A method for ensuring battery power during the trip of an electric wheelchair

Abstract

This application provides a method for ensuring sufficient battery power for an electric wheelchair during its journey, comprising the following steps: obtaining a user-defined itinerary for the next day, including a destination, a planned charging point, and a planned departure time; calculating the total battery power required to complete the itinerary, taking the planned charging point as the starting and ending point and combining it with a preset activity duration at the destination, wherein the total battery power required includes the round-trip battery power from the planned charging point to the destination and a preset redundant battery power corresponding to the preset activity duration; obtaining the current battery power of the electric wheelchair and predicting the predicted remaining battery power of the electric wheelchair at the planned departure time based on the current battery power and the estimated standby power consumption from the current time to the planned departure time; determining, based on the predicted remaining battery power and the total battery power required, whether the battery power is sufficient to complete the itinerary at the planned departure time; if not, issuing a charging reminder to the user before the planned departure time.

Description

Technical Field

[0001] This application relates to the field of electric wheelchair technology, and specifically to a method for ensuring the power supply during the trip of an electric wheelchair. Background Technology

[0002] In existing technologies, electric wheelchairs are generally equipped with simple low-battery alarm functions, which typically trigger an audible and visual alert when the battery level falls below a certain fixed threshold (e.g., 15%-20%). However, this generic alarm mechanism has a significant drawback: it completely fails to consider the user's specific travel plans for the following day. For users who rely on electric wheelchairs for daily activities, especially the elderly or those with mobility impairments, they often need to plan their trips to hospitals, supermarkets, and other destinations in advance. Existing technology only informs users that "the current battery level is low," but fails to address the core concern of "whether the current battery level is sufficient for my trip tomorrow." Users can only make rough estimates based on experience, which can easily lead to misjudgments—either being overly conservative and abandoning necessary trips, or being overly optimistic and running out of power en route, resulting in being stranded. This poses serious safety hazards and a poor user experience. Therefore, there is an urgent need for an intelligent safety assurance method that can proactively assess battery risk based on the user's specific travel plans. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the prior art, this application aims to provide a method for ensuring the travel power of an electric wheelchair, comprising the following steps: Obtain the user's planned itinerary for the next day, which includes the destination, planned charging points, and planned departure time; Using the planned charging point as the starting point and the end point, and combining the preset activity duration at the destination, calculate the total electricity demand required to complete the trip plan, wherein the total electricity demand includes the round trip electricity from the planned charging point to the destination, and a preset redundant electricity portion corresponding to the preset activity duration; Obtain the current battery level of the electric wheelchair, and based on the current battery level and the estimated standby power consumption from the current time to the planned departure time, predict the predicted remaining battery level of the electric wheelchair at the planned departure time; Based on the predicted remaining power and the total power demand, determine whether the power is sufficient to complete the trip plan at the planned departure time. If not, a charging reminder will be sent to the user before the scheduled departure time.

[0004] According to the technical solution provided in the embodiments of this application, the method further includes determining the battery feasibility of temporarily added destinations during the trip execution, including the following steps: When it is detected that the user has initiated a new temporary destination during the trip, the real-time location, real-time battery level and temporary destination information of the electric wheelchair are obtained; Starting from the real-time location, ending at the planned charging point, and passing through the temporary destination, a new temporary route is planned. Based on the temporary full route and the real-time battery level, calculate the total temporary power requirement required to complete the temporary full route; Based on the real-time battery level and the temporary total power demand, determine whether the battery currently has the power to travel to the temporary destination and safely return to the planned charging point; If not, generate and output a battery infeasibility alert for the temporary trip.

[0005] According to the technical solution provided in the embodiments of this application, the battery of the electric wheelchair is equipped with an external power supply port, and the method further includes the following steps: When it is detected that power is being supplied to an external device through the external power supply port, the current power consumption or cumulative power consumption of the external device is obtained in real time. Based on the current power consumption or cumulative power consumption, dynamically adjust the real-time available power or the predicted remaining power of the electric wheelchair; Based on the corrected real-time available power or the predicted remaining power, reassess whether it is sufficient to complete the trip plan or the temporary full route. If the assessment is reassessed as insufficient to complete the task, a power-limiting warning or interruption suggestion is generated and output for the power supply behavior of the external device.

[0006] According to the technical solution provided in the embodiments of this application, determining whether the battery power is sufficient to complete the planned trip at the planned departure time includes the following steps: Obtain the current health status parameters of the battery of the electric wheelchair; Based on the current health status parameters of the battery, determine the healthy discharge depth threshold; Determine whether the total power required to complete the trip plan will cause the battery discharge depth of the electric wheelchair to exceed the healthy discharge depth threshold; If so, it is determined that the battery power is insufficient to complete the trip plan.

[0007] According to the technical solution provided in the embodiments of this application, the method further includes the following steps: Acquire and learn users' habitual charging behavior data; When a user’s current charging behavior deviates from the usual charging behavior data, the user’s recent travel data and real-time battery status are analyzed. Based on the analysis results, determine whether there is a potential risk of being trapped due to running out of power; If so, a risk warning message will be generated and sent to the preset emergency contact.

[0008] According to the technical solution provided in the embodiments of this application, acquiring and learning a user's habitual charging behavior data, and detecting whether the current charging behavior deviates from the habitual charging behavior data, includes the following steps: Establish a dynamic habitual charging model for users. The dynamic habitual charging model is based on historical charging data to learn and characterize the joint probability distribution of the following parameters: charging start time interval, charging interval duration, and initial charging amount. When a new charging event occurs or a preset learning cycle is reached, the corresponding current charging parameters are obtained; The current charging parameters are input into the dynamic inertial charging model to calculate the abnormal probability value of its deviation from the joint probability distribution; If the abnormal probability value exceeds the preset deviation threshold, it is determined that the current charging behavior deviates from the usual charging behavior data.

[0009] According to the technical solution provided in the embodiments of this application, determining whether there is a potential risk of being trapped due to power depletion based on the analysis results includes the following steps: Obtain historical health degradation trend data of the battery of the electric wheelchair; Based on the battery's historical health degradation trend data and current battery health status parameters, the probability of the battery experiencing sudden performance degradation or failure within a preset future period is predicted. The probability of sudden performance degradation or failure is correlated with the user's current charging behavior deviation and real-time battery status. If the analysis shows that, under conditions of deviated charging behavior and low to medium battery level, the probability of the battery malfunctioning within a preset time period exceeds a preset safety threshold, then it is determined that there is a potential risk of the user being trapped due to a combination of sudden battery malfunction and insufficient battery power.

[0010] According to the technical solution provided in the embodiments of this application, acquiring and learning the user's habitual charging behavior data includes the following steps: Obtain the typical remaining battery level range when a user starts charging; The determination of whether there is a potential risk of being trapped due to power depletion, based on the analysis results, also includes: When it is detected that the user's recent charging starting power is consistently lower than the typical remaining power range, and the recent travel data shows that the user is going to non-habitual areas or routes more frequently, it is determined that there is a progressive high risk due to changes in the user's cognition or behavior patterns. When the progressive high risk is determined to exist, a progressive risk warning notification is generated and sent to the preset emergency contacts. The notification includes at least a brief description of the user's current behavior pattern changes and the current battery status information.

[0011] According to the technical solution provided in the embodiments of this application, the method further includes the following steps: Based on the current health status parameters of the electric wheelchair's battery, a safe power threshold for managing the external power supply port is dynamically determined; When the real-time battery level of the electric wheelchair falls below the safe battery threshold, a power supply restriction request is sent to the user; the user then decides whether to restrict or disconnect the external power supply port based on the nature of the external power supply device. The safe power threshold is negatively correlated with the current health status parameter of the battery, so that the lower the battery health status, the higher the safe power threshold is set.

[0012] According to the technical solution provided in the embodiments of this application, the method further includes the following steps: When it is determined that the battery needs maintenance based on the current health status parameters of the battery, the historical health degradation trend data of the battery, or the probability of the battery experiencing sudden performance degradation or failure, the proactive maintenance service docking process is triggered. The proactive maintenance service integration process includes: Generate service request data that includes a battery health diagnostic report and maintenance level recommendations; Based on the real-time location information of the electric wheelchair or the location of the planned charging point, match and recommend at least one available preset service provider; In the user terminal's interactive interface, at least one operable service entry point associated with the service request data is generated and displayed. The service entry point is used to provide users or the preset emergency contacts with interactive functions such as initiating service appointments with one click, obtaining service quotes, or directly contacting service providers.

[0013] Compared to existing technologies, the advantages of this application are as follows: This solution acquires and integrates the user's specific itinerary plan for the next day (destination, charging point, departure time, activity duration), transforming battery assessment from an independent judgment of device status into a personalized prediction closely linked to the user's travel needs. It directly answers the core question that users care about most: whether the current battery level is sufficient for tomorrow's trip, eliminating the uncertainty and anxiety associated with estimations based on experience. This solution performs calculations and assessments before the planned departure time and sends charging reminders in advance when the battery is low. This provides users with ample response time (such as finding charging stations and scheduling charging times), significantly shifting risk control from the journey itself to the trip planning stage. It achieves proactive and forward-looking power assurance, effectively avoiding the risk of being stranded due to depleted battery power. From simple power monitoring to multi-factor comprehensive modeling, the accuracy and reliability of power assessment are improved. This solution constructs a more refined power demand and consumption prediction model: Demand side: In addition to calculating the basic power consumption for the round trip, a preset redundant power portion corresponding to the preset activity duration is added, considering the user's possible power consumption during their stay at the destination (such as maintaining the control system in standby mode, minor adjustments to location, etc.), making the total power demand estimate more closely match the actual usage scenario. Supply side: In addition to obtaining the current battery level, it further estimates the standby energy consumption from the current moment to the planned departure time based on historical data or models, thereby predicting a more accurate remaining power at the departure time. Through two-way refined modeling and comparison, this solution greatly improves the accuracy of the judgment results, reducing two misjudgments: overly conservative estimates leading to abandoning the trip or overly optimistic estimates resulting in being stranded. Attached Figure Description

[0014] Figure 1 A flowchart illustrating the steps of the method for ensuring the travel power supply for an electric wheelchair provided in this application. Detailed Implementation

[0015] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0016] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0017] Example 1 As mentioned in the background section, in view of the problems in the prior art, this application proposes a method for ensuring the travel power of an electric wheelchair, such as... Figure 1 As shown, it includes the following steps: S1. Obtain the user-defined itinerary plan for the next day, which includes the destination, planned charging points, and planned departure time; S2. Taking the planned charging point as the starting point and the end point, and combining the preset activity duration at the destination, calculate the total electricity demand required to complete the trip plan, wherein the total electricity demand includes the round trip electricity from the planned charging point to the destination, and the preset redundant electricity portion corresponding to the preset activity duration. S3. Obtain the current battery level of the electric wheelchair, and based on the current battery level and the estimated standby power consumption from the current time to the planned departure time, predict the predicted remaining battery level of the electric wheelchair at the planned departure time. S4. Based on the predicted remaining power and the total power demand, determine whether the power is sufficient to complete the trip plan at the planned departure time; S5. If not, send a charging reminder to the user before the scheduled departure time.

[0018] Specifically, the system retrieves the user's planned itinerary for the following day: The user inputs or selects their travel intentions for the next day via a wheelchair controller or smartphone application. The itinerary is a structured dataset containing at least three elements: Destination: The specific location the user plans to visit, such as the outpatient department of the Municipal Central Hospital, or the supermarket at No. 123 Heping Road. This can be done through text input, map selection, or selection from the historical address book. Planned charging point: The location the user plans to return to and charge after completing the trip. In most home use scenarios, this point defaults to the user's home address. The system can also allow the user to specify other charging points, such as their children's homes or day care centers. Planned departure time: The specific time the user expects to begin the next day's itinerary, such as 9:30 AM tomorrow. This provides the system with a benchmark for calculating the time window. The system calculates the total power demand required to complete the planned trip. This calculation, performed in the background, consists of two core components: Round-trip power demand: Using the planned charging point as the starting and ending point, the system uses integrated map service APIs (such as Amap or Google Maps API) to plan an optimal or user-favored route from the charging point to the destination and calculates the distance. Next, the system calls a basic energy consumption model (in watt-hours per kilometer), based on the wheelchair's nominal energy consumption and the user's average driving speed historical data, to calculate the theoretical energy consumption for completing the round trip. Preset redundant power capacity: The system reserves buffer power to handle uncertain activities at the destination. Users can manually input an estimated stay duration (e.g., 2 hours at a hospital) when setting the trip, or the system can provide a default duration based on the destination type (e.g., supermarket, park). Redundant power capacity is calculated based on the wheelchair's low-power consumption rate during standby and low-speed movement multiplied by the preset activity duration. This portion of power is designed to cover energy consumption during periods of wandering, waiting, and low-speed movement at the destination that are not included in the fixed route. Predicted Remaining Battery Power at Planned Departure Time: This is a dynamic prediction step designed to assess the actual battery power available to the user at departure time. The system first acquires real-time data from the electric wheelchair's battery management system to obtain the current battery level. Then, the system calculates the estimated standby power consumption from the current time to the planned departure time. Even when the wheelchair is not in motion, its controller, communication module, sensors, etc., will still consume a small amount of power. This power consumption can be estimated by multiplying the historical average standby power by the time interval, or by using a conservative fixed power consumption value. Finally, a prediction is made: Predicted Remaining Battery Power = Current Battery Level - Estimated Standby Power Consumption. This value represents the theoretically available battery power at departure time without any additional charging by the user. Judgment and Reminder: The system compares the predicted remaining battery power with the total required battery power. If the predicted remaining battery power is greater than or equal to the total required battery power, the system determines that the battery power is sufficient and does not issue any proactive reminders to avoid disturbing the user. If the predicted remaining battery power is less than the total required battery power, the system determines that the battery power is insufficient to safely complete the next day's trip.At this time, the system will display a high-priority notification on the wheelchair controller screen and issue a gentle voice prompt, "Friendly reminder: According to your travel plans for tomorrow, the current battery may be low. It is recommended to charge it in time," before the planned departure time (for example, 3-6 hours in advance, or at a fixed time that evening). It will also push a message on the associated APP to remind the user to charge.

[0019] The technical advantage of this implementation lies in achieving proactive, personalized power risk assessment. Its principle is to transform the traditional, scenario-independent, general low-power alarm into a closed-loop calculation model based on specific objectives. This model integrates multiple factors: the user's subjective travel intentions (destination, time), objective route distance, conservative activity redundancy estimates, and the device's own standby power consumption. By executing the logical chain of plan input → demand modeling → current situation prediction → comparative decision → early intervention, the system can issue warnings hours before risks occur, allowing users ample response time (such as utilizing off-peak electricity rates at night). This fundamentally solves the anxiety and misjudgment caused by the inability to quantify whether power is sufficient, significantly improving the planning, safety, and user experience of electric wheelchair use. The essence of its technical principle is to transform uncertain travel needs into a deterministic power budget and compare it with dynamically predicted available resources, thereby achieving preventative management.

[0020] In a preferred embodiment, the method further includes determining the battery feasibility of temporarily added destinations during the trip execution, including the following steps: When it is detected that the user has initiated a new temporary destination during the trip, the real-time location, real-time battery level and temporary destination information of the electric wheelchair are obtained; Starting from the real-time location, ending at the planned charging point, and passing through the temporary destination, a new temporary route is planned. Based on the temporary full route and the real-time battery level, calculate the total temporary power requirement required to complete the temporary full route; Based on the real-time battery level and the temporary total power demand, determine whether the battery currently has the power to travel to the temporary destination and safely return to the planned charging point; If not, generate and output a battery infeasibility alert for the temporary trip.

[0021] Specifically, the system detects new temporary destinations through various means: Users can actively input a new address and set it as a temporary destination on the wheelchair controller or mobile app's map interface. Users can also use voice commands, such as "go to the pharmacy ahead." The system can detect when the wheelchair deviates from its planned route for an extended period and stops at a point of interest (POI) via continuous GPS positioning. After simple confirmation from the user, this point is set as the temporary destination. The system then acquires real-time information and replans the route: Once a temporary destination is set, the system immediately obtains three sets of key real-time data: Real-time location: The wheelchair's current precise latitude and longitude obtained via the GPS module. Real-time battery level: The instantaneous remaining battery percentage or watt-hours read from the battery management system. Temporary destination information: The geographical coordinates of the new destination. Subsequently, the system uses the real-time location as the starting point, the pre-set planned charging point (usually home) as the ending point, and forces a route through the temporary destination, calling the map API to replan a continuous temporary route. This route describes the complete journey from the current location → to the temporary destination → back to the charging point. Calculating and Determining Temporary Total Energy Demand: Based on the distance of the newly planned temporary route and an energy consumption model, the system calculates the total temporary energy demand required to complete the new journey. This calculation may also include redundancy for estimated short stops at temporary destinations. The system directly compares the real-time battery level (the actual current resource) with the total temporary energy demand (the resource required to complete the new plan). If the real-time battery level is sufficient to cover the total temporary energy demand with an appropriate safety margin, the system determines that the conditions are met and can silently support the user's journey, or display a confirmation message on the screen indicating sufficient battery power and the journey is possible. If the real-time battery level is insufficient, the system immediately generates and outputs a power infeasibility warning. This warning must clearly indicate the risk, for example, by displaying a pop-up window on the screen: "Current battery power is insufficient to support reaching the pharmacy and returning home safely. It is recommended to cancel this addition or find the nearest charging facility."

[0022] The technical advantage of this implementation lies in providing dynamic safety decision support during the trip, giving users the freedom to flexibly adjust their itinerary while setting clear safety boundaries. Its technical principle lies in building a real-time replanning and rapid evaluation engine. When the user's intention changes, the system does not rigidly adhere to the original plan, but quickly reconstructs a complete itinerary model based on the latest status (location, battery level) and the latest goal (temporary destination), with a safe return as the ultimate objective, and performs immediate resource checks. This method transforms the complex psychological estimation of whether one can still get home if they detour there into an instant and accurate calculation result. It effectively prevents users from acting impulsively due to spur-of-the-moment decisions, ultimately leading to a dangerous situation where the battery runs out halfway, achieving a balance between flexibility and safety. Essentially, it upgrades the static itinerary planning model to a dynamically reconstructable and real-time solveable model, ensuring that a safe return is verifiable at any decision point.

[0023] In a preferred embodiment, the battery of the electric wheelchair is equipped with an external power supply port, and the method further includes the following steps: When it is detected that power is being supplied to an external device through the external power supply port, the current power consumption or cumulative power consumption of the external device is obtained in real time. Based on the current power consumption or cumulative power consumption, dynamically adjust the real-time available power or the predicted remaining power of the electric wheelchair; Based on the corrected real-time available power or the predicted remaining power, reassess whether it is sufficient to complete the trip plan or the temporary full route. If the assessment is reassessed as insufficient to complete the task, a power-limiting warning or interruption suggestion is generated and output for the power supply behavior of the external device.

[0024] Specifically, external power supply port and monitoring: The battery pack or controller of the electric wheelchair integrates a universal power supply port, such as USB-A, USB-C, or a DC round connector, allowing users to connect mobile phones, portable medical devices (such as ventilators, infusion pumps), or tablets for charging. When a device is plugged in and charging begins, the wheelchair's power management circuitry acquires the current power consumption (in watts) of the external device in real time, or calculates the cumulative power consumption (in watt-hours) by accumulating power and time. This data is reported to the main control system via internal circuit communication (such as I2C, CAN bus). Dynamic correction of available power: After obtaining the power consumption data of the external device, the system initiates a dynamic correction process. For scenarios during travel (associated with temporary judgment scenarios), the system subtracts the cumulative power consumption of the external device from the real-time battery power to obtain a corrected real-time available power. This value more accurately reflects the net power available for wheelchair operation. For pre-departure scenarios (related to the planned scenario), when calculating the predicted remaining battery power, the system not only subtracts the estimated standby power consumption but also estimates or subtracts the estimated external power consumption of external devices that may occur from the current time to the departure time, thus obtaining a corrected predicted remaining battery power. Reassessment and Warning: The system uses the corrected battery power value to replace the original value and re-executes the judgment logic (i.e., whether it is sufficient to complete the planned trip or the temporary full route). If the reassessment result shows insufficient power, it means that the charging behavior of external devices has posed a substantial threat to trip safety. At this time, the system will generate and output a targeted power-limiting warning or interruption suggestion. For example, the screen may prompt: Charging your phone has affected your safety on the way home; it is recommended to stop charging or connect a power bank. Furthermore, the system can automatically limit the output current of the external power supply port to a very low level (such as trickle charging) or completely cut off its power supply, and simultaneously notify the user.

[0025] This implementation achieves refined partitioned management and risk tracing of total power consumption. Its technical principle involves introducing the concept of isolating and accounting for core battery life and additional function power consumption. The system dynamically divides the battery's total energy pool into a dedicated portion for mobile use and a shared portion for external devices by real-time monitoring of external loads. When the accounting detects that the use of the shared portion begins to erode the safety threshold of the dedicated portion, the system issues targeted alarms or even forcibly intervenes. This solves the problem of external power consumption becoming a black box in traditional solutions, allowing users to clearly know where the electricity is used and whether it affects safety. It transforms convenient external power supply from a hidden killer of battery life into a function that operates safely under intelligent supervision, reflecting the design philosophy of ensuring that core task resources are not squeezed out in a multi-functional integrated system through real-time auditing.

[0026] In a preferred embodiment, determining whether the battery power is sufficient to complete the planned trip at the scheduled departure time includes the following steps: Obtain the current health status parameters of the battery of the electric wheelchair; Based on the current health status parameters of the battery, determine the healthy discharge depth threshold; Determine whether the total power required to complete the trip plan will cause the battery discharge depth of the electric wheelchair to exceed the healthy discharge depth threshold; If so, it is determined that the battery power is insufficient to complete the trip plan.

[0027] Specifically, the system obtains the current battery health status parameters: It reads a series of parameters reflecting the battery's aging level from the Battery Management System (BMS). These parameters are far more than just a simple percentage of charge, mainly including: Current actual usable capacity: a percentage relative to the battery's nominal capacity when it was brand new (e.g., nominally 20Ah, currently only 16Ah can be charged). Battery internal resistance: ohmic internal resistance and polarization internal resistance, whose values ​​increase significantly with aging. Full charge voltage and discharge plateau voltage: the voltage characteristics of an aging battery will change. Historical average depth of discharge: the average depth of charge used in recent discharge cycles. The system determines a healthy depth of discharge threshold: based on the above health parameters, the system dynamically determines a healthy depth of discharge threshold using a preset algorithm or lookup table. This is a protective threshold, lower than the battery's physical limit (0%). The logic behind its setting is: the less healthy the battery, the more conservative the threshold should be (i.e., the larger the value, the smaller the range of usable charge). For example, a new battery with 95% health might have a threshold set at 85% (allowing the remaining 15% to be used); while an aging battery with only 70% health might have a threshold set at 60% (allowing only the remaining 40% to be used), leaving a larger safety buffer to prevent high-voltage drops. Judgment and Decision: The system first calculates the total power demand based on the trip plan. Then, it calculates the estimated percentage of battery power to be consumed if the trip is executed, i.e., the estimated depth of discharge. For example, starting with a full charge, the total power demand is 70% of the battery's total capacity, so the estimated depth of discharge is 70%. Next, a health protection judgment is performed: the system checks whether the estimated depth of discharge exceeds the healthy depth of discharge threshold. If it does, it is determined that the power is insufficient to complete the trip plan. This means that even if it is feasible from the perspective of simply having enough power (total power demand < current available power), it is unacceptable from the perspective of protecting the long-term health of the battery. The system will therefore trigger a charging reminder, suggesting that the user fully charge the battery before departure to ensure that the battery's depth of discharge is still within the healthy threshold at the end of the trip.

[0028] The technical advantage of this implementation lies in extending power supply assurance from the scope of single-use safety to the scope of long-term asset (battery) health management. Its technical principle is based on the scientific law that battery electrochemical lifespan is strongly correlated with depth of discharge (DOD). Deep discharge accelerates the irreversible loss of battery active materials and the increase in internal resistance. This solution establishes a dynamic mapping relationship between the real-time health status of the battery and the allowable depth of discharge, imposing a health budget constraint on each trip plan. The system acts like a battery health manager, caring not only about whether the user can return this time, but also about how long the battery can continue to function healthily with this usage. When it predicts that a trip will lead to unhealthy deep discharge, it intervenes in advance, guiding the user to change their charging behavior. This has significant economic value for expensive wheelchair batteries, and also indirectly ensures long-term range reliability by maintaining battery performance. Essentially, it adds a long-term cost function with battery health as a constraint to the trip planning optimization problem, achieving synergistic optimization of short-term use safety and long-term equipment reliability.

[0029] In a preferred embodiment, the method further includes the following steps: Acquire and learn users' habitual charging behavior data; When a user’s current charging behavior deviates from the usual charging behavior data, the user’s recent travel data and real-time battery status are analyzed. Based on the analysis results, determine whether there is a potential risk of being trapped due to running out of power; If so, a risk warning message will be generated and sent to the preset emergency contact.

[0030] Specifically, the system continuously and silently records key data for each charging event in the background, forming a historical database. Recorded data items include at least: the specific time charging started (e.g., 22:15 on October 26, 2023), the remaining battery percentage at the start of charging (e.g., 35%), and the interval between the previous charging session and the end of the previous session (e.g., 28 hours). The learning process is automatic. The system periodically (e.g., every 30 days) analyzes this historical data, using statistical methods to summarize the user's habitual patterns. For example, the system might calculate that the user typically starts charging between 9 PM and 11 PM, with typical charging intervals ranging from 20 to 30 hours, and usually initiates charging when the battery level is between 25% and 40%. These statistical patterns (averages, distribution ranges) constitute the habitual charging behavior data. Detecting deviations from current charging behavior: When a new charging event occurs, the system obtains its current charging parameters: current time, current battery level, and the interval between the previous event and the current charging session. The system compares these parameters with the learned habitual patterns. For example, if a user usually charges at night, but this time charges at 3 AM with the battery already down to 5%, the system will identify a significant deviation in both charging time and initial battery level. Analysis of recent travel data and real-time battery status: Travel data analysis: The system retrieves recent travel records (e.g., the past 48 hours), including GPS tracks, stops, and driving speeds. It checks for abnormal patterns, such as: whether the user has traveled to an unfamiliar area and stayed there for an extended period; whether there is an abnormal increase in energy consumption on a regular route (possibly due to insufficient tire pressure or increased load); and whether the user frequently takes short trips with the battery level at a critical value (e.g., <15%). Real-time battery status acquisition: Simultaneously, the system reads the current precise battery level and battery health status. Comprehensive assessment and warning of potential risks: The system correlates deviations in charging behavior with recent travel anomalies and real-time low battery status. The logic is as follows: a single deviation might be accidental, but abnormal charging combined with abnormal travel and low battery may indicate that the user's normal routine and judgment have been disrupted due to getting lost, physical discomfort, or other reasons, leading to forgetting or being unable to charge in time, and putting them in a high-risk situation. For example, if the system detects that the user has not charged as usual for more than 48 hours (deviation), GPS shows that they spent a long time in an unfamiliar park yesterday (abnormal travel), and the current battery level is only 10% (poor condition), the system will determine that there is a potential risk of being stranded due to depleted battery. Once the risk is determined, the system immediately issues a warning. It will not simply remind the user (who may no longer be able to respond effectively), but will generate a risk warning message containing key information and send it via mobile network (such as 4G / 5G module) or the user's mobile phone's internet connection to the mobile app or SMS of a pre-set emergency contact (such as children or caregivers).The information should be concise and to the point, for example: "Safety Warning: Your family member [User Name] has unusual charging habits and is currently located at [Current Location]. The battery level is only 10%, which may pose a safety risk. Please pay attention immediately." This implementation shifts from passive response to proactive risk detection. The system no longer simply alerts the user to low battery status; instead, it proactively analyzes the user's daily behavior patterns (charging habits) to detect potential signs of depletion. A correlation warning mechanism between abnormal behavior and safety risks is established: by correlating deviations in charging behavior with recent travel anomalies and real-time battery status, the system can identify more complex risk scenarios than a single event. For example, it can not only detect forgotten charging but also determine if this forgotten charging occurred after a recent, unfamiliar, and time-consuming trip, thus assessing whether the user may be in a high-risk state requiring external attention due to getting lost, fatigue, or physical discomfort. A safety network directly connecting to emergency contacts is constructed: upon risk assessment, warning information is sent directly to pre-set emergency contacts (such as children or caregivers), rather than just alerting the user who may already be at risk. This creates an effective safety net, ensuring that external assistance can be triggered promptly if the user is unable to help themselves, greatly improving the likelihood and timeliness of rescue in unexpected situations.

[0031] In a preferred embodiment, acquiring and learning a user's habitual charging behavior data, and detecting whether the current charging behavior deviates from the habitual charging behavior data, includes the following steps: Establish a dynamic habitual charging model for users. The dynamic habitual charging model is based on historical charging data to learn and characterize the joint probability distribution of the following parameters: charging start time interval, charging interval duration, and initial charging amount. When a new charging event occurs or a preset learning cycle is reached, the corresponding current charging parameters are obtained; The current charging parameters are input into the dynamic inertial charging model to calculate the abnormal probability value of its deviation from the joint probability distribution; If the abnormal probability value exceeds the preset deviation threshold, it is determined that the current charging behavior deviates from the usual charging behavior data.

[0032] Specifically, a dynamic habitual charging model is established: instead of defining habits using simple averages and fixed intervals, the system builds a statistical model. This model describes each user charging event as a combination of three parameters: charging start time T, charging interval duration I, and initial charging level S. Based on a large amount of historical data, the system uses algorithms (such as Gaussian mixture models or kernel density estimation) to learn the joint probability distribution of these three parameters in three-dimensional space. This means that the model knows that for this user, the probability of charging at 10 PM (T), after a 24-hour interval (I), with 30% battery remaining (S) is very high; while the probability of charging at 4 AM (T), after a 48-hour interval (I), with 5% battery remaining (S) is extremely low. This model is dynamic and is periodically updated with new data to adapt to the slow changes in habits.

[0033] Obtain current charging parameters: Whenever the user plugs in the charger (a new charging event occurs), or every fixed period (such as every Sunday), the system collects the current set of parameters (T_cur, I_cur, S_cur).

[0034] Calculating the anomaly probability value: The system inputs the current set of parameters (T_cur, I_cur, S_cur) into the established joint probability distribution model. The model calculates the probability density of the current set of parameters under this distribution. This calculated value is the reciprocal of the anomaly probability value—more intuitively, the smaller this value, the more the current behavior deviates from the historical normal pattern, and the higher its anomaly probability value (or anomaly score). For example, the probability density calculated for normal behavior might be 0.15, while the probability density calculated for a highly abnormal behavior might only be 0.001.

[0035] Deviation detection: The system presets a deviation threshold (e.g., a probability density below 0.01). The calculated probability density is compared to the threshold. If the probability density is lower than the deviation threshold (i.e., the abnormal probability value exceeds the standard), the system determines that the current charging behavior deviates from the usual charging behavior data. The advantage of this method is that it comprehensively considers the interaction of three parameters, and the judgment is probabilistic, better distinguishing between normal random fluctuations and genuine anomalies. For example, charging one hour later on a certain day, but with other parameters normal, might not be considered a deviation; however, if time, interval, and battery level are all slightly abnormal simultaneously, their combined probability may be very low, thus accurately detecting the deviation.

[0036] In a preferred embodiment, determining whether there is a potential risk of being trapped due to power depletion based on the analysis results includes the following steps: Obtain historical health degradation trend data of the battery of the electric wheelchair; Based on the battery's historical health degradation trend data and current battery health status parameters, the probability of the battery experiencing sudden performance degradation or failure within a preset future period is predicted. The probability of sudden performance degradation or failure is correlated with the user's current charging behavior deviation and real-time battery status. If the analysis shows that, under conditions of deviated charging behavior and low to medium battery level, the probability of the battery malfunctioning within a preset time period exceeds a preset safety threshold, then it is determined that there is a potential risk of the user being trapped due to a combination of sudden battery malfunction and insufficient battery power.

[0037] Specifically, the system acquires historical battery health degradation trend data: It not only records the battery's current state but also records the long-term changes in its health parameters (such as capacity and internal resistance) over time. For example, it records that over the past six months, the battery's actual usable capacity has decreased by an average of 0.8% per month. This curve represents the historical health degradation trend data. Combining the current battery health parameters with its degradation trend, the system uses predictive algorithms (such as time-series analysis or machine learning models) to estimate the probability of a sudden battery problem in the short term (e.g., the next 24 hours or the next full trip). This sudden problem does not refer to a slow capacity decline but rather to risks such as a sudden drop in individual cell voltage, a sharp increase in internal resistance, or BMS errors that could lead to a sudden and significant reduction in driving range or driving interruption. The prediction result is a probability value (e.g., a 2% probability of a sudden performance drop in the next 24 hours). This probability is extremely low for batteries with good health and stable trends; it increases for severely aged batteries with large parameter fluctuations. Multi-factor correlation analysis: The system no longer views battery risk or user behavior risk in isolation but performs correlation analysis. It assesses three risk factors together: Factor A (Battery Hardware Risk): The probability of sudden battery failure predicted in the previous step. Factor B (User Behavior Risk): Whether the current charging behavior deviates from the expected path (yes / no). Factor C (Real-Time Status Risk): The user's real-time battery status (e.g., the battery level is at a low to medium level, such as below 30%). The system has a built-in risk assessment matrix or formula. For example, the rule might be: a high risk is determined only if (Factor B is yes, Factor C is yes, and the probability of Factor A > a preset safety threshold (e.g., 1%)).

[0038] Assessing Potential Risks: Scenario: The system predicts a 2.5% probability (>1% threshold) that an aging battery will malfunction within the next 24 hours; simultaneously, it detects that the user is not charging as usual (behavioral deviation); and the current battery level is only 25% (low to medium level). All three conditions are met. System analysis indicates this is an extreme and dangerous situation combining the possibility of the battery itself malfunctioning at any time and the user's inability to charge in time for any reason. The risk of the user being trapped comes not only from the battery running out of power but also from the possibility of sudden battery failure. Therefore, the system determines there is a potential risk of the user being trapped due to a combination of sudden battery problems and insufficient power. This assessment is a higher level than a simple warning of insufficient power or behavioral deviation because it points to a more complex and sudden danger.

[0039] In a preferred embodiment, acquiring and learning the user's habitual charging behavior data includes the following steps: Obtain the typical remaining battery level range when a user starts charging; The determination of whether there is a potential risk of being trapped due to power depletion, based on the analysis results, also includes: When it is detected that the user's recent charging starting power is consistently lower than the typical remaining power range, and the recent travel data shows that the user is going to non-habitual areas or routes more frequently, it is determined that there is a progressive high risk due to changes in the user's cognition or behavior patterns. When the progressive high risk is determined to exist, a progressive risk warning notification is generated and sent to the preset emergency contacts. The notification includes at least a brief description of the user's current behavior pattern changes and the current battery status information.

[0040] Specifically, a charging threshold habit model is established: Building upon the general charging model, this step focuses more on the long-term pattern of the single dimension of initial charging capacity (S). The system analyzes the initial charging capacity of all historical charging events and statistically calculates the user's typical remaining capacity range. For example, by calculating the average and standard deviation, it is determined that the user typically starts charging when the remaining capacity is between 30% and 40%. This range is their comfort zone or safe charging threshold.

[0041] Monitoring Recent Charging Start-up Level Trends: Instead of looking at single instances, the system analyzes recent (e.g., the past two weeks) charging start-up level data. It calculates the average start-up level during this period and observes whether it consistently falls below the lower limit of the typical remaining battery level range learned historically (e.g., 30% in the example above). For instance, the system found that in the past two weeks, the user consistently waited until the battery level dropped below 20%, or even 10%, before charging, showing a trend of continuously exceeding the safety threshold. Analyzing Recent Travel Range Changes: Simultaneously, the system analyzes travel GPS data from the same period. It defines the user's frequented areas or familiar routes based on historical data (e.g., communities within 1-2 kilometers of home, frequently visited markets, hospital routes). The system checks whether the frequency of visits to these uncommon areas or routes has significantly increased in recent travel records. For example, the user rarely crossed a river before, but has visited unfamiliar areas on the other side three times in the past week. Determining Gradual High Risk: The system correlates the above two trends. The system's logic is as follows: If a user becomes less sensitive to or forgetful of the dangers of low battery (charging later and later), while simultaneously expanding their activity range unpredictably (going to more unfamiliar and distant places), the combination of these two trends indicates a possible change in the user's cognitive or behavioral patterns (such as early-stage dementia, anxiety, depression, or other symptoms affecting judgment and habits). This significantly increases the long-term risk of completely running out of power and becoming trapped when out and about due to misjudging battery levels or getting lost. When both trends are detected simultaneously, the system determines that there is a progressive high risk. This risk differs from a single instance of forgetting to charge; it is a slowly worsening risk situation that requires long-term monitoring by guardians. A progressive risk warning notification is sent: Once the determination is confirmed, the system generates a dedicated progressive risk warning notification and sends it to the emergency contact. The notification is more descriptive, for example: "Long-term care reminder: We have recently observed a significant change in [User Name]'s charging habits (often charging only when the battery level is below 20%), and their activity range has expanded compared to the past. This change in behavior may require your attention; we recommend strengthening communication and care. Current battery level: [X%]." This kind of warning does not require immediate action from the contact person, but it provides crucial early behavioral change information, helping caregivers to intervene in a timely manner and reflecting a deeper level of humanistic care.

[0042] In a preferred embodiment, the method further includes the following steps: Based on the current health status parameters of the electric wheelchair's battery, a safe power threshold for managing the external power supply port is dynamically determined; When the real-time battery level of the electric wheelchair is lower than the safe power threshold, a power supply restriction prompt is sent to the user; the user decides whether to restrict or cut off the external power supply port based on the nature of the external power supply device. The safe power threshold is negatively correlated with the current health status parameter of the battery, so that the lower the battery health status, the higher the safe power threshold is set.

[0043] Specifically, the system dynamically determines the safe charge threshold: It reads the battery's current health status parameters from the Battery Management System (BMS) in real-time or periodically. These parameters include, but are not limited to: the battery's actual usable capacity (as a percentage of nominal capacity), internal resistance, and a comprehensive State of Health (SOH) score (e.g., a value from 0-100%, where 100% represents brand new). The system internally uses an algorithm or lookup table to calculate or look up the corresponding safe charge threshold based on these health parameters. The core principle of this algorithm is a negative correlation: when the battery health is good (e.g., SOH > 80%), the safe charge threshold can be set relatively low (e.g., 15%). This means that when the charge is above 15%, external power is allowed freely; below 15%, it is restricted. When the battery health deteriorates (e.g., SOH drops to 60%), the system calculates a higher safe charge threshold (e.g., 30%). This is because aging batteries have unstable voltage and inaccurately advertised usable capacity in the low charge range, requiring a larger safety buffer to ensure core mobility functions. A simple implementation example: Safe battery power threshold (%) = Base threshold (e.g., 10%) + (100% - Battery SOH) × Adjustment coefficient. Thus, the lower the SOH, the higher the threshold. Real-time monitoring and automatic limiting: The system continuously monitors the real-time battery power of the electric wheelchair. When the real-time battery power is detected to be lower than the dynamically calculated safe battery power threshold, the system immediately executes protective actions. Automatic power limiting or disconnection: The main controller sends instructions to the power management chip responsible for the external power supply port. Instructions can be: Limit output: Limit the output current of the USB port from the standard 2A fast charging mode to a 0.5A slow charging or trickle charging mode. Complete disconnection: Directly shut off the output voltage of the external power supply port, stopping the external device from charging. Sending power limit prompts: Simultaneously, the system notifies the user via voice announcement or screen pop-up, for example: To protect your travel safety, external charging has been suspended. The current battery health is average; it is recommended to prioritize power supply to the wheelchair. Relationship maintenance and continuous adjustment: The above negative correlation is continuously maintained. As batteries continue to be used and age, the system periodically (e.g., monthly) reassesses parameters such as State of Health (SOH) and updates the safe power threshold accordingly. This means that for the same battery, the limit for external power supply is dynamically changing, becoming increasingly conservative, and always matching the battery's actual capabilities.

[0044] This solution enables personalized and adaptive external power management. It addresses the hidden risks faced by users of older batteries when using convenient functions (such as charging mobile phones). By linking safety thresholds to battery health, the system can more intelligently determine when convenience should be sacrificed for core safety, preventing the embarrassing situation of sudden battery drain due to performance degradation. This extends battery life within safe limits (avoiding over-discharge) and provides users with automatically enhanced safety protection as devices age.

[0045] In a preferred embodiment, the method further includes the following steps: When it is determined that the battery needs maintenance based on the current health status parameters of the battery, the historical health degradation trend data of the battery, or the probability of the battery experiencing sudden performance degradation or failure, the proactive maintenance service docking process is triggered. The proactive maintenance service integration process includes: Generate service request data that includes a battery health diagnostic report and maintenance level recommendations; Based on the real-time location information of the electric wheelchair or the location of the planned charging point, match and recommend at least one available preset service provider; In the user terminal's interactive interface, at least one operable service entry point associated with the service request data is generated and displayed. The service entry point is used to provide users or the preset emergency contacts with interactive functions such as initiating service appointments with one click, obtaining service quotes, or directly contacting service providers.

[0046] Specifically, the trigger determination can originate from multiple warning modules: The system determines that the discharge depth exceeds the health threshold and the battery's state of harm (SOH) is significantly low, recommending maintenance. The system predicts a high probability of sudden battery failure and poor overall condition, requiring repair. The system autonomously detects that the battery's SOH remains below a preset maintenance threshold (e.g., capacity < 80% of nominal capacity) or that internal resistance is abnormally high. When any of these conditions are met, the system determines that the battery requires maintenance and triggers subsequent procedures.

[0047] Generate Service Request Data: The system automatically generates a structured battery health diagnostic report. The report content is not raw data, but processed, easily understandable information, such as: Diagnostic Conclusion: Battery capacity has significantly decreased to 72% of nominal capacity, internal resistance is high, maintenance or replacement is recommended. Maintenance Level Recommendation: Intermediate maintenance (professional testing and balancing) / Replacement Recommendation (range has been significantly affected). Includes snapshots of key parameters: current SOH, cycle count, recent maximum differential voltage, etc. This information is packaged into a standardized service request data packet, which can be transmitted over the network.

[0048] Matching and recommending service providers: The system obtains the real-time location of the electric wheelchair (via GPS) or planned charging points (home address) from the user's profile. The system backend connects to a service provider database containing information on contracted or certified repair service outlets (name, address, service area, contact information, user ratings). Based on location information, the system performs proximity matching or regional recommendations, filtering for at least one available preset service provider. For example, within a 5-kilometer radius of the user's home address, it recommends an authorized service center of brand A (XX Road store) and a chain repair station of brand B (YY Plaza store).

[0049] Generate actionable service entry points: On the user's mobile app or wheelchair controller screen, the system generates a new interface or pop-up window. The top of the interface displays a concise diagnostic conclusion and recommendations. The bottom of the interface generates an actionable service entry point for each recommended service provider. Each entry point is a clear button or card, such as: "One-click appointment at Service Center A" button: Clicking this redirects to the service provider's online appointment page, and the previously generated service request data (diagnostic report) is automatically filled into the appointment's remarks section; the user only needs to select a time. "Get a quote from Service Station B online" button: Clicking this sends the service request data to the service station's customer service via in-app message or SMS, requesting a preliminary quote. "Contact customer service directly" button: Clicking this dials the preset service provider's phone number. These entry points are linked to the service request data, ensuring that service providers understand the core issue before contacting the user.

[0050] This solution significantly reduces the technical barriers and operational complexity for users seeking professional assistance. It bridges the last mile from problem discovery to resolution, transforming the early warning capabilities of smart hardware into tangible service accessibility. For elderly users, there's no need to search or describe complex problems themselves; a single click initiates a standardized service process, significantly improving user experience, sense of security, and problem-solving efficiency. Simultaneously, it provides service providers with accurate pre-diagnostic information, enhancing service readiness and professionalism.

[0051] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. The above descriptions are only preferred embodiments of this application. It should be noted that due to the limitations of written expression, while there are objectively infinite specific structures, those skilled in the art can make several improvements, modifications, or changes without departing from the principles of this invention, and can also combine the above technical features in an appropriate manner. These improvements, modifications, changes, or combinations, or the direct application of the inventive concept and technical solution to other situations without modification, should all be considered within the scope of protection of this application.

Claims

1. A method for ensuring battery power during the trip of an electric wheelchair, characterized in that, Includes the following steps: Obtain the user's planned itinerary for the next day, which includes the destination, planned charging points, and planned departure time; Using the planned charging point as the starting point and the end point, and combining the preset activity duration at the destination, calculate the total electricity demand required to complete the trip plan, wherein the total electricity demand includes the round trip electricity from the planned charging point to the destination, and a preset redundant electricity portion corresponding to the preset activity duration; Obtain the current battery level of the electric wheelchair, and based on the current battery level and the estimated standby power consumption from the current time to the planned departure time, predict the predicted remaining battery level of the electric wheelchair at the planned departure time; Based on the predicted remaining power and the total power demand, determine whether the power is sufficient to complete the trip plan at the planned departure time. If not, a charging reminder will be sent to the user before the scheduled departure time.

2. The method for ensuring the travel power supply for an electric wheelchair according to claim 1, characterized in that, The method also includes assessing the battery availability of temporarily added destinations during the trip, including the following steps: When it is detected that the user has initiated a new temporary destination during the trip, the real-time location, real-time battery level and temporary destination information of the electric wheelchair are obtained; Starting from the real-time location, ending at the planned charging point, and passing through the temporary destination, a new temporary route is planned. Based on the temporary full route and the real-time battery level, calculate the total temporary power requirement required to complete the temporary full route; Based on the real-time battery level and the temporary total power demand, determine whether the battery currently has the power to travel to the temporary destination and safely return to the planned charging point; If not, generate and output a battery infeasibility alert for the temporary trip.

3. The method for ensuring the travel power of an electric wheelchair according to claim 1, characterized in that: The electric wheelchair's battery is equipped with an external power supply port, and the method further includes the following steps: When it is detected that power is being supplied to an external device through the external power supply port, the current power consumption or cumulative power consumption of the external device is obtained in real time. Based on the current power consumption or cumulative power consumption, dynamically adjust the real-time available power or the predicted remaining power of the electric wheelchair; Based on the corrected real-time available power or the predicted remaining power, reassess whether it is sufficient to complete the trip plan or the temporary full route. If the assessment is reassessed as insufficient to complete the task, a power-limiting warning or interruption suggestion is generated and output for the power supply behavior of the external device.

4. The method for ensuring the travel power of an electric wheelchair according to claim 1, characterized in that: The determination of whether the battery power is sufficient to complete the planned trip at the scheduled departure time includes the following steps: Obtain the current health status parameters of the battery of the electric wheelchair; Based on the current health status parameters of the battery, determine the healthy discharge depth threshold; Determine whether the total power required to complete the trip plan will cause the battery discharge depth of the electric wheelchair to exceed the healthy discharge depth threshold; If so, it is determined that the battery power is insufficient to complete the trip plan.

5. The method for ensuring power supply for electric wheelchairs according to claim 1, characterized in that: The method further includes the following steps: Acquire and learn users' habitual charging behavior data; When a user’s current charging behavior deviates from the usual charging behavior data, the user’s recent travel data and real-time battery status are analyzed. Based on the analysis results, determine whether there is a potential risk of being trapped due to running out of power; If so, a risk warning message will be generated and sent to the preset emergency contact.

6. The method for ensuring the travel power of an electric wheelchair according to claim 5, characterized in that: Acquiring and learning a user's habitual charging behavior data, and detecting whether the current charging behavior deviates from the habitual charging behavior data, includes the following steps: Establish a dynamic habitual charging model for users. The dynamic habitual charging model is based on historical charging data to learn and characterize the joint probability distribution of the following parameters: charging start time interval, charging interval duration, and initial charging amount. When a new charging event occurs or a preset learning cycle is reached, the corresponding current charging parameters are obtained; The current charging parameters are input into the dynamic inertial charging model to calculate the abnormal probability value of its deviation from the joint probability distribution; If the abnormal probability value exceeds the preset deviation threshold, it is determined that the current charging behavior deviates from the usual charging behavior data.

7. The method for ensuring the travel power of an electric wheelchair according to claim 5, characterized in that: Based on the analysis results, determining whether there is a potential risk of being trapped due to depleted power includes the following steps: Obtain historical health degradation trend data of the battery of the electric wheelchair; Based on the battery's historical health degradation trend data and current battery health status parameters, the probability of the battery experiencing sudden performance degradation or failure within a preset future period is predicted. The probability of sudden performance degradation or failure is correlated with the user's current charging behavior deviation and real-time battery status. If the analysis shows that, under conditions of deviated charging behavior and low to medium battery level, the probability of the battery malfunctioning within a preset time period exceeds a preset safety threshold, then it is determined that there is a potential risk of the user being trapped due to a combination of sudden battery malfunction and insufficient battery power.

8. The method for ensuring the travel power of an electric wheelchair according to claim 5, characterized in that: The process of acquiring and learning users' habitual charging behavior data includes the following steps: Obtain the typical remaining battery level range when a user starts charging; The determination of whether there is a potential risk of being trapped due to power depletion, based on the analysis results, also includes: When it is detected that the user's recent charging starting power is consistently lower than the typical remaining power range, and the recent travel data shows that the user is going to non-habitual areas or routes more frequently, it is determined that there is a progressive high risk due to changes in the user's cognition or behavior patterns. When the progressive high risk is determined to exist, a progressive risk warning notification is generated and sent to the preset emergency contacts. The notification includes at least a brief description of the user's current behavior pattern changes and the current battery status information.

9. The method for ensuring the travel power of an electric wheelchair according to claim 3, characterized in that: The method further includes the following steps: Based on the current health status parameters of the electric wheelchair's battery, a safe power threshold for managing the external power supply port is dynamically determined; When the real-time battery level of the electric wheelchair is lower than the safe power threshold, a power supply restriction prompt is sent to the user; the user decides whether to restrict or cut off the external power supply port based on the nature of the external power supply device. The safe power threshold is negatively correlated with the current health status parameter of the battery, so that the lower the battery health status, the higher the safe power threshold is set.

10. The method for ensuring the travel power of an electric wheelchair according to claim 4, characterized in that: The method also includes the following steps: When it is determined that the battery needs maintenance based on the current health status parameters of the battery, the historical health degradation trend data of the battery, or the probability of the battery experiencing sudden performance degradation or failure, the proactive maintenance service docking process is triggered. The proactive maintenance service integration process includes: Generate service request data that includes a battery health diagnostic report and maintenance level recommendations; Based on the real-time location information of the electric wheelchair or the location of the planned charging point, match and recommend at least one available preset service provider; In the user terminal's interactive interface, at least one operable service entry point associated with the service request data is generated and displayed. The service entry point is used to provide users or the preset emergency contacts with interactive functions such as initiating service appointments with one click, obtaining service quotes, or directly contacting service providers.

Images