Method, device and medium for determining tasks of unmanned engineering machinery equipment

Abstract

The embodiment of the application provides a task determination method, device and equipment of unmanned engineering machinery and medium. The application relates to the field of task determination of unmanned engineering machinery, and the method comprises the following steps: in response to an assignment instruction of a plurality of to-be-completed tasks, a target unmanned engineering machinery device acquires metadata information of each to-be-completed task; according to the metadata information of each to-be-completed task and state information of the target unmanned engineering machinery device, the probability that the target unmanned engineering machinery device selects each to-be-completed task is obtained; and the target unmanned engineering machinery device determines a target to-be-completed task according to the probability of each to-be-completed task. The method is used to improve the task receiving efficiency of the unmanned engineering machinery device.

Description

Technical Field

[0001] This application relates to the field of task determination for unmanned engineering machinery and equipment, and more particularly to a method, apparatus, equipment, and medium for panoramic segmentation. Background Technology

[0002] With the expansion of engineering construction scale and the increasing demand for intelligent systems, unmanned engineering machinery cluster operations have become the core direction of industry development.

[0003] In complex scenarios such as earthwork excavation, road construction, and mining, existing technologies generally adopt a centralized control model for task allocation in construction machinery. This means that a control center assigns tasks to construction machinery based on the task and the operating status of each piece of equipment. However, in dynamic operating environments, task status and equipment operation are not fixed. Therefore, existing technologies suffer from the technical problem of low efficiency in determining tasks for unmanned construction machinery. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for determining tasks for unmanned construction machinery, in order to improve the efficiency of task determination for unmanned construction machinery.

[0005] In a first aspect, embodiments of this application provide a method for determining the task of unmanned engineering machinery, including:

[0006] The target unmanned engineering machinery responds to the assignment instructions for multiple tasks to be completed and obtains the metadata information for each task to be completed;

[0007] Based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery, the probability of the target unmanned construction machinery selecting each task to be completed is obtained;

[0008] The target unmanned engineering machinery equipment determines the target tasks to be completed based on the probability of each task to be completed.

[0009] In one possible implementation, the metadata information for each task to be completed includes: location information, required resources, task completion criteria, and reward mechanism.

[0010] In one possible implementation, the status information of the target unmanned construction machinery includes its own status information and environmental information; wherein, the own status information includes: equipment location information, equipment power or oil level information and equipment wear information; the environmental information is used to characterize the environmental conditions in which the target unmanned construction machinery is located within a preset range.

[0011] In one possible implementation, based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery, the probability of the target unmanned construction machinery selecting each task to be completed is obtained, including:

[0012] Based on the metadata information of each task to be completed, determine the priority, urgency, and expected benefits of each task.

[0013] Based on priority information, urgency information, and expected benefit information, determine the concentration information for each task to be completed;

[0014] Based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, the expected benefits of the target unmanned engineering machinery in completing each task to be completed are obtained;

[0015] Based on the concentration information of each task to be completed and the expected benefits of the target unmanned engineering machinery equipment in completing each task, the probability of the target unmanned engineering machinery equipment selecting each task to be completed is obtained.

[0016] In one possible implementation, based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, the expected benefits of the target unmanned engineering machinery in completing each task to be completed are obtained, including:

[0017] Based on the reward mechanism for each task to be completed, determine the task reward information for the target unmanned engineering machinery equipment for each task to be completed;

[0018] Based on the location information of the target unmanned construction machinery and the location information of each task to be completed, the distance information between the target unmanned construction machinery and each task to be completed is obtained.

[0019] Based on the resources required for each task to be completed and the task completion criteria, as well as the status information of the target unmanned engineering machinery, the expected cost for the target unmanned engineering machinery to complete each task to be completed is obtained.

[0020] Based on task reward information, distance information, and expected costs, the expected benefits of the target unmanned engineering machinery equipment in completing each task are obtained.

[0021] In one possible implementation, after determining the target task to be completed, the process includes:

[0022] The target unmanned construction machinery will determine the task assignment information for the target task to be completed and send it to all unmanned construction machinery.

[0023] When the target unmanned construction machinery is performing the target task, the working position and operating status of the target unmanned construction machinery will be sent to unmanned construction machinery within the preset range.

[0024] In one possible implementation, it also includes:

[0025] The target unmanned engineering machinery responds to the assignment instructions of multiple tasks to be completed, and obtains the metadata information of each task to be completed according to the task assignment contract of the blockchain. The task assignment contract is used to manage the task operation cycle of all tasks in the blockchain, which includes task release, task confirmation and acceptance, task execution and task completion.

[0026] Secondly, embodiments of this application provide a task determination device for unmanned engineering machinery, comprising:

[0027] The response module is used by the target unmanned engineering machinery equipment to respond to the assignment instructions of multiple tasks to be completed and to obtain the metadata information of each task to be completed.

[0028] The processing module is used to obtain the probability of the target unmanned construction machinery selecting each task based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery.

[0029] The determination module is used to determine the target unmanned engineering machinery equipment to complete the target tasks based on the probability of each task to be completed.

[0030] In one possible implementation, the metadata information for each task to be completed includes: location information, required resources, task completion criteria, and reward mechanism.

[0031] In one possible implementation, the status information of the target unmanned construction machinery includes its own status information and environmental information; wherein, the own status information includes: equipment location information, equipment power or oil level information and equipment wear information; the environmental information is used to characterize the environmental conditions in which the target unmanned construction machinery is located within a preset range.

[0032] In one possible implementation, the processing module is further configured to:

[0033] Based on the metadata information of each task to be completed, determine the priority, urgency, and expected benefits of each task.

[0034] Based on priority information, urgency information, and expected benefit information, determine the concentration information for each task to be completed;

[0035] Based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, the expected benefits of the target unmanned engineering machinery in completing each task to be completed are obtained;

[0036] Based on the concentration information of each task to be completed and the expected benefits of the target unmanned engineering machinery equipment in completing each task, the probability of the target unmanned engineering machinery equipment selecting each task to be completed is obtained.

[0037] In one possible implementation, the processing module is further configured to:

[0038] Based on the reward mechanism for each task to be completed, determine the task reward information for the target unmanned engineering machinery equipment for each task to be completed;

[0039] Based on the location information of the target unmanned construction machinery and the location information of each task to be completed, the distance information between the target unmanned construction machinery and each task to be completed is obtained.

[0040] Based on the resources required for each task to be completed and the task completion criteria, as well as the status information of the target unmanned engineering machinery, the expected cost for the target unmanned engineering machinery to complete each task to be completed is obtained.

[0041] Based on task reward information, distance information, and expected costs, the expected benefits of the target unmanned engineering machinery equipment in completing each task are obtained.

[0042] In one possible implementation, the determining module is further configured to:

[0043] The target unmanned construction machinery will determine the task assignment information for the target task to be completed and send it to all unmanned construction machinery.

[0044] When the target unmanned construction machinery is performing the target task, the working position and operating status of the target unmanned construction machinery will be sent to unmanned construction machinery within the preset range.

[0045] In one possible implementation, the response module is also used for:

[0046] The target unmanned engineering machinery responds to the assignment instructions of multiple tasks to be completed, and obtains the metadata information of each task to be completed according to the task assignment contract of the blockchain. The task assignment contract is used to manage the task operation cycle of all tasks in the blockchain, which includes task release, task confirmation and acceptance, task execution and task completion.

[0047] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0048] The memory stores computer-executed instructions;

[0049] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0050] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0051] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0052] The task determination method, apparatus, equipment, and medium for unmanned construction machinery provided in this application embodiment allow the target unmanned construction machinery to first acquire metadata information for each task after receiving allocation instructions for multiple tasks to be completed. Then, the target unmanned construction machinery, combined with its own state information, calculates the probability of selecting each task using a built-in algorithm. Based on the probability of selecting each task, the target unmanned construction machinery autonomously determines the final task to be executed. This achieves decentralized and intelligent task allocation, enabling the unmanned construction machinery to make adaptive decisions based on global task information and its own operating conditions, effectively improving task execution efficiency and resource utilization. Attached Figure Description

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0054] Figure 1 Flowchart of the task determination method for unmanned engineering machinery provided in this application Figure 1 ;

[0055] Figure 2 Flowchart of the task determination method for unmanned engineering machinery provided in this application Figure 2 ;

[0056] Figure 3 A schematic diagram of the task determination device for unmanned engineering machinery provided in this application;

[0057] Figure 4 A hardware schematic diagram of the task determination device for unmanned engineering machinery provided in this application.

[0058] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0059] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and approaches consistent with some aspects of this application as detailed in the appended claims.

[0060] In complex scenarios such as earthwork excavation, road construction, and mining, traditional manual operation and centralized control systems are insufficient to meet the demands of large-scale, highly dynamic, and multi-device collaborative operations. For example, in large-scale earthwork projects, dozens of excavators, transport vehicles, bulldozers, and other equipment need to dynamically adjust their operational strategies in real time based on task priorities, equipment status (such as battery power and bucket capacity), terrain changes, and sudden environmental disturbances (such as obstacles and weather changes). However, existing centralized control models suffer from high single-point failure risks, low task allocation efficiency, and insufficient handling of complex task dependencies, leading to high equipment idle rates, frequent operational conflicts, and even potential safety accidents. Furthermore, in dynamic environments, centralized systems struggle to quickly respond to changes in task status (such as temporarily added tasks or adjustments to task priorities), resulting in a decline in overall operational efficiency. Therefore, a decentralized task allocation mechanism is urgently needed, enabling each unmanned construction machinery device to make autonomous decisions based on real-time status and global task information, achieving efficient, safe, and collaborative cluster operations.

[0061] To address the aforementioned technical issues, this application provides a method, apparatus, equipment, and medium for determining tasks in unmanned construction machinery. Upon receiving assignment instructions for multiple tasks to be completed, the target unmanned construction machinery acquires metadata information for each task. Combining its own status information and the metadata information of each task, the target unmanned construction machinery calculates the probability of selecting each task. Based on this probability, the target unmanned construction machinery determines the target task to be acquired. This achieves intelligent and adaptive task acquisition, enabling the unmanned construction machinery to proactively acquire tasks based on global task information and its own operating conditions, rather than passively waiting for task assignment from the control center, effectively improving the accuracy and reliability of task execution in complex operating environments.

[0062] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0063] Figure 1 Flowchart of the task determination method for unmanned engineering machinery provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0064] S101. The target unmanned engineering machinery equipment responds to the assignment instructions of multiple tasks to be completed and obtains the metadata information of each task to be completed.

[0065] In this embodiment, the target unmanned construction machinery acquires structured metadata information of all tasks to be completed. This metadata ensures the global consistency of task information. By providing the target unmanned construction machinery with the global perspective required for decision-making, it is transformed from a passive execution unit that can only respond to a single command into an intelligent agent capable of overseeing the overall task situation. This marks a fundamental shift from traditional "push-based" task scheduling to "pull-based" autonomous decision-making, laying the foundation for subsequent intelligent selection.

[0066] S102. Based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery, obtain the probability of the target unmanned construction machinery selecting each task to be completed.

[0067] In this embodiment, after acquiring global task metadata, the target unmanned construction machinery synchronously calls upon its sensors to collect or reads its real-time self-state information from local storage. The decision probability calculation model built into the target unmanned construction machinery performs multi-dimensional matching and calculation between the task metadata and its own state, calculating the probability value of the equipment selecting each task to be completed. The probability calculated in this step is not a simple random assignment, but rather a quantitative reflection of the comprehensive expected benefits of the target unmanned construction machinery in performing different tasks. This makes the decision-making process both efficiency-oriented and cost-sensitive, demonstrating the rational decision-making capability of the autonomous intelligent agent.

[0068] S103. The target unmanned engineering machinery equipment determines the target tasks to be completed based on the probability of each task to be completed.

[0069] In this embodiment, the target unmanned construction machinery equipment determines a specific task as its "target task to be completed" based on the calculated probability value of each task to be completed, through a preset selection mechanism. This step transforms the decision intention calculated in the previous steps, which is still in the probability space, into a deterministic execution action. This enables the target unmanned construction machinery equipment to achieve efficient, dynamic, and adaptive task allocation and execution through autonomous decision-making without real-time intervention from a central scheduler, greatly improving the overall efficiency and adaptability of the operating system in complex construction environments.

[0070] The task determination method for unmanned construction machinery provided in this application involves the target unmanned construction machinery responding to allocation instructions for multiple tasks to be completed, acquiring metadata information for each task to be completed; obtaining the probability of the target unmanned construction machinery selecting each task based on the metadata information of each task to be completed and the state information of the target unmanned construction machinery; and determining the target task to be completed based on the probability of each task to be completed. This method realizes the autonomous decision-making process of the target unmanned construction machinery after receiving multi-task instructions, promotes the transformation of task allocation mode from centralized scheduling to autonomous application, and enables the unmanned construction machinery to actively initiate task acquisition behavior based on the global task situation and its own state, significantly enhancing the adaptability of task execution and the overall reliability of the system in dynamic operation scenarios.

[0071] Figure 2 Flowchart of the task determination method for unmanned engineering machinery provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the method for determining the task of unmanned construction machinery is described in detail. Steps S201 to S205 yield the probability of the target unmanned construction machinery selecting each task to be completed. Steps S206 to S207 enable the target unmanned construction machinery to determine and execute the target task to be completed. This method includes:

[0072] S201. The target unmanned engineering machinery equipment responds to the assignment instructions of multiple tasks to be completed and obtains the metadata information of each task to be completed.

[0073] In this embodiment, the target unmanned engineering machinery responds to the assignment instructions of multiple tasks to be completed and obtains the metadata information of each task to be completed according to the task assignment contract of the blockchain. The task assignment contract is used to manage the task operation cycle of all tasks in the blockchain. The task operation cycle includes task release, task confirmation and acceptance, task execution and task completion.

[0074] The target unmanned engineering machinery equipment accesses the blockchain network to query and invoke the "task allocation contract" deployed on the chain to obtain metadata information for all tasks to be completed. This task allocation contract is an automatically executing smart contract code whose core function is to act as a "public task register" and "rule executor," responsible for the entire lifecycle management of the entire state flow from task publication, assignment, execution to final completion verification and settlement, ensuring that the current state of any task is consistent, visible, and immutable to all network participants. The significance of blockchain here is that it provides a trusted data source and execution environment for distributed collaboration without the need for mutually trusted third parties, fundamentally avoiding the single point of failure, data tampering, and unfair scheduling problems that may exist in centralized systems.

[0075] Optionally, the metadata information for each task to be completed includes: location information, required resources, task completion criteria, and a reward mechanism. Location information includes not only the global coordinates or relative reference system coordinates of the task execution point, but also typically includes a description of the spatial boundaries of the work area, path points allowing equipment entry and exit, and spatial association information with related tasks (such as pick-up and unload points). This provides precise input for equipment path planning and navigation. Required resources are a clear definition of the capabilities and conditions necessary to perform the task. It is typically detailed as: equipment type requirements, core tool specifications, energy type and minimum reserves, and necessary sensor or actuator configurations. Task completion criteria are an objective measurement system that quantifies when a task is considered successfully completed. It usually consists of a set of detectable and verifiable indicators, such as: the total volume of material to be handled, the required flatness error range, the latest deadline for task completion, the maximum allowable energy consumption limit, and the safety regulations that must be met. The reward mechanism is an economically driven model that incentivizes equipment to proactively take on and efficiently complete tasks. Its design is highly flexible and strategic, aiming to guide the system to exhibit the desired overall behavior. Common mechanisms include: fixed base rewards linked to task difficulty and urgency; performance-based variable rewards to encourage efficient completion; and dynamic waiting rewards that automatically increase over time to prevent task starvation. Rewards can be settled in the system as credit points, tokens redeemable for services or priority access, or other forms of virtual incentives. This mechanism transforms task allocation from a simple scheduling problem into a self-optimizing problem that can be addressed through market mechanisms.

[0076] At the implementation level, the target device initiates a contract query call to the network through its integrated blockchain node module or light client. Taking a specific earthwork engineering task allocation as an example, after the central control system publishes a series of sub-tasks such as "earthwork excavation in area A," "material loading in area B," and "slag transportation at point C" to the blockchain, the metadata of these tasks is permanently recorded on the chain. After the target unmanned construction machinery equipment (such as an unmanned excavator) is started, it will automatically send a query request to the task allocation contract. The contract then returns a structured task list, in which the metadata of each task includes precise location information (such as GPS coordinates or relative beacon position), required resources (such as requiring the equipment type to be "excavator" and the bucket capacity to be greater than 2 cubic meters), task completion standards (such as excavation depth, volume, and flatness requirements), and reward mechanism. The reward mechanism here is a key economic model driving the self-organizing operation of the system, and its design can be diversified: for example, the "earthwork excavation in area A" task may be assigned a higher base reward score due to its urgency; the "material loading in area B" task may adopt a floating incentive where "the shorter the completion time, the higher the reward bonus"; while the "slag transportation at point C" task may adopt a piece-rate reward system based on "settlement according to actual transportation trips". This differentiated reward mechanism aims to guide equipment resources to flow naturally towards high-priority, high-efficiency operational links.

[0077] This step establishes a "single trusted source" for global task information, ensuring all devices make decisions based on the same immutable data, thus eliminating conflicts caused by information inconsistencies at the source. Secondly, the blockchain and smart contract-based architecture enables truly decentralized task publishing and access, making the system extremely robust. The failure of any single point (including traditional central servers) will not affect other devices' ability to continue acquiring tasks and functioning normally. Finally, structured metadata provides rich and accurate input for subsequent intelligent decision-making, enabling devices to perform quantitative benefit assessments rather than responding based on simple rules or fixed instructions. This is the cornerstone for achieving adaptive, intelligent task acquisition and collaboration. Through this step, unmanned engineering machinery transforms from a passive execution terminal into an autonomous intelligent agent capable of proactively sensing the global task situation.

[0078] S202. Based on the metadata information of each task to be completed, determine the priority information, urgency information, and expected benefit information of each task to be completed; based on the priority information, urgency information, and expected benefit information, determine the concentration information of each task to be completed; based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, obtain the expected benefit of the target unmanned engineering machinery in completing each task to be completed.

[0079] In this embodiment, the priority information of a task is usually preset by the task issuer or dynamically calculated in the contract based on the critical path of the project. For example, tasks associated with subsequent processes have higher priority. The urgency information can be dynamically determined based on the difference between the task deadline and the current time, or the duration of the task in the waiting queue. The expected benefit information is directly related to the reward mechanism in the metadata and can be calculated by combining the basic reward and possible performance-based floating rewards.

[0080] Optionally, the concentration information of each task to be completed essentially simulates the concept of "pheromone" in ant colony optimization. The numerical value intuitively reflects the overall urgency and value of the task at the global level, providing a global signal to guide equipment resources to high-value tasks. Concentration information is positively correlated with priority information, urgency information, and expected benefit information.

[0081] Optionally, while calculating the concentration information for each task to be completed, the target unmanned construction machinery simultaneously initiates an individualized assessment of its own execution capabilities, i.e., calculating the expected benefits of completing each task. This assessment deeply integrates task metadata with the real-time status information of the equipment. The status information of the target unmanned construction machinery includes its own status information and environmental information; the own status information includes: equipment location information, equipment battery or fuel level information, and equipment wear information; the environmental information is used to characterize the environmental conditions in which the target unmanned construction machinery is located within a preset range.

[0082] Optionally, equipment location information (usually provided by GNSS / RTK modules) is used to calculate the spatial distance to the task point; equipment battery or fuel level information determines the equipment's continuous operating capability and range; equipment wear information (such as engine hours and wear coefficients of key components) affects the risk and efficiency of performing high-load tasks. Environmental information, as a crucial supplement, is acquired through lidar, millimeter-wave radar, and visual sensors to characterize the environmental conditions within a preset range (e.g., a 50-meter radius), including the distribution of static obstacles, the movement of dynamic objects (such as other equipment and personnel), terrain slope, and road conditions. This information directly affects the complexity of path planning and driving safety costs. Calculating expected benefits is the process of matching and simulating task metadata (such as required resources and completion standards) with this multi-dimensional state information. For example, a leveling task requiring high-precision positioning is more likely to benefit equipment with good GNSS signals; a long-distance transportation task is more beneficial for equipment with sufficient battery power and low current load.

[0083] This step transforms abstract metadata into calculable concentration and benefit values, providing precise and quantifiable input for subsequent probability-based intelligent decision-making. This shifts the decision-making process from rule-based hard coding to optimization-based soft computing. Concentration information guides the target unmanned construction machinery (UCH) to focus on tasks crucial to the overall project schedule, preventing all UCH from rushing to simple, low-value tasks. Expected benefits ensure that resources are allocated prudently, selecting the most efficient and cost-effective task within the current context, achieving optimal resource allocation. By integrating dynamic environmental information in real-time, this step endows the decision-making system with contextual awareness, enabling it to adapt to complex and changing on-site conditions. For example, it automatically avoids tasks whose benefits drastically decrease due to temporary obstacles or congested areas, thereby enhancing the robustness and practicality of the entire task determination process.

[0084] S203. Based on the reward mechanism of each task to be completed, determine the task reward information of the target unmanned construction machinery for each task to be completed; based on the equipment location information of the target unmanned construction machinery and the location information of each task to be completed, obtain the distance information between the target unmanned construction machinery and each task to be completed; based on the resources required for each task to be completed and the task completion standards, as well as the status information of the target unmanned construction machinery, obtain the expected cost for the target unmanned construction machinery to complete each task to be completed.

[0085] In this embodiment, the target unmanned construction machinery determines the task reward information by parsing the reward mechanism of each task to be completed in the blockchain task allocation contract. This process is not simply reading a fixed value, but requires evaluating a total expected return based on preset dynamic calculation rules. For example, the reward mechanism for a "dust loading" task may stipulate: a basic reward of 50 credits, an additional 20 credits if completed within 30 minutes, and an additional 10 credits if the loading exceeds the standard by 10%. The target unmanned construction machinery needs to dynamically calculate an expected task reward based on its current status (such as remaining battery power and distance from the task point) and estimated capabilities (such as loading rate). This value may be a probability-based expected value. For example, if it is estimated that there is an 80% probability of triggering the efficiency reward, then the total expected reward value is 50 + 0.8(20 + 10) = 74 credits.

[0086] Optionally, the target unmanned engineering machinery utilizes its built-in positioning system (such as GNSS / RTK) to provide precise self-location information, and combines this with the mission's geographical location information obtained from metadata, to calculate the distance between the two through spatial geometric calculations (such as Euclidean distance or actual path planning distance). This distance information is a key factor in measuring the energy consumption and time cost required to perform the mission.

[0087] Optionally, the target unmanned engineering machinery equipment can calculate the expected cost through simulation. This requires a detailed matching and wear estimation of the task's "required resources" and "completion standards" with the equipment's own status information. For example, for a "deep compaction" task, the required resources are a "heavy-duty road roller with a working weight ≥ 20 tons," and the completion standard is "compaction degree reaching 95%, covering an area of ​​1000 square meters." The equipment needs to be assessed for: whether it meets the equipment type and specification requirements; based on its current wear status (such as engine efficiency and hydraulic system status) and historical data, the fuel or electricity consumption required to complete the compaction work of this area (energy cost); the additional equipment wear that may result from performing this high-intensity task (wear cost); and even the potential increase in operating time or risk (risk and time cost) based on real-time environmental information (such as ground slope and soil moisture). All these estimated cost items will be summarized to form a total expected cost.

[0088] This step empowers the target unmanned construction machinery to autonomously maximize its individual utility. By incorporating distance and expected costs, it naturally achieves "proximity-based allocation" and "capability matching" of tasks. For example, an unmanned construction machinery with sufficient battery power and low wear will tend to choose large tasks that are far away but offer high rewards, while an unmanned construction machinery with low battery power will rationally choose smaller tasks nearby, achieving load balancing and resource optimization. The ability to dynamically calculate rewards and costs gives the unmanned construction machinery extremely strong environmental adaptability. When the task reward mechanism changes, the unmanned construction machinery's own condition deteriorates, or the operating environment deteriorates, the unmanned construction machinery's benefit assessment of the same task will change in real time, thereby dynamically adjusting its decision preferences to ensure that it can continuously adapt to internal and external changes and maintain efficient and stable operation.

[0089] S204. Based on the task reward information, distance information, and expected cost, obtain the expected benefits of the target unmanned engineering machinery equipment in completing each task to be completed.

[0090] In this embodiment, the expected benefits of the target unmanned engineering machinery equipment in completing each task can be obtained according to the following formula:

[0091]

[0092] Where, n i R represents the expected benefit of an unmanned engineering machinery device completing the i-th task to be completed. i D represents the task reward information for the i-th unmanned engineering machinery equipment to complete the task; i Let C be the distance information between the target unmanned engineering machinery and the i-th task to be completed; let C be the expected cost for the target unmanned engineering machinery to complete the i-th task.

[0093] S205. Based on the concentration information of each task to be completed and the expected benefits of the target unmanned engineering machinery equipment in completing each task to be completed, obtain the probability of the target unmanned engineering machinery equipment selecting each task to be completed.

[0094] In this embodiment, the probability of the target unmanned engineering machinery selecting each task to be completed can be calculated according to the following formula:

[0095]

[0096] Among them, P i The probability of selecting the i-th task to be completed for the target unmanned engineering machinery equipment; For the concentration information of the i-th task to be completed; n i The expected benefit of the target unmanned engineering machinery equipment completing the i-th task to be completed; α is the weight of the concentration information, used to adjust the importance of the concentration information; β is the weight of the expected benefit, used to adjust the importance of the expected benefit.

[0097] In one possible implementation, α and β can be adaptively adjusted based on the metadata information of the task to be completed and the status information of the target unmanned construction machinery. For example, when the metadata of the task to be completed indicates that its urgency or global priority is extremely high (such as a rescue mission or a task located on the critical path of a project), the value of α is automatically increased. This amplifies the influence of the inherent "concentration" (urgency) of the task in decision-making, prompting the equipment group to prioritize such tasks and ensuring that critical nodes are not delayed, even if the immediate "expected benefit" of an individual unmanned construction machinery performing the task may not be the highest. For tasks marked with high environmental complexity (such as confined spaces or underground operations) or high uncertainty (such as unclear geological conditions) in the metadata, α can be moderately increased and β decreased. In complex environments, accurately predicting "expected benefits" is very difficult, and its value may be unreliable. Increasing the reliance on concentration information can reduce the decision-making risk caused by incorrect benefit assessment and guide the equipment to perform more certain and necessary tasks.

[0098] Optionally, when the target unmanned construction machinery's energy level is low, the β value should be significantly increased. This is because the primary goal of the target unmanned construction machinery at this time is to maximize the return on limited energy or to complete a task as quickly as possible that allows it to return to charging / refueling. A high β value makes the target unmanned construction machinery more inclined to choose tasks with the highest "expected benefit" per unit of energy consumption, avoiding failure due to performing low-efficiency tasks, thereby improving the survivability of individual machines and the overall task completion rate of the system. When critical components experience increased wear or the equipment's health status is alarming, the α value can be increased and the β value decreased. The risk of failure or further damage to unhealthy unmanned construction machinery performing high-load, high-efficiency tasks increases dramatically. In this case, it should be guided to prioritize tasks that are critical to the system but may have a milder load and be driven by "concentration," or pre-maintenance preparation tasks, rather than risking high efficiency. Unmanned construction machinery can maintain a historical record of its performance on different types of tasks. If the unmanned construction machinery consistently performs well in a certain task (high success rate, good efficiency), it can be given a higher β weight on similar new tasks to encourage it to continue to leverage its strengths. Conversely, it may reduce β, making it more dependent on the global task concentration α for selection, thus achieving a capability-based soft load balancing.

[0099] S206. The target unmanned engineering machinery equipment determines the target tasks to be completed based on the probability of each task to be completed.

[0100] In this embodiment, the probabilistic evaluation results are transformed into deterministic execution actions. The core of this approach is to achieve an intelligent decision-making mechanism that balances efficiency and exploratory nature. The method for selecting a target unmanned engineering machinery device to complete a task includes, but is not limited to, selecting the task with the highest probability, employing a probability distribution-based random selection strategy (such as roulette wheel selection) or a hybrid strategy (such as an ε-greedy strategy).

[0101] Optionally, a random selection strategy can ensure that the target unmanned engineering machinery equipment tends to select the task with the best expected benefits (utilizing existing knowledge) while retaining the possibility of exploring low-probability but potentially high-value tasks (exploring unknown opportunities), thereby avoiding local optima and enhancing the system's adaptability in dynamic environments.

[0102] For example, the target unmanned construction machinery first constructs a probability wheel based on the selection probability of each task to be completed calculated in step S205, where the area of ​​the sector occupied by each task is proportional to its probability value. Then, the target unmanned construction machinery generates a random number; the task whose sector it falls into is selected as the target task to be completed. For example, suppose there are three tasks A, B, and C, with selection probabilities of 0.5, 0.3, and 0.2, respectively. The device generates a random number of 0.76. Since 0.5(A) + 0.3(B) = 0.8 > 0.76, and 0.76 > 0.5(A), the random number falls within the range of task B. Therefore, the target unmanned construction machinery ultimately selects task B instead of the highest-probability task A. This mechanism ensures that even tasks with lower probabilities have a chance to be selected, preventing all devices from prematurely converging on the same "seemingly optimal" task, thus avoiding resource congestion.

[0103] This step, by introducing randomness, breaks the "local optimum" trap that traditional greedy algorithms may lead to, enabling the unmanned construction machinery swarm to explore a wider range of task selection options and thus discover a globally superior collaborative pattern in the long run. Secondly, probabilistic selection provides the unmanned construction machinery with inherent load balancing capabilities, as different machines make differentiated choices based on their independently generated random numbers, naturally achieving a distributed allocation of tasks. Finally, this decision-making approach aligns closely with the philosophy of swarm intelligence algorithms (such as ant colony optimization), allowing the entire unmanned construction machinery swarm to exhibit complex, adaptive collaborative efficiency through the simple probabilistic behavior of individual machines, ultimately improving the robustness and overall efficiency of task execution in complex operating environments.

[0104] S207. The target unmanned construction machinery equipment will send the task acquisition information of the target task to be completed to all unmanned construction machinery equipment; and when the target unmanned construction machinery equipment is performing the target task, it will send the working position and operating status of the target unmanned construction machinery equipment to the unmanned construction machinery equipment within the preset range.

[0105] In this embodiment, after autonomously determining the task to be executed, the target unmanned construction machinery equipment immediately initiates a crucial dual communication mechanism to transform individual decisions into public information that can be perceived and collaboratively utilized by the group. The design principle of this step stems from the fundamental needs of "consensus" and "coordination" in distributed collaborative systems, aiming to solve the problems of task conflicts, resource competition, and path interference caused by limited local visibility among devices. The target unmanned construction machinery equipment first broadcasts its "claim declaration" for the target task—including task identifier, claiming equipment identity, and timestamp—to all online unmanned construction machinery equipment in the network via a blockchain network or dedicated communication link. This broadcast is not a simple notification, but rather an on-chain confirmation and public announcement of the change in the task allocation contract status on the blockchain. Its technical essence is to declare the transfer of ownership of a specific task resource to the entire system, thereby logically marking the task as "occupied," fundamentally preventing other devices from repeatedly claiming the task, and establishing a task mutual exclusion lock mechanism in a decentralized environment.

[0106] Meanwhile, during the physical execution phase of the task, the target unmanned construction machinery continuously transmits its dynamic working position and operational status (such as speed, working posture, and current action) to neighboring unmanned construction machinery within a pre-defined physical range via low-latency local communication networks (such as 5G-V2X, Wi-Fi 6 mesh, or dedicated short-range communication). This design simulates the collaborative behavior of biological groups in nature through local perception. For example, an unmanned excavator performing an "earthmoving and loading" task will continuously broadcast the swing range of its bucket, the expected loading point location, and the direction of its intended movement to dump trucks and other equipment within a 50-meter radius. After receiving this information, nearby dump trucks can plan their reversing paths in advance to accurately dock at the loading point, while other equipment can adjust their own paths accordingly to maintain a safe distance and avoid entering the hazardous working area. This coordination based on local real-time state sharing enables complex collaborative operational behaviors to emerge in the equipment cluster, such as efficient cross-operations, safe dynamic obstacle avoidance, and smooth convoy movement, without relying on a central scheduler for millisecond-level micro-command.

[0107] This step ensures the consistency and fairness of task allocation, while the partial sharing of working status and location provides a data foundation for real-time and flexible on-site collaboration, significantly improving operational safety and overall efficiency, and enabling the equipment cluster to adaptively respond to dynamically changing on-site environments.

[0108] Figure 3 A schematic diagram of the task determination device for unmanned engineering machinery provided in this application is shown below. Figure 3 As shown, the task determination device 30 for unmanned engineering machinery equipment provided in this embodiment includes:

[0109] The response module 301 is used for the target unmanned engineering machinery equipment to respond to the assignment instructions of multiple tasks to be completed and to obtain the metadata information of each task to be completed.

[0110] The processing module 302 is used to obtain the probability of the target unmanned construction machinery selecting each task based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery.

[0111] The determination module 303 is used to determine the target unmanned engineering machinery equipment to complete the target task based on the probability of each task to be completed.

[0112] In one possible implementation, the metadata information for each task to be completed includes: location information, required resources, task completion criteria, and reward mechanism.

[0113] In one possible implementation, the status information of the target unmanned construction machinery includes its own status information and environmental information; wherein, the own status information includes: equipment location information, equipment power or oil level information and equipment wear information; the environmental information is used to characterize the environmental conditions in which the target unmanned construction machinery is located within a preset range.

[0114] In one possible implementation, the processing module 302 is further configured to:

[0115] Based on the metadata information of each task to be completed, determine the priority, urgency, and expected benefits of each task.

[0116] Based on priority information, urgency information, and expected benefit information, determine the concentration information for each task to be completed;

[0117] Based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, the expected benefits of the target unmanned engineering machinery in completing each task to be completed are obtained;

[0118] Based on the concentration information of each task to be completed and the expected benefits of the target unmanned engineering machinery equipment in completing each task, the probability of the target unmanned engineering machinery equipment selecting each task to be completed is obtained.

[0119] In one possible implementation, the processing module 302 is further configured to:

[0120] Based on the reward mechanism for each task to be completed, determine the task reward information for the target unmanned engineering machinery equipment for each task to be completed;

[0121] Based on the location information of the target unmanned construction machinery and the location information of each task to be completed, the distance information between the target unmanned construction machinery and each task to be completed is obtained.

[0122] Based on the resources required for each task to be completed and the task completion criteria, as well as the status information of the target unmanned engineering machinery, the expected cost for the target unmanned engineering machinery to complete each task to be completed is obtained.

[0123] Based on task reward information, distance information, and expected costs, the expected benefits of the target unmanned engineering machinery equipment in completing each task are obtained.

[0124] In one possible implementation, the determining module 303 is further configured to:

[0125] The target unmanned construction machinery will determine the task assignment information for the target task to be completed and send it to all unmanned construction machinery.

[0126] When the target unmanned construction machinery is performing the target task, the working position and operating status of the target unmanned construction machinery will be sent to unmanned construction machinery within the preset range.

[0127] In one possible implementation, the response module 301 is further configured to:

[0128] The target unmanned engineering machinery responds to the assignment instructions of multiple tasks to be completed, and obtains the metadata information of each task to be completed according to the task assignment contract of the blockchain. The task assignment contract is used to manage the task operation cycle of all tasks in the blockchain, which includes task release, task confirmation and acceptance, task execution and task completion.

[0129] The task determination device for unmanned engineering machinery provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0130] Figure 4 A hardware schematic diagram of the task determination device for the unmanned engineering machinery equipment provided in this application. (For example...) Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0131] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0132] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0133] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0134] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0135] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0136] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0137] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0138] The aforementioned readable 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 read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0139] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0140] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, methods, or units, and may be electrical, mechanical, or other forms.

[0141] The units described 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.

[0142] In addition, the functional units in the various embodiments of the present invention 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.

[0143] If a function 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 invention, or the part that contributes to the prior art, or a 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 several 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 invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0144] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0145] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining the task of unmanned engineering machinery, characterized in that, include: The target unmanned engineering machinery equipment responds to the assignment instructions of multiple tasks to be completed and obtains the metadata information of each task to be completed; Based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery, the probability of the target unmanned construction machinery selecting each task to be completed is obtained; The target unmanned engineering machinery equipment determines the target tasks to be completed based on the probability of each task to be completed.

2. The method according to claim 1, characterized in that, The metadata information for each task to be completed includes: location information, required resources, task completion criteria, and reward mechanism.

3. The method according to claim 1, characterized in that, The status information of the target unmanned construction machinery includes its own status information and environmental information; wherein, the own status information includes: equipment location information, equipment power or oil level information and equipment wear information; the environmental information is used to characterize the environmental conditions in which the target unmanned construction machinery is located within a preset range.

4. The method according to any one of claims 1-3, characterized in that, The step of obtaining the probability of the target unmanned construction machinery selecting each task based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery includes: Based on the metadata information of each task to be completed, determine the priority information, urgency information, and expected benefit information of each task to be completed; Based on the priority information, the urgency information, and the expected benefit information, determine the concentration information of each of the tasks to be completed; Based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery, the expected benefits of the target unmanned engineering machinery in completing each task to be completed are obtained; Based on the concentration information of each of the tasks to be completed and the expected benefits of the target unmanned engineering machinery equipment in completing each of the tasks to be completed, the probability of the target unmanned engineering machinery equipment selecting each of the tasks to be completed is obtained.

5. The method according to claim 4, characterized in that, The step of obtaining the expected benefits of the target unmanned engineering machinery equipment in completing each task based on the metadata information of each task to be completed and the status information of the target unmanned engineering machinery equipment includes: Based on the reward mechanism of each task to be completed, determine the task reward information of the target unmanned engineering machinery for each task to be completed; Based on the equipment location information of the target unmanned construction machinery and the location information of each task to be completed, the distance information between the target unmanned construction machinery and each task to be completed is obtained. Based on the resources required for each task to be completed and the task completion criteria, as well as the status information of the target unmanned engineering machinery, the expected cost for the target unmanned engineering machinery to complete each task to be completed is obtained. Based on the task reward information, the distance information, and the expected cost, the expected benefits of the target unmanned engineering machinery equipment in completing each of the tasks to be completed are obtained.

6. The method according to claim 1, characterized in that, After determining the target task to be completed, the process includes: The target unmanned construction machinery will determine the task assignment information of the target task to be completed and send it to all unmanned construction machinery. When the target unmanned construction machinery device performs the target task to be completed, the working position and operating status of the target unmanned construction machinery device are sent to unmanned construction machinery devices within a preset range.

7. The method according to claim 1, characterized in that, Also includes: The target unmanned engineering machinery responds to the assignment instructions of multiple tasks to be completed, and obtains the metadata information of each task to be completed according to the task assignment contract of the blockchain; wherein, the task assignment contract is used to manage the task operation cycle of all tasks in the blockchain, and the task operation cycle includes task release, task confirmation and acceptance, task execution and task completion.

8. A task determination device for unmanned engineering machinery, characterized in that, include: The response module is used for the target unmanned engineering machinery equipment to respond to the assignment instructions of multiple tasks to be completed and to obtain metadata information of each task to be completed; The processing module is used to obtain the probability that the target unmanned construction machinery will select each task to be completed based on the metadata information of each task to be completed and the status information of the target unmanned construction machinery. The determination module is used by the target unmanned engineering machinery equipment to determine the target task to be completed based on the probability of each task to be completed.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images