A control method, system, storage medium and device for a nursing robot

Abstract

The present application provides a control method, system, storage medium and device for a nursing robot, and relates to the field of intelligent robot technology. The method comprises: determining a target working area corresponding to the nursing robot, the target working area comprises a plurality of wards and at least one workstation, each of the wards comprises at least one patient; determining the working task of the nursing robot based on the pathological information of each of the patients and the work instructions sent by the workstation, the working task comprises the nursing task of at least one patient; generating a target path based on the working task; and controlling the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task. The implementation of the technical solution provided by the present application improves the efficiency of nursing.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent robots, and in particular to a control method, system, storage medium and device for a nursing robot. Background Art

[0002] With the development of medical technology and the aging of the population, the problem of tight medical resources has become increasingly prominent. In order to improve medical efficiency, major hospitals have gradually introduced intelligent equipment to assist medical staff in completing daily nursing work. Among them, nursing robots play an important role in reducing the workload of medical staff.

[0003] At present, nursing robots used in hospitals usually adopt fixed routes for patrol-style nursing. Nursing robots visit wards in sequence according to pre-set time points and fixed routes to provide corresponding nursing services to patients. However, due to the dynamic changes in the patient's condition and physical condition, this preset route nursing method is difficult to respond to the patient's actual needs in a timely manner, often resulting in uneven distribution of nursing resources and low nursing efficiency. Summary of the invention

[0004] The present application provides a control method, system, storage medium and device for a nursing robot, which improves the efficiency of nursing.

[0005] In a first aspect, the present application provides a control method for a nursing robot, the method comprising:

[0006] Determine a target working area corresponding to the nursing robot, wherein the target working area includes a plurality of wards and at least one workstation, and each of the wards includes at least one patient;

[0007] Determine the work task of the nursing robot based on the pathological information of each of the patients and the work instruction sent by the workstation, wherein the work task includes at least one nursing task for the patient;

[0008] generating a target path based on the work task;

[0009] The nursing robot is controlled to arrive at the corresponding ward along the target path to complete the nursing task.

[0010] By adopting the above technical solution, the target working area corresponding to the nursing robot is determined, and the work task of the nursing robot is determined based on the patient's pathological information and the work instructions sent by the workstation, so as to realize the dynamic allocation of nursing tasks and avoid the problem of uneven distribution of nursing resources caused by the traditional fixed route inspection method. The target path is generated based on the work task, and the nursing robot is controlled to arrive at the corresponding ward according to the target path to complete the nursing task, so that the nursing robot can flexibly adjust the mobile route according to actual needs, improve the utilization efficiency of nursing resources, break through the limitations of traditional nursing robots' fixed routes and fixed time points for inspection, realize the intelligent scheduling and precise execution of nursing services, and improve the quality and efficiency of nursing.

[0011] In a second aspect of the present application, a control system of a nursing robot is provided, the system comprising:

[0012] A working area determination module, used to determine a target working area corresponding to the nursing robot, wherein the target working area includes a plurality of wards and at least one workstation, and each of the wards includes at least one patient;

[0013] A work task determination module, used to determine the work task of the nursing robot based on the pathological information of each of the patients and the work instruction sent by the workstation, wherein the work task includes a nursing task for at least one patient;

[0014] A target path generation module, used for generating a target path based on the work task;

[0015] The control execution module is used to control the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task.

[0016] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0017] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] This application determines the target working area corresponding to the nursing robot, and determines the work task of the nursing robot based on the patient's pathological information and the work instructions sent by the workstation, thereby realizing the dynamic allocation of nursing tasks and avoiding the problem of uneven distribution of nursing resources caused by the traditional fixed route inspection method. The target path is generated based on the work task, and the nursing robot is controlled to arrive at the corresponding ward along the target path to complete the nursing task, so that the nursing robot can flexibly adjust the mobile route according to actual needs, improve the utilization efficiency of nursing resources, break through the limitations of traditional nursing robots' fixed routes and fixed time points for inspection, realize the intelligent scheduling and precise execution of nursing services, and improve the quality and efficiency of nursing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of a control method of a nursing robot provided in an embodiment of the present application;

[0021] Figure 2 It is a module schematic diagram of a control system of a nursing robot provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0023] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0028] Please refer to Figure 1 , a flow chart of a control method of a nursing robot is proposed, the method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on a control system of a nursing robot. The computer program can be integrated in a computer device, or can be run as an independent tool application. Specifically, the method includes steps 10 to 40, and the above steps are as follows:

[0029] Step 10: Determine a target working area corresponding to the nursing robot, where the target working area includes multiple wards and at least one workstation, and each ward includes at least one patient.

[0030] In the embodiment of this application, the nursing robot refers to an intelligent device that can move autonomously and perform nursing tasks, including a chassis system: a mobile chassis and a lidar navigation system, which can achieve a default moving speed of 0.7m / s and a maximum moving speed of 1.2m / s. A status indicator light strip is provided at the bottom to display the working, charging, fault and other status, and has an automatic recharging function; a multi-sensor system: equipped with a lidar, a depth camera, a fisheye camera and a nine-axis sensor for environmental perception and autonomous navigation; an interactive system: including a 10.1-inch 1080P main display, a 12M interactive camera, a 6-microphone array and a face recognition camera. Among them, the display screen can be used to display information such as patient medication instructions, the interactive camera supports taking photos and video calls, the microphone array can achieve 360-degree sound source positioning and voice recognition within a range of 5 meters, and the face recognition camera is used for patient identification; medical detection system: through the supporting detection equipment, it can perform the collection function of multiple vital signs data including blood oxygen, blood pressure, electrocardiogram, blood sugar, body temperature, etc.; drug distribution system: with drug storage and distribution functions, support directional drug collection through patient wristband scanning code; disinfection system: equipped with corresponding disinfection devices, can assist in the disinfection of wards and corridors; remote control system: supports remote operation, remote video calls, remote monitoring and remote system upgrades. Among them, the main functions that the nursing robot can perform include: patient vital signs data collection, drug distribution, environmental disinfection, remote video education, etc., which can replace medical staff to complete a number of basic nursing tasks. Its head can rotate within the range of -90°~+180° in the horizontal direction and -5°~+40° in the pitch direction to adapt to the needs of different work scenarios.

[0031] In the embodiment of the present application, the target working area refers to the specific working range to which the nursing robot is assigned, which includes multiple wards and at least one workstation, wherein each ward is provided with a bed for hospitalized patients, and each ward includes at least one patient, and each ward is marked with an electronic logo to facilitate positioning and navigation of the nursing robot.

[0032] In the embodiment of the present application, the workstation refers to a control center for centralized management and dispatch by medical staff. It is equipped with an information processing terminal for receiving and processing patient care demand information, issuing work instructions to nursing robots, and receiving information fed back by nursing robots during the execution of nursing tasks, thereby realizing real-time monitoring and management of nursing tasks.

[0033] Specifically, in order to improve the working efficiency of the nursing robot, it is necessary to first determine the target working area of ​​the nursing robot. The target working area is the specific working range assigned to the nursing robot, and the management range can be a certain floor or a certain department of the hospital. After determining the management range, the multi-sensor system of the nursing robot collects real-time dynamic information in each ward in the management range, including the number of patients, nursing level, special needs and spatial location, and generates ward status information. Among them, the multi-sensor system includes a laser radar, a depth camera, a fisheye camera and a nine-axis sensor, which can fully perceive the ward environment status. Based on the acquired ward status information, the system classifies each ward and obtains the classification result. In the classification process, factors such as the urgency of nursing needs, the complexity of nursing tasks and the frequency of ward visits are comprehensively considered, and the wards within the management range are divided into different nursing levels. Subsequently, the wards of the same classification category in the classification results are combined into a work area, and the spatial distribution density of each work area is calculated. The calculation of spatial distribution density needs to consider factors such as the physical distribution of the ward, the service radius and the difficulty of passage. In order to ensure workload balance, the system will optimize and adjust the work area. If there is a first work area with a spatial distribution density less than the lower limit of the preset density range, at least two first work areas within the preset range will be merged; if there is a second work area with a spatial distribution density greater than the upper limit of the preset density range, the second work area will be re-divided until the spatial distribution density of each work area is within the preset density range. Finally, according to the functional characteristics of the nursing robot, a target work area that meets the working attributes of the nursing robot is selected from each work area.

[0034] Based on the above embodiment, as an optional embodiment, the step of determining the target working area corresponding to the nursing robot may further include the following steps:

[0035] Step 101: Determine the management scope of the nursing robot in the hospital.

[0036] Specifically, in order to clarify the working scope of nursing robots and ensure the effective coverage of their nursing services, it is first necessary to determine the areas in the hospital that support nursing robots for nursing, that is, the management scope. Specifically, according to the actual building structure and nursing needs of the hospital, the areas equipped with intelligent facilities such as smart beds, intelligent infusion systems, and patient monitoring equipment are designated as management scopes. The management scope usually includes a floor of the inpatient department or multiple wards in a department, as well as corresponding nurse stations, treatment rooms and other workstations. These areas are equipped with network communication facilities and charging piles and other infrastructure required to support the operation of nursing robots.

[0037] Step 102: Collect real-time dynamic information in each ward within the management scope and generate ward status information.

[0038] Specifically, after determining the management scope, the nursing robot patrols each ward within the management scope through its multi-sensor system and collects real-time dynamic information. For example, the nursing robot moves within the management scope at a default moving speed of 0.7m / s, obtains the spatial layout of the ward through lidar and depth camera, detects the traffic environment with a nine-axis sensor, and collects spatial status information including bed usage, medical equipment layout, and item placement. At the same time, the nursing robot obtains real-time monitoring data of patients by interacting with smart devices in the ward; collects personnel information in the ward through a 12M interactive camera and a face recognition camera; and uses a 6-microphone array to perform voice recognition and interaction within a range of 5 meters to obtain nursing needs information. The nursing robot integrates and analyzes the various types of information collected to generate ward status information. The status information mainly includes: the number of patients in the ward and their basic information, the patient's real-time vital signs data (blood oxygen, blood pressure, electrocardiogram, blood sugar, body temperature and other indicators collected by the medical testing system), current nursing needs (such as infusion status, medication needs, emergency calls, etc.), environmental parameters (such as temperature, humidity, disinfection status, etc.) and the working status of facilities and equipment in the ward.

[0039] Step 103: Classify each ward based on the ward status information to obtain a classification result.

[0040] Specifically, the severity of the patient's condition is assessed based on the patient's vital signs data (including blood oxygen, blood pressure, electrocardiogram, blood sugar, body temperature and other indicators) in the ward status information; secondly, the complexity of the nursing task is assessed based on the patient's nursing needs (such as infusion status, medication needs, emergency calls, etc.); finally, the environmental protection needs are assessed in combination with the working status of the facilities and equipment in the ward. The system performs weighted calculations on the evaluation results of these three dimensions to obtain a comprehensive score for each ward, and accordingly divides the ward into three nursing levels: high, medium and low, thereby obtaining the ward classification results.

[0041] Step 104: Divide the work area according to the classification results, and determine the target work area corresponding to the nursing robot.

[0042] Specifically, after obtaining the grading results, the wards with the same grading results are preliminarily combined to form candidate work areas. Then the spatial distribution density of the wards in each candidate work area is calculated. If the spatial distribution density of a candidate work area is lower than the lower limit of the preset density range, the area is merged with the adjacent candidate work area of ​​the same level; if the spatial distribution density of a candidate work area is higher than the upper limit of the preset density range, the area is re-divided into multiple sub-areas. Through this dynamic adjustment, a work area with a reasonable spatial distribution is finally formed. Finally, the system determines the final target work area based on the working attributes of the nursing robot.

[0043] Based on the above embodiment, as an optional embodiment, the step of dividing the working area according to the classification result and determining the target working area corresponding to the nursing robot may also include the following steps:

[0044] Step 1041: Combine wards of the same grading category in the grading results into one working area.

[0045] Specifically, the wards with the same nursing level in the grading results are combined to form an initial work area. The ward grading results can be obtained first, which contain the nursing level information of each ward. Then all wards within the management scope are retrieved, and wards with the same nursing level are divided into the same group to form initial work areas corresponding to high, medium and low nursing levels. During the combination process, the system establishes the topological relationship between wards through the spatial information obtained by the nursing robot's laser radar and depth camera, and preferentially combines wards of the same level with adjacent spatial positions to reduce the movement cost of the nursing robot when performing tasks.

[0046] Step 1042: Calculate the spatial distribution density of each working area.

[0047] Specifically, after completing the ward combination, the system needs to calculate the spatial distribution density of each work area to evaluate the rationality of the work area division. The actual area of ​​each work area, including the ward area and the necessary channel area connecting the wards, can be measured by lidar and depth cameras. At the same time, the system counts the number of wards in each work area and considers the number of beds in each ward as a weight factor. The calculation formula for spatial distribution density is: spatial distribution density = ∑ (ward weight) / work area area, where the ward weight is positively correlated with the number of beds in the ward. For example, if a work area is 200 square meters, including 4 double wards (weight 2) and 2 single wards (weight 1), the spatial distribution density of the work area is (4×2+2×1) / 200=0.05.

[0048] Step 1043: If there is a first working area whose spatial distribution density is less than the lower limit value in the preset density range, at least two first working areas within the preset range are merged; if there is a second working area whose spatial distribution density is greater than the upper limit value in the preset density range, the second working area is re-divided until the idle distribution density of each working area is within the preset density range.

[0049] Specifically, a preset density range of the working area is set, for example, the lower limit value in the preset density range is 0.03, and the upper limit value in the preset density range is 0.08. This range is determined based on the maximum service capacity and the minimum operating efficiency of the nursing robot. After the system calculates the spatial distribution density of each working area, it compares it with the preset density range to identify the working area that needs to be adjusted. When the system detects a first working area with a spatial distribution density less than 0.03, it means that the workload in this area is too low and there may be a waste of nursing resources. At this time, the system will search for other first working areas with the same low spatial distribution density within a preset range (usually the reachable range of 10 minutes under the condition of the maximum moving speed of the nursing robot of 1.2m / s). The system analyzes the distance and traffic conditions between these first working areas through the spatial information obtained by the laser radar and the depth camera. During the merging process, the system gives priority to merging the first working area that can be connected through the least channel. For example, when it is detected that the spatial distribution density of area A (150 square meters, 4 wards) and area B (100 square meters, 3 wards) is less than 0.03, and the two areas are connected by only one straight channel, and the idle distribution density of the merged working area is within the preset density range, the system will give priority to merging the two areas to form a new working area (250 square meters, 7 wards).

[0050] In contrast, when the system detects a second work area with a spatial distribution density greater than 0.08, it indicates that the workload in the area is too high and may affect the quality of care. At this time, based on the spatial distribution characteristics of the wards in the area, it is divided into multiple work areas. During the division process, the system first identifies the natural demarcation points in the area (such as corridor corners, fire doors, etc.) through the channel information collected by the nine-axis sensor. Subsequently, the system divides the area at these demarcation points to ensure that each sub-area has a relatively independent passage path after the division. For example, when the spatial distribution density of a second work area (300 square meters, 12 wards) is greater than 0.08, the system may divide it into two work areas along the intersection of the corridor (each sub-area has an area of ​​150 square meters and 6 wards). By continuously performing density detection and area adjustment, the spatial distribution density of all work areas falls within the preset range of 0.03 to 0.08. This dynamic adjustment mechanism can effectively balance the workload of each work area and improve the utilization efficiency of nursing resources.

[0051] Step 1044: Select a target work area that meets the working attributes of the nursing robot from among the work areas.

[0052] Specifically, the working attribute information of the nursing robot is first obtained, including its hardware configuration (such as the type of medical detection system, the capacity of the drug delivery cabin, the specifications of the infusion monitoring equipment, etc.) and performance parameters (such as the default moving speed of 0.7m / s, the maximum moving speed of 1.2m / s, the battery life, the task processing capacity, etc.). At the same time, the system analyzes the characteristic information of each work area, including the nursing level of the wards in the area, the main type of nursing needs, the distribution of equipment, etc. In the process of selecting the target work area, the system uses a multi-dimensional matching algorithm for evaluation. First, the system calculates the matching degree between the functional indicators of the nursing robot and the needs of each work area. For example, for a nursing robot equipped with a complete medical detection system (including blood oxygen, blood pressure, electrocardiogram, blood sugar and body temperature detection modules), the system will give priority to work areas with higher nursing levels and frequent vital signs monitoring; for a nursing robot equipped with a large-capacity drug delivery cabin, the system will give priority to work areas with concentrated medication needs. Secondly, the system evaluates the adaptability between the performance parameters of the nursing robot and the spatial characteristics of the work area. Specifically, the system analyzes the traffic conditions in the work area through the channel information collected by the nine-axis sensor to ensure that the selected target work area meets the mobility and steering requirements of the nursing robot. In addition, the system also needs to consider the maximization of the work efficiency of the nursing robot. The work efficiency of the nursing robot is evaluated by calculating the expected service time (including movement time, task execution time and charging time) of the nursing robot in each work area. For example, when the battery life of a nursing robot is 4 hours, the system will give priority to the work area that can be fully covered within the time range, and ensure that the location of the charging pile is convenient for timely replenishment of power. At the same time, the system evaluates the interaction needs of the nursing robot with the medical staff and patients in the area through the data collected by the 6-microphone array and interactive camera of the nursing robot, ensuring that the selected target work area matches the interaction capabilities of the nursing robot. This target work area selection method based on multi-dimensional matching realizes the precise connection between the functional characteristics of the nursing robot and the work requirements.

[0053] Step 20: Based on the pathological information of each patient and the work instructions sent by the workstation, determine the work tasks of the nursing robot, where the work tasks include at least one nursing task for a patient.

[0054] Specifically, the pathological information of each patient in the target work area is obtained through the hospital's information management system, including basic medical information such as disease type, severity of the disease, treatment plan, medication requirements, and nursing level. At the same time, the system receives work instructions sent by workstations such as nurse stations and doctor's offices in real time. These instructions may include routine nursing arrangements, temporary medical orders, emergency disposal requirements, etc. When determining work tasks, the system adopts a hierarchical and classified task generation mechanism. First, the system prioritizes patients according to the nursing level in the pathological information, and prioritizes the nursing needs of patients with high nursing levels in the task list. For example, for critically ill patients who need to continuously monitor their vital signs, the system will arrange regular testing tasks through the medical detection system of the nursing robot (including blood oxygen, blood pressure, electrocardiogram, blood sugar, and body temperature detection modules), and the detection frequency can be dynamically adjusted according to the needs of the disease. Secondly, the system analyzes the work instructions sent by the workstation and converts the instructions into specific execution tasks. For example, when receiving an infusion nursing instruction, the system will formulate an execution plan including subtasks such as infusion rate adjustment, cannula replacement, and infusion reaction monitoring according to the specifications of the infusion monitoring equipment equipped by the nursing robot.

[0055] The system also needs to consider the timeliness and relevance of tasks. For tasks with clear execution time requirements (such as scheduled medication, preoperative preparation, etc.), the system will schedule them as mandatory tasks to be executed in a specified time period. For tasks with logical associations (such as the need for physical sign testing before medication), the system will set the order of task execution in accordance with medical standards. For example, when a patient needs antihypertensive drug treatment, the nursing robot will first measure blood pressure through its medical testing system, and then feedback to the doctor through the 12M interactive camera based on the measurement results, and then execute the medication task after confirmation.

[0056] In addition, the system receives real-time nursing demand information in the ward through the nursing robot's 6-microphone array, and can dynamically adjust and supplement work tasks. When it detects that the patient has a new nursing demand through voice, the system will evaluate the urgency of the demand and insert it into the existing task sequence. The nursing robot performs tasks in the working area at a default moving speed of 0.7m / s. In case of emergency, it can be increased to a maximum moving speed of 1.2m / s to ensure timely response.

[0057] Based on the above embodiment, as an optional embodiment, the step of determining the work task of the nursing robot based on the pathological information of each patient and the work instruction sent by the workstation may also include the following steps:

[0058] Step 201: Analyze the pathological information of each patient to obtain the nursing need level.

[0059] Specifically, in order to accurately assess the priority and resource requirements of nursing work, the system needs to conduct in-depth analysis of the patient's pathological information and classify the work instructions. The patient's pathological information is obtained through the hospital information management system, including medical data such as the main diagnosis, complications, treatment plans, medication records, and vital signs change trends. A multi-level evaluation model is used to analyze these pathological information, and the nursing demand level is calculated by setting different evaluation dimensions (such as vital sign stability, treatment compliance, self-care ability, etc.). For example, when a patient's vital signs (such as blood oxygen, blood pressure, electrocardiogram, blood sugar, body temperature, etc.) fluctuate abnormally, the system will increase the nursing demand level accordingly according to the fluctuation amplitude and duration; when the patient has multiple complications and they affect each other, the system will comprehensively evaluate the severity of each symptom and appropriately increase the nursing demand level.

[0060] Step 202: Obtain the task type and task timeliness in the work order sent by the workstation, and determine the task complexity corresponding to the nursing task of each patient according to the task type.

[0061] Specifically, after obtaining the work instructions sent by the workstation, the task type and task timeliness information contained in the instructions are parsed. The identification of task types is based on a preset nursing task classification system, which covers multiple categories such as routine nursing, therapeutic nursing, and life nursing. The instructions sent by the workstation are received through the 6-microphone array and 12M interactive camera equipped by the nursing robot, and the instruction content is matched with the task classification system to determine the specific task type. At the same time, the task timeliness in the instructions is analyzed, and the task timeliness is divided into three levels: emergency tasks (need to be executed immediately), scheduled tasks (need to be executed at a specific time), and regular tasks (can be flexibly executed within a longer time range).

[0062] Based on the determined task type, the complexity of each nursing task is further evaluated. The evaluation of task complexity takes into account multiple factors: first, the technical requirements for task execution. For example, tasks that require the use of a nursing robot's medical detection system to monitor multiple indicators simultaneously will be rated as having a high complexity; second, the duration of the task. For example, long-term tasks that require continuous monitoring by a nursing robot will have a correspondingly increased complexity; third, the collaborative requirements of the task. If the task requires cooperation with medical staff, the system will adjust the complexity of the task by evaluating the difficulty of collaboration.

[0063] Step 203: Calculate the task priority based on the nursing demand level, task complexity and task timeliness.

[0064] Specifically, in an optional embodiment, the nursing demand level is divided into special level (critical care), level one (intensive care), level two (ordinary care) and level three (rehabilitation care); the task complexity is divided into high complexity (multi-parameter monitoring and treatment), moderate complexity (single treatment operation) and regular complexity (basic care); the task timeliness is divided into emergency tasks (immediate execution), scheduled tasks (executed at a specific time) and regular tasks (flexible execution time). The priority is determined by comparing level by level. First, the basic priority is determined according to the task timeliness. The emergency task is marked as the highest priority, the scheduled task is second, and the regular task is the last; in the case of the same timeliness, it is further subdivided according to the nursing demand level. The special nursing demand obtains the highest priority in the timeliness category, and then decreases in order; when the timeliness and nursing demand level are the same, the final priority division is performed according to the task complexity, and the highly complex task has the highest priority. For example, when a nursing robot receives an emergency vital signs monitoring task for a critically ill patient through its medical detection system (including blood oxygen, blood pressure, electrocardiogram, blood sugar and body temperature detection modules), this task will be given the highest priority; while a routine complex ward round task for a recovering patient will be given a lower priority.

[0065] In another optional embodiment, a three-layer priority evaluation structure can be constructed, with task timeliness as the first layer of judgment basis, nursing demand level as the second layer of judgment basis, and task complexity as the third layer of judgment basis. First, all tasks are divided into three main levels according to task timeliness: emergency task layer, scheduled task layer, and regular task layer. In each main level, it is further divided into four sub-levels according to the nursing demand level, forming a special nursing sub-level, a first-level nursing sub-level, a second-level nursing sub-level, and a third-level nursing sub-level. Finally, in each sub-level, the final priority is subdivided according to the complexity of the task. After receiving the task information, the priority is evaluated according to this hierarchical structure. For example, when the system receives a critically ill patient infusion monitoring task that needs to be executed immediately, the task will first be classified into the emergency task layer, then classified into the first-level nursing sub-level within the layer, and finally determined as a highly complex task based on its use of infusion monitoring equipment, thereby obtaining the corresponding priority.

[0066] Step 204: Sort the nursing tasks corresponding to each patient according to the task priority and generate a task queue.

[0067] Specifically, the nursing tasks of each patient are arranged in order of priority from high to low to form a task queue. During the sorting process, the system adopts a priority comparison strategy to insert new nursing tasks into the appropriate positions in the queue in sequence. For example, when a patient needs immediate nursing tasks for vital signs monitoring (blood oxygen, blood pressure, electrocardiogram, blood sugar, and body temperature, etc.), the system will place it at the front of the queue because it has the attributes of an emergency task and is a special nursing requirement; while regular ward rounds with conventional complexity will be placed at the back of the queue.

[0068] Step 205: Based on the current state of the nursing robot and the complexity of the task, determine the work task in the task queue.

[0069] Specifically, after the task queue is formed, the system needs to select appropriate work tasks from the queue according to the current state of the nursing robot. The status information of the nursing robot mainly includes the status of available resources (such as the occupancy of the medical detection system and infusion monitoring equipment), the operating status of the equipment (such as battery power, mobile system status), etc. When determining the work tasks, the system usually starts from the front of the task queue, such as selecting 3-5 nursing tasks with the highest priority to form a set of work tasks. For example, when the nursing robot has sufficient power (above 70%) and the medical detection system is idle, the system will select 4 high-priority tasks that require vital signs monitoring from the front of the queue to form a group of continuously executed work tasks.

[0070] Based on the above embodiment, as an optional embodiment, based on the current state of the nursing robot and the complexity of the task, the step of determining the work task in the task queue may also include the following steps:

[0071] Step 2051: Obtain the current state of the nursing robot, which includes the remaining power and execution efficiency.

[0072] Specifically, the current state of the nursing robot is obtained, including the remaining power and execution efficiency. Among them, the execution efficiency is a comprehensive indicator reflecting the current working state of the nursing robot. The indicator is calculated through the collected execution data, and the value range is 0-100%. For example, when all functional modules of the nursing robot (such as medical detection system, infusion monitoring equipment, etc.) are in the best working state, the execution efficiency is 100%.

[0073] Step 2052: Calculate the unit power consumption and execution time of each nursing task in the task queue based on the task complexity and execution efficiency.

[0074] Specifically, the unit power consumption and execution time of each nursing task in the task queue are calculated based on the task complexity and execution efficiency. For nursing tasks with higher task complexity, such as tasks that require the simultaneous use of multiple detection modules (blood oxygen, blood pressure, electrocardiogram, blood sugar, and body temperature, etc.) for vital sign monitoring, the unit power consumption is larger; accordingly, the execution time will also be longer. When the execution efficiency decreases, the system will adjust the calculation results accordingly. For example, when the execution efficiency is 80%, the system will divide the basic execution time by 0.8 to obtain the actual execution time, and divide the basic unit power consumption by 0.8 to obtain the actual unit power consumption.

[0075] Step 2053: Starting from the first nursing task in the task queue, the total power consumption and total execution time of each nursing task are cumulatively calculated.

[0076] Specifically, the cumulative calculation starts from the first nursing task in the task queue. For example, when the first task is to monitor the infusion of critically ill patients, the estimated power consumption is 10% and the execution time is 30 minutes; the second task is to perform routine vital signs detection, the estimated power consumption is 5% and the execution time is 15 minutes; the third task is to assist patients with rehabilitation training, the estimated power consumption is 8% and the execution time is 25 minutes. The system will accumulate these values ​​in turn to obtain the total power consumption (10%, 15%, 23%) and the total execution time (30 minutes, 45 minutes, 70 minutes) up to each task.

[0077] Step 2054: When the total power consumption reaches a preset proportion of the remaining power, or the total execution time meets the preset working time, the current nursing task is determined as a deadline task.

[0078] Specifically, the embodiment of the present application presets two task deadline conditions: the total power consumption reaches 75% of the remaining power (preset ratio), or the total execution time reaches 120 minutes (preset working time). When any one of the conditions is triggered, the current task is determined to be a deadline task. For example, when the remaining power of the nursing robot is 30%, the maximum amount of power allowed is 22.5% (30%×75%). Therefore, in the above example, the total power consumption of the third task of 23% exceeds the allowed value, and the system will determine the second task as a deadline task. Alternatively, if the total execution time exceeds 120 minutes, the current task will be determined as a deadline task even if the total power consumption does not reach the preset ratio.

[0079] Step 2055: Determine the task sequence consisting of the first nursing task to the deadline task as the work task.

[0080] Specifically, the task sequence consisting of the first nursing task to the deadline task is determined as the work task. Among them, the moving speed (between 0.7m / s and 1.2m / s) can also be adjusted according to the urgency of the work task to ensure that various nursing tasks are completed efficiently within the power limit. This method of determining work tasks based on the current state realizes the reasonable planning of nursing tasks and the optimal allocation of resources. By accurately evaluating the resource requirements of a single task and combining it with the preset deadline conditions, the system can assign the optimal combination of work tasks to the nursing robot, which not only ensures the reliability of task execution, but also improves the efficiency of the use of nursing resources.

[0081] Step 30: Generate a target path based on the work tasks.

[0082] Specifically, in order to achieve efficient movement of the nursing robot, the system needs to generate a reasonable target path based on the work task. First, the target position information of each nursing task in the work task and the current position information of the nursing robot are obtained. Through the collected environmental data, the system determines each target position and its surrounding key intersection positions as path nodes, and constructs a path node graph, which can be understood as a path map of the target work area. In the path node graph, the traffic status between each path node is marked based on real-time environmental data. The road section where static obstacles (such as walls and fixed equipment) are detected is marked as an impassable state, the road section where dynamic obstacles (such as medical staff and patients) are detected is marked as a temporary impassable state, and the unobstructed road section is marked as a passable state. For each pair of adjacent path nodes, the system calculates the movement cost according to its traffic status, the distance between nodes, and the type of area. The improved A* algorithm is used as the preset pathfinding algorithm, and the path nodes are traversed through heuristic search to calculate the total movement cost of different path combinations. The algorithm finds the path combination with the minimum movement cost by evaluating the actual cost and estimated cost between nodes, and determines it as the target path.

[0083] Based on the above embodiment, as an optional embodiment, the step of generating a target path based on the work task may further include the following steps:

[0084] Step 301: Obtain the target position corresponding to each nursing task in the work task.

[0085] Specifically, the target location information of each nursing task in the work task is obtained, including the location of the ward where vital signs monitoring (blood oxygen, blood pressure, electrocardiogram, blood sugar and body temperature, etc.) is required, the location of the infusion room where the infusion monitoring task is performed, and the current location of the nursing robot. These location information are represented by three-dimensional coordinate points in the hospital coordinate system and are used to determine the basic nodes of the path node graph.

[0086] Step 302: construct a path node graph based on each target location, and mark the traffic status between each path node in the path node graph.

[0087] Specifically, the spatial data of the hospital environment is collected, and in the environment map with a basic unit of 0.1 m × 0.1 m, the key intersections, corner positions and channel intersections between each target position are also used as path nodes, so as to construct a path node graph containing complete navigation information. For example, when the nursing robot needs to move from the current position to Ward 3 and the infusion room, the system not only uses these target positions as path nodes, but also determines the corridor corner points and door positions between them as path nodes to form a connected node network. While constructing the path node graph, the traffic status between each path node is marked through the collected environmental information. For example, the road section where static obstacles such as walls and fixed equipment are detected is marked as a permanent inaccessible state; the road section where dynamic obstacles such as medical staff and patients are detected is marked as a temporary inaccessible state, and the status information is updated every 0.5 seconds; the road section without obstacles is marked as a passable state. When the nursing robot is performing its tasks, the traffic status information will directly affect the choice of its moving speed. The maximum speed can reach 1.2m / s on passable sections, and it will drop to the default speed of 0.7m / s when approaching obstacles or special areas.

[0088] Step 303: Calculate the movement cost between each path node according to the traffic status.

[0089] Specifically, the movement cost is calculated according to the traffic status between each path node. For the road section marked as passable, its basic movement cost is equal to the Euclidean distance between the path nodes; for the road section marked as temporarily impassable, the system multiplies its basic movement cost by the preset obstacle avoidance coefficient 1.5; for the road section marked as permanently impassable, the system sets its movement cost to infinity to ensure that the road section will not be selected into the final path. The system also dynamically adjusts the movement cost according to the type of area where the road section is located and the urgency of the task. For example, when the road section is located in the intensive care area, the system multiplies the movement cost of the road section by the safety factor of 1.2, so that the nursing robot reduces the movement speed to 0.5m / s; when the road section corresponds to an emergency care task, such as the need for immediate vital signs monitoring (blood oxygen, blood pressure, electrocardiogram, blood sugar and body temperature detection), the system divides the movement cost of the road section by the acceleration factor of 1.3, so that the nursing robot increases the movement speed to 1.2m / s.

[0090] Step 304: Based on the movement cost, a preset path-finding algorithm is used to traverse each path node to obtain a path combination with the minimum movement cost, and the path combination with the minimum movement cost is determined as the target path.

[0091] Specifically, based on the calculated movement cost, the system uses the improved A* algorithm as the preset path-finding algorithm to traverse the path nodes. The algorithm uses a heuristic search strategy to calculate the actual cost g(n) from the starting point to the node and the estimated cost h(n) from the node to the end point for each path node, and uses their sum f(n)=g(n)+h(n) as the evaluation value of the node. During the search process, the algorithm prioritizes expanding nodes with smaller evaluation values, and obtains multiple possible path combinations through iterative calculations. For example, when the nursing robot needs to go from the current position to Ward 3 and the infusion room in turn, the algorithm will generate multiple path plans passing through different corridors and corner points. The path combination with the smallest evaluation value is determined as the target path, that is, the path combination has the best comprehensive mobility performance after considering the traffic status, area restrictions and task urgency.

[0092] Step 40: Control the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task.

[0093] Specifically, after the corresponding target path is determined, the nursing robot needs to be controlled to arrive at the corresponding wards one by one along the target path to complete the nursing task. When the nursing robot arrives at the target position of the corresponding ward along the target path, it first collects the patient's facial image through its equipped 12M interactive camera, and reads the electronic wristband information worn by the patient through the identity recognition module, and compares and verifies the collected identity information with the hospital database. At the same time, the nursing robot collects the patient's vital signs data through its onboard vital signs monitoring equipment, including key indicators such as blood oxygen, blood pressure, electrocardiogram, blood sugar and body temperature.

[0094] When the system confirms that the patient's identity information has been successfully verified, it immediately sends an opening command to the medicine storage cabinet, and controls the medicine storage cabinet corresponding to the patient's medication information to automatically open. The medicine storage cabinet sends a reminder message of "Please take the medicine" through the voice broadcast system, and displays the patient's medication information on the cabinet door display screen. The system uses the built-in gravity sensor and infrared sensor of the medicine storage cabinet to detect the opening status and medication removal status of the storage cabinet in real time. If the medication removal operation is not detected within the preset 180 seconds, the system will automatically mark the patient as not having taken the medicine. This information will be recorded in the patient's electronic medical record and synchronized to the hospital workstation in real time through the communication module of the nursing robot.

[0095] At the same time, the collected vital sign data is analyzed in real time and compared with the preset healthy vital sign data range. When any vital sign data is found to be out of the safe range (for example, blood pressure is higher than 160 / 100mmHg, or blood oxygen saturation is lower than 95%), an early warning message is immediately sent to the workstation through the wireless communication network. The early warning message contains key information such as patient identity information, abnormal vital sign data, and collection time, so that medical staff can understand the patient's condition in time and take corresponding measures.

[0096] See also Figure 2 , is a module diagram of a control system of a nursing robot provided in an embodiment of the present application. The control system of the nursing robot may include: a work area determination module, a work task determination module, a target path generation module and a control execution module, wherein:

[0097] A working area determination module, used to determine a target working area corresponding to the nursing robot, wherein the target working area includes a plurality of wards and at least one workstation, and each of the wards includes at least one patient;

[0098] A work task determination module, used to determine the work task of the nursing robot based on the pathological information of each of the patients and the work instruction sent by the workstation, wherein the work task includes a nursing task for at least one patient;

[0099] A target path generation module, used for generating a target path based on the work task;

[0100] The control execution module is used to control the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task.

[0101] Optionally, the working area determination module is also used to determine the management scope of the nursing robot in the hospital;

[0102] Collecting real-time dynamic information in each ward within the management scope and generating ward status information;

[0103] Classifying each of the wards based on the ward status information to obtain a classification result;

[0104] The working area is divided according to the classification result, and the target working area corresponding to the nursing robot is determined.

[0105] Optionally, the work area determination module is further used to combine wards of the same grading category in the grading results into one work area;

[0106] Calculating the spatial distribution density of each of the working areas;

[0107] If there is a first working area whose spatial distribution density is less than the lower limit value in the preset density range, at least two of the first working areas within the preset range are merged; if there is a second working area whose spatial distribution density is greater than the upper limit value in the preset density range, the second working area is re-divided until the idle distribution density of each of the working areas is within the preset density range;

[0108] A target working area that matches the working attributes of the nursing robot is selected from each of the working areas.

[0109] Optionally, the work task determination module is further used to combine wards of the same grading category in the grading results into one work area;

[0110] Calculating the spatial distribution density of each of the working areas;

[0111] If there is a first working area whose spatial distribution density is less than the lower limit value in the preset density range, at least two of the first working areas within the preset range are merged; if there is a second working area whose spatial distribution density is greater than the upper limit value in the preset density range, the second working area is re-divided until the idle distribution density of each of the working areas is within the preset density range;

[0112] A target working area that matches the working attributes of the nursing robot is selected from each of the working areas.

[0113] Optionally, the work task determination module is further used to obtain the current state of the nursing robot, wherein the current state includes the remaining power and the execution efficiency;

[0114] Calculate the unit power consumption and execution time of each nursing task in the task queue based on the task complexity and the execution efficiency;

[0115] Starting from the first nursing task in the task queue, cumulatively calculating the total power consumption and total execution time of each nursing task;

[0116] When the total power consumption reaches a preset proportion of the remaining power, or the total execution time meets the preset working time, the current nursing task is determined as a deadline task;

[0117] The task sequence consisting of the first nursing task to the deadline task is determined as the work task.

[0118] Optionally, the target path generation module is further used to obtain the target position corresponding to each nursing task in the work task;

[0119] Constructing a path node graph based on each of the target locations, and marking the traffic status between each of the path nodes in the path node graph;

[0120] Calculate the movement cost between each of the path nodes according to the traffic status;

[0121] Based on the movement cost, each path node is traversed using a preset path-finding algorithm to obtain a path combination with the minimum movement cost, and the path combination with the minimum movement cost is determined as the target path.

[0122] Optionally, the control execution module is further used to collect the patient's identity information and vital sign data after the nursing robot arrives at the target position of the corresponding ward;

[0123] When the identity information is successfully verified, the corresponding medicine storage cabinet is controlled to open and a reminder message is issued;

[0124] The opening status of the medicine storage cabinet is detected. If no medicine taking operation is detected within a preset time, the patient is marked as not having taken medicine. When any of the vital sign data exceeds the corresponding preset health vital sign data range, an early warning message is sent to the workstation.

[0125] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0126] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a control method for a nursing robot in the above embodiment. The specific execution process can be found in the specific description of the above embodiment and will not be repeated here.

[0127] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0128] The communication bus 302 is used to realize the connection and communication between these components.

[0129] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0130] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0131] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0132] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a control method of a nursing robot.

[0133] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program storing a control method of a nursing robot in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0136] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0139] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0140] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A control method for a nursing robot, characterized in that: The method comprises: Determine a target working area corresponding to the nursing robot, wherein the target working area includes a plurality of wards and at least one workstation, and each of the wards includes at least one patient; Analyze the pathological information of each of the patients to obtain a nursing needs level; Obtaining the task type and task timeliness in the work order sent by the workstation, and determining the task complexity corresponding to the nursing task of each patient according to the task type; Calculating the task priority based on the nursing demand level, the task complexity and the task timeliness; Sort the nursing tasks corresponding to each patient according to the task priority and generate a task queue; Acquire the current state of the nursing robot, wherein the current state includes the remaining power and the execution efficiency; Calculate the unit power consumption and execution time of each nursing task in the task queue based on the task complexity and the execution efficiency; Starting from the first nursing task in the task queue, cumulatively calculating the total power consumption and total execution time of each nursing task; When the total power consumption reaches a preset proportion of the remaining power, or the total execution time meets the preset working time, the current nursing task is determined as a deadline task; Determine the task sequence consisting of the first nursing task to the deadline task as a work task, wherein the work task includes at least one patient nursing task; generating a target path based on the work task; Control the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task.

2. The control method of the nursing robot according to claim 1, characterized in that: The step of determining a target working area corresponding to the nursing robot includes: Determine the management scope of nursing robots in hospitals; Collecting real-time dynamic information in each ward within the management scope and generating ward status information; Classifying each of the wards based on the ward status information to obtain a classification result; The working area is divided according to the classification result, and the target working area corresponding to the nursing robot is determined.

3. The control method of the nursing robot according to claim 2, characterized in that: The dividing the working area according to the classification result and determining the target working area corresponding to the nursing robot includes: Combining wards of the same grading category in the grading results into one working area; Calculating the spatial distribution density of each of the working areas; If there is a first working area whose spatial distribution density is less than the lower limit value in the preset density range, at least two of the first working areas in the preset range are merged; if there is a second working area whose spatial distribution density is greater than the upper limit value in the preset density range, the second working area is re-divided until the idle distribution density of each working area is within the preset density range; A target working area that matches the working attributes of the nursing robot is selected from each of the working areas.

4. The control method of the nursing robot according to claim 1, characterized in that: The generating a target path based on the work task includes: Obtaining the target position corresponding to each nursing task in the work task; Constructing a path node graph based on each of the target locations, and marking the traffic status between each of the path nodes in the path node graph; Calculate the movement cost between each of the path nodes according to the traffic status; Based on the movement cost, each path node is traversed using a preset path-finding algorithm to obtain a path combination with the minimum movement cost, and the path combination with the minimum movement cost is determined as the target path.

5. The control method of the nursing robot according to claim 1, characterized in that: Controlling the nursing machine The person arrives at the corresponding ward according to the target path to complete the nursing task, including: When the nursing robot arrives at the target location of the corresponding ward, it collects the patient's identity information and vital sign data; When the identity information is successfully verified, the corresponding medicine storage cabinet is controlled to open and a reminder message is issued; The opening status of the medicine storage cabinet is detected. If no medicine taking operation is detected within a preset time, the patient is marked as not having taken medicine. When any of the vital sign data exceeds the corresponding preset health vital sign data range, an early warning message is sent to the workstation.

6. A control system for a nursing robot, characterized in that: The system comprises: A working area determination module, used to determine a target working area corresponding to the nursing robot, wherein the target working area includes a plurality of wards and at least one workstation, and each of the wards includes at least one patient; A work task determination module is used to analyze the pathological information of each of the patients to obtain a nursing demand level; obtain the task type and task timeliness in the work instruction sent by the workstation, and determine the task complexity corresponding to the nursing task of each of the patients according to the task type; calculate the task priority based on the nursing demand level, the task complexity and the task timeliness; sort the nursing tasks corresponding to each patient according to the task priority to generate a task queue; obtain the current state of the nursing robot, which includes the remaining power and execution efficiency; calculate the unit power consumption and execution time of each of the nursing tasks in the task queue based on the task complexity and the execution efficiency; starting from the first nursing task in the task queue, cumulatively calculate the total power consumption and total execution time of each of the nursing tasks; when the total power consumption reaches a preset proportion of the remaining power, or the total execution time meets the preset working time, determine the current nursing task as a deadline task; determine the task sequence consisting of the first nursing task to the deadline task as a work task, and the work task includes the nursing task of at least one patient; A target path generation module, used for generating a target path based on the work task; The control execution module is used to control the nursing robot to arrive at the corresponding ward along the target path to complete the nursing task.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-5.

Images