Method, system and equipment for intelligently replacing bedding and clothing of sickbed

Abstract

The invention discloses an intelligent replacement method, system and device for sickbed bedding and clothing, and relates to the technical field of medical instruments, and the method comprises the steps: building a sickbed grid map based on a sickbed position database, and determining a target grid corresponding to a target sickbed; setting an optimal path by taking the minimum energy consumption as a constraint and combining an initial grid of the robot; the robot moves along the path and collects a target bedding and clothing image; performing collaborative analysis on the sickbed use log and the bedding and clothing image to obtain a target pollution index; when the pollution index reaches a preset threshold value, reading an intelligent replacement plan; and the robot completes bedding and clothing replacement according to the plan. The technical problems that existing sickbed bedding and clothing replacement depends on manual operation, efficiency is low, the standardization degree is low, the cross infection risk is high and labor cost is high are solved, and the technical effects that through an automatic and intelligent robot system, efficient and standardized replacement of sickbed bedding and clothing is achieved, the cross infection risk is reduced, and the labor cost is reduced are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to an intelligent replacement method, system and device for hospital bed sheets and quilts. Background Art

[0002] In the modern medical care field, the replacement of hospital bed sheets and quilts is a frequent and important daily task. There are many problems with the traditional manual replacement method: on the one hand, the manual operation efficiency is low, and it is difficult to meet the rapid replacement needs of a large number of hospital beds. Especially in the case of frequent patient turnover or emergencies, it is easy to affect the nursing efficiency and patient experience. On the other hand, the standardization degree of manual replacement is low, and it is easy to have non-standard operations, increasing the risk of cross-infection. In addition, frequent physical labor not only increases the work burden of medical staff, but also leads to continuous increase in the hospital's investment in labor costs. Summary of the Invention

[0003] This application provides an intelligent replacement method, system and device for hospital bed sheets and quilts, which are used to solve the technical problems of low efficiency, low standardization degree, high risk of cross-infection and high labor cost existing in the replacement of existing hospital bed sheets and quilts relying on manual operation.

[0004] In view of the above problems, this application provides an intelligent replacement method, system and device for hospital bed sheets and quilts.

[0005] In the first aspect, this application provides an intelligent replacement method for hospital bed sheets and quilts. The method includes: establishing a bed grid map based on a bed position database, where the bed grid map includes a target grid corresponding to a target bed; setting a target optimal path by combining the target grid and an initial grid corresponding to a hospital bed sheet and quilt replacement robot with the minimum energy consumption as a constraint; the hospital bed sheet and quilt replacement robot moves and acquires a target bed sheet image along the target optimal path; performing collaborative analysis on a target usage log of the target bed and the target bed sheet image to obtain a target soiling index; when the target soiling index reaches a predetermined soiling threshold, reading an intelligent replacement plan; and the hospital bed sheet and quilt replacement robot performing bed sheet and quilt replacement on the target bed based on the intelligent replacement plan.

[0006] Second aspect, the present application provides an intelligent replacement system for hospital bed bedding, the system comprising: a grid map construction module for establishing a hospital bed grid map based on a hospital bed position database, wherein the hospital bed grid map includes a target grid corresponding to a target hospital bed; an optimal path setting module for setting a target optimal path by taking minimum energy consumption as a constraint and combining the target grid and an initial grid corresponding to a hospital bed bedding replacement robot; a bedding image acquisition module for the hospital bed bedding replacement robot to move and acquire a target bedding image under the target optimal path; a collaborative analysis module for performing collaborative analysis on a target usage log of the target hospital bed and the target bedding image to obtain a target soiling index; an intelligent replacement plan reading module for reading an intelligent replacement plan when the target soiling index reaches a predetermined soiling threshold; and a bedding replacement execution module for the hospital bed bedding replacement robot to perform bedding replacement on the target hospital bed based on the intelligent replacement plan.

[0007] Third aspect, the present application provides an electronic device, comprising: a processor, the processor being coupled to a memory, the memory being used for storing a program, and when the program is executed by the processor, the system is enabled to execute the method according to any one of the first aspect.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] An intelligent replacement method, system and device for hospital bed bedding provided in an embodiment of the present application relate to the technical field of medical devices. By establishing a grid map based on a hospital bed position database, planning an optimal path with minimum energy consumption; the robot moves along the path and acquires a bedding image; combining the hospital bed usage log and the image analysis to obtain a soiling index; when the soiling index reaches a threshold, reading an intelligent replacement plan and performing bedding replacement, it solves the technical problems that the existing replacement of hospital bed bedding depends on manual operation, has low efficiency, low standardization degree, high risk of cross-infection and high labor cost, and realizes the technical effects of efficiently and standardly replacing hospital bed bedding through an automated and intelligent robot system, reducing the risk of cross-infection and reducing labor costs. Description of the Drawings

[0010] Figure 1 It is a schematic flow chart of an intelligent replacement method for hospital bed bedding provided by the present application;

[0011] Figure 2 It is a schematic structural diagram of an intelligent replacement system for hospital bed bedding provided by the present application;

[0012] Figure 3 It is a schematic structural diagram of an electronic device provided by the present application.

[0013] Description of the reference numerals:

[0014] Grid map construction module 11, optimal path setting module 12, bedding image acquisition module 13, sub-collaborative analysis module 14, intelligent replacement plan reading module 15, bedding replacement execution module 16, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. Detailed implementation manners

[0015] This application provides an intelligent replacement method, system and device for hospital bed bedding, which is used to solve the technical problems of low efficiency, low standardization degree, high risk of cross-infection and high labor cost in the existing replacement of hospital bed bedding relying on manual operation.

[0016] Embodiment 1, as Figure 1 shown, this application provides an intelligent replacement method for hospital bed bedding, and the method includes:

[0017] P10: Establish a hospital bed grid map based on the hospital bed position database, where the hospital bed grid map includes target grids corresponding to the target hospital bed.

[0018] Further, step P10 of the embodiment of this application further includes:

[0019] P11: Obtain the target obstacle position information of the target area, where the target obstacle position information includes the first position of the first obstacle; P12: Establish an initial grid map according to the first position of the first obstacle; P13: Obtain any hospital bed, and the any hospital bed corresponds to any hospital bed position; P14: Mark the any hospital bed position corresponding to the any hospital bed on the initial grid map to obtain the hospital bed grid map.

[0020] It should be understood that, first, a hospital bed grid map is established based on the hospital bed position database. The grid map is a map representation method that divides the space into several regular grids (grids). By establishing a hospital bed grid map, each hospital bed corresponds to one or more target grids in the map. This map form is convenient for the robot to perform path planning and obstacle avoidance operations.

[0021] Before constructing the grid map, first obtain the target obstacle position information in the target area. These obstacles may include furniture, equipment or other immovable objects in the ward. The position information of these obstacles is the key data for the robot to perform path planning and obstacle avoidance operations. For example, assume that there is a first obstacle in the target area, and its position information (such as coordinates or area range) is recorded as "the first position". By using sensors (such as lidar, infrared sensors or vision systems) to obtain the position information of these obstacles, basic data can be provided for subsequent map construction.

[0022] Based on the obtained obstacle position information, the robot divides the target area into several grids and marks the areas where obstacles are located as non-passable grids. These non-passable grids are specially marked on the map to distinguish the passable areas. The initial grid map is the robot's preliminary perception of the environment, which provides a basic framework for subsequent hospital bed position marking and path planning. For example, if the first obstacle is located at a specific coordinate, then in the initial grid map, the grid corresponding to this coordinate will be marked as an obstacle grid.

[0023] After the initial grid map is constructed, the next step is to obtain the position information of the hospital bed. The hospital bed position is a key element in the grid map because the robot needs to accurately find the position of each hospital bed to complete the bedding replacement task. The hospital bed position information can be obtained through the hospital bed position database, which records the exact positions of all hospital beds in the ward. For example, assume there is an arbitrary hospital bed, and its position information (such as coordinates or area range) is recorded as "arbitrary hospital bed position", and this position information will be used as the target point for the robot's navigation.

[0024] Finally, mark the hospital bed position information on the initial grid map. The hospital bed positions are marked as special target grids, which are clearly distinguished on the map so that the robot can identify and navigate to the target hospital beds. The marking process can be achieved by matching the hospital bed position database with the coordinate system of the grid map. For example, if the hospital bed position is the (X, Y) coordinate, then in the grid map, the grid corresponding to this coordinate will be marked as a hospital bed grid.

[0025] Through the above steps, a complete grid map containing hospital bed positions and obstacle information is constructed. This map not only provides the robot with a global perception of the environment but also provides a basis for its subsequent path planning and bedding replacement tasks. The construction process of the grid map fully considers the complexity of the ward environment. By combining the target obstacle position information and the hospital bed position database, it ensures that the robot can efficiently and safely complete tasks in a dynamic environment.

[0026] P20: Set the target optimal path with the minimum energy consumption as the constraint, combining the target grid and the initial grid corresponding to the hospital bed bedding replacement robot.

[0027] Furthermore, step P20 of the embodiment of the present application further includes:

[0028] P21: Construct the first set of movable grids of the initial grid and extract the first grid from the first set of movable grids; P22: Calculate the first energy consumption value when the hospital bed sheet changing robot moves from the initial grid to the first grid; P23: Calculate the number of grid distances from the first grid to the target grid and read the predetermined energy consumption coefficient; P24: Perform weighted calculation on the number of grid distances with the predetermined energy consumption coefficient as the weight to obtain the first estimated energy consumption value; P25: Take the sum of the first energy consumption value and the first estimated energy consumption value and denote it as the first fitness of the first grid; P26: Optimize to obtain the first optimal grid with the minimum first fitness as the constraint, and construct the target optimal path based on the first optimal grid.

[0029] Optionally, in the path planning process of the hospital bed sheet changing robot, the key lies in how to efficiently reach the position of the target hospital bed (target grid) from the initial position (initial grid). To achieve this goal, the path planning needs to take the minimum energy consumption as the constraint condition, comprehensively consider the actual moving energy consumption and the path distance, ensure that the robot can quickly reach the target hospital bed, and can optimize its energy consumption and extend the battery life.

[0030] First of all, the robot needs to determine all possible moving directions starting from its initial position (initial grid), that is, the first set of movable grids, which is the set of adjacent grids that the robot can move to. For example, the robot can move in the up, down, left, right or diagonal directions, and the adjacent grids in each direction may become the next target position. In this way, the robot can quickly evaluate all possible moving paths and provide a basis for subsequent energy consumption calculation.

[0031] For each grid in the first set of movable grids, the robot needs to calculate the energy consumption required to move from the initial grid to this grid. This energy consumption value is called the first energy consumption value, which reflects the energy consumption of the robot in the actual moving process. The energy consumption calculation can be based on factors such as the moving speed of the robot, the load condition and the terrain condition. For example, the robot consumes less energy when moving on a flat ground, while it consumes more energy when climbing a slope or carrying a heavy load. By accurately calculating the energy consumption of each moving direction, the robot can provide a more accurate energy consumption assessment for path planning.

[0032] Next, after determining the energy consumption from the initial grid to each first grid, the robot also needs to evaluate the path from these grids to the target hospital bed. By calculating the distance between each first grid and the target grid, expressed in the number of grids, that is, the number of grid distances of the first. At the same time, read a predetermined energy consumption coefficient, which is used to evaluate the energy consumption of the robot when moving on each grid and can be adjusted according to terrain, obstacle density or other environmental factors to more accurately reflect the actual energy consumption situation.

[0033] Furthermore, to more accurately evaluate the energy consumption from each first grid to the target grid, the system multiplies the number of first distance grids by a predetermined energy consumption coefficient to obtain a first estimated energy consumption value. This weighted calculation process takes into account the relationship between the path length and the actual energy consumption, ensuring that the path planning not only pursues the shortest distance but also takes into account energy consumption optimization. In this way, the robot can more comprehensively evaluate the energy consumption of each possible path.

[0034] Next, for each first grid, add the first energy consumption value (the actual energy consumption from the initial grid to the first grid) to the first estimated energy consumption value (the estimated energy consumption from the first grid to the target grid) to obtain the first fitness of the grid. The first fitness is a comprehensive index that reflects the total energy consumption from the initial grid through this grid to the target grid. By calculating the fitness of each first grid, the robot can quickly evaluate the advantages and disadvantages of each possible path.

[0035] Finally, by comparing the first fitness of all first grids, select the grid with the minimum fitness as the first optimal grid. Based on this first optimal grid, the robot gradually constructs a target optimal path from the initial position to the target hospital bed. This path not only considers the shortest distance of the path but also optimizes the energy consumption, ensuring that the robot has the highest efficiency and the lowest energy consumption when completing the task.

[0036] Furthermore, step P23 of the embodiment of the present application further includes:

[0037] P23-1: Calculate the first Manhattan distance from the first grid to the target grid; P23-2: Obtain the unit length of the unit grid, and combine the first Manhattan distance to obtain the number of first distance grids.

[0038] Specifically, in the path planning process of the hospital bed bedding replacement robot, in order to accurately calculate the distance from the current grid (the first grid) to the target hospital bed position (the target grid), the first Manhattan distance can be further calculated and combined with the unit grid length to obtain the accurate number of first distance grids, so as to provide accurate path length information for subsequent energy consumption evaluation.

[0039] Specifically, first, in order to evaluate the path length from the current grid (the first grid) to the target hospital bed position (the target grid), the robot first needs to calculate the first Manhattan distance between the two. The Manhattan distance is a commonly used method for calculating path length in a grid map, especially suitable for scenarios where movement is only allowed in the horizontal or vertical directions. It measures the distance by calculating the sum of the absolute coordinate differences between two points in the horizontal and vertical directions. For example, if the coordinates of the first grid are (x1, y1) and the coordinates of the target grid are (x2, y2), then the first Manhattan distance D can be calculated by the formula: D = |x2 - x1| + |y2 - y1|. This distance calculation method is particularly suitable for the robot to move in the regularly arranged environment of the ward because it can intuitively reflect the number of grids the robot needs to pass through and avoid complex diagonal movement calculations. In this way, the robot can quickly evaluate the path length from the current position to the target hospital bed, providing a basis for subsequent path planning.

[0040] Next, after obtaining the first Manhattan distance, the robot needs to convert it into the specific number of first distance grids for subsequent energy consumption estimation. To this end, it is necessary to obtain the unit length of the unit grid, that is, the actual physical length of each grid. In the application scenario of the hospital bed bedding replacement robot, the ward map is divided into regular grids, and the length of each grid is known. By dividing the first Manhattan distance by the unit grid length, the number of grids that need to be passed through from the first grid to the target grid can be obtained, that is, the number of first distance grids.

[0041] Exemplarily, assume that the unit grid length is 1 meter and the calculated first Manhattan distance is 10 meters. Then the number of first distance grids is 10 grids. This value reflects the number of grids the robot needs to pass through under ideal conditions (without considering obstacles), providing a basis for subsequent energy consumption estimation. In this way, the robot can more accurately evaluate the energy consumption of the path, thereby optimizing the path planning to ensure the highest efficiency and lowest energy consumption when completing the task.

[0042] Through the above steps, the robot can accurately calculate the distance from the current grid to the target hospital bed and convert it into the number of grids. This process not only provides accurate path length information for subsequent energy consumption estimation but also ensures the scientificity and practicality of path planning.

[0043] Furthermore, step P26 of the embodiment of the present application further includes:

[0044] P26-1: Extract the second grid from the first set of movable grids and obtain the second fitness of the second grid; P26-2: Determine whether the second fitness is less than the first fitness; P26-3: If it is less, use the second grid as the first optimal grid, and if it is not less, use the first grid as the first optimal grid.

[0045] In a possible embodiment of the present application, during the path planning of the hospital bed bedding replacement robot, in order to further optimize the path selection and ensure the minimum energy consumption, the fitness of multiple grids can be dynamically evaluated, and the optimal grids can be gradually selected as part of the path, so as to construct the optimal path from the initial position to the target hospital bed.

[0046] First, during the iterative process of path planning, the robot not only needs to evaluate the fitness of the current grid (the first grid), but also needs to consider other possible moving directions. For this purpose, the system extracts another grid from the first set of movable grids (that is, the set of all adjacent grids that the robot can possibly move to when starting from the initial grid), that is, the second grid, and calculates its fitness, that is, the second fitness. Fitness is a comprehensive index that reflects the total energy consumption from the initial grid through this grid to the target grid. By calculating the fitness of the second grid, the robot can dynamically evaluate the energy consumption of other paths and provide data support for subsequent path optimization.

[0047] Furthermore, after obtaining the fitness of the second grid, the system needs to compare the second fitness with the currently known first fitness. This comparison process is a key link in path optimization. If the second fitness is less than the first fitness, it means that the path from the initial grid through the second grid to the target grid is more advantageous in terms of energy consumption. On the contrary, if the second fitness is not less than the first fitness, it means that the current first grid is still a better choice. Through this dynamic comparison mechanism, the robot can evaluate the advantages and disadvantages of different paths in real time, ensuring the scientificity and dynamics of path planning.

[0048] Among them, according to the fitness comparison result, a better grid is selected as part of the path. If the second fitness is less than the first fitness, the second grid is marked as the first optimal grid and incorporated into the path planning; if the second fitness is not less than the first fitness, the first grid continues to be the current optimal choice. Through this dynamic comparison and selection mechanism, the robot can gradually select the optimal path to ensure the minimum energy consumption when completing the task. This process not only optimizes the path planning, ensures the scientificity and dynamics of path planning, but also optimizes the task execution efficiency of the robot through minimum energy consumption.

[0049] P30: The hospital bed bedding replacement robot moves and acquires the target bedding image under the target optimal path.

[0050] Specifically, during the process of the robot moving along the target optimal path, it will use the vision system carried on it to collect the image of the bedding on the target hospital bed, and these images will provide an important basis for subsequent analysis of the degree of soiling.

[0051] When performing the task of changing bedding, the hospital bed bedding changing robot will move autonomously according to the previously planned target optimal path (i.e., the optimal path from the initial position to the target hospital bed under the constraint of minimizing energy consumption). During the movement, the robot will activate the vision sensors on its top or front, such as a 360° rotating camera or a depth camera, to collect the image of the bedding on the target hospital bed. These cameras are equipped with LED fill lights to ensure clear images can be obtained under different lighting conditions.

[0052] When the robot arrives near the target hospital bed, the vision system will automatically focus and take images of the bedding. These images not only include the overall appearance of the bedsheet and quilt cover, but may also capture details such as wrinkles and stains. After the image collection is completed, the robot will transmit these image data to its control system for further analysis and processing.

[0053] Through the above steps, the robot can efficiently collect the image of the bedding on the target hospital bed during the movement, providing accurate visual information for subsequent analysis of the degree of soiling and replacement decision-making. This process not only reflects the automation and intelligence of the robot system, but also demonstrates the practical application value of vision technology in the field of medical care.

[0054] P40: Co-analyze the target usage log of the target hospital bed and the target bedding image to obtain the target soiling index.

[0055] Furthermore, step P40 of the embodiment of the present application further includes:

[0056] P41: Extract the latest usage record from the target usage log; P42: Match the latest usage user corresponding to the latest usage record and obtain the user characteristic information of the latest usage user; P43: Analyze the user characteristic information to obtain the estimated soiling index; P44: Collect the target soiling feature set of the target bedding image and perform an evaluation analysis on the target soiling feature set to obtain the evaluated soiling index; P45: Take the mean of the estimated soiling index and the evaluated soiling index as the target soiling index.

[0057] It should be understood that in order to accurately evaluate the soiling degree of the bedding, the robot needs to combine two data sources: the target usage log of the hospital bed and the target bedding image collected through the vision system. The target usage log records the usage situation of the hospital bed, including patient information, usage duration, last replacement time, etc. These information provide important background data for the evaluation of the soiling degree. The target bedding image is obtained through a vision sensor and can directly reflect the actual state of the bedding, such as stains, wrinkles, etc. By performing collaborative analysis on these two data, the soiling degree of the bedding can be evaluated more comprehensively.

[0058] Specifically, the robot first extracts the latest usage records from the target usage log of the hospital bed. These records contain detailed information about the most recent use of the hospital bed, such as the patient's check-in time, check-out time, and the usage duration of the hospital bed. The latest usage records are important reference bases for evaluating the soiling degree of the bedding because they directly reflect the usage situation of the bedding. For example, if the hospital bed has been used for a long time or the patient has frequent activities, it may cause the bedding to get dirty more easily.

[0059] Next, after extracting the latest usage records, the system will match the corresponding latest user and obtain the user characteristic information of this user. These characteristic information may include the patient's age, gender, disease type, treatment cycle, etc. For example, certain diseases may cause the patient to sweat more or require frequent replacement of the bedding. These information have important reference value for evaluating the soiling degree of the bedding. By obtaining these user characteristic information, the robot can more accurately estimate the soiling degree of the bedding.

[0060] Furthermore, based on the obtained user characteristic information, these information are analyzed through a pre-set algorithm or model. For example, by the importance of each user characteristic information, a weight coefficient is configured for each characteristic, and then based on the weight coefficient, combined with the real-time obtained user characteristic information for weighted calculation, so as to obtain an estimated soiling index. For example, if the patient has a certain disease that causes profuse sweating, the system may estimate a higher soiling degree of the bedding based on this characteristic. The estimated soiling index is a preliminary evaluation result based on user characteristics and is used as a reference for subsequent comprehensive analysis. This process utilizes the individual characteristics of the patient and provides a scientific basis for the evaluation of the soiling degree.

[0061] Meanwhile, the target bedding images collected by the vision system are used to extract the target dirt feature set in the images. These features may include the size, color, distribution of stains, and the degree of wrinkles of the bedding. Similarly, by collecting the sample features of each stain and training a stain recognition model through machine learning methods, the size, color, distribution, etc. of the stains can be obtained, and by weighting each feature, the cleanliness of the bedding can be comprehensively evaluated to obtain an image-based evaluation dirt index. For example, if the image shows stains or wrinkles with darker colors or larger areas on the bedding, the evaluation dirt index will increase accordingly. This process takes advantage of the visual technology and can intuitively reflect the actual state of the bedding.

[0062] Finally, the estimated dirt index (the evaluation result based on user characteristics) and the evaluation dirt index (the result based on image analysis) are comprehensively processed, and the mean of the two is taken as the final target dirt index. This comprehensive analysis method takes into account both the individual characteristics of the user and the actual state of the bedding, thus improving the accuracy and reliability of the dirt degree evaluation. In this way, the robot can more accurately judge whether the bedding needs to be replaced, avoiding unnecessary resource waste.

[0063] Furthermore, step P43 of the embodiment of the present application further includes:

[0064] P43-1: Extract the first underlying disease in the user characteristic information; P43-2: Combine big data to form the first virus type set carried by the first underlying disease; P43-3: Extract the diagnosed diseases in the user characteristic information; P43-4: Combine big data to form the diagnosed virus type set carried by the diagnosed diseases; P43-5: Based on the first virus type set and the diagnosed virus type set, form a target virus type set; P43-6: Perform an evaluation analysis on the target virus type set to obtain the estimated dirt index.

[0065] Optionally, in the intelligent decision-making process of the hospital bed bedding replacement system, how to evaluate the dirt degree of the bedding through user characteristic information can be further refined, especially for potential pathogen risks. This process analyzes the user's underlying diseases and diagnosed diseases, and combines big data analysis to accurately evaluate the virus types that the bedding may carry, so as to obtain the estimated dirt index.

[0066] Specifically, first, analyze the user's characteristic information to evaluate the potential dirt degree of the bedding, especially for the possible pathogens. Extract the first underlying disease in the user characteristic information (i.e., the user's main chronic disease or long-term health problem). For example, if the user has diabetes, this information will be extracted because diabetic patients may be more prone to certain types of skin infections, thus affecting the cleanliness of the bedding.

[0067] Next, in combination with big data (i.e., statistical information extracted from a large number of medical records), a first set of virus types carried related to the first underlying disease is formed. For example, by analyzing the medical record data of a large number of diabetic patients, the system discovers that the common virus types carried by such patients include certain specific skin viruses or bacteria, and this information will be organized into a set for subsequent risk assessment.

[0068] Subsequently, the diagnosed disease in the user feature information (i.e., the disease that the user is currently being treated for) is extracted. For example, if the user is being treated for influenza, this information will also be extracted. Similarly, in combination with big data, a set of virus types carried related to the diagnosed disease is formed. For example, the common virus types carried by influenza patients will be organized into a set for evaluating the potential risks of the current disease.

[0069] After obtaining the above two sets of virus types, the system combines them to form a comprehensive target set of virus types. This set contains all the virus types that the user may carry, whether due to underlying diseases or current diagnosed diseases. For example, if the user has both diabetes and influenza, then the target set of virus types will contain the skin viruses related to diabetes and the influenza virus.

[0070] Finally, the target set of virus types is evaluated and analyzed. By combining factors such as the transmission risk and survival time of the virus, through methods such as weighted fusion calculation, an estimated soiling index is calculated. This index reflects the risk degree of the bedding being likely to carry pathogens, providing a basis for subsequent disinfection and replacement decisions. For example, if the target set of virus types contains viruses with high transmission risks, the soiling index is higher and more stringent disinfection measures are required. This process not only improves the scientificity and accuracy of soiling assessment but also provides an important basis for subsequent intelligent disinfection strategies to ensure the hygienic safety of the hospital bed environment.

[0071] P50: When the target soiling index reaches a predetermined soiling threshold, read the intelligent replacement plan.

[0072] Specifically, the calculated target soiling index (i.e., a quantitative indicator for comprehensively evaluating the soiling degree of the bedding) is used to determine whether the bedding needs to be replaced. This index is obtained based on the collaborative analysis of the hospital bed usage log and the image of the bedding, and can accurately reflect the actual usage situation and cleaning status of the bedding.

[0073] When the target fouling index reaches or exceeds a preset fouling threshold (a standard value for determining whether the bedding needs to be replaced, which can be set according to the hospital's hygiene requirements and actual operation needs), the system will automatically trigger the bedding replacement operation. At this time, the robot will read the pre-stored intelligent replacement plan (a detailed bedding replacement operation process that contains all the action instructions and parameter settings required for the robot to perform the replacement task).

[0074] Among them, the intelligent replacement plan is formulated in advance according to different fouling degrees, bedding types, and bed layouts, etc., which can ensure that the robot can complete the task efficiently and accurately during the replacement process. For example, if the fouling degree of the bedding is relatively high, the plan may instruct the robot to adopt a more thorough replacement and disinfection process; while for slightly fouled bedding, a faster replacement plan may be adopted. In this way, the robot can flexibly adjust the operation process according to the actual situation, ensure that each replacement meets the hygiene standards, and optimize the resource utilization at the same time.

[0075] Through the above steps, the hospital bed bedding replacement robot can intelligently decide whether to replace the bedding based on a scientific fouling assessment standard (fouling threshold) and a preset operation process (intelligent replacement plan), and efficiently execute the replacement task.

[0076] P60: The hospital bed bedding replacement robot replaces the bedding of the target hospital bed based on the intelligent replacement plan.

[0077] Further, before the hospital bed bedding replacement robot replaces the bedding of the target hospital bed based on the intelligent replacement plan, the embodiment of the present application further includes step P60a, and step P60a further includes:

[0078] P61a: Extract the intelligent disinfection strategy embedded in the intelligent replacement plan; P62a: Develop a target disinfection plan for the target virus type set according to the intelligent disinfection strategy; P63a: Activate the disinfection module of the hospital bed bedding replacement robot, and disinfect the target hospital bed in combination with the target disinfection plan.

[0079] In a possible embodiment of the present application, the robot replaces the bedding of the target hospital bed according to the intelligent replacement plan. And, before the actual replacement, in order to ensure the hygiene and safety of the hospital bed environment, the robot needs to disinfect the hospital bed.

[0080] Before performing the bedding replacement, the robot will extract the intelligent disinfection strategy embedded in the intelligent replacement plan, that is, a fixed disinfection plan formulated according to the usage of the hospital bed and the possible types of pathogens. This strategy contains key information such as the target object of disinfection, disinfection methods (such as ultraviolet disinfection, ozone disinfection, etc.), and disinfection intensity.

[0081] Next, according to the extracted intelligent disinfection strategy, further optimize the strategy for the specific pathogen types (i.e., the target virus type set) that may exist on the target hospital bed. For example, adjust the scheme parameters to determine a more targeted target disinfection scheme, which includes key information such as the target object of disinfection, disinfection methods (such as ultraviolet disinfection, ozone disinfection, etc.), and disinfection intensity. After formulating the target disinfection scheme, the robot will activate its built-in disinfection module, such as a system equipped with ultraviolet lamps, ozone generators, or other disinfection devices, and comprehensively disinfect the target hospital bed according to the requirements of the target disinfection scheme.

[0082] After completing the disinfection process, the robot will officially enter the bedding replacement stage. According to the intelligent replacement plan, the robot will activate its robotic arm and end effector (such as a pneumatic suction cup or gripper), and grab new bedding according to the preset process to replace the old bedding on the hospital bed. This process is not only efficient but also ensures the standardization and hygiene of the replacement operation, effectively reducing the pathogen risk that may exist on the hospital bed.

[0083] In summary, the embodiments of the present application have at least the following technical effects:

[0084] The present application first establishes a grid map of hospital beds based on the hospital bed position database to determine the target grid corresponding to the target hospital bed; then, with the minimum energy consumption as the constraint, combines the initial grid of the robot to set the optimal path; the robot moves along this path and collects images of the target bedding; then collaboratively analyzes the hospital bed usage log and the bedding image to obtain the target soiling index; when the soiling index reaches the preset threshold, reads the intelligent replacement plan; finally, the robot completes the bedding replacement according to the plan.

[0085] It achieves the technical effects of realizing the efficient and standardized replacement of hospital bed bedding through an automated and intelligent robot system, reducing the risk of cross-infection, and reducing labor costs.

[0086] Embodiment 2, based on the same inventive concept as the intelligent replacement method for a kind of hospital bed bedding in the foregoing embodiment, as Figure 2 shown, the present application provides an intelligent replacement system for hospital bed bedding. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes:

[0087] A grid map construction module 11, configured to establish a grid map of hospital beds based on the hospital bed position database, where the grid map of hospital beds includes the target grid corresponding to the target hospital bed.

[0088] An optimal path setting module 12, configured to set the target optimal path with the minimum energy consumption as the constraint, in combination with the target grid and the initial grid corresponding to the hospital bed bedding replacement robot.

[0089] The bedding image acquisition module 13 is configured to move and acquire a target bedding image while the hospital bed bedding replacement robot moves along the target optimal path.

[0090] The collaborative analysis module 14 is configured to perform collaborative analysis on the target usage log of the target hospital bed and the target bedding image to obtain a target soiling index.

[0091] The intelligent replacement plan reading module 15 is configured to read an intelligent replacement plan when the target soiling index reaches a predetermined soiling threshold.

[0092] The bedding replacement execution module 16 is configured to replace the bedding of the target hospital bed by the hospital bed bedding replacement robot based on the intelligent replacement plan.

[0093] Furthermore, the grid map construction module 11 is further configured to perform the following steps:

[0094] Obtain the target obstacle position information of the target area, where the target obstacle position information includes the first position of the first obstacle;

[0095] Establish an initial grid map according to the first position of the first obstacle;

[0096] Obtain any hospital bed, where the any hospital bed corresponds to an arbitrary hospital bed position;

[0097] Mark the arbitrary hospital bed position corresponding to the any hospital bed on the initial grid map to obtain the hospital bed grid map.

[0098] Furthermore, the optimal path setting module 12 is further configured to perform the following steps:

[0099] Form a first movable grid set of the initial grid, and extract the first grid in the first movable grid set; calculate the first energy consumption value of the hospital bed bedding replacement robot moving from the initial grid to the first grid; calculate the first distance grid number from the first grid to the target grid, and read a predetermined energy consumption coefficient; perform weighted calculation on the first distance grid number with the predetermined energy consumption coefficient as the weight to obtain a first estimated energy consumption value; take the sum of the first energy consumption value and the first estimated energy consumption value, and denote it as the first fitness of the first grid; with the minimum of the first fitness as the constraint, optimize to obtain the first optimal grid, and form the target optimal path based on the first optimal grid.

[0100] Furthermore, the optimal path setting module 12 is further configured to perform the following steps:

[0101] Calculate the first Manhattan distance from the first grid to the target grid; obtain the unit length of the unit grid, and combine the first Manhattan distance to obtain the first distance grid number.

[0102] Further, the optimal path setting module 12 is further configured to perform the following steps:

[0103] Extract the second grid from the first movable grid set, and obtain the second fitness of the second grid; determine whether the second fitness is less than the first fitness; if it is less, use the second grid as the first optimal grid, and if it is not less, use the first grid as the first optimal grid.

[0104] Further, the collaborative analysis module 14 is further configured to perform the following steps:

[0105] Extract the latest usage record from the target usage log; match the latest usage user corresponding to the latest usage record, and obtain the user feature information of the latest usage user; analyze the user feature information to obtain an estimated pollution index; collect the target pollution feature set of the target bedding image, and perform an evaluation analysis on the target pollution feature set to obtain an evaluation pollution index; take the mean of the estimated pollution index and the evaluation pollution index as the target pollution index.

[0106] Further, the collaborative analysis module 14 is further configured to perform the following steps:

[0107] Extract the first underlying disease from the user feature information; combine big data to form the first set of virus types carried by the first underlying disease; extract the diagnosed diseases from the user feature information; combine big data to form the set of virus types carried by the diagnosed diseases; based on the first set of virus types carried and the set of virus types carried by the diagnosed diseases, form a target set of virus types; perform an evaluation analysis on the target set of virus types to obtain the estimated pollution index.

[0108] Further, the bedding replacement execution module 16 is further configured to perform the following steps:

[0109] Extract the intelligent disinfection strategy embedded in the intelligent replacement plan; formulate a target disinfection plan for the target set of virus types according to the intelligent disinfection strategy; activate the disinfection module of the hospital bed bedding replacement robot, and disinfect the target hospital bed in combination with the target disinfection plan.

[0110] Exemplary electronic device

[0111] Next, refer to Figure 3 to describe the electronic device of the embodiments of the present application.

[0112] Based on the same inventive concept as the intelligent replacement method of a hospital bed bedding in the foregoing embodiments, the present application further provides an intelligent replacement system for hospital bed bedding, including: a processor, the processor is coupled to a memory, and the memory is used to store a program, when the program is executed by the processor, the system is enabled to execute the steps of the method described in Embodiment 1.

[0113] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may further include a bus architecture 304. Among them, the communication interface 303, the processor 302, and the memory 301 may be interconnected through the bus architecture 304; the bus architecture 304 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0114] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the solution of the present application.

[0115] The communication interface 303 uses any device such as a transceiver for communicating with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Networks (WLAN), wired access networks, etc.

[0116] The memory 301 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can exist independently and be connected to the processor through the bus architecture 304. The memory can also be integrated with the processor.

[0117] Among them, the memory 301 is used to store the computer execution instructions for executing the solution of this application, and is controlled by the processor 302 for execution. The processor 302 is used to execute the computer execution instructions stored in the memory 301, so as to implement an intelligent replacement method for the hospital bed bedding provided in the above embodiments of this application.

[0118] It should be noted that the above sequence of embodiments of this application is only for description and does not represent the superiority or inferiority of the embodiments. And the above has described specific embodiments of this specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.

[0120] This specification and the drawings are only exemplary descriptions of this application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application is intended to include these changes and modifications.

Claims

1. An intelligent replacement method for hospital bed bedding, characterized in that, Including: Establish a hospital bed grid map based on the hospital bed position database, wherein the hospital bed grid map includes a target grid corresponding to a target hospital bed; Taking minimum energy consumption as a constraint, combine the target grid and the initial grid corresponding to the hospital bed bedding replacement robot to set a target optimal path; The hospital bed bedding replacement robot moves and acquires a target bedding image under the target optimal path; Perform collaborative analysis on the target usage log of the target hospital bed and the target bedding image to obtain a target soiling index; When the target soiling index reaches a predetermined soiling threshold, read the intelligent replacement plan; The hospital bed bedding replacement robot replaces the bedding of the target hospital bed based on the intelligent replacement plan.

2. The intelligent replacement method of the hospital bed bedding according to claim 1, characterized in that, Establishing a hospital bed grid map based on the hospital bed position database includes: Obtain the target obstacle position information of the target area, wherein the target obstacle position information includes the first position of the first obstacle; Establish an initial grid map according to the first position of the first obstacle; Obtain any hospital bed, and the any hospital bed corresponds to any hospital bed position; Mark the any hospital bed position corresponding to the any hospital bed on the initial grid map to obtain the hospital bed grid map.

3. The intelligent replacement method of the hospital bed bedding according to claim 1, wherein, Taking minimum energy consumption as a constraint, combining the target grid and the initial grid corresponding to the hospital bed bedding replacement robot to set a target optimal path includes: Form a first movable grid set of the initial grid, and extract the first grid in the first movable grid set; Calculate the first energy consumption value of the hospital bed bedding replacement robot moving from the initial grid to the first grid; Calculate the first distance grid number from the first grid to the target grid, and read a predetermined energy consumption coefficient; Perform weighted calculation on the first distance grid number with the predetermined energy consumption coefficient as a weight to obtain a first estimated energy consumption value; Take the sum of the first energy consumption value and the first estimated energy consumption value, and denote it as the first fitness of the first grid; Taking the minimum of the first fitness as a constraint, optimize to obtain a first optimal grid, and form the target optimal path based on the first optimal grid.

4. The intelligent replacement method of a hospital bed bedding according to claim 3, characterized in that, Calculating the first distance grid number from the first grid to the target grid includes: Calculate the first Manhattan distance from the first grid to the target grid; Obtain the unit length of the unit grid, and combine the first Manhattan distance to obtain the first distance grid number.

5. The intelligent replacement method of the hospital bed bedding according to claim 3, characterized in that, Taking the minimum of the first fitness as a constraint, optimizing to obtain a first optimal grid includes: Extract the second grid in the first movable grid set, and obtain the second fitness of the second grid; Judge whether the second fitness is less than the first fitness; If it is less, use the second grid as the first optimal grid, if it is not less, use the first grid as the first optimal grid.

6. The intelligent replacement method of the hospital bed bedding according to claim 1, wherein, Performing collaborative analysis on the target usage log of the target hospital bed and the target bedding image to obtain a target soiling index includes: Extract the latest usage record in the target usage log; Match the latest usage user corresponding to the latest usage record, and obtain the user characteristic information of the latest usage user; Analyze the user characteristic information to obtain an estimated soiling index; Collect the target filth feature set of the target bedding image, and evaluate and analyze the target filth feature set to obtain an evaluation filth index; Take the mean of the estimated filth index and the evaluation filth index as the target filth index.

7. The intelligent replacement method of the hospital bed bedding according to claim 6, characterized in that, Analyze the user feature information to obtain an estimated filth index, including: Extract the first underlying disease in the user feature information; Combine big data to form the first virus type set carried by the first underlying disease; Extract the diagnosed disease in the user feature information; Combine big data to form the diagnosed virus type set carried by the diagnosed disease; Based on the first virus type set and the diagnosed virus type set, form a target virus type set; Evaluate and analyze the target virus type set to obtain the estimated filth index.

8. The intelligent replacement method of the hospital bed bedding according to claim 7, characterized in that, Before the bedding replacement robot for the target hospital bed replaces the bedding of the target hospital bed based on the intelligent replacement plan, it further includes: Extract the intelligent disinfection strategy embedded in the intelligent replacement plan; Formulate a target disinfection plan for the target virus type set according to the intelligent disinfection strategy; Activate the disinfection module of the bedding replacement robot for the target hospital bed, and disinfect the target hospital bed in combination with the target disinfection plan.

9. An intelligent replacement system for hospital bed bedding, characterized in that, The system is used to execute the steps of the method according to any one of claims 1 to 8, and the system includes: A grid map construction module, configured to establish a hospital bed grid map based on a hospital bed position database, wherein the hospital bed grid map includes a target grid corresponding to the target hospital bed; An optimal path setting module, configured to set a target optimal path by taking the minimum energy consumption as a constraint and combining the target grid and the initial grid corresponding to the bedding replacement robot for the target hospital bed; A bedding image acquisition module, configured to move and acquire a target bedding image by the bedding replacement robot for the target hospital bed along the target optimal path; A collaborative analysis module, configured to perform collaborative analysis on the target usage log of the target hospital bed and the target bedding image to obtain a target filth index; An intelligent replacement plan reading module, configured to read an intelligent replacement plan when the target filth index reaches a predetermined filth threshold; A bedding replacement execution module, configured to replace the bedding of the target hospital bed by the bedding replacement robot for the target hospital bed based on the intelligent replacement plan.

10. An electronic device, characterized in that, Including: A processor, the processor is coupled with a memory, and the memory is used to store a program. When the program is executed by the processor, the system is caused to execute the steps of the method according to any one of claims 1 to 8.

Images