current optimal executor, thereby improving the overall execution efficiency and quality.

[0030] Regarding step S104 above, the collaborative relationship refers to the interaction between executors during task execution. There are various types of collaborative relationships, including but not limited to complementary, substitutive, and cooperative relationships, or at least one of these. A complementary relationship means that executors of different spatial elements can complement each other to complete tasks that a single executor cannot complete independently. A substitutive relationship means that one executor can substitute for another to complete the same type of task. A cooperative relationship means that multiple executors work together to complete the same task. Collaborative scheduling adjustment is based on these collaborative relationships, optimizing the initial orchestration results. For example, pairing executors with complementary relationships to handle the same task, using substitutable executors as backup options, and arranging multiple executors to work collaboratively for tasks requiring cooperation. The target orchestration result is the final task allocation scheme after collaborative optimization.

[0031] It should be noted that, based on the initial orchestration results, this embodiment identifies the collaborative relationships between various executors, conducts targeted collaborative scheduling optimization and adjustment, streamlines the task connection and cooperation logic of multiple executors, solves the problem of unreasonable task allocation, and ultimately achieves rational task allocation for scenarios with multiple executors, effectively improving the collaborative efficiency among multiple executors.

[0032] In summary, this embodiment of the present disclosure, through the multi-executor spatiotemporal task intelligent orchestration method in steps S101 to S104, first comprehensively acquires the exclusive profile information of various types of executors in the target digital space, accurately grasps the characteristics of each type of executor, then conducts multi-dimensional in-depth analysis of the target spatiotemporal task and decomposes it into multiple sub-tasks adapted to different execution needs, and accurately assigns suitable executors to each sub-task based on the matching score between the sub-task and the executor profile, forming an initial task orchestration result that fits the multi-executor scenario, further identifies the collaborative relationships between the executors based on the initial orchestration result, and conducts targeted collaborative scheduling optimization and adjustment, streamlines the task connection and cooperation logic of the multi-executor, solves the problem of unreasonable task allocation, and finally achieves rational task allocation for the multi-executor scenario, effectively improving the collaborative efficiency among the multi-executor.

[0033] The following is a detailed description of the further contents included in steps S101 to S104 in the embodiments of this disclosure.

[0034] Please see Figure 2 , Figure 2 yes Figure 1 The flowchart further includes step S101. In some embodiments, when the executors of different spatial elements include biological human executors, digital human executors, and robot executors, the process of obtaining corresponding profile information for the executors of multiple different spatial elements within the target digital space may further include steps S201 to S203: Step S201: For biological human executors, digital human executors, and robot executors, collect corresponding position data, status data, and historical performance data respectively to obtain general dimension data for each type of executor; Step S202: Collect differentiated capability dimension data for the execution characteristics of biological human executors, digital human executors, and robot executors respectively; Step S203: Integrate general dimension data and capability dimension data to generate profile information for each executor.

[0035] In the above steps, the common dimensional data refers to the shared information possessed by all types of executors. Location data includes the executor's real-time location coordinates, historical location trajectory, and activity range, collected through spatial positioning sensors such as UWB, Bluetooth beacons, or visual positioning systems. Status data includes the executor's current state, such as busy, idle, or resting; for biological human executors, it also includes health status (healthy, fatigued, sick) and emotional state (happy, neutral, tense), obtained through sensor monitoring or manual reporting. Historical performance data includes task completion rate, average response time, error rate, and satisfaction rating, calculated statistically from historical execution records.

[0036] Capability dimension data comprises differentiated information collected based on the characteristics of executors in different spatial elements. For example, for biological human executors, capability dimension data may include language abilities such as the number and fluency of languages ​​mastered, communication ability scores, judgment ability scores, a list of professional skills including guided tours and interactive activities, and learning ability scores. This data can be obtained through skills assessments, historical work evaluations, and self-reporting. For digital human executors, capability dimension data includes speech synthesis quality scores, image generation quality scores, supported languages, and a list of interaction modes such as voice, gestures, and facial expressions. This data can be obtained from the performance parameters of the digital human system. For robotic executors, capability dimension data includes mobility abilities such as movement speed and accuracy, grasping abilities such as the types of objects that can be grasped and grasping force control, perception abilities such as the capabilities of sensors like vision and LiDAR, and navigation abilities such as path planning accuracy and obstacle avoidance. This data can be obtained from the robot's technical specifications or evaluated through actual testing.

[0037] For example, the profile information of a biological human executor may include: location data: currently located in exhibition hall A; status: busy; historical performance: completion rate 95%; response time 2.5 seconds; ability dimensions: language ability: fluent in Chinese, daily communication in English, communication ability 0.85, judgment ability 0.9; professional skills: guiding, explaining, and interacting. The profile information of a digital human executor may include: location data: virtual location fixed in the entrance hall; status: idle; historical performance: satisfaction 4.8 / 5.0; ability dimensions: speech synthesis quality 0.9, image generation quality 0.85; supported languages: Chinese, English, Japanese; interaction modes: voice, gestures. The profile information of a robot executor may include: location data: currently located at a charging station; status: idle; historical performance: task completion rate 98%; ability dimensions: moving speed 1.0 m / s, moving accuracy 0.05 m, grasping ability: can grasp objects under 1 kg; perception ability: vision and LiDAR; navigation accuracy 0.1 m.

[0038] It should be noted that this embodiment constructs a complete multi-dimensional executor profile by collecting general-dimensional data and differentiated capability-dimensional data. The general-dimensional data ensures the comparability of executors of different spatial elements in terms of location, status, and historical performance, providing a unified benchmark for matching calculations. The differentiated capability-dimensional data fully reflects the unique advantages of executors of different spatial elements, providing detailed basis for accurate matching. This profile construction method, which combines general and differentiated data, ensures the comprehensiveness of the data while avoiding information redundancy.

[0039] Please see Figure 3 , Figure 3 yes Figure 1 The flowchart further includes step S102. In some embodiments, the process of performing multi-dimensional data analysis on the target spatiotemporal task and decomposing the target spatiotemporal task into multiple different sub-tasks based on the analysis results may also include steps S301 to S303: Step S301: Analyze the task description of the target spatiotemporal task and extract the analysis data under the dimensions of task capability requirements, time requirements, and space requirements respectively; Step S302: Based on the task type of the target spatiotemporal task, match the preset task decomposition template to identify the execution stage and independent subtask units of the target spatiotemporal task; Step S303: Generate a standardized task description for each subtask unit, and based on the analysis data of the target spatiotemporal task, configure the appropriate capability requirements, time requirements and space requirements for each subtask to obtain multiple different subtasks.

[0040] In the above steps, the task description is natural language text input by the user or generated by the system based on a pre-defined pattern. Examples include providing a guided tour of an exhibition hall for a technology enthusiast or offering product explanations and shopping guidance to a shopper. The parsing process uses natural language processing technology to extract key information. The capability requirements are extracted to determine the type and level of skills needed for the task. For example, a guided tour requires language and communication skills, while a technology enthusiast might require a higher level of professional explanation. The time requirements are extracted to determine the duration and deadline of the task. The spatial requirements are extracted to determine the location of the task, such as exhibition hall A or the introductory hall, and whether movement is required, such as from the introductory hall to the main hall.

[0041] The preset task breakdown template is a standard structure predefined based on common task types. For example, the template for a guided tour task can be broken down into a preparation stage, a welcome stage, a main explanation stage, an interaction stage, and a farewell stage, with each stage corresponding to one or more sub-task units. The standardized description of each sub-task unit generates a detailed description of each sub-task. For example, the sub-task of the welcome stage can be described as greeting visitors in the lobby, giving a self-introduction and an overall introduction. Based on the ability requirements, time requirements, and space requirements obtained from the main task analysis, the system assigns corresponding sub-task requirements to each sub-task. For example, the welcome stage is assigned a language ability requirement of 0.6, a duration of 60 seconds, and a location in the lobby; the main explanation stage is assigned a language ability requirement of 0.9, a duration of 1800 seconds, and a location in the main hall.

[0042] For example, for a guided tour task for science enthusiasts, the parsed requirements are: language ability 0.8, communication ability 0.7, total time requirement 2400 seconds with no specific deadline, and space requirement from the introductory hall to the main halls A, B, and C. After matching the guided tour task template, subtasks are generated: Subtask 1: Welcome and Introduction (language ability 0.6, duration 120 seconds, location: introductory hall); Subtask 2: Explanation of Science Exhibit A (language ability 0.8, professional knowledge 0.8, duration 600 seconds, location: main hall A); Subtask 3: Explanation of Science Exhibit B (language ability 0.8, professional knowledge 0.8, duration 600 seconds, location: main hall B); Subtask 4: Interactive Experience Guidance (interaction ability 0.7, duration 300 seconds, location: interactive area); Subtask 5: Farewell and Feedback Collection (communication ability 0.6, duration 180 seconds, location: exit).

[0043] Furthermore, the embodiments of this disclosure can also verify each subtask. The verification includes checking the completeness of the subtask, such as whether there are capability requirements, time requirements, space requirements, etc., and checking the rationality of the subtask, such as whether the time requirements are reasonable and whether the space requirements are achievable. It also includes checking the coverage of the subtask, such as whether all subtasks cover all the requirements of the main task, thereby ensuring the rationality of the generated subtasks.

[0044] It should be noted that the embodiments of this disclosure scientifically decompose complex tasks into independently executable subtasks by combining task parsing and template matching. Task parsing ensures that task requirements are accurately extracted, while template matching ensures that the decomposition structure conforms to industry standards. The combination of the two makes subtask generation both accurate and efficient.

[0045] Please see Figure 4 , Figure 4 yes Figure 3 The flowchart further includes step S303. In some embodiments, during the process of configuring suitable capability requirements, time requirements, and space requirements for each subtask based on the analysis data of the target spatiotemporal task to obtain multiple different subtasks, steps S401 to S404 may also be included: Step S401: Based on the analysis data of the target spatiotemporal task, configure the appropriate capability requirements, time requirements and space requirements for each subtask to obtain multiple different initial subtasks; Step S402: Perform time-series dependency analysis, resource dependency analysis, data dependency analysis and logical dependency analysis on each initial subtask to obtain the multi-dimensional dependency relationship corresponding to each initial subtask; Step S403: Construct a dependency graph between subtasks based on the multi-dimensional dependencies of each initial subtask, and perform cyclic dependency verification and execution reachability verification on the dependency graph; Step S404: Based on the verified dependency graph, perform topological sorting on each initial subtask to obtain multiple sorted subtasks.

[0046] In the steps above, the initial subtasks are the set of subtasks that have been decomposed according to the task template but whose dependencies have not yet been analyzed. Temporal dependency analysis determines the temporal order between subtasks; for example, the welcome and introduction must be completed before the exhibit presentation. Resource dependency analysis determines whether subtasks compete for the same resource; for example, two presentation tasks need to use the same screen resource. Data dependency analysis determines the data flow relationship between subtasks; for example, interactive experience guidance requires obtaining the output data from the exhibit presentation. Logical dependency analysis determines the business logic relationship between subtasks; for example, farewell and feedback collection must be performed after all presentation tasks are completed.

[0047] A dependency graph is a graph structure with subtasks as nodes and dependencies as directed edges, used to visually represent the mutual constraints between subtasks. Circular dependency checks detect the existence of cycles in the graph, such as A depending on B, B depending on C, and C depending on A. This situation can lead to deadlock, requiring a redesign of task decomposition or dependency relationships. Reachability checks ensure that all subtasks can be reached from the initial state through dependencies, with no isolated task nodes. Topological sorting is the process of transforming the dependency graph into a linear sequence, ensuring that the sorted subtask order satisfies all dependency constraints.

[0048] For example, for the five subtasks of the navigation task, temporal dependency analysis reveals that: subtask 1 must be executed first; subtasks 2 and 3 can be executed in parallel but after subtask 1; subtask 4 can be executed after subtask 2 or 3 but must be executed after subtask 1; and subtask 5 must be executed after all subtasks. Resource dependency analysis shows that subtasks 2 and 3 both require the same screen, resulting in resource contention, necessitating staggered scheduling. Data dependency analysis reveals that subtask 4 requires the output data from subtasks 2 and 3. Logical dependency analysis confirms that subtask 5 must be executed last. After constructing the dependency graph, cyclic dependency verification passes, and the topological sorting result is: subtask 1, subtask 2, subtask 3, subtask 4, subtask 5, where subtasks 2 and 3 can be executed in parallel.

[0049] It should be noted that the embodiments of this disclosure comprehensively capture the complex relationships between subtasks through multi-dimensional dependency analysis. The construction and verification of the dependency graph ensures the logical correctness of task decomposition, and the topology sorting provides a clear execution order for subsequent scheduling and execution. This process avoids task execution conflicts or deadlocks caused by chaotic dependency relationships and improves the reliability of task orchestration.

[0050] Please see Figure 5 , Figure 5 yes Figure 1 The flowchart further includes step S103. In some embodiments, the process of matching each subtask with the profile information corresponding to different executors to obtain the matching score of different executors under each subtask, and assigning corresponding executors to each subtask based on the matching score to generate the initial orchestration result corresponding to the target spatiotemporal task may also include steps S501 to S504: Step S501: For a single subtask and a single executor, based on the subtask's capability requirements and the executor's profile information, evaluate the executor's capability coverage and capability level from multiple capability dimensions, including professional knowledge, emotional interaction, persistence and stability, personalized service, and physical interaction, and calculate the corresponding capability matching score. Step S502: Calculate the location matching score, time matching score, and historical performance matching score corresponding to the executor and the subtask. Calculate the ability matching score, location matching score, time matching score, and historical performance matching score according to preset weights to obtain the corresponding comprehensive matching score. Step S503: For multiple sorted subtasks, filter available executors whose status, location, and load meet the execution requirements; Step S504: Select the executor with the highest comprehensive matching score from the available executors and assign it to the corresponding subtask. Update the status information of the corresponding executor synchronously. After traversing all subtasks and completing the assignment, generate the initial arrangement result corresponding to the target spatiotemporal task.

[0051] In the above steps, the calculation of the ability matching score is based on the five core ability dimensions of professional knowledge, emotional interaction, long-term stability, personalized service, and physical interaction as the core evaluation framework. First, based on the execution requirements of the sub-task, the ability type requirements, ability level thresholds and corresponding weights under each dimension are obtained. Then, it is judged whether the executor has the ability type required by each dimension of the sub-task. The ability level of the executor under the corresponding dimension is compared one by one to see if it meets the task requirements. Finally, the comprehensive ability matching score is calculated by weighting.

[0052] The evaluation criteria for each dimension are as follows: Professional knowledge dimension assesses the executor's knowledge base, professional explanation, professional judgment, and problem-solving abilities in the corresponding task domain; Emotional interaction dimension assesses the executor's ability to recognize emotions, respond with empathy, guide interaction, and adapt to multimodal interactions; Durability and stability dimension assesses the executor's continuous execution reliability, task failure rate, state stability, and service duration tolerance; Personalized service dimension assesses the executor's ability to identify user needs, adapt customized services, and generate and adjust personalized content; and Physical interaction dimension assesses the executor's spatial movement, physical manipulation, environmental perception, and physical contact interaction abilities. For different types of executors, the evaluation indicators for each dimension are adapted to their execution characteristics. For example, for robotic executors, the focus is on evaluating physical interaction and durability and stability; for digital human executors, the focus is on evaluating emotional interaction, personalized service, and professional knowledge; and for biological human executors, a comprehensive evaluation of all dimensions is conducted.

[0053] In the specific calculation, for each core capability dimension required by the sub-task, the capability level satisfaction of that dimension is first calculated. For example, if the sub-task requires a language ability of 0.8, and the executor has a language ability of 0.9, the capability level satisfaction is min(0.9 / 0.8, 1.0) = 1.0; if the executor does not have language ability, the capability matching score is 0. The capability matching score can be the weighted average of the satisfaction of each capability. The location matching score is calculated based on the Euclidean distance between the executor's current location and the sub-task execution location. The closer the distance, the higher the score; exceeding a certain threshold results in a score of 0. The time matching score is calculated based on the degree of overlap between the executor's available time window and the sub-task's time window. Complete overlap results in a full score, while no overlap results in a score of 0. The historical performance matching score is calculated based on a comprehensive assessment of the executor's task completion rate, response time, error rate, etc.; executors with high completion rates, fast responses, and low error rates receive higher scores. The preset weights can be adjusted according to the scenario. For example, in efficiency-first scenarios, the weight of the time matching score can be increased, while in quality-first scenarios, the weight of the capability matching score and the historical performance score can be increased.

[0054] The preset weights of the aforementioned capability matching score, location matching score, time matching score, and historical performance matching score can be flexibly adjusted according to the application scenario. For example, in efficiency-first scenarios, the weights of time matching score and location matching score can be increased; in service quality-first scenarios, the weights of capability matching score and historical performance matching score can be increased; and in business conversion-first scenarios, the weights of capability matching score corresponding to personalized service and emotional interaction dimensions can be increased.

[0055] Furthermore, in screening available executors, this embodiment of the disclosure needs to check whether the executor's current status is idle, whether its location is within a reasonable range, and whether its load has not exceeded the upper limit. For example, an executor in a busy state cannot be assigned new tasks; an executor whose location is too far from the task execution point may not arrive on time; and an executor whose load is full cannot receive any more additional tasks. After the assignment is completed, the executor's status information needs to be updated synchronously, such as changing the status to busy and recording the assigned tasks and the time they are occupied, for use in subsequent task assignments.

[0056] For example, the subtask of explaining technology exhibit A requires a language ability score of 0.8, professional knowledge score of 0.8, a duration of 600 seconds, and a location in theme hall A. Available performers include human A, digital human B, and robot C. Matching scores are calculated as follows: Human A has a matching score of 0.95 for ability, 0.9 for location, 0.8 for time, and 0.85 for historical performance, for a total score of 0.88; Digital human B has a matching score of 0.92 for ability, 1.0 for location (fixed virtual location), 0.9 for time, and 0.9 for historical performance, for a total score of 0.93; Robot C lacks language ability, has a matching score of 0.2, and a total score of 0.35. The system selects digital human B, with the highest total score, and assigns it to this subtask.

[0057] It should be noted that the embodiments of this disclosure, by constructing an evaluation system encompassing professional knowledge, emotional interaction, long-term stability, personalized service, and physical interaction, achieve standardized and comprehensive quantitative evaluation of the capabilities of three different types of executors: biological humans, digital humans, and robots. This solves the problems of inconsistent evaluation dimensions and insufficient matching accuracy among different types of executors. At the same time, by combining execution constraints such as location, time, and historical performance, a comprehensive evaluation of the suitability between sub-tasks and executors is achieved. Screening available executors avoids invalid allocation, and updating the status after allocation ensures the accuracy of subsequent allocations. This allocation mechanism based on comprehensive scoring can find the current optimal executor for each sub-task, thereby improving overall execution efficiency and quality.

[0058] Furthermore, various matching algorithms can be used in this embodiment to assign tasks to executors. For example, a greedy algorithm can be used: first, subtasks are topologically sorted according to priority and dependency to ensure dependent tasks are executed first; then, for each subtask, all available executors are traversed to calculate a comprehensive matching score, and the executor with the highest score is selected for assignment; after assignment, the executor's status information is updated, and the next subtask is processed. The greedy algorithm is simple to implement, computationally efficient, and suitable for scenarios with high real-time requirements.

[0059] In some embodiments, this disclosure may also employ a dynamic programming algorithm for globally optimal matching. The dynamic programming algorithm constructs a state space, where each state represents the assigned task set and the executor state. Starting from the initial state, it performs state transitions, attempts to assign the current subtask to each available executor, calculates the matching score after assignment, updates the executor state, and finally finds the globally optimal allocation scheme through backtracking. The dynamic programming algorithm can find a globally optimal solution and is suitable for scenarios with a small number of tasks and extremely high requirements for matching quality.

[0060] In some embodiments, this disclosure may also employ a genetic algorithm for matching optimization. The genetic algorithm first generates an initial population, with each chromosome representing a task allocation scheme; then it calculates the fitness of each chromosome, which is the sum of the matching scores of all subtasks, while considering the penalty term for dependency constraints; next, it retains individuals with high fitness through selection operations, and generates new individuals through crossover and mutation operations, converging to the optimal solution after multiple generations of iterative evolution. The genetic algorithm is suitable for scenarios with a large number of tasks, complex constraints, and a large search space, and can find an approximate optimal solution within a reasonable time.

[0061] For example, for the five sub-tasks decomposed into a tour guide task, the matching score between each sub-task and available executors is calculated. When using a greedy algorithm, each sub-task is processed sequentially according to topological sorting, and the executor with the highest current score is selected for assignment. When using a dynamic programming algorithm, the system considers all possible assignment combinations to find the globally optimal allocation scheme that maximizes the total score. When using a genetic algorithm, the system searches through multiple generations of evolution to find an approximate optimal allocation under dependency constraints. Regardless of the algorithm used, a complete initial orchestration result is ultimately generated, completing the assignment of all sub-tasks and executors.

[0062] It should be noted that the embodiments of this disclosure comprehensively consider four core factors—capability, location, time, and historical performance—through multi-dimensional matching score calculation, achieving a comprehensive evaluation of the suitability between sub-tasks and executors. Screening available executors avoids invalid allocation, and updating the status after allocation ensures the accuracy of subsequent allocations. Furthermore, the embodiments of this disclosure provide multiple matching algorithms, such as greedy algorithms, dynamic programming algorithms, and genetic algorithms, which can be flexibly selected according to the task scale, real-time requirements, and optimization goals of the actual application scenario. This ensures both matching efficiency and matching quality, providing an adaptable task orchestration scheme for digital spaces with different spatial elements.

[0063] Please see Figure 6 , Figure 6 yes Figure 1 The flowchart further includes step S104. In some embodiments, the process of identifying the collaborative relationships between various executors based on the initial orchestration results, and adjusting the collaborative scheduling of each executor based on the collaborative relationships to generate the target orchestration result corresponding to the target spatiotemporal task may further include steps S601 to S602: Step S601: Based on the initial orchestration results, identify the complementary, substitutive, and collaborative relationships among the executors as the collaborative relationships among the executors; Step S602: Combining time, space, and execution resource constraints, the executor combination and task allocation in the initial orchestration result are coordinated and adjusted based on the collaborative relationship to generate the target orchestration result corresponding to the target spatiotemporal task.

[0064] In the above steps, complementarity refers to the ability of different spatial elements to complement each other and complete tasks that are difficult for a single executor to accomplish independently. For example, biological human executors possess judgment and emotional interaction capabilities, while robotic executors possess physical manipulation capabilities; their complementarity allows them to complete tasks that require both judgment and manipulation.

[0065] In the initial orchestration, if a task is assigned to a single executor but actually requires multiple capabilities, the system can identify complementary relationships and adjust the task to be completed collaboratively by multiple executors. Substitution relationships refer to situations where one executor can substitute for another to complete the same task. For example, a digital human executor can replace a biological human executor for information broadcasting, and a robot executor can replace a human for transporting goods. In the initial orchestration, if an executor is overloaded or unavailable, the system can identify substitution relationships and reassign the task to other replaceable types of executors. Collaborative relationships refer to multiple executors jointly participating in completing the same task, typically requiring coordinated scheduling to ensure smooth cooperation. For example, when humans and robots collaborate to move goods, they need to coordinate movement speed, stopping timing, etc.

[0066] Cooperative scheduling adjustment is an optimization process based on cooperative relationships to the initial orchestration results. Time constraint adjustment considers the order and parallelism of tasks, scheduling complementary executors to work in parallel within the same time period, and using substitute executors as backup options. Spatial constraint adjustment considers the movement paths and operating space of executors, avoiding spatial conflicts; for example, arranging robots to move along fixed routes while humans operate in safe areas. Execution resource constraint adjustment considers the allocation of resources such as equipment and tools; for example, allocating screen resources to digital humans that need to be displayed, and allocating transport tools to robots that need to move.

[0067] For example, in the initial scheduling, the subtask of guiding visitors to theme hall A was assigned to the robot executor, and the subtask of explaining exhibit A was assigned to the digital human executor. The system recognizes a collaborative relationship between the robot and digital human executors; that is, the robot is responsible for path guidance, and the digital human is responsible for content explanation. The two can work together to complete the overall guided tour service. The collaborative scheduling adjustment aligns the time windows of these two subtasks, ensuring that the digital human begins its explanation just as the robot guides the visitor to exhibit A. At the same time, the optimal path is planned for the robot to avoid conflicts with the activity space of the bio-human executor.

[0068] Subsequently, the system, aiming to enhance the dynamic scheduling, content generation, emotional interaction, and commercial conversion capabilities of the target digital space, performs global collaborative scheduling adjustments to obtain the globally optimal arrangement scheme. Specifically, the system optimizes time constraints by precisely aligning the time windows of the three sub-tasks, ensuring that the digital human simultaneously initiates a personalized explanation tailored to the visitor's profile when the robot guides the visitor to exhibit A. At the end of the explanation, the system simultaneously triggers the connection process of the biological human executor, avoiding visitor waiting or process interruptions. In addition, spatial constraints are optimized by planning the optimal navigation path for the robot, avoiding the fixed service area of ​​the biological human executor and the activity space of other devices, while precisely matching the virtual display point of the digital human with the physical location of exhibit A, ensuring consistency between online and offline spaces. Furthermore, resource constraints are optimized by prioritizing the allocation of screen and audio resources in the area where exhibit A is located to the digital human executor, prioritizing the allocation of mobile space around the exhibit to the robot executor, and allocating high-priority visitor data synchronization permissions to the biological human executor, ensuring the maximum release of the capabilities of each executor.

[0069] Through this collaborative scheduling adjustment, the system not only achieved smooth cooperation among multiple executors, but also improved the dynamic scheduling capability of space through robot path optimization, enhanced the spatial content generation capability through personalized explanation content generation by digital humans, and improved the spatial emotional interaction capability through dual-track interaction between biological humans and digital humans.

[0070] It should be noted that the embodiments of this disclosure comprehensively capture the interaction between executors by identifying three types of collaborative relationships: complementarity, substitution, and cooperation. The collaborative scheduling adjustment optimizes the initial arrangement based on these relationships, enabling executors to cooperate better and avoiding the inefficiency of each acting independently.

[0071] Please see Figure 7 , Figure 7 yes Figure 1 The flowchart further includes steps S104. In some embodiments, after generating the target orchestration result corresponding to the target spatiotemporal task, the multi-actor spatiotemporal task intelligent orchestration method may further include steps S701 to S703: Step S701: Real-time detection of whether resource conflicts, time conflicts, or space conflicts occur during the execution of the target spatiotemporal task; among them, resource conflicts are multiple subtasks competing for the same execution resource, time conflicts are multiple tasks of the same executor with overlapping time windows, and space conflicts are multiple executors with conflicting execution spaces. Step S702: When multiple conflicts are detected, the priority order of conflict handling is determined based on the pre-configured task priority and executor priority. Step S703: Process each conflict in order of priority, and resolve the corresponding conflict by adjusting the time window, reallocating the execution space, reallocating the execution resources, or rematching the executor during the processing, and update the target orchestration result corresponding to the target spatiotemporal task synchronously.

[0072] In some embodiments, after generating the target orchestration result corresponding to the target spatiotemporal task, the multi-actor spatiotemporal task intelligent orchestration method may further include a conflict resolution step to detect in real time whether resource conflicts, time conflicts or spatial conflicts occur during the execution of the target spatiotemporal task.

[0073] Among them, resource conflict refers to multiple sub-tasks competing for the same execution resource, such as two explanation tasks needing to use the same screen; time conflict refers to the overlapping time windows of multiple tasks by the same executor; space conflict refers to the overlapping execution spaces of multiple executors, which may cause interference or security risks.

[0074] When multiple conflicts are detected, the priority order for conflict handling can be determined based on pre-configured task priorities and executor priorities. For example, security-related tasks have higher priority than ordinary tasks, and experienced executors have higher priority than novices. Each conflict is handled in order of priority. The conflict can be resolved by adjusting at least one of the following: time window adjustment (e.g., staggering time periods), reallocating execution space (e.g., dividing into different regions), reallocating execution resources (e.g., allocating spare resources), or rematching executors (e.g., changing executors). The target orchestration results corresponding to the target spatiotemporal task are updated synchronously.

[0075] For example, during task execution, if it is found that both the human guide and the robot need to use the same passage at the same time, resulting in a spatial conflict, the system will adjust the path of the transport robot according to the priority configuration. The robot for the tour guide task has a higher priority and the robot for the transport task has a lower priority. The system will wait for the tour guide to pass before entering the passage, and at the same time update the robot's navigation path and task time window to ensure that the two do not interfere with each other.

[0076] It should be noted that the embodiments disclosed herein ensure the stability and security of the task execution process through real-time conflict detection and priority-driven resolution mechanisms. The conflict resolution not only considers the immediate handling of current conflicts, but also achieves dynamic adjustment by updating the orchestration results, enabling the system to adapt to changes during the execution process and improving overall robustness.

[0077] Please see Figure 8 This disclosure also provides a multi-actor spatiotemporal task intelligent orchestration system, which can implement the above-mentioned multi-actor spatiotemporal task intelligent orchestration method. The multi-actor spatiotemporal task intelligent orchestration system includes: The profile information acquisition module 801 is used to acquire corresponding profile information for executors of multiple different spatial elements within the target digital space. The task decomposition module 802 is used to obtain the target spatiotemporal task to be executed in the target digital space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results. The task and executor matching module 803 is used to match each subtask with the profile information corresponding to different executors, obtain the matching score of different executors under each subtask, and assign the corresponding executor to each subtask based on the size of the matching score, and generate the initial arrangement result corresponding to the target spatiotemporal task. The collaborative scheduling module 804 is used to identify the collaborative relationships between various executors based on the initial orchestration results, and to perform collaborative scheduling adjustments on each executor based on the collaborative relationships, thereby generating the target orchestration results corresponding to the target spatiotemporal task.

[0078] In summary, the multi-executor spatiotemporal task intelligent orchestration system, through the spatiotemporal task intelligent orchestration method for executing multi-executor spatiotemporal tasks in the above embodiments, first comprehensively acquires the exclusive profile information of various types of executors within the target digital space, accurately grasps the characteristics of each type of executor, then conducts multi-dimensional in-depth analysis of the target spatiotemporal task and breaks it down into multiple sub-tasks adapted to different execution needs. Based on the matching score between sub-tasks and executor profiles, suitable executors are accurately assigned to each sub-task according to the matching degree, forming an initial task orchestration result that fits the multi-executor scenario. Furthermore, based on the initial orchestration result, the system identifies and analyzes the collaborative relationships between executors, conducts targeted collaborative scheduling optimization and adjustment, streamlines the task connection and cooperation logic of multi-executors, solves the problem of unreasonable task allocation, and ultimately achieves rational task allocation for multi-executor scenarios, effectively improving the collaborative efficiency among multi-executors.

[0079] The specific implementation of the multi-executor spatiotemporal task intelligent orchestration system is basically the same as the specific embodiment of the multi-executor spatiotemporal task intelligent orchestration method described above, and will not be repeated here. Subject to meeting the requirements of the embodiments of this disclosure, the multi-executor spatiotemporal task intelligent orchestration system may also be equipped with other functional modules to implement the multi-executor spatiotemporal task intelligent orchestration method described above.

[0080] This disclosure also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned multi-actor spatiotemporal task intelligent orchestration method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0081] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store operating devices and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the spatiotemporal task intelligent orchestration method for multiple executors according to the embodiments of this disclosure. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0082] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-actor spatiotemporal task intelligent orchestration method.

[0083] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] The embodiments described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided by this disclosure. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by this disclosure are also applicable to similar technical problems.

[0085] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this disclosure, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0086] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] Those skilled in the art will understand that all or some of the steps, apparatuses, or functional modules / units in the methods disclosed above can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0088] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in this disclosure and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0089] It should be understood that in this disclosure, "at least one item" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0090] In the several embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0091] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0093] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present disclosure. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present disclosure shall be within the scope of the claims of the present disclosure.

Claims

1. A spatiotemporal task intelligent orchestration method with multiple executors, characterized in that, include: For the executors of multiple different spatial elements within the target digital space, obtain corresponding profile information for each. Obtain the target spatiotemporal task to be executed in the target data space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results; Each subtask is matched with the profile information corresponding to different executors to obtain the matching score of different executors under each subtask, and the corresponding executor is assigned to each subtask based on the size of the matching score to generate the initial arrangement result corresponding to the target spatiotemporal task; Based on the initial orchestration result, the collaborative relationship between each executor is identified, and based on the collaborative relationship, the executors are coordinated and adjusted to generate the target orchestration result corresponding to the target spatiotemporal task.

2. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 1, characterized in that, The executors of the different spatial elements include biological human executors, digital human executors, and robotic executors; The executor for each of the multiple different spatial elements within the target digital intelligence space acquires corresponding profile information, including: For the biological human executor, the digital human executor, and the robot executor, corresponding position data, status data, and historical performance data are collected respectively to obtain general dimension data for each type of executor; Differentiated capability dimension data are collected for the execution characteristics of the biological human executor, the digital human executor, and the robot executor, respectively. By integrating the general dimension data and the capability dimension data, profile information corresponding to each executor is generated.

3. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 1, characterized in that, The process involves performing multi-dimensional data analysis on the target spatiotemporal task, and decomposing the target spatiotemporal task into multiple different sub-tasks based on the analysis results, including: The task description of the target spatiotemporal task is analyzed, and analytical data are extracted from the dimensions of task capability requirements, time requirements, and space requirements. Based on the task type of the target spatiotemporal task, a preset task decomposition template is matched to identify the execution stage and independent sub-task units of the target spatiotemporal task; A standardized task description is generated for each subtask unit, and based on the analysis data of the target spatiotemporal task, adaptive capability requirements, time requirements, and space requirements are configured for each subtask to obtain multiple different subtasks.

4. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 3, characterized in that, The analysis data based on the target spatiotemporal task is used to configure appropriate capability requirements, time requirements, and space requirements for each subtask, resulting in multiple different subtasks, including: Based on the analysis data of the target spatiotemporal task, the capability requirements, time requirements and space requirements of each subtask are configured to obtain multiple different initial subtasks; Perform time-series dependency analysis, resource dependency analysis, data dependency analysis and logical dependency analysis on each of the initial subtasks to obtain the multi-dimensional dependency relationships corresponding to each of the initial subtasks; Based on the multi-dimensional dependencies of each initial subtask, a dependency graph is constructed between the subtasks, and the dependency graph is subjected to cyclic dependency verification and execution reachability verification. Based on the verified dependency graph, the initial subtasks are topologically sorted to obtain multiple sorted subtasks.

5. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 4, characterized in that, The step of matching each subtask with the profile information corresponding to different executors to obtain matching scores for different executors under each subtask, and assigning corresponding executors to each subtask based on the matching scores, thereby generating the initial orchestration result corresponding to the target spatiotemporal task, includes: For a single subtask and a single executor, based on the capability requirements of the subtask and the profile information of the executor, the capability coverage and capability level of the executor are evaluated from multiple capability dimensions, including professional knowledge, emotional interaction, persistence and stability, personalized service, and physical interaction, and the corresponding capability matching score is calculated. Calculate the location matching score, time matching score, and historical performance matching score corresponding to the executor and the subtask. Then, calculate the capability matching score, location matching score, time matching score, and historical performance matching score by weighting them according to preset weights to obtain the corresponding comprehensive matching score. For multiple sorted subtasks, filter available executors that meet the execution requirements based on their status, location, and load; The executor with the highest comprehensive matching score is selected from the available executors and assigned to the corresponding subtask. The status information of the corresponding executor is updated synchronously. After all subtasks are traversed and the assignment is completed, the initial arrangement result corresponding to the target spatiotemporal task is generated.

6. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 1, characterized in that, The step of identifying the collaborative relationships between the executors based on the initial orchestration result, and adjusting the collaborative scheduling of each executor based on the collaborative relationships to generate the target orchestration result corresponding to the target spatiotemporal task includes: Based on the initial arrangement results, complementary, substitutive, and collaborative relationships among the executors are identified as the collaborative relationships among the executors. By combining time, space, and execution resource constraints, and based on the collaborative relationship, the executor combination and task allocation in the initial orchestration result are coordinated and adjusted to generate the target orchestration result corresponding to the target spatiotemporal task.

7. The spatiotemporal task intelligent orchestration method for multiple executors according to claim 1, characterized in that, After generating the target orchestration result corresponding to the target spatiotemporal task, the multi-actor spatiotemporal task intelligent orchestration method further includes: Real-time detection of whether resource conflicts, time conflicts, or spatial conflicts occur during the execution of the target spatiotemporal task; wherein, the resource conflict is multiple subtasks competing for the same execution resource, the time conflict is multiple tasks of the same executor with overlapping time windows, and the spatial conflict is multiple executors having conflicting execution spaces; When multiple conflicts are detected, the priority order for conflict handling is determined based on pre-configured task priorities and executor priorities. Each conflict is processed sequentially according to the priority order, and the corresponding conflict is resolved during the processing by at least one of the following: time window adjustment, execution space reallocation, execution resource reallocation, or executor rematch. The target orchestration result corresponding to the target spatiotemporal task is updated synchronously.

8. A spatiotemporal task intelligent orchestration system with multiple executors, characterized in that, include: The profile information acquisition module is used to acquire corresponding profile information for executors of multiple different spatial elements within the target digital space. The task decomposition module is used to acquire the target spatiotemporal task to be executed in the target digital space, perform multi-dimensional data analysis on the target spatiotemporal task, and decompose the target spatiotemporal task into multiple different sub-tasks based on the analysis results. The task and executor matching module is used to match each of the sub-tasks with the profile information corresponding to different executors, obtain the matching score of different executors under each sub-task, and assign a corresponding executor to each sub-task based on the size of the matching score, and generate the initial arrangement result corresponding to the target spatiotemporal task. The collaborative scheduling module is used to identify the collaborative relationships between the executors based on the initial orchestration results, and to perform collaborative scheduling adjustments on the executors based on the collaborative relationships, thereby generating the target orchestration results corresponding to the target spatiotemporal task.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the spatiotemporal task intelligent orchestration method for multiple executors as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the spatiotemporal task intelligent orchestration method for multiple executors as described in any one of claims 1 to 7.

Images