Low-power-consumption long-standby method and system

Abstract

The embodiment of the invention provides a low-power-consumption and long-standby method and system. When the equipment enters a standby mode, a multi-sensor fusion algorithm is started, data of the light sensor, the motion sensor and the heat sensor are integrated, and ambient light intensity and human body activity signals are obtained through Bayesian network analysis. And dynamically adjusting screen settings by applying an adaptive brightness and refresh rate adjustment algorithm in combination with a visual comfort model, reducing the brightness to the lowest visibility and switching to a low refresh rate mode. Meanwhile, a wake-up mechanism triggered by an event is set, a wake-up process is started when a specific external input event is received, and standby is kept if an unspecific event is received. And optimizing the activation time interval of the wireless module by using a time sequence prediction algorithm, and formulating an intermittent connection strategy. The battery capacity, the user behavior mode and the task priority are comprehensively considered, a power management scheme is generated, and the standby time is maximized. According to the technical scheme provided by the embodiment of the invention, the standby time and the energy utilization efficiency of the intelligent medical kit are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent medical equipment, and more particularly to a low-power consumption and long-standby method and system. Background Art

[0002] Smart medical boxes are widely used in hospitals, clinics, home care and other places to store and manage medicines, medical devices and patient data. These devices usually need to remain in standby mode for a long time to ensure that they can respond quickly and provide necessary medical services when needed. Therefore, low power consumption and long standby capability have become one of the key requirements of smart medical boxes. In addition, the equipment must also have efficient energy management and rapid response capabilities to ensure that it can start up and perform critical tasks in a timely manner in an emergency.

[0003] Currently, most smart medical boxes use simple energy-saving modes to extend standby time, such as reducing screen brightness or turning off the screen at fixed time intervals. Some devices are also equipped with basic wake-up mechanisms that can reactivate the system when receiving external input signals. However, these methods are usually static and lack dynamic adaptability to environmental changes and user behavior, and cannot fully utilize multi-sensor data for intelligent management.

[0004] However, existing solutions have the following major flaws: Most existing energy-saving modes are based on fixed time intervals or preset conditions, and cannot dynamically adjust screen setting parameters according to actual ambient light intensity and human activity signals, resulting in limited energy consumption optimization effects. Traditional wake-up mechanisms cannot distinguish between specific and non-specific types of external input events, which can easily cause unnecessary system wake-ups, increase energy consumption, and may affect user experience. Existing solutions fail to fully consider factors such as battery power, user behavior patterns, and task priorities to generate personalized power management solutions, making it difficult to maximize standby time and ensure efficient data synchronization and status updates.

[0005] In order to solve the above problems, the present invention proposes a low-power and long standby method, which realizes efficient energy saving and rapid response of the smart medical box through a multi-sensor fusion algorithm, adaptive brightness and refresh rate adjustment, an event-triggered wake-up mechanism, a time series prediction algorithm and a power management solution combining multi-dimensional factors, and significantly improves the standby time and energy utilization efficiency. Summary of the invention

[0006] The embodiments of the present application provide a low-power consumption and long-standby method and system to solve the problems of short standby time and low energy utilization efficiency of smart medical boxes in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a low power consumption and long standby method, comprising:

[0008] When the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate sensing data from the light sensor, the motion sensor, and the thermal sensor through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box;

[0009] According to the fusion data of the combination of the ambient light intensity and the human activity signal, an adaptive brightness and refresh rate adjustment algorithm is applied, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box;

[0010] According to the fusion data of the ambient light intensity and the human activity signal, setting a wake-up mechanism based on event triggering, wherein the wake-up mechanism is used to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received;

[0011] Using a time series prediction algorithm, according to the timing of the wake-up event determined by the wake-up mechanism, the optimal data synchronization timing or status update timing of the smart medical box is predicted, and according to the current network load and expected transmission delay obtained, the time interval for activating the wireless module in the smart medical box is optimized, and an intermittent connection strategy is formulated;

[0012] Based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy, a power management solution is generated to maximize the standby time.

[0013] Optionally, the screen setting parameters of the smart medical box are dynamically adjusted by applying an adaptive brightness and refresh rate adjustment algorithm based on the fusion data of the ambient light intensity and the human activity signal in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes setting the display screen brightness of the smart medical box to a minimum visibility level and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode to reduce the energy consumption of the display component of the smart medical box, including:

[0014] Using the fused data of the ambient light intensity and the human activity signal as input to an adaptive brightness and refresh rate adjustment algorithm and a visual comfort model, and generating an evaluation result of the degree of interaction between the user and the smart medical box;

[0015] When the evaluation result indicates that the user has not interacted with the smart medical box, the brightness of the display screen of the smart medical box is gradually reduced until the minimum visibility level is reached, and at the same time, the refresh mode of the display screen is switched to a preset low refresh rate mode to reduce the energy consumption of the display component, thereby obtaining the screen setting parameters.

[0016] Optionally, when the evaluation result indicates that the user has not interacted with the smart medical box, the brightness of the display screen of the smart medical box is gradually reduced until the minimum visibility level is reached, and the refresh mode of the display screen is switched to a preset low refresh rate mode to reduce the energy consumption of the display component, and the screen setting parameters are obtained, including:

[0017] When the evaluation result indicates that the user has not interacted with the smart medical box, a screen energy saving program is started, wherein the screen energy saving program refers to a set of software logic or algorithm designed in the smart medical box to reduce the energy consumption of the display component;

[0018] Using the screen energy saving program, the display screen brightness of the smart medical box is gradually reduced from the current setting value with a preset step length until the minimum visibility level defined by the visual comfort model is reached, thereby obtaining the screen brightness setting;

[0019] According to the screen brightness setting, while adjusting the brightness of the smart medical box, based on the evaluation result, switching the refresh mode of the display screen of the smart medical box from the normal refresh rate mode to the preset low refresh rate mode, generating a refresh mode configuration, so as to reduce power consumption caused by screen updating;

[0020] By adjusting the brightness and switching the refresh mode, the screen brightness and refresh rate are comprehensively adjusted to obtain optimized screen setting parameters.

[0021] Optionally, the use of a time series prediction algorithm predicts the optimal data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and optimizes the time interval for activating the wireless module in the smart medical box according to the acquired current network load and expected transmission delay, and formulates an intermittent connection strategy, including:

[0022] Using the sensing data, and based on an event-triggered wake-up mechanism, record specific wake-up event history data to generate a data set;

[0023] Analyze and process the data set using a time series prediction algorithm, build a prediction model that can identify the occurrence rules of wake-up events and user behavior patterns, and predict the best data synchronization time or status update time through the prediction model to generate a prediction result;

[0024] Monitor and obtain current network load information in real time, evaluate expected transmission delay, and generate network status assessment results;

[0025] According to the prediction result and the network status evaluation result, the time interval for activating the wireless module is optimized to generate a time interval setting;

[0026] Based on the time interval setting, an intermittent connection strategy is formulated.

[0027] Optionally, the optimizing the time interval for activating the wireless module according to the prediction result and the network status evaluation result to generate the time interval setting includes:

[0028] Based on the historical data and default configuration of the smart medical box, an initial time interval for activating the wireless module is set to obtain an initial time interval setting;

[0029] Combining the prediction result with the network status assessment result, performing data fusion analysis on the two, identifying key factors affecting the activation frequency of the wireless module, and obtaining a list of key factors, wherein the key factors include user behavior patterns, network load conditions, and data synchronization requirements;

[0030] Using a preset optimization algorithm, based on the key factor list, the time interval for activating the wireless module is adjusted to generate a preliminary optimized time interval setting;

[0031] By simulating the wireless module activation behavior in different scenarios, evaluating whether the initially optimized time interval setting meets the expected performance indicators, the performance indicators include energy efficiency ratio, response time and data transmission success rate, and obtaining simulation verification results;

[0032] According to the simulation verification result, further fine-tune the time interval for activating the wireless module to ensure that the optimized activation time interval setting can achieve the best effect in the actual operating environment, and generate the optimized activation time interval value;

[0033] Based on the optimized activation time interval value, a wireless module activation time interval setting is generated and applied to the smart medical box.

[0034] Optionally, when the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate sensing data from light sensors, motion sensors, and thermal sensors through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box, including:

[0035] Using a preset condition, the state of the smart medical box is judged and processed to obtain a standby mode detection result, wherein the preset condition is that the time when the user does not interact with the device exceeds a set threshold;

[0036] Based on the standby mode detection result, a multi-sensor fusion algorithm is started to activate the light sensor, the motion sensor and the thermal sensor to prepare for collecting sensing data;

[0037] Use the activated sensors to monitor the light intensity, human movement and temperature changes in the environment in real time to obtain original sensing data;

[0038] Inputting the acquired raw sensing data into a multi-sensor fusion algorithm, integrating and processing the data from different sensors, and generating fused data;

[0039] Based on the fused data, a Bayesian network analysis method is applied to perform probabilistic reasoning processing on the fused data to evaluate and determine the existence and characteristics of ambient light intensity and human activity signals.

[0040] Optionally, setting a wake-up mechanism based on event triggering according to the fusion data of the combination of the ambient light intensity and the human activity signal, wherein the wake-up mechanism is used to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received, includes:

[0041] According to a preset rule, define an event type corresponding to an external input event, wherein the event type includes a specific type or a non-specific type;

[0042] Based on the fused data, a wake-up mechanism is configured and processed, a condition for starting a system wake-up process when a specific type of external input event is received is set, and a wake-up condition setting is generated;

[0043] For non-specific external input events, set filtering rules to ensure that these events do not mistakenly trigger the wake-up process and generate filtering rule settings;

[0044] By using the event type definition rules, wake-up condition settings and filtering rule settings, the occurrence of external input events is monitored in real time. When an external input event is detected, it is determined whether the external input event meets the preset specific type; if so, the system wake-up process is immediately started; if not, the filtering rules are applied to determine whether to ignore the event or continue to stay in standby mode, and an event response result is generated;

[0045] According to the event response results, feedback information from actual operation is collected to evaluate the performance of the wake-up mechanism;

[0046] Based on the result of the feedback information collection, the wake-up condition setting and the filtering rule setting are dynamically optimized and adjusted to improve the accuracy and efficiency of the wake-up mechanism and generate an optimized wake-up mechanism.

[0047] In a second aspect, an embodiment of the present application provides a low power consumption and long standby system, including:

[0048] an acquisition module, configured to start a multi-sensor fusion algorithm when the smart medical box enters a standby mode, so as to integrate sensing data from a light sensor, a motion sensor, and a thermal sensor through the multi-sensor fusion algorithm, and analyze the sensing data through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box;

[0049] an adjustment module, for dynamically adjusting the screen setting parameters of the smart medical box by applying an adaptive brightness and refresh rate adjustment algorithm according to the fusion data of the combination of the ambient light intensity and the human activity signal, in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box;

[0050] A setting module, configured to set a wake-up mechanism based on event triggering according to the fusion data of the ambient light intensity and the human activity signal, wherein the wake-up mechanism is configured to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received;

[0051] A prediction module, used to use a time series prediction algorithm to predict the optimal data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and to optimize the time interval for activating the wireless module in the smart medical box according to the current network load and expected transmission delay obtained, and to formulate an intermittent connection strategy;

[0052] A generation module is used to generate a power management solution to maximize standby time based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy.

[0053] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a low-power long standby method as described in the first aspect above.

[0054] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, wherein when the computer program is executed by a computer, a low-power consumption and long standby method as described in the first aspect is implemented.

[0055] In an embodiment of the present application, when the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate the sensing data from the light sensor, the motion sensor and the thermal sensor through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain the ambient light intensity and the human activity signal around the smart medical box; based on the fusion data composed of the ambient light intensity and the human activity signal, an adaptive brightness and refresh rate adjustment algorithm is applied, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box, wherein the process of adjusting the screen setting parameters of the smart medical box includes setting the display screen brightness of the smart medical box to the minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode to reduce the energy consumption of the display component of the smart medical box; based on the The fusion data of the combination of the ambient light intensity and the human activity signal is used to set an event-triggered wake-up mechanism, wherein the wake-up mechanism is used to start the system wake-up process when a specific type of external input event is received, and to perform filtering operations and maintain a standby state when a non-specific type of external input event is received; a time series prediction algorithm is used to predict the optimal data synchronization timing or status update timing of the smart medical box according to the timing of the wake-up event determined by the wake-up mechanism, and the time interval for activating the wireless module in the smart medical box is optimized according to the current network load and expected transmission delay obtained, and an intermittent connection strategy is formulated; based on the battery power of the smart medical box, the user behavior pattern obtained, and the multi-dimensional factors of the task priority, a power management solution is generated in combination with the screen setting parameters and the intermittent connection strategy to maximize the standby time.

[0056] This application effectively reduces unnecessary energy consumption by optimizing screen settings and wireless module activation time intervals, thereby significantly extending the standby time of the device. Dynamic adjustment of screen brightness and refresh rate not only saves power, but also ensures the user's visual comfort and improves the overall user experience. The event-triggered wake-up mechanism ensures that the device can respond quickly when needed, while avoiding overreaction to non-critical events, improving the response efficiency of the system. The time series prediction algorithm is used to accurately predict the optimal data synchronization time, ensuring the efficiency and reliability of data transmission. Taking into account battery power, user behavior patterns and task priorities, a personalized power management plan is generated, which further optimizes resource allocation and enhances the adaptability and flexibility of the device.

[0057] Furthermore, the embodiment of the present application also dynamically adjusts the screen setting parameters of the smart medical box based on the fusion data of ambient light intensity and human activity signals, and applies an adaptive brightness and refresh rate adjustment algorithm combined with a visual comfort model. When the evaluation results show that the user is not interacting with the device, the screen brightness is gradually reduced to the lowest visibility level and switched to a low refresh rate mode to reduce the energy consumption of the display component. Using a time series prediction algorithm, a data set is generated based on the historical data of wake-up events recorded by the wake-up mechanism. A prediction model is constructed through analysis and processing to predict the optimal data synchronization or status update timing, and the time interval for wireless module activation is optimized according to the current network load and expected transmission delay, and an intermittent connection strategy is formulated.

[0058] Through the above method, the energy utilization efficiency and standby time of the smart medical box are significantly improved. By dynamically adjusting the screen brightness and refresh rate, unnecessary energy consumption is reduced while ensuring the user's visual comfort. In addition, the activation time and data synchronization timing of the wireless module are optimized using a time series prediction algorithm, which reduces network transmission energy consumption and improves the accuracy and timeliness of data transmission. Overall, this method not only extends the working time of the device, but also enhances the system's response speed and user experience.

[0059] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 A flow chart of a low power consumption and long standby method provided by the present application is shown;

[0062] Figure 2 A schematic diagram of the structure of a low-power long standby system provided by the present application is shown;

[0063] Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0065] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0066] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0067] Figure 1 A flowchart of a low power consumption and long standby method is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0068] 101. When the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate sensing data from the light sensor, the motion sensor, and the thermal sensor through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box;

[0069] When the smart medical box enters standby mode, the multi-sensor fusion algorithm is activated. The algorithm integrates data from light sensors, motion sensors, and thermal sensors, and analyzes these sensing data through a Bayesian network to obtain accurate ambient light intensity and human activity signals. Light sensors are used to measure the light level of the surrounding environment; motion sensors detect movement near the device; thermal sensors sense human body heat, and together provide comprehensive environmental information. This data is used to evaluate the current usage scenario and user interaction level.

[0070] When the smart medical box enters standby mode, the system automatically activates the multi-sensor fusion algorithm. The algorithm first collects data from light sensors, motion sensors, and thermal sensors, and then analyzes the data through a Bayesian network to generate a comprehensive report on ambient light intensity and human activity signals. This information provides key input for subsequent steps, ensuring that all adjustments are based on the most accurate real-time data.

[0071] In a hospital environment, a smart medical box is installed in a ward to manage emergency medicines. When the device enters standby mode, the light sensor detects that the light in the room has dimmed, the motion sensor does not detect any movement, and the thermal sensor does not sense human heat. This data is processed by the multi-sensor fusion algorithm, which concludes that there is no user interaction at the moment, and then passes this information to the subsequent screen setting adjustment module to prepare for entering energy-saving mode.

[0072] 102. According to the fusion data of the combination of the ambient light intensity and the human activity signal, an adaptive brightness and refresh rate adjustment algorithm is applied, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box;

[0073] According to the fusion data of the ambient light intensity and human activity signal obtained in step 101, the screen setting parameters of the smart medical box are dynamically adjusted by applying the adaptive brightness and refresh rate adjustment algorithm combined with the visual comfort model. This step includes gradually reducing the screen brightness to the minimum visibility level and switching the refresh mode of the display screen to a preset low refresh rate mode to reduce the energy consumption of the display component. The visual comfort model ensures that the screen can maintain basic visibility even in a low power consumption state.

[0074] The fused data is fed into an adaptive brightness and refresh rate adjustment algorithm, which, combined with a visual comfort model, generates an assessment of the user's level of interaction. If the assessment shows that the user is not interacting with the device, the system gradually reduces the screen brightness and switches to a low refresh rate mode, significantly reducing the energy consumption of the display components. This process is gradual, ensuring that the user experience is not affected.

[0075] Continuing with the hospital ward example above, the smart medical box begins to gradually reduce the screen brightness until it reaches the minimum visibility level after confirming that there is no user interaction. At the same time, the screen refresh rate switches from the standard 60Hz to a more energy-efficient 30Hz. The nurse station monitoring system can still remotely view the device status, but the screen light is almost invisible on site, reducing unnecessary power waste.

[0076] 103. According to the fusion data of the ambient light intensity and the human activity signal, a wake-up mechanism based on event triggering is set, wherein the wake-up mechanism is used to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received;

[0077] Based on the fusion data of ambient light intensity and human activity signals, an event-triggered wake-up mechanism is set up. This mechanism can start the system wake-up process when receiving a specific type of external input event (such as an emergency button press or an RFID tag approaching), and perform filtering operations and remain in standby mode when receiving non-specific events (such as slight vibration or background noise). This can avoid unnecessary system wake-ups and further save energy.

[0078] The fused data is used to set the wake-up conditions, which trigger the system to wake up only when the specific conditions are met. For example, when the emergency button is pressed or a specific RFID tag is approaching, the system wakes up immediately and is ready to respond. For non-specific events, they are ignored through the filtering mechanism to maintain a low power consumption state. This ensures the system's fast responsiveness and high energy efficiency.

[0079] Continuing with the example of a hospital ward, when a nurse approaches the smart medical box with a key card with an RFID tag, the thermal sensor and motion sensor detect abnormal activity, and the RFID reader confirms the legitimate access request. At this point, the event-triggered wake-up mechanism is quickly activated, and the smart medical box immediately resumes from standby to working state, allowing the nurse to quickly take out the required medicine. If an unrelated person passes by, the device remains in standby mode and does not respond.

[0080] 104. Using a time series prediction algorithm, according to the timing of the wake-up event determined by the wake-up mechanism, predict the best data synchronization timing or status update timing of the smart medical box, and according to the current network load and expected transmission delay obtained, optimize the time interval for activating the wireless module in the smart medical box, and formulate an intermittent connection strategy;

[0081] Using the time series prediction algorithm, the optimal data synchronization time or status update time of the smart medical box is predicted according to the wake-up event timing determined by the wake-up mechanism, and the time interval for wireless module activation is optimized and an intermittent connection strategy is formulated based on the current network load and expected transmission delay. This helps to ensure the efficiency and timeliness of data synchronization when network resources are limited.

[0082] First, a data set is generated using sensing data and historical wake-up event data. Then, the data is analyzed using a time series prediction algorithm to build a prediction model that can identify the regularity of wake-up events and user behavior patterns. Next, the network load is monitored in real time and the expected transmission delay is evaluated to generate a network status evaluation result. Finally, based on the prediction results and network status evaluation results, the time interval for wireless module activation is optimized, the time interval setting is generated, and an intermittent connection strategy is formulated accordingly.

[0083] In a hospital environment, smart medical boxes experience multiple data synchronization needs every day, such as drug inventory updates or patient information uploads. Through the time series prediction algorithm, the system predicts that 8 am and 5 pm are the best times for data synchronization because the network load is low and the transmission delay is minimal during these two time periods. Therefore, the wireless module is only activated during these two time periods and remains disconnected at other times, which not only ensures the timeliness of data synchronization but also minimizes energy consumption.

[0084] 105. Generate a power management plan based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy, to maximize the standby time.

[0085] Based on the battery level of the smart medical box, user behavior patterns, task priorities and other multi-dimensional factors, combined with the previously adjusted screen setting parameters and the formulated intermittent connection strategy, a personalized power management plan is generated to maximize standby time. This plan takes into account all factors that may affect energy consumption and ensures that the device can operate efficiently under various conditions.

[0086] A power management plan is generated by comprehensively considering factors such as battery power, user behavior patterns, and task priorities. The plan not only includes screen settings and wireless module activation strategies, but also involves other potential energy-saving measures, such as shutting down unnecessary background processes or reducing CPU frequency. The ultimate goal is to extend the standby time of the device as much as possible without affecting functionality.

[0087] In a hospital environment, the power management solution of the smart medical box takes into account the frequent use of medical staff during the day and the actual situation of less use at night. During the day, the device maintains a high response speed and data synchronization frequency to support daily operations; at night, the screen brightness is reduced to the minimum, the wireless module is only activated at the best predicted time, and the background processes are reduced accordingly, ensuring that the device can be in standby for a long time at night without affecting normal use the next day.

[0088] Through the implementation of steps 101 to 105, the present invention realizes efficient and energy-saving management of the smart medical box in standby mode. The multi-sensor fusion algorithm ensures the accuracy of environmental data, the adaptive brightness and refresh rate adjustment algorithm reduces the screen energy consumption, the event-triggered wake-up mechanism avoids unnecessary system wake-ups, the time series prediction algorithm optimizes the timing of data synchronization, and the personalized power management solution maximizes the standby time. The overall method not only significantly extends the working time of the device, but also improves the user experience and response efficiency. It is particularly suitable for the field of smart medical equipment that requires long standby time and response at any time.

[0089] In order to solve the problem that the judgment of the smart medical box when entering the standby mode is not accurate enough, in some embodiments, when the smart medical box enters the standby mode in step 101, a multi-sensor fusion algorithm is started to integrate the sensing data from the light sensor, the motion sensor and the thermal sensor through the multi-sensor fusion algorithm, and the sensing data is analyzed through the Bayesian network to obtain the ambient light intensity and the human activity signal around the smart medical box, including:

[0090] Using preset conditions, the state of the smart medical box is judged and processed to obtain a standby mode detection result, wherein the preset condition is that the time when the user has not interacted with the device exceeds a set threshold; based on the standby mode detection result, a multi-sensor fusion algorithm is started to activate the light sensor, the motion sensor and the heat sensor to prepare for collecting sensing data; using the activated sensors, the light intensity, human movement and temperature changes in the environment are monitored in real time to obtain raw sensing data; the obtained raw sensing data is input into the multi-sensor fusion algorithm, the data from different sensors are integrated and processed to generate fused data; based on the fused data, a Bayesian network analysis method is applied to perform probabilistic reasoning on the fused data to evaluate and determine the existence and characteristics of ambient light intensity and human activity signals.

[0091] In this embodiment, in order to more accurately determine whether the smart medical box should enter the standby mode, preset conditions are introduced to determine the device status. These preset conditions are based on the time when the user does not interact with the device for more than a set threshold, such as 3 minutes or 5 minutes. This preset condition ensures that the device will not mistakenly enter the standby mode due to a short period of no interaction, thereby improving the accuracy of the judgment.

[0092] In the embodiment of the present application, first, the system uses preset conditions to judge the state of the smart medical box and obtain the standby mode detection result. If it is confirmed that the time for which the user has not interacted with the device exceeds the set threshold, the multi-sensor fusion algorithm is started, and the light sensor, motion sensor, and heat sensor are activated to prepare to collect sensing data. Next, the activated sensor monitors the light intensity, human movement, and temperature changes in the environment in real time to obtain raw sensing data. Subsequently, these raw sensing data are input into the multi-sensor fusion algorithm, and the data from different sensors are integrated and processed to generate fused data. Finally, based on the fused data, the Bayesian network analysis method is applied to perform probabilistic reasoning on the fused data to evaluate and determine the existence and characteristics of ambient light intensity and human activity signals.

[0093] Here is a specific example:

[0094] In a hospital ward environment, a smart medical box is installed near the nurse station to manage emergency medicines. When the nurse leaves for a period of time, the system starts timing to check if there is any user interaction. Assume that the preset condition is that the user has not interacted with the device for more than 5 minutes. Once this time threshold is reached, the system confirms that it has entered the standby mode detection phase.

[0095] At this point, the system starts the multi-sensor fusion algorithm and activates the light sensor, motion sensor, and heat sensor. The light sensor starts to monitor the surrounding light level and finds that the light is gradually getting darker; the motion sensor detects no obvious movement; and the heat sensor does not sense any human body heat. These raw sensing data are collected and input into the multi-sensor fusion algorithm for integration and processing to generate fused data.

[0096] Then, the Bayesian network analysis method performs probabilistic reasoning on the fused data and concludes that there is indeed no user interaction in the current environment, and the ambient light intensity is low, with no human activity signals. Based on this conclusion, the system officially enters standby mode and prepares to implement subsequent energy-saving measures, such as adjusting the screen brightness and refresh rate.

[0097] Through this method, the smart medical box can not only determine whether to enter standby mode more accurately, but also ensure efficient response when it is really needed, avoiding unnecessary energy consumption. It is particularly suitable for the field of smart medical equipment that requires long standby time and response at any time.

[0098] In order to solve the problem that the screen setting adjustment of the smart medical box in the low power consumption mode is not intelligent enough, in some embodiments, the fusion data combined by the ambient light intensity and the human activity signal in step 102 is applied to dynamically adjust the screen setting parameters of the smart medical box by applying an adaptive brightness and refresh rate adjustment algorithm in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes setting the display screen brightness of the smart medical box to the minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode to reduce the energy consumption of the display component of the smart medical box, including:

[0099] In this embodiment, the fusion data of the combination of the ambient light intensity and the human activity signal is used as the input of the adaptive brightness and refresh rate adjustment algorithm and the visual comfort model, and the evaluation result of the degree of interaction between the user and the smart medical box is generated; when the evaluation result shows that the user has not interacted with the smart medical box, the brightness of the display screen of the smart medical box is gradually reduced until the minimum visibility level is reached, and the refresh mode of the display screen is switched to the preset low refresh rate mode at the same time to reduce the energy consumption of the display component, and the screen setting parameters are obtained. In order to more accurately evaluate the degree of user interaction and optimize the screen setting accordingly, the system introduces an adaptive brightness and refresh rate adjustment algorithm and a visual comfort model. The fusion data (i.e., the ambient light intensity and the human activity signal) is used as input to generate the evaluation result of the degree of interaction between the user and the smart medical box. This evaluation not only takes into account the changes in ambient light, but also integrates the existence and intensity of human activity to ensure that the adjusted screen setting can save energy without affecting the user's visual experience.

[0100] In an embodiment of the present application, first, the fused data composed of the ambient light intensity and the human activity signal is used as input and passed to the adaptive brightness and refresh rate adjustment algorithm and the visual comfort model. Through these models, the system generates an evaluation result of the degree of interaction between the user and the smart medical box. If the evaluation result shows that the user has not interacted with the device, the system will gradually reduce the brightness of the display screen until the minimum visibility level is reached, and at the same time switch the refresh mode of the display screen to the preset low refresh rate mode. This process is gradual, ensuring that the user can quickly return to a normal visual state when returning in a short time, reducing unnecessary energy consumption, while also ensuring the user's visual comfort.

[0101] Here is a specific example:

[0102] In a hospital environment, a smart medical box is installed in a ward to manage emergency medicines. When the nurse leaves for a while, the multi-sensor fusion algorithm confirms that there is no user interaction. At this time, the system starts the adaptive brightness and refresh rate adjustment algorithm and the visual comfort model, and generates fusion data using the previously collected ambient light intensity and human activity signals. Based on this data, the system evaluates and concludes that there is no user interaction.

[0103] Based on this evaluation result, the system begins to gradually reduce the screen brightness of the smart medical box from the standard brightness to the minimum visibility level. At the same time, the screen refresh rate is also switched from the standard 60Hz to the more energy-efficient 30Hz. This process is not completed instantly, but is carried out in stages to ensure that even if the user suddenly returns, they can still see the remaining key information on the screen, such as the location of the emergency button or basic operation prompts. This not only achieves energy-saving effects, but also maintains the necessary visibility and improves the user experience.

[0104] In addition, when the nurse approaches the smart medical box again, the thermal sensor and motion sensor detect that someone is approaching, and the system responds immediately, quickly restoring the screen brightness and refresh rate to normal levels, ready to receive operation instructions. This intelligent adjustment of screen settings not only extends the standby time of the device, but also improves the response speed, which is particularly suitable for the field of smart medical equipment that requires long standby time and response at any time.

[0105] With this approach, the smart medical box can not only more accurately adjust screen settings based on user interaction, but also ensure the best visual experience and energy efficiency in all environments.

[0106] In order to solve the problem that the screen setting adjustment of the smart medical box is not fine enough when the user does not interact, in some embodiments, when the evaluation result in step 102 indicates that the user has not interacted with the smart medical box, the display screen brightness of the smart medical box is gradually reduced until the minimum visibility level is reached, and the refresh mode of the display screen is switched to a preset low refresh rate mode at the same time to reduce the energy consumption of the display component, and the screen setting parameters are obtained, including:

[0107] When the evaluation result indicates that the user has not interacted with the smart medical box, a screen energy saving program is started, and the screen energy saving program refers to a set of software logic or algorithms designed in the smart medical box to reduce the energy consumption of the display component; using the screen energy saving program, the display screen brightness of the smart medical box is gradually reduced from the current setting value in a preset step size until the minimum visibility level defined by the visual comfort model is reached, thereby obtaining the screen brightness setting; according to the screen brightness setting, while performing the brightness adjustment of the smart medical box, based on the evaluation result, the refresh mode of the display screen of the smart medical box is switched from the normal refresh rate mode to the preset low refresh rate mode, and a refresh mode configuration is generated to reduce the power consumption caused by screen updates; through the operations of brightness adjustment and refresh mode switching, the screen brightness and refresh rate are comprehensively adjusted to obtain optimized screen setting parameters.

[0108] In this embodiment, in order to control the screen energy consumption more meticulously, the system introduces a screen energy saving program. The screen energy saving program refers to a set of software logic or algorithms designed in the smart medical box, which is specifically used to reduce the energy consumption of the display component. This program is not only responsible for gradually reducing the screen brightness, but also for switching the refresh mode to ensure maximum power saving without affecting the user experience.

[0109] In the embodiment of the present application, first, when the evaluation result shows that the user has not interacted with the smart medical box, the system starts the screen energy saving program. The screen energy saving program starts with the current screen brightness setting value, and gradually decreases the brightness in preset steps (for example, reducing the brightness by 5% each time) until the minimum visibility level defined by the visual comfort model is reached. This process is gradual, ensuring that even if the user suddenly returns, the remaining key information on the screen can be seen, such as the location of the emergency button or basic operation prompts.

[0110] At the same time, while performing brightness adjustment, based on the evaluation results, the screen energy saving program switches the display screen refresh mode of the smart medical box from the normal refresh rate mode to the preset low refresh rate mode (for example, from 60Hz to 30Hz). This switch reduces the power consumption caused by screen updates and further optimizes energy use. Through the combined operation of brightness adjustment and refresh mode switching, the optimized screen setting parameters are finally generated to ensure that basic visibility and response speed can be maintained in a low power consumption state.

[0111] Here is a specific example:

[0112] In a hospital environment, a smart medical box is installed in a ward to manage emergency medicines. When the nurse leaves for a period of time, the multi-sensor fusion algorithm confirms that there is no user interaction. At this time, the system starts the screen energy saving program and determines that there is no user interaction based on the evaluation results generated by the previously collected ambient light intensity and human activity signals.

[0113] The screen energy saving procedure starts with the current screen brightness (assumed to be 100%) and gradually reduces the brightness in steps of 5%. Every few seconds, the brightness is reduced by 5% until the minimum visibility level defined by the visual comfort model is reached (for example, 10%). At the same time, the screen refresh rate is switched from the standard 60Hz to a more energy-saving 30Hz. This gradual brightness adjustment and refresh rate switching ensures that even if the nurse returns suddenly, it can quickly return to normal viewing without being unable to immediately obtain critical information because the screen is completely turned off.

[0114] In addition, when the nurse approaches the smart medical box again, the thermal sensor and motion sensor detect that someone is approaching, and the system responds immediately, quickly restoring the screen brightness and refresh rate to normal levels, ready to receive operation instructions. This intelligent adjustment of screen settings not only extends the standby time of the device, but also improves the response speed, which is particularly suitable for the field of smart medical equipment that requires long standby time and response at any time.

[0115] In this way, the smart medical box can not only adjust the screen settings more accurately according to user interaction, but also ensure the best visual experience and energy efficiency in various environments. The application of the screen energy saving program enables the device to significantly reduce unnecessary power consumption without affecting functionality, further improving the overall performance and user experience.

[0116] In order to solve the problem that the smart medical box does not respond accurately to external input events in standby mode, in some embodiments, the fusion data combined by the ambient light intensity and the human activity signal in step 103 is used to set an event-triggered wake-up mechanism, which is used to start the system wake-up process when a specific type of external input event is received, and perform filtering operations and maintain standby mode when a non-specific type of external input event is received, including:

[0117] According to the preset rules, the event type corresponding to the external input event is defined, and the event type includes a specific type or a non-specific type; based on the fusion data, the wake-up mechanism is configured and processed, and the conditions for starting the system wake-up process when a specific type of external input event is received are set, and the wake-up condition setting is generated; for non-specific types of external input events, filtering rules are set to ensure that these events do not mistakenly trigger the wake-up process, and the filtering rule setting is generated; using the event type definition rules, wake-up condition settings and filtering rule settings, the occurrence of external input events is monitored in real time, and when an external input event is detected, it is determined whether the external input event meets the preset specific type; if yes, the system wake-up process is started immediately; if not, the filtering rules are applied to decide whether to ignore the event or continue to maintain the standby state, and an event response result is generated; according to the event response result, feedback information in actual operation is collected to evaluate the performance of the wake-up mechanism; based on the results of the feedback information collection, the wake-up condition settings and filtering rule settings are dynamically optimized and adjusted to improve the accuracy and efficiency of the wake-up mechanism, and an optimized wake-up mechanism is generated.

[0118] In this embodiment, in order to improve the accuracy and efficiency of the wake-up mechanism, the system introduces pre-set rules to define the types of external input events and distinguish between specific and non-specific types of events. Specific types of events are those that clearly require an immediate response, such as an emergency button press or an RFID tag approaching; non-specific types of events are those that may mistakenly trigger the wake-up process, such as background noise or slight vibrations. Through these rules, the system can more accurately determine which events should trigger the wake-up process and which should be filtered out.

[0119] In the embodiment of the present application, first, according to the pre-set rules, the event type corresponding to the external input event is defined, which is divided into specific types (such as emergency button pressing, RFID tag approaching) and non-specific types (such as slight vibration, background noise). Based on the fusion data (ambient light intensity and human activity signals), the wake-up mechanism is configured and processed, and the conditions for starting the system wake-up process when a specific type of external input event is received are set, and the wake-up condition settings are generated. For non-specific types of external input events, filter rules are set to ensure that these events do not mistakenly trigger the wake-up process, and filter rule settings are generated.

[0120] Next, use the event type definition rules, wake-up condition settings, and filter rule settings to monitor the occurrence of external input events in real time. When an external input event is detected, the system will determine whether the event meets the preset specific type. If so, the system wake-up process is immediately started; if not, the filter rules are applied to decide whether to ignore the event or continue to stay in standby mode, and generate event response results.

[0121] Finally, based on the event response results, the system collects feedback information from actual operation and evaluates the performance of the wake-up mechanism. Based on this feedback information, the wake-up condition settings and filter rule settings are dynamically optimized to improve the accuracy and efficiency of the wake-up mechanism and generate an optimized wake-up mechanism. This dynamic optimization ensures that the system can continuously improve its responsiveness in a constantly changing environment.

[0122] Here is a specific example:

[0123] In a hospital ward environment, the smart medical box is installed near the nurse station to manage emergency medicines. The system pre-sets the types of external input events: specific types of events include pressing the emergency button and approaching RFID tags with legal authority; non-specific types of events include slight vibrations, background noise or other irrelevant sensing signals.

[0124] When the nurse leaves for a period of time, the smart medical box enters standby mode. At this point, the system begins to monitor external input events in real time. Suppose a nurse approaches the smart medical box with an RFID tag with legal permissions, the thermal sensor and motion sensor detect abnormal activity, and the RFID reader confirms the legal access request. The system determines that this is a specific type of event based on preset rules, and immediately starts the system wake-up process, allowing the nurse to quickly take out the required medicine.

[0125] On the other hand, if some unrelated people pass by, causing slight vibrations or background noise, the system will ignore these events based on non-specific type filtering rules, remain in standby mode, and not respond. This can avoid unnecessary wake-ups and save power.

[0126] In addition, the system also collects actual operational feedback information of each wake-up event, such as wake-up time, user interaction frequency, etc. By analyzing this feedback information, the system can dynamically adjust the wake-up condition settings and filter rule settings to further optimize the wake-up mechanism. For example, if false triggers are found to occur frequently within a certain period of time, the system may tighten the filter rules or adjust the recognition threshold of specific events to improve accuracy.

[0127] Through this method, the smart medical box can not only respond to the actual needs of users more accurately, but also effectively reduce false awakenings, thereby significantly extending the standby time of the device and improving energy efficiency. This intelligent wake-up mechanism is particularly suitable for the field of smart medical equipment that requires long standby time and response at any time, ensuring that the equipment can operate efficiently in various complex environments.

[0128] In order to solve the problem that the smart medical box is not intelligent enough in selecting the timing of data synchronization and status update, in some embodiments, the time series prediction algorithm in step 104 is used to predict the best data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and the time interval for activating the wireless module in the smart medical box is optimized according to the current network load and expected transmission delay obtained, and an intermittent connection strategy is formulated, including:

[0129] Utilize the sensing data and record specific historical data of wake-up events based on an event-triggered wake-up mechanism to generate a data set; use a time series prediction algorithm to analyze and process the data set, build a prediction model that can identify the occurrence rules of wake-up events and user behavior patterns, and predict the optimal data synchronization time or status update time through the prediction model to generate a prediction result; monitor and obtain current network load information in real time, evaluate the expected transmission delay, and generate a network status evaluation result; optimize the time interval for activating the wireless module based on the prediction result and the network status evaluation result, and generate a time interval setting; formulate an intermittent connection strategy based on the time interval setting.

[0130] In this embodiment, in order to more intelligently select the best time for data synchronization and status update, the system introduces a time series prediction algorithm. The algorithm analyzes and processes historical wake-up event data to build a prediction model that can identify the regularity of wake-up events and user behavior patterns. Through these models, the system can predict the best time for data synchronization or status update, thereby avoiding unnecessary data transmission when the network load is high or the transmission delay is large. In addition, the system also monitors the current network status in real time, evaluates the expected transmission delay, and ensures that the wireless module is activated under the optimal conditions, further saving power and improving data transmission efficiency.

[0131] In the embodiment of the present application, first, the system uses sensing data and records specific wake-up event history data based on the event-triggered wake-up mechanism to generate a data set. These data sets contain the specific time and type of each wake-up event, as well as relevant environmental information (such as light intensity, human activity signals, etc.). Next, these data sets are analyzed and processed using a time series prediction algorithm to build a prediction model for identifying the occurrence pattern of wake-up events and user behavior patterns. Through these models, the system can predict the best possible data synchronization time or status update time in the future and generate prediction results. At the same time, the system monitors and obtains the current network load information in real time, evaluates the expected transmission delay, and generates a network status evaluation result. These evaluation results are combined with the prediction results to jointly determine the time interval for the activation of the wireless module. Specifically, the system optimizes the time interval for the activation of the wireless module according to the predicted best time and the current network status, and generates a time interval setting. Finally, based on these time interval settings, the system formulates an intermittent connection strategy to ensure that the wireless module is activated when needed and remains disconnected at other times to maximize power saving and ensure the efficiency and timeliness of data transmission.

[0132] Here is a specific example:

[0133] In a hospital environment, a smart medical box is installed near the nurse station to manage emergency medicines and patient information. The system experiences multiple data synchronization needs every day, such as drug inventory updates or patient information uploads. To optimize this process, the system first records historical data for each wake-up event, including the event type (such as emergency button press, RFID tag proximity), event time, and environmental conditions at the time (such as light intensity, human activity signals).

[0134] Next, the system uses time series prediction algorithms to analyze these historical data and build prediction models. Through these models, the system predicts that 8 a.m. and 5 p.m. are the best times for data synchronization, because these two time periods are usually when medical staff take over shifts, the network load is low and the transmission delay is minimal. Therefore, the system decides to activate the wireless module for data synchronization during these two time periods.

[0135] At the same time, the system monitors the current network load in real time and evaluates the expected transmission delay. Suppose at 9 a.m. on a certain weekday, the network load suddenly increases, and the system finds that this is not the best time for transmission. Therefore, the system adjusts the time interval for wireless module activation and postpones it to the next predicted best time (i.e. 5 p.m.) to avoid unnecessary data transmission under high load conditions, thereby saving power and improving transmission efficiency.

[0136] In addition, the system also collects actual operational feedback information of each data synchronization, such as synchronization speed, transmission success rate, etc. By analyzing this feedback information, the system can dynamically adjust the prediction model and time interval settings to further optimize the timing of data synchronization and status updates. For example, if it is found that transmission failures frequently occur within a certain period of time, the system may re-evaluate the network load threshold or adjust the parameters of the prediction model to improve accuracy.

[0137] Through this method, the smart medical box can not only more intelligently select the best time for data synchronization and status update, but also effectively reduce unnecessary data transmission, significantly extend the standby time of the equipment and improve energy efficiency. This intelligent time series prediction algorithm is particularly suitable for the field of smart medical equipment that needs to be on standby for a long time and respond at any time, ensuring that the equipment can operate efficiently in various complex environments.

[0138] In order to solve the problem that the activation time interval setting of the wireless module of the smart medical box is not intelligent enough, in some embodiments, the step 104 optimizes the activation time interval of the wireless module according to the prediction result and the network status evaluation result to generate the time interval setting, including:

[0139] Based on the historical data and default configuration of the smart medical box, the initial time interval for activating the wireless module is set and processed to obtain the initial time interval setting; in combination with the prediction result and the network status assessment result, the two are subjected to data fusion analysis to identify the key factors affecting the activation frequency of the wireless module and obtain a list of key factors, wherein the key factors include user behavior patterns, network load conditions, and data synchronization requirements; using a preset optimization algorithm, based on the list of key factors, the time interval for activating the wireless module is adjusted and processed to generate a preliminary optimized time interval setting; by simulating the activation behavior of the wireless module in different scenarios, it is evaluated whether the preliminary optimized time interval setting meets the expected performance indicators, wherein the performance indicators include energy efficiency ratio, response time, and data transmission success rate, to obtain a simulation verification result; according to the simulation verification result, the time interval for activating the wireless module is further fine-tuned to ensure that the optimized activation time interval setting can achieve the best effect in the actual operating environment, and an optimized activation time interval value is generated; based on the optimized activation time interval value, a time interval setting for activating the wireless module is generated and applied to the smart medical box.

[0140] In this embodiment, in order to more accurately set the activation time interval of the wireless module, the system introduces the process of initial setting based on historical data and default configuration, key factor identification, optimization algorithm adjustment and simulation verification. First, the system sets the initial time interval for wireless module activation based on the historical data and default configuration of the smart medical box. Then, combining the prediction results with the network status assessment results, the key factors affecting the activation frequency of the wireless module, such as user behavior patterns, network load conditions and data synchronization requirements, are identified through data fusion analysis. Next, the preset optimization algorithm is used to adjust the time interval for wireless module activation according to these key factors to generate a preliminary optimized time interval setting. Subsequently, by simulating the activation behavior of the wireless module under different scenarios, it is evaluated whether the preliminary optimized time interval setting meets the expected performance indicators (such as energy efficiency ratio, response time and data transmission success rate). Finally, according to the simulation verification results, the time interval for wireless module activation is further fine-tuned to ensure that the optimized activation time interval setting can achieve the best effect in the actual operating environment.

[0141] In the embodiment of the present application, first, based on the historical data and default configuration of the smart medical box, the system sets the initial time interval for the activation of the wireless module to obtain the initial time interval setting. This step ensures that the system has a reasonable starting point and avoids the uncertainty caused by adjusting from scratch. Secondly, combining the prediction results with the network status assessment results, the system performs data fusion analysis on the two, identifies the key factors affecting the activation frequency of the wireless module, and obtains a list of key factors. These key factors include but are not limited to user behavior patterns, network load conditions, and data synchronization requirements. In this way, the system can more comprehensively understand which factors have an important impact on the activation frequency of the wireless module. Then, using a preset optimization algorithm, based on the above-mentioned list of key factors, the system adjusts the time interval for the activation of the wireless module and generates a preliminary optimized time interval setting. The optimization algorithm takes into account the interaction between multiple factors to ensure that the adjusted settings are both reasonable and efficient. Further, by simulating the activation behavior of the wireless module in different scenarios, the system evaluates whether the preliminary optimized time interval setting meets the expected performance indicators, such as energy efficiency ratio, response time, and data transmission success rate. This step ensures that the system has been fully tested before actual application, reducing the risk in actual operation. Finally, based on the simulation verification results, the system further fine-tunes the activation time interval of the wireless module to ensure that the optimized activation time interval setting can achieve the best effect in the actual operating environment. Finally, the optimized activation time interval value is generated and applied to the smart medical box.

[0142] Here is a specific example:

[0143] In a hospital environment, a smart medical box is installed near the nurse station to manage emergency medicines and patient information. The system experiences multiple data synchronization needs every day, such as drug inventory updates or patient information uploads. To optimize this process, the system first sets the initial time interval for wireless module activation to once an hour based on historical data and default configuration.

[0144] Next, the system combines the prediction model (predicting that 8 a.m. and 5 p.m. are the best times for data synchronization) with the real-time monitoring of network status assessment results (the current network load is low and the transmission delay is minimal) to perform data fusion analysis. Through analysis, the system identifies several key factors: user behavior patterns (such as the handover time of medical staff), network load conditions (such as peak hours on weekdays), and data synchronization requirements (such as data upload tasks at a fixed time every day).

[0145] Then, the system uses a preset optimization algorithm to adjust the time interval for activating the wireless module based on these key factors and generate a preliminary optimized time interval setting, such as changing it to activate once at 8 am and once at 5 pm every day.

[0146] To ensure that these settings are effective in actual operation, the system simulates the wireless module activation behavior in different scenarios to evaluate whether the initially optimized time interval settings meet the expected performance indicators, such as energy efficiency ratio, response time, and data transmission success rate. If the simulation finds that the data transmission success rate is slightly low in a certain period of time, the system will further fine-tune the wireless module activation time interval, such as advancing the afternoon activation time to 4:30 to avoid possible network congestion.

[0147] Finally, the system generates optimized activation time interval values ​​based on the simulation verification results and applies them to the smart medical box. This not only improves the efficiency of data synchronization and status update, but also significantly extends the standby time of the device and reduces unnecessary power consumption. This intelligent time interval optimization is particularly suitable for the field of smart medical equipment that requires long standby time and is responsive at any time, ensuring that the equipment can operate efficiently in various complex environments.

[0148] Through this method, the smart medical box can not only more intelligently choose the best time for data synchronization and status update, but also effectively reduce unnecessary data transmission, significantly extend the standby time of the device and improve energy efficiency. This multi-step optimization process ensures that the system can achieve the best results in actual operation, improving overall performance and user experience.

[0149] This application considers that smart medical boxes play a vital role in environments such as hospitals, clinics, and home care, and are used to store and manage medicines, medical devices, and patient data. These devices usually need to remain in standby mode for a long time to ensure that they can respond quickly and provide necessary medical services when needed. Therefore, low power consumption and long standby capability become one of the key requirements of smart medical boxes.

[0150] However, traditional screen setting adjustment methods are usually static, lacking dynamic adaptability to environmental changes and user behavior, and unable to fully utilize multi-sensor data for intelligent management. In addition, existing solutions fail to fully consider factors such as ambient light intensity and human activity signals, resulting in unnecessary energy consumption and poor user experience.

[0151] To overcome these problems, the R&D team introduced an adaptive brightness and refresh rate adjustment algorithm, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box based on the fusion data of ambient light intensity and human activity signals. This approach not only reduces the energy consumption of the display component, but also ensures the user's visual comfort, improves the overall performance and user experience, and therefore proposes a new optional solution, which includes:

[0152] According to the fusion data of the combination of the ambient light intensity and the human activity signal, an adaptive brightness and refresh rate adjustment algorithm is applied, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box, wherein the process of adjusting the screen setting parameters of the smart medical box includes setting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode to reduce the energy consumption of the display component of the smart medical box, including:

[0153] Based on the fusion data of the ambient light intensity E and the human activity signal A, the adaptive brightness and refresh rate adjustment algorithm is input into the visual comfort model to generate an evaluation result R:

[0154]

[0155] Among them, f V is a function defined by the visual comfort model, where E is the ambient light intensity, A is the human activity signal, and β E and β A are the weight coefficients of ambient light intensity and human activity signal, γ E and δ A is the corresponding exponential parameter;

[0156] According to the evaluation result R, when the evaluation result indicates that the user does not interact with the device temporarily or only interacts slightly with the device, the display screen brightness B of the smart medical box is gradually reduced until the minimum visibility level B is reached. min , and at the same time switch the refresh mode of the display screen to the preset low refresh rate mode F min , in order to reduce the energy consumption of the display component, the screen setting parameter S is obtained:

[0157]

[0158] Among them, adjust is an adjustment function used to adjust the screen brightness B and refresh rate F according to the evaluation result R, B min is the minimum visibility level, F min is the preset low refresh rate mode, θ R is the preset evaluation result threshold;

[0159] In the above adjustment process, the fusion data change C is continuously used to monitor the current usage scene. Once it is detected that the human activity signal is significantly enhanced or other wake-up conditions are met, the normal screen brightness B is immediately adjusted. normal and refresh rate settings F normal To perform recovery processing:

[0160]

[0161] Among them, S′ is the screen setting parameter after recovery, and recover is a recovery function used to decide whether to restore the normal screen brightness B according to the human activity signal A or other wake-up conditions detected by the fusion data change C normal and refresh rate settings F normal , η A It is the preset human activity signal threshold.

[0162] The following is a detailed explanation of each parameter:

[0163] Ambient light intensity E: Indicates the light level of the environment around the smart medical box. Real-time monitoring and data collection through light sensors, usually expressed as a percentage or standardized value (full light is 1). Used to evaluate the brightness of the current environment and affect the screen brightness adjustment.

[0164] Human activity signal A: indicates whether there is human activity around the smart medical box and its intensity. It is monitored and collected in real time through motion sensors and thermal sensors, usually expressed as a percentage or a standardized value (full activity is 1). It is used to determine whether the user is near the device and affects the adjustment of screen brightness and refresh rate.

[0165] Ambient light intensity weight coefficient β E: Indicates the degree of influence of ambient light intensity on the evaluation results. It is preset based on experimental data and user feedback, and is usually obtained through multiple tests and optimizations. It adjusts the proportion of ambient light intensity in the evaluation results.

[0166] Human activity signal weight coefficient β A : Indicates the degree of influence of human activity signals on the evaluation results. It is preset based on experimental data and user feedback, and is usually obtained through multiple test optimizations. It adjusts the proportion of human activity signals in the evaluation results.

[0167] Ambient light intensity index parameter γ E :Used to adjust the sensitivity of ambient light intensity. Preset based on experimental data and user feedback, usually obtained through multiple tests and optimization. Curve that controls the impact of ambient light intensity on evaluation results.

[0168] Human activity signal index parameter δ A :Used to adjust the sensitivity of human activity signals. Preset based on experimental data and user feedback, usually obtained through multiple test optimizations. Controls the influence of human activity signals on the evaluation results.

[0169] Evaluation result threshold θ R : The criteria used to determine whether to enter power saving mode. Preset based on experimental data and user feedback, usually optimized through multiple tests. Determines when to reduce the screen brightness to the minimum visible level and switch to low refresh rate mode.

[0170] Minimum visibility level B min : The minimum visibility setting for screen brightness. Preset based on visual comfort model and experimental data. Ensures that the screen still maintains basic visibility in energy saving mode.

[0171] Default low refresh rate mode F min : The lowest setting for screen refresh rate. Preset based on visual comfort model and experimental data. Reduces power consumption caused by screen updates.

[0172] Normal screen brightness B normal and refresh rate F normal : Normal settings for screen brightness and refresh rate. Preset based on device default configuration and user needs. Ensures users get the best visual experience when interacting.

[0173] The following is an introduction to the design reasons of each sub-item:

[0174] This part of the formula is used to evaluate the effect of ambient light intensity. Exponential function It can amplify changes in ambient light intensity, especially in low-light environments, so that the system can respond more sensitively to light changes.E It is used to adjust the proportion of ambient light intensity in the entire evaluation result.

[0175] This part of the formula is used to evaluate the impact of human activity signals. Exponential function It can capture the nonlinear changes of human activity signals, especially in low activity situations, so that the system can more accurately identify whether the user exists. A It is used to adjust the proportion of human activity signals in the overall evaluation results.

[0176] The addition of the effects of ambient light intensity and human activity signals is to comprehensively consider the overall impact of the two factors on the screen settings. In this way, the system can dynamically adjust the screen brightness and refresh rate under different environmental conditions to ensure that power is saved without affecting the user experience.

[0177] The purpose of this formula is to achieve intelligent adjustment of the screen settings of the smart medical box. By combining the fusion data of ambient light intensity and human activity signals, applying adaptive brightness and refresh rate adjustment algorithms, and combining visual comfort models, the system can dynamically adjust the screen brightness and refresh rate to reduce the energy consumption of display components. This design not only improves energy utilization efficiency, but also ensures the visual comfort of users. It is particularly suitable for the field of smart medical equipment that requires long standby time and is responsive at any time. Through precise screen brightness and refresh rate adjustment, the system significantly extends the standby time of the device and improves overall performance and user experience.

[0178] Here is a specific example:

[0179] In a hospital environment, a smart medical box is installed near the nurse station to manage emergency medicines and patient information. The system experiences multiple user interaction needs every day, such as checking drug inventory or updating patient information. To optimize this process, the system uses the fusion data of the ambient light intensity E and the human activity signal A to generate an evaluation result R through an adaptive brightness and refresh rate adjustment algorithm combined with a visual comfort model. Based on the evaluation result R, the system dynamically adjusts the screen brightness B and refresh rate F of the smart medical box to reduce the energy consumption of the display component. At the same time, the system continuously monitors the current usage scenario, and once it detects that the human activity signal is significantly enhanced or other wake-up conditions are met, it immediately restores the normal screen brightness and refresh rate settings.

[0180] Assume the following parameters: ambient light intensity E: 0.2 (full light is 1); human activity signal A: 0.1 (full activity is 1); ambient light intensity weight coefficient β E :0.6; human activity signal weight coefficient β A :0.4; ambient light intensity index parameter γ E:0.5; human activity signal index parameter δ A :1.5; preset evaluation result threshold θ R : 0.3; minimum visibility level B min : 0.1 (full brightness is 1); preset low refresh rate mode F min : 30Hz (standard refresh rate is 60Hz); normal screen brightness B normal : 1.0; normal refresh rate F normal :60Hz; preset human activity signal threshold η A : 0.8;

[0181] First, calculate the evaluation result R:

[0182]

[0183] Substituting the values:

[0184] R=0.6·e 0.5·0.2 +0.4·(1-e -1.5·0.1 )

[0185] R=0.6·e 0.1 +0.4·(1-e -0.15 )

[0186] R≈0.6·1.1052+0.4·(1-0.8607)

[0187] R≈0.6631+0.4·0.1393

[0188] R≈0.6631+0.05572

[0189] R≈0.7188

[0190] Next, adjust the screen setting parameters S according to the evaluation result R:

[0191]

[0192] Since R≈0.7188>θ R =0.3, the system determines that the current ambient light intensity and human activity signals are not sufficient to trigger the energy-saving mode, so the current screen brightness and refresh rate settings remain unchanged.

[0193] Assume that after a period of time, the ambient light intensity drops to 0.1 and the human activity signal also drops to 0.05. Recalculate the evaluation result R:

[0194] R=0.6·e 0.5·0.1 +0.4·(1-e -1.5·0.05 )

[0195] R=0.6·e0.05 +0.4·(1-e -0.075 )

[0196] R≈0.6·1.0513+0.4·(1-0.9277)

[0197] R≈0.63078+0.4·0.0723

[0198] R≈0.63078+0.02892

[0199] R≈0.6597

[0200] At this time, although R is still greater than the threshold θ R , but approaching the threshold, the system may gradually reduce the screen brightness to the minimum visibility level B min , and switch the refresh rate to F min , to save power:

[0201] S=(B min , F min )=(0.1,30Hz)

[0202] Finally, suppose the nurse approaches the smart medical box again, the human activity signal is significantly enhanced to 0.9, and the system immediately restores the normal screen brightness and refresh rate settings:

[0203]

[0204] Since A=0.9>η A =0.8, the system immediately returns to normal screen brightness and refresh rate settings:

[0205] S′=(B normal , F normal )=(1.0,60Hz)

[0206] Through the above calculations, the system dynamically adjusts the screen brightness and refresh rate settings of the smart medical box under different ambient light intensity and human activity signal conditions to reduce the energy consumption of the display components while ensuring the user's visual comfort. Specifically, in the initial state, when the ambient light intensity and human activity signal are high, the system evaluation results show R = 0.7188, which exceeds the threshold θ R , so the current screen brightness and refresh rate settings are maintained. When the ambient light intensity and human activity signals weaken, the system evaluation result shows R = 0.6597, which is close to the threshold. The system gradually reduces the screen brightness to the minimum visibility level B min , and switch the refresh rate to F minWhen the user returns, when the human activity signal significantly increases to 0.9, the system immediately restores the normal screen brightness and refresh rate settings to ensure that the user can quickly obtain the required information.

[0207] This intelligent screen setting adjustment is particularly suitable for smart medical equipment that needs to be on standby for a long time and respond at any time, ensuring that the equipment can operate efficiently in various complex environments. Through precise adjustment of screen brightness and refresh rate, the system not only improves energy efficiency, but also significantly extends the standby time of the equipment, improving overall performance and user experience.

[0208] This application considers that smart medical boxes play a vital role in environments such as hospitals, clinics, and home care, and are used to store and manage medicines, medical devices, and patient data. These devices usually need to remain in standby mode for a long time to ensure that they can respond quickly and provide necessary medical services when needed. Therefore, low power consumption and long standby capability become one of the key requirements of smart medical boxes.

[0209] However, traditional methods for setting the activation time interval of wireless modules are usually static, lacking dynamic adaptability to environmental changes and user behavior, and unable to fully utilize multi-sensor data for intelligent management. In addition, existing solutions fail to fully consider factors such as network load and expected transmission delay, resulting in unnecessary energy consumption and inefficient data transmission.

[0210] To overcome these problems, the R&D team introduced a time series prediction algorithm, combined with the network status evaluation results of real-time monitoring, optimized the time interval for wireless module activation, and formulated an intermittent connection strategy. This method not only improves the efficiency of data synchronization and status updates, but also significantly extends the standby time and energy efficiency of the device. Therefore, a new optional solution is proposed, which includes:

[0211] Using a time series prediction algorithm, according to the wake-up event timing determined by the wake-up mechanism, the optimal data synchronization timing or status update timing of the smart medical box is predicted, and according to the current network load and expected transmission delay obtained, the time interval for activating the wireless module in the smart medical box is optimized, and an intermittent connection strategy is formulated, including:

[0212] Using the sensing data, and based on the event-triggered wake-up mechanism, record specific wake-up event history data to generate a data set D;

[0213] The data set D is analyzed and processed using the time series prediction algorithm, combined with the weight w i and the exponential parameter λ i , calculate the prediction result P through the following formula:

[0214]

[0215] Among them, f M is the function defined by the time series prediction algorithm M, D is the dataset of the integrated sensing data and wake-up event history data, and w i is the weight of each data point, e is the base of the natural logarithm, and λ i is the exponential parameter for each data point;

[0216] Monitor and obtain current network load information L in real time and evaluate expected transmission delay T d , combined with the weight w L and w T , calculate the network status assessment result N using the following formula:

[0217] N=g(L,T d , w L , w T )=w L ·L+w T ·T d

[0218] Among them, g is an evaluation function, L is the current network load information, T d is the expected transmission delay, w L and w T are the weights of network load and transmission delay respectively;

[0219] According to the prediction result P and the network status evaluation result N, combined with the weight w P 、w N and exponential parameter α, the optimized time interval setting I is calculated by the following formula:

[0220]

[0221] Among them, h is an optimization function, which is used to comprehensively consider the prediction result P and the network status evaluation result N to determine the optimal time interval setting I, w P and w N are the weights of the prediction results and network status assessment results, respectively, and α is an exponential parameter;

[0222] Based on the optimized time interval setting I, combined with the battery power B and the user behavior pattern weight w U , formulate intermittent connection strategy S:

[0223]

[0224] Where k is a policy generation function based on the time interval setting I, battery power B and user behavior pattern weight w U Develop specific intermittent connection strategies S; B minis the preset minimum battery power threshold. When the battery power is lower than this threshold, the system gives priority to saving power and keeps the current strategy unchanged. U is the time interval scaling factor adjusted according to the user behavior pattern.

[0225] The following is a detailed explanation of each parameter:

[0226] Dataset D: Integrated sensing data and wake-up event history data. Through multi-sensor fusion algorithms such as light sensors, motion sensors, and thermal sensors, the time type and related environmental information of each wake-up event are monitored and recorded in real time to form a historical data set. It is used to predict the timing of future wake-up events.

[0227] Weight w i :The weight of each data point, indicating the importance of the data point in the prediction. It is obtained based on historical data analysis and machine learning model optimization, usually adjusted through multiple tests. It adjusts the impact of different data points on the prediction results.

[0228] Exponential parameter λ i : Exponential parameter for each data point, used to adjust the impact curve of the data point. Based on historical data analysis and machine learning model optimization, usually adjusted through multiple tests. Controls the sensitivity of the data point to the prediction result.

[0229] The base of the natural logarithm, e: a mathematical constant approximately equal to 2.71828. It is used to calculate exponential functions and simulate nonlinear trends.

[0230] Current network load information L: Indicates the current network load. Real-time monitoring and data collection through network monitoring tools, usually expressed as a percentage or standardized value (full load is 1). Used to evaluate the current network status and affect the setting of the wireless module activation time interval.

[0231] Expected transmission delay T d : Indicates the estimated time required for data transmission. It is monitored and estimated in real time through network performance monitoring tools, usually in seconds. It is used to evaluate the current network status and affect the setting of the wireless module activation time interval.

[0232] Network load weight w L and the transmission delay weight w T : Respectively represent the degree of influence of network load and transmission delay on the network status evaluation results. Preset based on experimental data and user feedback, usually obtained through multiple test optimizations. Adjust the proportion of network load and transmission delay in the overall evaluation results.

[0233] Prediction result weight w P and the network status assessment result weight w N: Respectively represent the influence of the prediction result and network status assessment result on the final time interval setting. Preset based on experimental data and user feedback, usually obtained through multiple test optimizations. Adjust the weight of the prediction result and network status assessment result in the entire optimization process.

[0234] Exponential parameter α: used to adjust the sensitivity of the prediction results and network status evaluation results. It is preset based on experimental data and user feedback, and is usually obtained through multiple test optimizations. It controls the influence of the prediction results and network status evaluation results on the final time interval setting.

[0235] Battery Level B: Indicates the current battery level of the smart medical box. Real-time monitoring and data collection through the built-in battery management system, usually expressed as a percentage. Used to formulate intermittent connection strategies to ensure that the device prioritizes power saving when the battery is low.

[0236] User behavior pattern weight w U : Indicates the degree of influence of user behavior patterns on the interval adjustment. Based on historical data analysis and user behavior model optimization, usually adjusted through multiple tests. Adjusts the influence of user activity frequency on the interval setting.

[0237] Minimum battery level threshold B min : The preset minimum battery level threshold below which the system prioritizes power conservation. Preset based on device needs and user feedback. Decides when to keep the current policy unchanged to extend device standby time.

[0238] The following is an introduction to the design reasons of each sub-item:

[0239] w L L: This part of the formula is used to evaluate the impact of the current network load on the network status. The network load L directly reflects the current busyness of the network. A higher load means more data transmission demand and potential congestion. By introducing the weight w L , the importance of network load in the overall evaluation results can be adjusted to ensure that the system can more accurately reflect the current network busyness.

[0240] w T ·T d :This part of the formula is used to evaluate the impact of expected transmission delay on network conditions. Transmission delay T d It directly reflects the time required for data to be sent and received. Longer delay means poorer transmission efficiency. T , the importance of transmission delay in the entire evaluation result can be adjusted to ensure that the system can more accurately reflect the transmission efficiency of the current network.

[0241] wL L and w T ·T d The purpose of adding them together is to comprehensively consider the overall impact of network load and transmission delay on network conditions. Network load and transmission delay are both important factors that affect data transmission efficiency, but their mechanisms of action are different. Network load reflects the current busyness of the network, while transmission delay reflects the actual speed of data transmission. By adding the two together, a comprehensive network status assessment result can be obtained, allowing the system to make the optimal time interval setting under different network conditions.

[0242] The purpose of this formula is to comprehensively evaluate the current network load and transmission delay, so as to determine the optimal activation time interval of the wireless module in the smart medical box. L and w T , the weight of network load and transmission delay in the evaluation results can be flexibly adjusted to ensure that the system can dynamically adjust the activation time interval of the wireless module according to different network conditions. This design not only improves the efficiency of data transmission, but also significantly extends the standby time of the device, improving the overall performance and user experience.

[0243] Here is a specific example:

[0244] In a hospital environment, a smart medical box is installed near the nurse station to manage emergency medicines and patient information. The system experiences multiple data synchronization needs every day, such as updating drug inventory or uploading patient information. To optimize this process, the system generates a dataset D using sensing data and historical wake-up event data, and calculates the prediction result P using a time series prediction algorithm. At the same time, the system monitors the current network load information L and the expected transmission delay T in real time. d , calculate the network status evaluation result N. Finally, based on the prediction result P and the network status evaluation result N, combined with the battery power B and the user behavior pattern weight w U , formulate intermittent connection strategy S.

[0245] Assume the following parameters:

[0246] Dataset D: integrated sensing data and wake-up event history data; number of data points n = 5;

[0247] The weight w of each data point i = [0.2, 0.15, 0.3, 0.2, 0.15];

[0248] The exponential parameter λ for each data point i = [-0.1, -0.2, -0.15, -0.25, -0.1];

[0249] The integrated data D i=[8, 6, 7, 9, 5]; Network load information L: The current network load information is 0.7 (full load is 1);

[0250] Expected transmission delay T d : The expected transmission delay is 2 seconds; the network load weight is w L :0.6; Transmission delay weight w T :0.4; prediction result weight w P :0.8; network status assessment result weight w N : 0.2; exponential parameter α: 0.5; battery power B: 0.8 (full power is 1); user behavior pattern weight w U :0.1(frequent activity);

[0251] First, calculate the prediction result P:

[0252]

[0253] Substituting the values:

[0254] P=0.2·e -0.1·8 +0.15 e -0.2.6 +0.3 e -0.15·7 +0.2 e -0.25.9 +0.15 e -0.1·5

[0255] P=0.2·e -0.8 +0.15 e -1.2 +0.3 e -1.05 +0.2 e -2.25 +0.15 e -0.5

[0256] P≈0.2·0.4493+0.15·0.3012+0.3·0.3499+0.2·0.1054+0.15·0.6065

[0257] P≈0.08986+0.04518+0.10497+0.02108+0.09098

[0258] P≈0.352

[0259] Next, calculate the network status assessment result N:

[0260] N=g(L,T d , w L , w T )=w L ·L+w T ·T d

[0261] Substituting the values:

[0262] N=0.6·0.7+0.4·2

[0263] N = 0.42 + 0.8

[0264] N = 1.22

[0265] Then, calculate the optimized time interval setting I:

[0266]

[0267] Substituting the values:

[0268]

[0269] I≈2.15

[0270] Finally, formulate an intermittent connection strategy S:

[0271]

[0272] Assume that the preset minimum battery power threshold B min =0.2, user behavior pattern weight w U =0.1, and user activity is frequent:

[0273] S = "shorten the time interval to" 2.15·(1-0.1)

[0274] s="Shorten the time interval to" 2.15·0.9

[0275] S≈"shorten the time interval to"1.935

[0276] Through the above calculations, the system obtains the optimized time interval setting I≈2.15 minutes, and further shortens the time interval to about 1.935 minutes based on the frequent user activities. This means that the smart medical box will activate the wireless module for data synchronization and status update in a shorter time interval, thereby ensuring a quick response when the user needs it, while avoiding unnecessary data transmission when the network load is high or the transmission delay is large, saving power and improving data transmission efficiency.

[0277] This intelligent time interval optimization is particularly suitable for smart medical devices that require long standby time and are always responsive, ensuring that the equipment can operate efficiently in a variety of complex environments. Through precise time interval adjustment, the system not only improves the efficiency of data synchronization and status updates, but also significantly extends the standby time and energy efficiency of the equipment, improving overall performance and user experience.

[0278] Figure 2 A structural diagram of a low-power long standby system is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0279] An acquisition module 21 is used to start a multi-sensor fusion algorithm when the smart medical box enters the standby mode, so as to integrate the sensing data from the light sensor, the motion sensor and the thermal sensor through the multi-sensor fusion algorithm, and analyze the sensing data through a Bayesian network to obtain the ambient light intensity and the human activity signal around the smart medical box;

[0280] An adjustment module 22, configured to dynamically adjust the screen setting parameters of the smart medical box by applying an adaptive brightness and refresh rate adjustment algorithm according to the fusion data of the combination of the ambient light intensity and the human activity signal, in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box;

[0281] A setting module 23, configured to set a wake-up mechanism based on event triggering according to the fusion data of the ambient light intensity and the human activity signal, wherein the wake-up mechanism is configured to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received;

[0282] The prediction module 24 is used to use a time series prediction algorithm to predict the optimal data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and optimize the time interval for activating the wireless module in the smart medical box according to the current network load and expected transmission delay obtained, and formulate an intermittent connection strategy;

[0283] The generation module 25 is used to generate a power management solution to maximize the standby time based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy.

[0284] Figure 2 The low power consumption long standby system can perform Figure 1 The implementation principle and technical effect of the low-power long standby method described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the low-power long standby system in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail.

[0285] In one possible design, Figure 2The low power consumption and long standby system of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0286] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0287] The processing component 32 is used for the above Figure 1 The XX method of the embodiment.

[0288] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0289] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0290] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0291] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0292] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0293] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0294] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The low power consumption and long standby method of the illustrated embodiment.

[0295] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0296] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0297] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0298] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A low power consumption and long standby method, characterized in that: include: When the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate sensing data from the light sensor, the motion sensor, and the thermal sensor through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box; According to the fusion data of the combination of the ambient light intensity and the human activity signal, an adaptive brightness and refresh rate adjustment algorithm is applied, combined with a visual comfort model, to dynamically adjust the screen setting parameters of the smart medical box, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box; According to the fusion data of the ambient light intensity and the human activity signal, setting a wake-up mechanism based on event triggering, wherein the wake-up mechanism is used to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received; Using a time series prediction algorithm, according to the wake-up event timing determined by the wake-up mechanism, the optimal data synchronization timing or status update timing of the smart medical box is predicted, and according to the current network load and expected transmission delay obtained, the time interval for activating the wireless module in the smart medical box is optimized, and an intermittent connection strategy is formulated; Based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy, a power management solution is generated to maximize the standby time.

2. The method according to claim 1, characterized in that The method comprises applying an adaptive brightness and refresh rate adjustment algorithm based on the fusion data of the ambient light intensity and the human activity signal, and dynamically adjusting the screen setting parameters of the smart medical box in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes setting the display screen brightness of the smart medical box to a minimum visibility level and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode to reduce the energy consumption of the display component of the smart medical box, including: Using the fused data of the ambient light intensity and the human activity signal as input to an adaptive brightness and refresh rate adjustment algorithm and a visual comfort model, and generating an evaluation result of the degree of interaction between the user and the smart medical box; When the evaluation result indicates that the user has not interacted with the smart medical box, the brightness of the display screen of the smart medical box is gradually reduced until the minimum visibility level is reached, and at the same time, the refresh mode of the display screen is switched to a preset low refresh rate mode to reduce the energy consumption of the display component, thereby obtaining the screen setting parameters.

3. The method according to claim 2, characterized in that When the evaluation result indicates that the user has not interacted with the smart medical box, the brightness of the display screen of the smart medical box is gradually reduced until the minimum visibility level is reached, and the refresh mode of the display screen is switched to a preset low refresh rate mode to reduce the energy consumption of the display component, and the screen setting parameters are obtained, including: When the evaluation result indicates that the user has not interacted with the smart medical box, a screen energy saving program is started, wherein the screen energy saving program refers to a set of software logic or algorithm designed in the smart medical box to reduce the energy consumption of the display component; Using the screen energy saving program, the display screen brightness of the smart medical box is gradually reduced from the current setting value with a preset step length until the minimum visibility level defined by the visual comfort model is reached, thereby obtaining the screen brightness setting; According to the screen brightness setting, while adjusting the brightness of the smart medical box, based on the evaluation result, switching the refresh mode of the display screen of the smart medical box from the normal refresh rate mode to the preset low refresh rate mode, generating a refresh mode configuration, so as to reduce power consumption caused by screen updating; By adjusting the brightness and switching the refresh mode, the screen brightness and refresh rate are comprehensively adjusted to obtain optimized screen setting parameters.

4. The method according to claim 1, characterized in that: The method utilizes a time series prediction algorithm to predict the optimal data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and optimizes the time interval for activating the wireless module in the smart medical box according to the current network load and expected transmission delay obtained, and formulates an intermittent connection strategy, including: Using the sensing data, and based on an event-triggered wake-up mechanism, record specific wake-up event history data to generate a data set; Analyze and process the data set using a time series prediction algorithm, build a prediction model that can identify the occurrence rules of wake-up events and user behavior patterns, and predict the best data synchronization time or status update time through the prediction model to generate a prediction result; Monitor and obtain current network load information in real time, evaluate expected transmission delay, and generate network status assessment results; According to the prediction result and the network status evaluation result, the time interval for activating the wireless module is optimized to generate a time interval setting; Based on the time interval setting, an intermittent connection strategy is formulated.

5. The method according to claim 4, characterized in that The step of optimizing the time interval for activating the wireless module according to the prediction result and the network status evaluation result to generate a time interval setting includes: Based on the historical data and default configuration of the smart medical box, an initial time interval for activating the wireless module is set to obtain an initial time interval setting; Combining the prediction result with the network status assessment result, performing data fusion analysis on the two, identifying key factors affecting the activation frequency of the wireless module, and obtaining a list of key factors, wherein the key factors include user behavior patterns, network load conditions, and data synchronization requirements; Using a preset optimization algorithm, based on the key factor list, the time interval for activating the wireless module is adjusted to generate a preliminary optimized time interval setting; By simulating the wireless module activation behavior in different scenarios, evaluating whether the initially optimized time interval setting meets the expected performance indicators, the performance indicators include energy efficiency ratio, response time and data transmission success rate, and obtaining simulation verification results; According to the simulation verification result, further fine-tune the time interval for activating the wireless module to ensure that the optimized activation time interval setting can achieve the best effect in the actual operating environment, and generate the optimized activation time interval value; Based on the optimized activation time interval value, a wireless module activation time interval setting is generated and applied to the smart medical box.

6. The method according to claim 1, characterized in that When the smart medical box enters the standby mode, a multi-sensor fusion algorithm is started to integrate sensing data from light sensors, motion sensors, and thermal sensors through the multi-sensor fusion algorithm, and the sensing data is analyzed through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box, including: Using a preset condition, the state of the smart medical box is judged and processed to obtain a standby mode detection result, wherein the preset condition is that the time when the user does not interact with the device exceeds a set threshold; Based on the standby mode detection result, a multi-sensor fusion algorithm is started to activate the light sensor, the motion sensor and the thermal sensor to prepare for collecting sensing data; Use the activated sensors to monitor the light intensity, human movement and temperature changes in the environment in real time to obtain original sensing data; Inputting the acquired raw sensing data into a multi-sensor fusion algorithm, integrating and processing the data from different sensors, and generating fused data; Based on the fused data, a Bayesian network analysis method is applied to perform probabilistic reasoning processing on the fused data to evaluate and determine the existence and characteristics of ambient light intensity and human activity signals.

7. The method according to claim 1, characterized in that The method further comprises: setting a wake-up mechanism based on event triggering according to the fusion data of the ambient light intensity and the human activity signal, wherein the wake-up mechanism is used to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received, including: According to a preset rule, define an event type corresponding to an external input event, wherein the event type includes a specific type or a non-specific type; Based on the fused data, a wake-up mechanism is configured and processed, a condition for starting a system wake-up process when a specific type of external input event is received is set, and a wake-up condition setting is generated; For non-specific external input events, set filtering rules to ensure that these events do not mistakenly trigger the wake-up process and generate filtering rule settings; By using the event type definition rules, wake-up condition settings and filtering rule settings, the occurrence of external input events is monitored in real time. When an external input event is detected, it is determined whether the external input event meets the preset specific type; if so, the system wake-up process is immediately started; if not, the filtering rules are applied to determine whether to ignore the event or continue to stay in standby mode, and an event response result is generated; According to the event response results, feedback information from actual operation is collected to evaluate the performance of the wake-up mechanism; Based on the result of the feedback information collection, the wake-up condition setting and the filtering rule setting are dynamically optimized and adjusted to improve the accuracy and efficiency of the wake-up mechanism and generate an optimized wake-up mechanism.

8. A low power consumption and long standby system, characterized in that: include: an acquisition module, configured to start a multi-sensor fusion algorithm when the smart medical box enters a standby mode, so as to integrate sensing data from a light sensor, a motion sensor, and a thermal sensor through the multi-sensor fusion algorithm, and analyze the sensing data through a Bayesian network to obtain ambient light intensity and human activity signals around the smart medical box; an adjustment module, for dynamically adjusting the screen setting parameters of the smart medical box by applying an adaptive brightness and refresh rate adjustment algorithm according to the fusion data of the combination of the ambient light intensity and the human activity signal, in combination with a visual comfort model, wherein the process of adjusting the screen setting parameters of the smart medical box includes adjusting the display screen brightness of the smart medical box to a minimum visibility level, and simultaneously switching the refresh mode of the smart medical box to a preset low refresh rate mode, so as to reduce the energy consumption of the display component of the smart medical box; A setting module, configured to set a wake-up mechanism based on event triggering according to the fusion data of the ambient light intensity and the human activity signal, wherein the wake-up mechanism is configured to start a system wake-up process when a specific type of external input event is received, and to perform a filtering operation and maintain a standby state when a non-specific type of external input event is received; A prediction module, used to use a time series prediction algorithm to predict the optimal data synchronization timing or status update timing of the smart medical box according to the wake-up event timing determined by the wake-up mechanism, and to optimize the time interval for activating the wireless module in the smart medical box according to the current network load and expected transmission delay obtained, and to formulate an intermittent connection strategy; A generation module is used to generate a power management solution to maximize standby time based on the battery power of the smart medical box, the acquired user behavior pattern, and the multi-dimensional factors of task priority, combined with the screen setting parameters and the intermittent connection strategy.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a low-power consumption and long standby method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a low-power consumption and long standby method as claimed in any one of claims 1 to 7 is implemented.

Images