Targeted control method and system of drug-loaded nano robot

Abstract

The invention relates to the technical field of drug-loaded nano-robot control, and discloses a targeted control method and system for a drug-loaded nano-robot. The method comprises the following steps: building a task-resource matching model by receiving internal region division and treatment requirements of a living body and combining the performance and real-time position of a nano-robot; and according to the model, adopting a partition strategy to deploy the robot and optimize a control signal, and realizing accurate area distribution. And then planning a task time sequence of the treatment points, and analyzing intervals to formulate an execution plan. The matching degree of drug supply and robot endurance is evaluated, parameters are detected and adjusted to solve resource conflicts, and a steady drug delivery progress scheme is formed. And finally, executing the scheme, and dynamically regulating and controlling the instruction based on the real-time environment and state data. According to the method, fine scheduling and resource collaboration of the nano-robot cluster are realized, and the accuracy and efficiency of targeted drug delivery and the reliability of the treatment process are improved.

Description

Technical Field

[0001] This invention relates to the field of drug-loaded nanorobot control technology, specifically to a targeted control method and system for drug-loaded nanorobots. Background Technology

[0002] Drug-loaded nanorobots have shown great potential in disease treatment, particularly in targeted cancer therapy. Existing targeted control methods largely focus on guiding a swarm of nanorobots as a whole to the macroscopic lesion region. This control strategy relies on relatively simple navigation logic, such as utilizing chemotaxis or following a single external field gradient. This approach treats the treatment area as a homogeneous whole, lacking a structured understanding of the complex microenvironment within the organism.

[0003] Existing technical solutions have shortcomings. Because the target area is not finely divided and the performance differences between individual robots are not considered, drug distribution may be uneven. Some high-demand sub-regions may have insufficient drug dosage, while other areas may have excessive dosage, affecting efficacy and increasing the risk of side effects. Conventional control methods mainly focus on spatial arrival, and their task planning is often static and sequential, lacking management of resource coordination and conflicts over time. The working time of nanorobots is limited by the energy or drug reserves they carry, and drug metabolism and replenishment are also periodic. Static task sequences cannot cope with resource competition problems that arise during execution, leading to interruptions in treatment or significantly reduced efficacy.

[0004] This invention addresses the challenge of precisely and differentiatedly allocating nanorobot resources based on the heterogeneous characteristics of regions within an organism and dynamic treatment needs. It also addresses how to coordinate drug supply, robot energy consumption, and task execution timing over long treatment cycles to avoid resource conflicts and ensure the continuity and stability of the treatment plan. Summary of the Invention

[0005] The purpose of this invention is to provide a targeted control method and system for drug-loaded nanorobots to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides a method for targeted control of drug-loaded nanorobots, the method comprising: Receive data on the internal region division of organisms and parameters of drug treatment requirements, and combine the performance characteristics and real-time position information of nanorobots to establish a model of the correspondence between task requirements and robot resources; Based on the aforementioned correspondence model, a partitioned allocation strategy is adopted to deploy nanorobots to specific regions, while optimizing the control signal configuration to generate regional robot allocation results. Based on the regional robot allocation results, the task execution sequence and time arrangement of key treatment points are planned, the task interval is determined through time series analysis, and the task sequence plan is output. For the task sequence plan, the matching between the drug supply cycle and the robot working time is evaluated, resource conflicts are detected and task parameters are adjusted to form a conflict resolution strategy; By applying the aforementioned conflict resolution strategy, the task timeline and resource allocation scheme are reorganized to generate a detailed dosing schedule. The system executes the detailed drug administration schedule and collects environmental sensor data and robot status information in real time, dynamically adjusting control commands accordingly.

[0007] Preferably, the step of establishing the correspondence model between task requirements and robot resources specifically includes: Obtain the geometric dimensions and drug demand intensity of the partitioned volume region, as well as the working capacity and spatial coordinates of the nanorobot, and calculate the matching degree index between demand and resources; Using the matching degree index, construct a mapping table between requirement items and resource items, and mark the priority level; Verify the completeness and consistency of the association mapping table, and generate a correspondence model between task requirements and robot resources, specifically as follows: Iterate through each requirement item in the association mapping table and check whether there is at least one resource item corresponding to it. At the same time, iterate through each resource item and check whether it is assigned at least one requirement item. Verify whether the priority levels marked in the association mapping table are consistent with the predefined priority rules, including checking whether the priority values ​​are within a valid range and whether the level order is logically correct; When a missing correspondence or priority conflict is found between a requirement item and a resource item, the contents of the association mapping table are automatically adjusted, including supplementing the correspondence or correcting the priority level. After the integrity and consistency verification is passed, the adjusted association mapping table is converted into a correspondence model between task requirements and robot resources.

[0008] Preferably, the step of generating the regional robot allocation result specifically includes: Based on the correspondence model between the task requirements and robot resources, the priority order and resource constraints of each region are analyzed, and a dynamic allocation algorithm is used to determine the robot deployment scheme. Integrate control signal requirements with robot deployment plans, optimize signal transmission paths, and generate regional robot allocation results; The specific steps for analyzing the priority order and resource constraints of each region based on the correspondence model between task requirements and robot resources, and determining the robot deployment scheme using a dynamic allocation algorithm, are as follows: The priority order of each region is read from the correspondence model between the task requirements and robot resources, and a region sorting list is generated according to the priority. For each region, analyze the resource constraints, including the maximum number of robots available, the upper limit of robot working capacity, and spatial distribution constraints; A dynamic allocation algorithm is adopted, starting from the highest priority area and allocating robots according to the intensity of drug demand in the area, with the number of available robot resources updated in real time during allocation. During the allocation process, check whether the resource constraints are met. If resources are insufficient, pause the allocation and record the areas to be processed. Allocation will continue after the resources are released. The final output is a robot deployment scheme that satisfies the priority order and resource constraints.

[0009] Preferably, the steps for planning the output task sequence are as follows: Based on the regional robot allocation results, the task dependencies of key treatment points are identified, and the task start time and duration are calculated. The task execution order is arranged through a time-series optimization model to determine reasonable task intervals and generate a task sequence plan, specifically as follows: Based on task dependencies, a directed graph model of task sequences is constructed, where nodes represent tasks and directed edges represent the sequential dependencies between tasks. Calculate the earliest possible start time and the latest allowed start time for each task, and identify the set of tasks on the critical path; By adjusting the task order on non-critical paths using a time-series optimization model, and prioritizing tasks with close dependencies, the total task execution time can be reduced. Calculate the minimum safe interval between adjacent tasks based on task execution duration and resource availability to ensure no time conflicts. The optimized task sequence and safety intervals are integrated to generate the final task sequence plan.

[0010] Preferably, the step of forming a conflict resolution strategy specifically includes: Analyze the drug supply time points and robot availability time windows in the task sequence plan to detect overlapping conflicts and resource shortages. Adjust task time parameters and resource allocation ratios to resolve conflicts and generate conflict resolution strategies.

[0011] Preferably, the step of generating a detailed dosing schedule specifically includes: Based on the conflict resolution strategy, the task time points are recalculated and resource allocation is optimized, and the timeline and allocation scheme are integrated. Verify the feasibility and consistency of the schedule, and generate a detailed dosing schedule.

[0012] Preferably, the steps for dynamically adjusting the control command are as follows: Real-time monitoring of biological environmental change indicators and robot operation status data; comparison of planned progress with actual execution. Calculate the deviation value, adjust the control signal parameters, and update the control command.

[0013] Preferably, the step of calculating the matching degree index between demand and resources specifically includes: Collect data on drug demand and robot working capacity in different zones, and calculate the ratio of demand to resources; Summarize the ratio values ​​of each region to generate a matching index.

[0014] Preferably, the step of optimizing the control signal configuration specifically includes: Based on the regional robot allocation results, analyze the signal transmission requirements and optimize signal strength and frequency parameters; Adjust the signal configuration to match robot deployment and generate an optimized control signal configuration.

[0015] Preferably, the present invention also includes a targeting control system for a drug-loaded nanorobot, the system including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of the targeting control method for the drug-loaded nanorobot described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are: By establishing a model mapping task requirements to robot resources and implementing a partitioned allocation strategy and control signal optimization, fine-grained scheduling of nanorobot swarms was achieved. This method decomposes macroscopic treatment needs into specific sub-regions within the organism, while assigning differentiated tasks based on the performance characteristics of individual robots. This allows high-performance robots to be prioritized for deployment in areas with more pressing needs and to receive matching control parameters, thus changing the traditional extensive mode of controlling robot swarms as a homogeneous whole. It improves the uniformity and targeting accuracy of drug distribution within the target area, enhancing the specificity of treatment and the efficiency of local drug utilization.

[0017] By evaluating the matching between drug supply cycles and robot working time, and proactively detecting resource conflicts to adjust task parameters, a time-series-based dynamic programming and conflict resolution capability is formed. When generating task sequences, this method not only considers the logical order of tasks but also incorporates resource constraints such as drug replenishment and robot endurance as core planning elements for forward-looking simulation and verification. When multiple tasks are predicted to compete for the same limited resource, the system can resolve conflicts by adjusting task start times or execution rhythms. This ensures the feasibility and robustness of complex drug administration protocols in the time dimension, enabling the entire treatment process to execute smoothly according to the predetermined schedule, avoiding treatment interruptions or effect fluctuations caused by resource bottlenecks, and improving the reliability of the automated treatment system. Attached Figure Description

[0018] Figure 1 This is a schematic diagram illustrating the working principle of the targeted control method for the drug-loaded nanorobot described in this invention. Figure 2 A flowchart for establishing the correspondence model; Figure 3 A comparison chart of the actual allocation of nanorobots to the partitioned volume region and resource constraints; Figure 4 To output a flowchart of the task sequence plan; Figure 5 This is a graph showing the trend of deviation changes during real-time monitoring of the drug-loaded nanorobot treatment process. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1This invention provides a targeted control method for drug-carrying nanorobots. The method includes: receiving data on the internal region division of a biological organism and drug treatment requirement parameters; establishing a correspondence model between task requirements and robot resources by combining the performance characteristics and real-time position information of the nanorobots; deploying the nanorobots to specific regions using a partitioned allocation strategy based on the correspondence model, while optimizing the control signal configuration to generate regional robot allocation results; planning the task execution sequence and time arrangement for key treatment points based on the regional robot allocation results, determining task intervals through time series analysis, and outputting a task sequence plan; evaluating the matching between the drug supply cycle and robot working time for the task sequence plan, detecting resource conflicts and adjusting task parameters to form a conflict resolution strategy; applying the conflict resolution strategy to reorganize the task timeline and resource allocation scheme to generate a detailed drug administration schedule; executing the detailed drug administration schedule, and collecting environmental sensor data and robot status information in real time to dynamically adjust control commands.

[0021] Example 1: See Figure 2 In practical implementation, the geometric dimensions and drug demand intensity of the partitioned volume are obtained. The geometric dimensions of the partitioned volume include length, width, and height. The drug demand intensity is the minimum effective concentration of drug required per unit volume. Simultaneously, the working capacity and spatial coordinates of the nanorobots are obtained. The working capacity of the nanorobots is the maximum number of drug molecules that a single nanorobot can carry in a single mission. The spatial coordinates are the real-time three-dimensional position data of the nanorobots in the Cartesian coordinate system within the biological body. A matching degree index between demand and resources is calculated. This index quantifies the degree of agreement between the drug demand of the partitioned volume and the working capacity of the nanorobots. By processing the drug demand and nanorobot working capacity data of the partitioned volume, the demand-resource ratio is calculated. This ratio is the ratio of the drug demand of the partitioned volume to the working capacity of the nanorobots. The ratio values ​​of each region are summarized, and a normalization method is applied to generate a comprehensive matching degree index ranging from 0 to 1. The matching degree index is calculated using a matching degree calculation function, defined as follows: in: It is an indicator of the matching degree between demand item i and resource item j. This refers to the drug requirement in partition i. It is the average drug requirement for all regional body areas. This refers to the working capacity of nanorobot j. This represents the average working capacity of all nanorobots. In some embodiments, a mapping table between demand items and resource items is constructed using a matching degree index. A demand item is a unique identifier for a given area and its associated drug demand intensity data. A resource item is a unique number for a nanorobot and its associated working capacity and spatial coordinate data. The mapping table is a two-dimensional matrix structure, with rows representing demand items and columns representing resource items. The matrix element values ​​are calculated using the matching degree index. Priority levels are assigned to each demand item in the mapping table according to predefined medical urgency rules. Priority labels are integer values ​​from 1 to 10. In specific implementations, the integrity and consistency of the mapping table are verified. Integrity checks involve traversing each demand item in the mapping table to confirm that each demand item has at least one resource item with which it is mapped, and simultaneously traversing each resource item to confirm that each resource item is assigned to at least one demand item. Consistency checks verify whether the priority levels in the mapping table are consistent with predefined priority rules, including checking whether the priority values ​​are within the valid range of 1 to 10, and checking whether high-priority demand items always prioritize resource allocation over low-priority demand items. It is understandable that when a missing or conflicting priority level is found between a requirement item and a resource item, the content of the association mapping table is automatically adjusted. The adjustment operation for missing items involves establishing a mapping connection between the requirement item and the resource item. The adjustment operation for conflicting priority levels involves correcting erroneous priority label values ​​in the association mapping table according to predefined priority rules. In some embodiments, after integrity and consistency verification is passed, the adjusted association mapping table is converted into a correspondence model between task requirements and robot resources. The conversion process involves reorganizing the data structure of the association mapping table into a bipartite graph model with weighted attributes. One vertex set of the bipartite graph model represents all task requirement items, and the other vertex set represents all robot resource items. Edges represent feasible allocation relationships between task requirements and robot resources, and the weight attributes of the edges are determined by the matching degree index and the priority level. Optionally, the priority level label can be dynamically adjusted based on external input parameters. In specific implementations, the correspondence model between task requirements and robot resources is stored in memory in matrix form for quick access by subsequent partitioning allocation strategies. It is understood that the calculation of the matching degree index can be iterative to reflect real-time changes in drug demand or robot status.

[0022] Example 2: In specific implementation, the priority order and resource constraints of each region are analyzed based on the correspondence model between task requirements and robot resources. The correspondence model between task requirements and robot resources provides structured data on region priority values ​​and resource constraints. Resource constraints include the maximum number of available robots, the upper limit of robot working capacity, and spatial distribution constraints. The maximum number of available robots is the upper limit of the total number of nanorobots that can be put into operation simultaneously in the system. The upper limit of robot working capacity is the maximum drug load that a single nanorobot can handle per unit time. Spatial distribution constraints are the minimum safe interval distance that nanorobots must meet in the biological body. A dynamic allocation algorithm is used to determine the robot deployment scheme. The dynamic allocation algorithm reads the priority order of each region from the correspondence model between task requirements and robot resources, sorts all regional zones from high to low priority values, and generates an ordered regional sorting list. Each entry in the regional sorting list contains a regional zone identifier and the corresponding priority value. In practical implementation, resource constraints are resolved for each partition in the region ranking list. The resolution process involves extracting the maximum number of nanorobots allowed to be deployed in that partition, the maximum total working capacity of nanorobots within that partition, and the minimum spatial spacing requirement between nanorobots. A dynamic allocation algorithm is used, starting from the beginning of the region ranking list, which corresponds to the highest priority partition. The required number of nanorobots is calculated based on the drug demand intensity of the partition. The drug demand intensity is the product of the drug concentration required per unit volume of the partition and the volume of the partition. The dynamic allocation algorithm uses an allocation quantity calculation function to determine the initial allocation value for each partition. The allocation quantity calculation function is defined as follows: in: This is the initial number of nanorobots allocated to partition i. It is the total drug demand in partition i. This is the upper limit of the working capacity of nanorobots. This refers to the current number of available nanorobots. This represents the rounding up function. In some embodiments, the dynamic allocation algorithm updates the number of available robot resources in real time during execution. Whenever a specific number of nanorobots are allocated to a partition, the system deducts the corresponding number from the available nanorobot resource pool. The initial value of the available nanorobot resource pool is the maximum number of robots available. During the allocation process, the system continuously checks whether the resource constraints are met. If the resource demand of the current partition exceeds the available resources, the allocation operation for that partition is paused, and the partition is recorded as a pending area, and the system continues processing the next partition in the area sorting list. It can be understood that when a high-priority partition releases nanorobot resources, the system re-examines the resource demand of the pending areas. The release of nanorobot resources occurs when the treatment task in the partition is completed or interrupted. The dynamic allocation algorithm re-evaluates the feasibility of resource allocation for the pending areas according to the order of the area sorting list, and finally outputs a robot deployment scheme that satisfies the priority order and resource constraints. In practical implementation, the signal transmission path is optimized by integrating control signal requirements with the robot deployment scheme. Control signal requirements include the type, strength, and frequency parameters of the control signals. The robot deployment scheme provides spatial distribution information of the nanorobots. Optimizing the signal transmission path is achieved by minimizing signal transmission delay and maximizing signal coverage, generating regional robot allocation results. These results are data structures containing a list of nanorobot identifiers allocated to each partition, control signal parameters for each nanorobot, and a signal transmission path topology. Optionally, the dynamic allocation algorithm maintains a resource allocation state matrix during the allocation process. This matrix records in real-time the number of nanorobots allocated to each partition, the working status of each nanorobot, and the amount of remaining available resources. Optionally, the generation of regional robot allocation results can be iterative to adapt to real-time changes in resource status. In practical implementation, the influence of biological tissue characteristics on signal attenuation is considered when optimizing the signal transmission path; for example, signal strength parameters are adjusted based on tissue density.

[0023] See Figure 3 This is a dual-bar chart, with the area of ​​each region on the x-axis and the number of robots on the y-axis. It clearly shows the correspondence between the actual allocation of nanorobots and the resource ceiling in each region: dark bars represent the actual allocation, and light gray bars represent the robot resource ceiling for that region. This chart is a visual verification of the dynamic allocation algorithm: it not only intuitively shows the matching degree between resource deployment and constraints in each region, but also reflects the core logic of fine-grained scheduling and differentiated resource configuration in the method. It helps to quickly determine whether robot resources are reasonably allocated within regional constraints, providing an intuitive basis for resource distribution in subsequent task planning.

[0024] Example 3: See Figure 4In specific implementation, the task dependencies of key treatment points are identified based on the regional robot allocation results. The regional robot allocation results provide information on the deployment location and quantity of nanorobots in each zone. Key treatment points are specific locations within the organism where drug release needs to be prioritized. Task dependencies are the sequential constraints between treatment tasks. The task start time and duration are calculated. The task start time is the earliest time point at which the task can begin execution after all prerequisite dependencies are satisfied. The task duration is the length of time required for the task to be completed from start to finish. The task execution order is arranged through a time-series optimization model, which is a mathematical model used to optimize task scheduling and time arrangement. A reasonable task interval is determined. The task interval is the minimum time difference between the start times of adjacent tasks. A task sequence plan is generated, which is a structured output containing the task execution order and time arrangement. In practical implementation, a directed graph model of task sequence is constructed based on task dependencies. The directed graph model consists of nodes and directed edges. Nodes represent individual treatment tasks, and directed edges represent the sequential dependencies between tasks. For example, an edge from task A to task B indicates that task A must be completed before task B begins. The earliest possible start time and the latest allowed start time of each task are calculated. The earliest possible start time is the earliest time point when the task can start after considering the duration of all preceding tasks. The latest allowed start time is the latest start time point of the task that does not affect the overall task completion deadline. The set of tasks on the critical path is identified. The critical path is the longest path from the start node to the end node in the directed graph model, and the set of tasks on the critical path is the set of all tasks on the path.

[0025] In some embodiments, the task order on non-critical paths is adjusted using a timing optimization model. Non-critical paths are sequences of tasks not on critical paths. Tasks with close dependencies are prioritized; these are tasks with multiple preceding or succeeding dependencies. This compresses the total task execution time, which is the total time span of all tasks from start to finish. The minimum safe interval between adjacent tasks is calculated based on task execution duration and resource availability. Task execution duration is the length of time a single task takes from start to finish, resource availability is the number of nanorobots available at a specific time point, and the minimum safe interval is the minimum time difference that ensures no resource conflicts occur when adjacent tasks are executed, thus ensuring no time conflicts. The optimized task order and safe interval are then integrated to generate the final task sequence plan. The task sequence plan is a data structure containing the identifier, start time, end time, and interval information between tasks for each task.

[0026] In practical implementation, the timing optimization model uses mathematical methods to calculate task time parameters. For example, the earliest possible start time of a task is calculated through forward propagation, and the latest allowed start time is calculated through backward propagation. The critical path is identified by calculating the total path time, and the calculation of the minimum safety interval considers task duration and resource contention factors. In some embodiments, the mathematical expression of the minimum safety interval is an interval calculation function, defined as: in: It is the minimum safe interval. It is the duration of the k-th task. It is the number of adjacent tasks. This is a resource availability index, representing the average number of available nanorobots. It can be understood that when adjusting the task order, the time-series optimization model recalculates the earliest possible start time and the latest allowed start time of each task to ensure that the adjusted task sequence satisfies all dependencies and resource constraints.

[0027] Optionally, after the task sequence plan is generated, its feasibility and consistency are verified, such as checking for overlapping task times or resource limitations. Once verified, the final plan is output. Optionally, the task sequence plan can be stored and visualized in the form of a Gantt chart or timetable for easy subsequent execution and monitoring. In practice, the task sequence plan generation process is iterative. The time-series optimization model adjusts the task order and intervals based on real-time feedback until the optimal solution is found. When generating the task sequence plan, the time-series optimization model first constructs a directed graph model based on the regional robot allocation results and task dependencies, calculates the earliest possible start time and latest allowed start time for each task, and identifies the task set on the critical path. The model then receives real-time feedback, including changes in task execution status and resource availability updates. By adjusting the task order on non-critical paths, it prioritizes tasks with close dependencies to compress the total task execution time. In each iteration, the model recalculates the minimum safe interval between adjacent tasks to ensure no time conflicts and verifies whether the adjusted sequence satisfies resource constraints and dependencies. This process is repeated until the task order and intervals reach the optimal solution, that is, the total task execution time is minimized and all constraints are satisfied.

[0028] Example 4: In specific implementation, the drug supply time point and robot availability time window in the task sequence plan are analyzed. The drug supply time point is the timestamp of the drug delivery to a specific biological partition predefined in the task sequence plan. The robot availability time window is the time interval during which the nanorobot is in a working state. Overlapping conflicts and resource shortage problems are detected. Overlapping conflicts are the phenomenon of multiple drug supply time points competing for the same robot resources in the same time period. Resource shortage problems are the situation where the number of available nanorobots is lower than the requirements of concurrent tasks. The conflict is resolved by adjusting the task time parameters and resource allocation ratio. The task time parameters include the task start time and task duration. The resource allocation ratio is the distribution of the number of nanorobots in different tasks. A conflict resolution strategy is generated. The conflict resolution strategy includes the modified set of time parameters and resource allocation scheme. In practice, task timelines are recalculated and resource allocation is optimized based on conflict resolution strategies. Recalculating task timelines involves updating the start and end times of each task based on the conflict resolution strategy. Optimizing resource allocation involves reallocating nanorobot resources to eliminate resource competition. The timeline and allocation scheme are integrated. The timeline is the adjusted time sequence of all tasks, and the allocation scheme is the updated nanorobot deployment plan. The feasibility and consistency of the schedule are verified. Feasibility means that the schedule satisfies all time and resource constraints, and consistency means that there are no contradictions in the task order and dependencies in the schedule. A detailed dosing schedule is generated, which is a structured output containing the final task time arrangement and resource allocation details.

[0029] In some embodiments, the detection of overlapping conflicts and resource shortages is achieved by scanning all task items in the task sequence plan, for example, by using a time window comparison algorithm to identify time overlaps and a resource requirement comparison algorithm to identify resource shortages. Referring to Table 1, the conflict detection results in the task sequence plan are recorded in a structured table.

[0030] Table 1: Task Sequence Plan Conflict Detection Table Task Identifier Drug supply time point Robot available time window start Robot's available time window ends Time overlap conflict Resource shortage conflict TASK_001 08:00 07:30 08:30 no no TASK_002 08:15 08:00 09:00 yes yes TASK_003 09:30 09:15 10:00 no no In practice, adjusting task time parameters and resource allocation ratios uses a time adjustment function, which is defined as follows: in: These are the adjusted task time parameters. These are the original task time parameters. It is a time overlap adjustment factor. It is a time overlap conflict index. It is a resource shortage adjustment coefficient. This is a resource shortage conflict index. It's understandable that it includes a time overlap adjustment coefficient. Adjustment coefficient for insufficient resources With time as the dimension, the time overlap and conflict index Conflict index with insufficient resources The parameter is dimensionless, ensuring that the dimensions are consistent on both sides of the formula.

[0031] In some embodiments, recalculating task time points and optimizing resource allocation involves an iterative adjustment algorithm. This algorithm progressively modifies task time points and resource allocations according to a conflict resolution strategy until all conflicts are resolved. Integrating the timeline and allocation scheme involves merging the modified time parameters and resource allocation scheme into a unified data structure. It is understood that verifying the feasibility and consistency of the schedule is achieved by checking whether the time parameters are within a reasonable range and whether the resource allocation meets the requirements, for example, by using a constraint satisfaction algorithm to verify the plan's feasibility. Optionally, when generating a detailed dosing schedule, the plan output is in a machine-readable timetable format. Optionally, the detailed dosing schedule includes the start time, end time, and a list of allocated resource identifiers for each task. In specific implementations, the application of conflict resolution strategies may involve multiple adjustment cycles, with conflicts re-checked after each cycle until the plan is feasible. It is understood that the detailed dosing schedule, as the final output, is used to guide the actual control operations of the nanorobot.

[0032] Example 5: In specific implementation, real-time monitoring of biological environmental change indicators and robot operation status data is conducted. Biological environmental change indicators include pH value, temperature value, and concentration value of specific biomarkers in the internal regions of the organism. Robot operation status data includes the nanorobot's position coordinates, remaining drug dosage, and movement speed information. The planned progress is compared with the actual execution status. The planned progress is the predetermined task time arrangement and resource allocation scheme in the detailed drug administration schedule. The actual execution status is the real-time task completion status fed back by the nanorobot and the readings of environmental sensors. The deviation value is calculated and the control signal parameters are adjusted. The deviation value is a measure of the difference between the planned value and the actual value. The control signal parameters include the strength, frequency, and modulation method of the control signal. The control instructions are updated. The control instructions are the specific operation command sequence sent to the nanorobot. In practice, data on drug demand and robot working capacity are collected for each zone. Drug demand for each zone is the minimum drug dose required to maintain the therapeutic effect per unit time. Robot working capacity data is the maximum drug load and release rate of the nanorobot in the current state. The ratio of demand to resources is calculated. The ratio is the ratio of the real-time drug demand of each zone to the current working capacity of the nanorobot. The ratio values ​​of each zone are summarized to generate a matching index. The matching index is a comprehensive value that reflects the degree of matching between demand and resources in all zones.

[0033] In some embodiments, signal transmission requirements are analyzed based on the regional robot allocation results. The regional robot allocation results determine the number and spatial distribution of nanorobots deployed in each zone. Signal transmission requirements include control signal coverage, signal penetration depth, and anti-interference capability requirements. Signal strength and frequency parameters are optimized; signal strength is the transmission power level of the control signal, and frequency parameters are the carrier frequency and modulation frequency of the control signal. The signal configuration is adjusted to match the robot deployment; the signal configuration is the set of operating parameters for the control signal transmitter, generating an optimized control signal configuration. It can be understood that the real-time monitoring process is achieved by periodically collecting sensor data and robot status information, such as reading environmental indicators and robot position every second. When comparing the planned progress with the actual execution, the actual task start time is compared with the planned start time, and the actual drug release amount is compared with the planned release amount, calculating time deviation and dosage deviation.

[0034] In practical implementation, the deviation value is calculated using a multidimensional deviation calculation function, which is defined as follows: in: This is the overall deviation value. It is the planned time. It is the actual time. This is the planned drug dosage. This is the actual drug dosage. It is the time deviation weighting coefficient. This is the dose deviation weighting coefficient. It can be understood that the control signal parameters are adjusted based on the overall deviation value. When the overall deviation value exceeds a predetermined threshold, the intensity and frequency parameters of the control signal are adjusted proportionally. For example, the signal intensity is increased to improve the response speed of the nanorobot, and the frequency parameters are modified to adapt to the characteristics of the current biological environment.

[0035] Optionally, when updating control commands, the adjusted control signal parameters are encoded into a machine-readable command format, and the control commands are transmitted wirelessly to the nanorobot swarm. Optionally, the matching degree index is calculated using a weighted average method, averaging the ratio values ​​of each partitioned body region according to regional importance. In specific implementations, signal attenuation models and biological tissue characteristics are considered when optimizing signal strength and frequency parameters to ensure that the control signals can effectively reach all deployment areas. It is understood that after generating the optimized control signal configuration, the system will verify the compatibility of the new configuration with the current environmental conditions to avoid signal interference or failure. Real-time monitoring and dynamic adjustment constitute a closed-loop control system, continuously optimizing the targeted control process of the nanorobots.

[0036] See Figure 5This is a line graph, with the monitoring time point on the horizontal axis and the deviation value on the vertical axis. The two lines represent the changing trends of time deviation and dosage deviation during treatment. This graph is a visualization of the closed-loop control logic, intuitively showing the stability changes of the treatment process. It reflects the accuracy of real-time monitoring and verifies the ability of the dynamic adjustment strategy to correct deviations, providing data support for evaluating the continuity and reliability of the treatment plan.

[0037] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for targeted control of drug-loaded nanorobots, characterized by, The method comprises the following steps: Receiving internal region division data and drug treatment demand parameters of the organism, combining performance characteristics and real-time position information of the nanorobot, and establishing a corresponding relationship model between task demand and robot resources; According to the corresponding relationship model, the nanorobot is deployed to a specific region by using a partition allocation strategy, and a control signal configuration is optimized to generate a regional robot allocation result; Based on the regional robot allocation result, a task execution sequence and time arrangement of key treatment points are planned, a task interval is determined through time sequence analysis, and a task sequence plan is output; For the task sequence plan, the matching of drug supply cycle and robot working time is evaluated, resource conflicts are detected, and task parameters are adjusted to form a conflict resolution strategy; The conflict resolution strategy is applied to reorganize the task timeline and resource allocation scheme to generate a detailed drug administration progress plan; The detailed drug administration progress plan is executed, and environmental sensor data and robot state information are collected in real time to dynamically adjust the control instructions.

2. The targeting control method for drug-loaded nanorobots according to claim 1, characterized in that, The step of establishing the corresponding relationship model between the task demand and the robot resources is specifically: Obtaining the geometric size and drug demand intensity of the partition body region, and the working capacity and spatial coordinates of the nanorobot, and calculating the matching degree index between demand and resources; Using the matching degree index, an association mapping table between demand items and resource items is constructed, and priority levels are marked; Verify the integrity and consistency of the association mapping table to generate the corresponding relationship model between the task demand and the robot resources, specifically: Traverse each demand item in the association mapping table, check if there is at least one resource item corresponding to it, and traverse each resource item, check if it is assigned at least one demand item; Check if the priority levels marked in the association mapping table are consistent with the predefined priority rules, including checking if the priority values are within the valid range and if the level order is logical; When the corresponding relationship between demand items and resource items is missing or the priority level is conflicting, automatically adjust the content of the association mapping table, including supplementing the corresponding relationship or correcting the priority level; After the integrity and consistency verification is passed, the adjusted association mapping table is converted into the corresponding relationship model between the task demand and the robot resources. 3.The method of claim 2, wherein, The step of generating the regional robot allocation result is specifically: According to the corresponding relationship model between the task demand and the robot resources, analyze the priority order and resource limitation conditions of each region, and determine the robot deployment scheme by using a dynamic allocation algorithm; Integrate the control signal demand and the robot deployment scheme, optimize the signal transmission path, and generate the regional robot allocation result; The step of determining the robot deployment scheme by using a dynamic allocation algorithm according to the corresponding relationship model between the task demand and the robot resources is specifically: Read the priority order of each region from the corresponding relationship model between the task demand and the robot resources, and generate a region sorting list according to the priority level; For each region, analyze the resource limitation conditions, including the maximum number of available robots, the upper limit of robot working capacity, and the spatial distribution constraints; The dynamic allocation algorithm is adopted to allocate the robots from the area with the highest priority according to the drug demand intensity of the area, and the number of available robot resources is updated in real time during the allocation; During the allocation process, it is checked whether the resource limit condition is met, and if the resources are insufficient, the allocation is suspended and the area to be processed is recorded, and the allocation is continued after the resources are released; The final output is a robot deployment scheme that meets the priority order and resource limit. 4.The method of claim 3, wherein the drug-loaded nanorobot is controlled by a magnetic field. The step of outputting the task sequence plan is specifically: Based on the area robot allocation result, the task dependency relationship of the key treatment point is identified, and the task start time and duration are calculated; Through a timing optimization model, the task execution order is arranged, the reasonable task interval is determined, and the task sequence plan is generated, specifically: Based on the task dependency relationship, a directed graph model of the task sequence is constructed, where the nodes represent tasks and the directed edges represent the precedence dependency between tasks; The earliest possible start time and the latest allowable start time of each task are calculated, and the task set on the critical path is identified; Through a timing optimization model, the task order on the non-critical path is adjusted, and tasks with close dependency relationships are arranged in priority to compress the total task execution time; According to the task execution duration and resource availability, the minimum safety interval between adjacent tasks is calculated to ensure no time conflict; The optimized task order and safety interval are integrated to generate the final task sequence plan. 5.The method of claim 4, wherein, The step of forming a conflict resolution strategy is specifically: Analyze the drug supply time points in the task sequence plan and the robot available time window to detect overlapping conflicts and resource shortage problems; Adjust the task time parameters and resource allocation ratio to solve the conflict and generate a conflict resolution strategy. 6.The method of claim 5, wherein, The step of generating a detailed drug administration progress plan is specifically: According to the conflict resolution strategy, the task time points are recalculated and the resource layout is optimized, and the timeline and allocation scheme are integrated; Verify the feasibility and consistency of the progress plan to generate a detailed drug administration progress plan. 7.The method of claim 6, wherein the drug-loaded nanorobot is controlled by a magnetic field. The step of dynamically adjusting the control instruction is specifically: Real-time monitoring of biological environment change indicators and robot running state data, comparing the planned progress with the actual execution; Calculate the deviation value and adjust the control signal parameters to update the control instruction. 8.The method of claim 2, wherein the drug-loaded nanorobot is a drug-loaded nanorobot of claim 1. The step of calculating the matching degree index between demand and resource is specifically: Collect the drug demand amount and robot work capacity data of the partition body area, and calculate the ratio of demand and resource; Summarize the ratio values of each area to generate a matching degree index.

9. The targeting control method for drug-loaded nanorobots according to claim 3, characterized in that, The step of optimizing the control signal configuration is specifically: According to the area robot allocation result, analyze the signal transmission demand, optimize the signal strength and frequency parameters; Adjust the signal configuration to match the robot deployment to generate an optimized control signal configuration.

10. A targeted control system of drug-loaded nanorobots, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor, when executing the computer program, implements the steps of the target control method of the drug-loaded nanorobot in any one of claims 1 to 9.

Images