Intelligent shared wheelchair control system for accompanying diagnosis

Abstract

The invention relates to the technical field of intelligent shared wheelchairs, in particular to an intelligent shared wheelchair control system for accompanying diagnosis, and the system comprises a reservation module which obtains a user reservation request and completes the reservation of an intelligent shared wheelchair; the demand information acquisition module acquires a target department ward of a user; the indoor navigation and state monitoring module is used for acquiring an indoor traffic map of a hospital and monitoring the treatment state of a ward of a target department in real time; the accompanying diagnosis path optimization module takes the accompanying diagnosis navigation path as an optimization target, creates a target department ward accompanying diagnosis knowledge graph based on a hospital indoor traffic map, and creates an accompanying diagnosis navigation path optimization model based on a grey wolf optimization algorithm and the target department ward accompanying diagnosis knowledge graph; optimizing the accompanying diagnosis navigation path through the accompanying diagnosis navigation path optimization model to obtain an optimal accompanying diagnosis navigation path; the intelligent navigation module controls the intelligent shared wheelchair to operate according to the optimal diagnosis accompanying navigation path. The utilization rate of the intelligent shared wheelchair can be improved, and meanwhile the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent shared wheelchairs, and in particular to an intelligent shared wheelchair control system for accompanying medical consultation. Background Art

[0002] Shared wheelchairs provide convenience to users with limited mobility to a certain extent and have been widely used in hospitals, nursing homes and other places. Especially in hospital scenarios, shared wheelchairs can not only help patients with limited mobility to move easily within the hospital, but also realize automatic obstacle avoidance, safety monitoring, automatic navigation and other functions. For example:

[0003] Invention patent CN106726208A, a smart shared wheelchair control system, discloses "including an RC main controller module, a motor driver, a data acquisition module and a sensor module; the sensor module detects the road conditions around the smart shared wheelchair in real time and collects images of the leader, the data acquisition module receives the image information of the sensor module, and the data acquisition module transmits the image information to the RC main controller module; the RC main controller module performs comprehensive analysis and processing on the collected image information according to a preset program, generates reasonable instructions and transmits them to the motor driver to drive the motor, thereby realizing the tracking walking and automatic avoidance of the smart shared wheelchair"; Invention patent CN116270047A, an electric wheelchair control system and method for realizing intelligent motion and remote health monitoring, discloses "high-sensitivity automatic following based on UWB ranging, based on nine-axis IMU and GPS&North The dual-mode bucket realizes high-precision positioning, the millimeter-wave radar realizes low-latency intelligent obstacle avoidance function, and the customized vital signs monitoring system based on RFID can provide users with high-accuracy, non-invasive real-time health monitoring"; the invention patent CN110320921A, an automatic navigation shared intelligent wheelchair system for hospital transportation, discloses "the use of visual positioning and autonomous navigation technology, indoor automatic driving technology and multi-modal intelligent control technology to realize the automatic navigation of the "shared intelligent wheelchair"; the use of mobile Internet technology and cloud platform technology on the mobile phone APP to realize "one-click reservation", so that the successfully booked intelligent shared wheelchair can "autonomously navigate" in the hospital and arrive at the designated location for service; after the rental is successful, the multi-modal intelligent control technology is used to control the wheelchair to reach the destination; after the wheelchair service is completed, it can also "automatically navigate" and be returned.

[0004] Although the above solutions have solved the problem of tight human resources in hospitals and simplified the hospital's cumbersome rental procedures, the hospital's traffic is high, especially when there are multiple outpatient appointments or multiple examinations. How to control smart shared wheelchairs during the accompanying process, optimize the navigation path, reduce the time users use shared wheelchairs, increase the utilization rate of smart shared wheelchairs, and at the same time improve user experience and promote the application of smart shared wheelchairs in multiple fields are still urgent problems that need to be solved. Summary of the invention

[0005] The present invention aims to provide an intelligent shared wheelchair control system for accompanying medical treatment. Based on the Gray Wolf optimization algorithm and the target department ward accompanying medical treatment knowledge graph, an accompanying medical treatment navigation path optimization model is created, and the accompanying medical treatment navigation path is optimized through the accompanying medical treatment navigation path optimization model to obtain the optimal accompanying medical treatment navigation path, so as to improve the utilization rate of intelligent shared wheelchairs and improve the user experience at the same time.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme:

[0007] An intelligent shared wheelchair control system for accompanying a patient for medical consultation, comprising:

[0008] The reservation module is used to obtain the user's reservation request and complete the reservation of the smart shared wheelchair;

[0009] Demand information acquisition module, used to obtain the user's target department and ward;

[0010] Indoor navigation and status monitoring module, used to obtain the hospital's indoor traffic map and monitor the treatment status of the target department ward in real time;

[0011] The accompanying diagnosis path optimization module is used to take the accompanying diagnosis navigation path as the optimization target, create the accompanying diagnosis knowledge graph of the target department ward based on the hospital indoor traffic map, create the accompanying diagnosis navigation path optimization model based on the gray wolf optimization algorithm and the accompanying diagnosis knowledge graph of the target department ward, and optimize the accompanying diagnosis navigation path through the accompanying diagnosis navigation path optimization model to obtain the best accompanying diagnosis navigation path;

[0012] The intelligent navigation module is used to control the operation of the intelligent shared wheelchair according to the optimal accompanying navigation path.

[0013] The principles and advantages of this solution are: in actual application, the user's reservation request is obtained through the reservation module, and the reservation of the smart shared wheelchair is completed, so that after the user's reservation is completed, the smart shared wheelchair automatically navigates to the user's location to improve convenience; the user's target department and ward are obtained through the demand information acquisition module to facilitate subsequent optimized navigation; the hospital's indoor traffic map is obtained through the indoor navigation and status monitoring module, and the medical status of the target department and ward is monitored in real time; through the accompanying path optimization module, the accompanying navigation path is taken as the optimization target, and the target department and ward accompanying knowledge graph is created based on the hospital's indoor traffic map, and the accompanying navigation path optimization model is created based on the gray wolf optimization algorithm and the target department and ward accompanying knowledge graph, and the accompanying navigation path optimization model is used to optimize the accompanying navigation path to obtain the optimal accompanying navigation path; the intelligent navigation module controls the operation of the intelligent shared wheelchair according to the optimal accompanying navigation path to reach the target location for service. By creating a knowledge graph for accompanying patients, it is convenient to filter out the required content from the hospital's indoor traffic map and reduce the impact of redundant data on the accuracy of optimization results. By creating an accompanying patient navigation path optimization model based on the Grey Wolf optimization algorithm and the accompanying patient knowledge graph of the target department ward, it is convenient to quickly, accurately and efficiently obtain the best accompanying patient navigation path while considering multi-dimensional influencing factors.

[0014] Preferably, as an improvement, the accompanying path optimization module includes a target department ward accompanying knowledge graph creation sub-module: it is used to identify all feasible wheelchair paths from the user's current position to the target department ward from the hospital's indoor traffic map, and create an accompanying knowledge graph with the department ward and the current position as nodes, the department ward waiting time as node attributes, the wheelchair feasible paths between nodes as edges, and the estimated path duration as edge attributes.

[0015] Technical effect: The hospital's indoor traffic map contains the overall traffic route conditions of the hospital. After obtaining the user's target department or ward, all feasible wheelchair path plans for the target department or ward are identified on demand and a knowledge graph is generated, which facilitates intuitive understanding of the traffic conditions, eliminates redundant data, and improves optimization speed.

[0016] Preferably, as an improvement, the waiting time in the department ward is predicted based on the treatment status of the target department ward by fitting historical data with a neural network model.

[0017] Technical effect: By predicting the waiting time in department wards, it is convenient to optimize the navigation path.

[0018] Preferably, as an improvement, the accompanying path optimization module further includes:

[0019] The submodule for creating the accompanying medical path optimization model is used to treat each accompanying medical path plan as a gray wolf, initialize the gray wolf population, and determine the fitness function and constraints;

[0020] The iterative submodule of the companion path optimization model is used to determine the number of iterations, update the position and fitness of each gray wolf, and define the α wolf position that meets the termination condition as the optimal navigation path.

[0021] Technical effect: It is easy to simulate the leadership hierarchy and hunting mechanism of gray wolves in nature to obtain the final prey position as the best navigation path.

[0022] Preferably, as an improvement, the fitness function is determined by the total usage time of the smart shared wheelchair, the total occupation time of the smart shared wheelchair and the traffic instability, and the fitness function is:

[0023] S T,t,N =w1T time a +w2t z b +w3N w c

[0024] Among them, T time is the estimated time taken for the path, t z is the total time that the smart shared wheelchair is occupied, N w is the traffic instability coefficient, w1, w2, w3 are proportional adjustment constant coefficients, and a, b, c are scaling constant factors of the factor influence degree.

[0025] Technical effect: The fitness function makes it easier to update and iterate the position of the gray wolf.

[0026] Preferably, as an improvement, the method for determining the estimated time spent on the path is: obtaining video information of the reachable path, dividing the video information into grids and numbering them based on the building type, parsing the travel direction information and congestion information in each grid, and predicting the time spent based on the travel direction information and congestion information. The prediction model is as follows:

[0027]

[0028] Among them, t i is the historical unit distance passing time of grid i, L i is the travel distance of grid i, f i is the constant coefficient affecting the number of walking directions in grid i, F i The number of walking directions in grid i, y i is the congestion impact constant coefficient in grid i, r i is the number of people in grid i, s iis the area of ​​grid i.

[0029] Technical effect: Different building types have different passing times due to the influence of channel width, pedestrian flow, etc. By dividing the grid and calculating the passing time separately, the prediction accuracy can be improved.

[0030] Preferably, as an improvement, the constraint conditions include:

[0031] J tg ∈k tg

[0032] z=min(z w )

[0033] h i ∈H

[0034] J tg represents the time period when the smart shared wheelchair is in the department ward g, k tg represents the opening time period of the department ward g, z represents the number of turns, and z w represents the set of turning times, h i is the environmental data of the intelligent shared wheelchair passing through grid i, and H represents the set of qualified environmental data.

[0035] Technical effect: It is convenient to ensure that when some departments and wards are only open during specific hours, the traversal is completed during that period, and the turns are minimized to improve comfort, while ensuring that the environment of the navigation path enables the smart shared wheelchair to work normally.

[0036] Preferably, as an improvement, the number of iterations is confirmed by dynamically adjusting the number of iterations, and the adjustment model of the number of iterations is:

[0037]

[0038] Among them, N0 is the minimum number of iterations, x is the number of optimization variables, τ x The constant coefficient for adjusting the optimization complexity corresponding to the number of optimization variables, and x0 is the threshold value for the number of optimization variables.

[0039] Technical effect: Variables jointly determine the final navigation solution. The more variables there are, the larger the problem dimension is. By dynamically adjusting the number of iterations, the search space can be fully explored, while also improving iteration efficiency.

[0040] Preferably, as an improvement, the intelligent navigation module further includes:

[0041] The wheelchair status monitoring module is used to monitor the status of the smart shared wheelchair in real time. The status of the smart shared wheelchair includes positioning accuracy, signal status, power status, seat adjustment parameters, and sensor fault status;

[0042] The road condition monitoring submodule is used to obtain the road condition of the best navigation path for medical consultation in real time, determine the accessibility, and re-optimize the navigation path when the best navigation path for medical consultation is not accessible;

[0043] The user behavior monitoring submodule is used to obtain the user's physical monitoring data and surveillance video in real time and synchronize them to the third-party monitoring terminal.

[0044] The technical effect ensures that the target location can be reached smoothly according to the best accompanying navigation path.

[0045] Preferably, as an improvement, it also includes a three-party monitoring module for authenticating the permissions of the three-party monitoring end and controlling the smart shared wheelchair based on the permissions, wherein the permissions include viewing permissions, information interaction permissions and target department ward modification permissions.

[0046] Technical effect: When the user seeks medical treatment independently, the guardian can accompany the user in the cloud, the doctor can grasp the user's situation in time, and in case of emergencies, the target department and ward can be adjusted in time to adjust the navigation path. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The figure is a schematic diagram of the structure of an intelligent shared wheelchair control system for accompanying medical consultation;

[0048] Figure 2 Schematic diagram of the iterative process of the accompanying patient path optimization model. DETAILED DESCRIPTION

[0049] The following is further described in detail through specific implementation methods:

[0050] Embodiment 1

[0051] The embodiment is basically as shown in the attached Figure 1 As shown, an intelligent shared wheelchair control system for accompanying a patient for medical consultation comprises:

[0052] The reservation module is used to obtain user reservation requests and complete quick reservations for smart shared wheelchairs; the user sends a reservation request through the client, and after receiving the reservation request, the system sends the available smart shared wheelchair information to the client, the available smart shared wheelchair information includes location information, quantity information, and device status information. The device status information includes the remaining battery life of the smart shared wheelchair, and the user selects the smart shared wheelchair to complete the reservation.

[0053] The demand information acquisition module is used to obtain the user's target department and ward. The target department and ward represent the department and ward involved in the whole process of the hospital, such as outpatient department, laboratory department, pharmacy, ward, payment registration window, result acquisition window, etc. In this embodiment, after the user successfully makes an appointment, the user's target department and ward are directly obtained from the hospital's patient information management system, such as the user needs to go to the registration window, payment window, user needs to go to multiple clinics, user needs to go to multiple examination windows, etc. In order to increase the flexibility of the smart shared wheelchair, the user's voice information can also be recognized through the voice interaction module to obtain the user's target department and ward.

[0054] The indoor navigation and status monitoring module is used to obtain the hospital's indoor traffic map and monitor the patient status of the target department ward in real time. The hospital's indoor traffic map includes the floor plan (including size and slope information), department location, elevator and stair location. The patient status includes the number of people waiting and the doctor's working status.

[0055] The accompanying medical consultation path optimization module is used to take the accompanying medical consultation navigation path as the optimization target, create a target department ward accompanying medical consultation knowledge graph based on the hospital indoor traffic map, create an accompanying medical consultation navigation path optimization model based on the gray wolf optimization algorithm and the target department ward accompanying medical consultation knowledge graph, and optimize the accompanying medical consultation navigation path through the accompanying medical consultation navigation path optimization model to obtain the best accompanying medical consultation navigation path.

[0056] The accompanying path optimization module includes a target department ward accompanying knowledge graph creation submodule: used to identify all wheelchair feasible paths from the user's current position to the target department ward from the hospital indoor traffic map, and create an accompanying knowledge graph with the department ward and the current position as nodes, the department ward queue time as the node attribute, the wheelchair feasible path between nodes as the edge, and the estimated path time as the edge attribute. The wheelchair feasible path is confirmed according to the width requirement, slope requirement, turning radius, and ground material; for example, in this embodiment, the wheelchair feasible path is usually at least 90 cm, the barrier-free door width is at least 80 cm, the slope of the slope should not exceed 1:12 (every 12 units of horizontal distance forward, the vertical height rises 1 unit), the turning radius for accommodating wheelchairs is at least 1.5 meters, the ground is flat, there are no bumps and bumps to ensure the stability of the wheelchair, the ground has appropriate friction, and it should not be too slippery or too rough, etc. The department ward queue time is based on the target department ward visit status by fitting historical data through a neural network model, taking the visit status as input and the queue time as output, and predicting the queue time. In this embodiment, the specific prediction method of the department ward queue time is not limited.

[0057] The accompanying medical treatment path optimization module also includes: an accompanying medical treatment path optimization model creation submodule, which is used to take each accompanying medical treatment navigation path plan as a gray wolf, initialize the gray wolf population, and determine the fitness function and constraint conditions; for example, the target department wards include d1, d2, and d3. Starting from the target position, there are 6 plans arranged in the order of reaching. It is assumed that in the order of d2, d3, and d1, there are n0 paths from the target position to d2, n1 paths from d2 to d3, and n2 paths from d3 to d1. Therefore, a variety of accompanying medical treatment navigation path plans can be formed, and each accompanying medical treatment navigation path plan is taken as a gray wolf, that is, as a solution X, and the gray wolf population is initialized to obtain Xi (i=1, 2, ..., n).

[0058] The fitness function is determined by the total usage time of the smart shared wheelchair, the total occupation time of the smart shared wheelchair and the traffic instability. The fitness function is:

[0059] S T,t,N =w1T time a +w2t z b +w3N w c

[0060] Among them, T time is the estimated time spent on the path, i.e. the total time the smart shared wheelchair is used, t z is the total time that the smart shared wheelchair is occupied, which affects the service efficiency of the smart shared wheelchair. The total time that the smart shared wheelchair is occupied is the sum of the total time that the smart shared wheelchair is used, the waiting time in queue and the consultation time. N w is the travel instability coefficient, which is used to measure the degree of influence of unstable factors encountered when traveling on a specific path on the travel efficiency. It can evaluate the travel efficiency of wheelchairs in different directions or paths. The travel instability coefficient is determined as follows: all unstable locations in the hospital are marked with feature points, the number of feature points passed by the accompanying navigation path is obtained, and the pre-stored comparison table of the number of feature points and the travel instability coefficient is queried to obtain the travel instability coefficient; w1, w2, and w3 are proportional adjustment constant coefficients, and a, b, and c are factor influence degree scaling constant factors.

[0061] The estimated time spent on the path affects the power consumption of the smart shared wheelchair. The method for determining the estimated time spent on the path is as follows: obtaining video information of the accessible path, dividing the video information into grids and numbering them based on the building type, parsing the travel direction information and congestion information in each grid, and predicting the time spent based on the travel direction information and congestion information. The prediction model is as follows:

[0062]

[0063] Among them, t i is the historical unit distance passing time of grid i, L i is the travel distance of grid i, f i is the constant coefficient affecting the number of walking directions in grid i, F i The number of walking directions in grid i, y i is the congestion impact constant coefficient in grid i, y i 、f i All pre-stored, r i is the number of people in grid i, s i is the area of ​​grid i.

[0064] Considering that the service windows of some departments and wards are only open at specific times, and at the same time, the time spent at non-essential stops should be minimized, and the number of turns should be reduced to improve travel efficiency. In addition, under special weather and lighting conditions, such as rainy or cold weather or dim light conditions, wheelchairs are difficult to move and their safety is limited, so they need to be restrained. The restraints include:

[0065] J tg ∈k tg

[0066] z=min(z w )

[0067] h i ∈H

[0068] J tg represents the time period when the smart shared wheelchair is in the department ward g, k tg represents the opening time period of the department ward g, z represents the number of turns, and z w represents the set of turning times, h i is the environmental data of the intelligent shared wheelchair passing through grid i, and H represents the set of qualified environmental data.

[0069] The iterative submodule of the companion path optimization model is used to determine the number of iterations, update the positions and fitness of each gray wolf, and define the α wolf position that meets the termination condition as the optimal navigation path. Since the variables jointly determine the final navigation solution, the more variables, the larger the problem dimension. By dynamically adjusting the number of iterations, the search space can be fully explored, and the iteration efficiency is also improved. The number of iterations is confirmed by dynamic adjustment, and the adjustment model of the number of iterations is:

[0070]

[0071] Among them, N0 is the minimum number of iterations, x is the number of optimization variables, τ x The constant coefficient for adjusting the optimization complexity corresponding to the number of optimization variables, and x0 is the threshold value for the number of optimization variables.

[0072] The intelligent navigation module is used to control the operation of the intelligent shared wheelchair according to the optimal navigation path for accompanying the patient. The intelligent navigation module also includes:

[0073] The wheelchair status monitoring module is used to monitor the status of the smart shared wheelchair in real time. The status of the smart shared wheelchair includes positioning accuracy, signal status, power status, seat adjustment parameters, and sensor fault status. When the wheelchair deviates from the predetermined route, that is, the positioning accuracy is low, it can be inferred that there is a deviation in the positioning system of the wheelchair, and the communication between the wheelchair and the control system will be interrupted due to signal interference or network failure. When the wheelchair has low power, the entire accompanying medical consultation process cannot be completed, and sensor failure affects the normal operation of the wheelchair. The seat adjustment parameters reflect the user's personal preferences. By monitoring the status of the smart shared wheelchair in real time, it is easy to discover and solve problems in a timely manner, ensuring that the target location can be smoothly reached according to the optimal accompanying medical consultation navigation path, while improving the user experience.

[0074] The road condition monitoring submodule is used to obtain the road condition of the best accompanying navigation path in real time and judge the accessibility. When the best accompanying navigation path is not reachable, the accompanying path is re-optimized to avoid temporary obstacles that block the operation of the smart wheelchair and improve the flexibility of the smart shared wheelchair.

[0075] The user behavior monitoring submodule is used to obtain the user's physical monitoring data and monitoring video in real time, and synchronize them to the third-party monitoring terminal. It also includes a third-party monitoring module, which is used to authenticate the permissions of the third-party monitoring terminal and control the smart shared wheelchair based on the permissions, including viewing permissions, information interaction permissions, and target department ward modification permissions; when the user seeks medical treatment independently, the guardian can accompany the user in the cloud, the doctor can grasp the user's situation in time, and in case of emergencies, the target department ward can be adjusted in time to adjust the navigation path.

[0076] Embodiment 2

[0077] Considering that when users choose a smart shared wheelchair on their own, they cannot clearly determine the required usage time, so they usually choose the smart shared wheelchair with the longest remaining power available time. This will cause customers who only need to use it for a short time to occupy resources, and customers who need to use it for a long time will not be able to make an appointment, resulting in resource waste, imbalance between supply and demand, and increased maintenance costs of smart shared wheelchairs. In this embodiment, different from the first embodiment, after receiving the appointment request, the system obtains the best accompanying navigation path, predicts the power consumption based on the best accompanying navigation path, and automatically allocates the smart shared wheelchair with the least power redundancy based on the power consumption. The predicted power consumption model is:

[0078]

[0079] Among them, H hTo predict power consumption, p q is the motor power, T time The total usage time of the smart shared wheelchair, x q is the battery efficiency, θ is the slope coefficient, and ω is the power floating adjustment constant.

[0080] Considering that the supply of smart shared wheelchairs is less than the demand during peak periods, when multiple users make reservations at the same time, the reservation module is also used to obtain user priorities and complete reservations based on user priorities.

[0081] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical solutions and / or characteristics in the solution is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical solution of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent shared wheelchair control system for accompanying a patient for medical consultation, characterized in that: include: The reservation module is used to obtain the user's reservation request and complete the reservation of the smart shared wheelchair; Demand information acquisition module, used to obtain the user's target department and ward; Indoor navigation and status monitoring module, used to obtain the hospital's indoor traffic map and monitor the treatment status of the target department ward in real time; The accompanying diagnosis path optimization module is used to take the accompanying diagnosis navigation path as the optimization target, create the accompanying diagnosis knowledge graph of the target department ward based on the hospital indoor traffic map, create the accompanying diagnosis navigation path optimization model based on the gray wolf optimization algorithm and the accompanying diagnosis knowledge graph of the target department ward, and optimize the accompanying diagnosis navigation path through the accompanying diagnosis navigation path optimization model to obtain the best accompanying diagnosis navigation path; The intelligent navigation module is used to control the operation of the intelligent shared wheelchair according to the optimal accompanying navigation path.

2. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 1, characterized in that: The accompanying path optimization module includes a target department ward accompanying knowledge graph creation submodule: it is used to identify all wheelchair feasible paths from the user's current location to the target department ward from the hospital's indoor traffic map, and create an accompanying knowledge graph with the department ward and the current location as nodes, the department ward waiting time as node attributes, the wheelchair feasible paths between nodes as edges, and the estimated path duration as edge attributes.

3. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 2, characterized in that: The queuing time of the department ward is predicted based on the treatment status of the target department ward by fitting historical data with a neural network model.

4. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 3, characterized in that: The accompanying diagnosis path optimization module also includes: The submodule for creating the accompanying medical path optimization model is used to treat each accompanying medical path plan as a gray wolf, initialize the gray wolf population, and determine the fitness function and constraints; The iterative submodule of the companion path optimization model is used to determine the number of iterations, update the position and fitness of each gray wolf, and define the α wolf position that meets the termination condition as the optimal navigation path.

5. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 4, characterized in that: The fitness function is determined by the total usage time of the smart shared wheelchair, the total occupation time of the smart shared wheelchair and the traffic instability. The fitness function is: <h2 style=";text-align:left;direction:ltr">S<h2 style=";text-align:left;direction:ltr"> T,t,N <h2 style=";text-align:left;direction:ltr"> =w1T<h2 style=";text-align:left;direction:ltr"> time <h2 style=";text-align:left;direction:ltr"> a <h2 style=";text-align:left;direction:ltr"> +w2t<h2 style=";text-align:left;direction:ltr"> z <h2 style=";text-align:left;direction:ltr"> b <h2 style=";text-align:left;direction:ltr"> +w3N<h2 style=";text-align:left;direction:ltr"> w <h2 style=";text-align:left;direction:ltr"> c Among them, T time is the estimated time taken for the path, t z is the total time that the smart shared wheelchair is occupied, N w is the traffic instability coefficient, w1, w2, w3 are proportional adjustment constant coefficients, and a, b, c are scaling constant factors of the factor influence degree.

6. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 5, characterized in that: The method for determining the estimated time spent on the path is as follows: obtaining video information of the accessible path, dividing the video information into grids and numbering them based on the building type, parsing the traveling direction information and congestion information in each grid, and predicting the time spent based on the traveling direction information and congestion information. The prediction model is as follows: Among them, t i is the historical unit distance passing time of grid i, L i is the travel distance of grid i, f i is the constant coefficient affecting the number of walking directions in grid i, F i The number of walking directions in grid i, y i is the congestion impact constant coefficient in grid i, r i is the number of people in grid i, s i is the area of ​​grid i.

7. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 4, characterized in that: The constraints include: J tg ∈k tg from=min(from w ) h i ∈H J tg represents the time period when the smart shared wheelchair is in the department ward g, k tg represents the opening time period of the department ward g, z represents the number of turns, and z w represents the set of turning times, h i is the environmental data of the intelligent shared wheelchair passing through grid i, and H represents the set of qualified environmental data.

8. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 4, characterized in that: The number of iterations is determined by dynamic adjustment, and the adjustment model of the number of iterations is: Among them, N0 is the minimum number of iterations, x is the number of optimization variables, τ x The constant coefficient for adjusting the optimization complexity corresponding to the number of optimization variables, and x0 is the threshold value for the number of optimization variables.

9. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 1, characterized in that: The intelligent navigation module also includes: The wheelchair status monitoring module is used to monitor the status of the smart shared wheelchair in real time. The status of the smart shared wheelchair includes positioning accuracy, signal status, power status, seat adjustment parameters, and sensor fault status; The road condition monitoring submodule is used to obtain the road condition of the best navigation path for medical consultation in real time, determine the accessibility, and re-optimize the navigation path when the best navigation path for medical consultation is not accessible; The user behavior monitoring submodule is used to obtain the user's physical monitoring data and surveillance video in real time and synchronize them to the third-party monitoring terminal.

10. The intelligent shared wheelchair control system for accompanying a patient for medical consultation according to claim 1, characterized in that: It also includes a three-party monitoring module, which is used to authenticate the permissions of the three-party monitoring end and control the smart shared wheelchair based on the permissions, including viewing permissions, information interaction permissions and target department and ward modification permissions.

Images