Multi-scenario adjustment control method and system for intelligent electric bed based on artificial intelligence

Abstract

The present invention discloses a multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence, including detecting the user's behavioral intention, when determining that the arrival probability is greater than a preset value, inputting the current time and user identity information into a scene prediction model, matching a first configuration scheme according to the output scene type, to configure the use parameters of the intelligent electric bed; detecting the user's posture change data and the duration of each posture, analyzing the user's use status according to the duration, adjusting the first configuration scheme according to the use status analysis result, and generating a second configuration scheme; predicting the force tendency of the user's intelligent electric bed during use according to the user's posture change data, and optimizing the second configuration scheme, and adjusting the intelligent electric bed according to the optimized scheme. The present invention can adaptively adjust the parameters of the electric bed for different users in different use scenarios, meet the user's personalized use needs, and improve the user experience.

Description

Technical Field

[0001] The present invention relates to the field of smart home control technology, and in particular to an artificial intelligence-based multi-scene adjustment control method and system for a smart electric bed. Background Art

[0002] With the advancement of technology and the improvement of consumers' requirements for quality of life, smart electric beds have gradually evolved into smart home products that integrate comfort, convenience and health management, and have been widely welcomed by consumers. However, the current control and adjustment of smart electric beds usually requires the user to issue control instructions for adjustment. Whenever switching between different users or different scenes, it is necessary to rely on the user to adjust. This operation process is cumbersome and reduces the user experience. In addition, the configuration of specific control parameters depends solely on the user's own preferences, lacking scientific guidance and adaptive adjustment capabilities, which makes it impossible for users to use smart electric beds scientifically and healthily. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned above, the present invention provides an artificial intelligence-based multi-scene adjustment and control method and system for an intelligent electric bed.

[0004] In a first aspect, the present invention provides a multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence, the method comprising:

[0005] Detect the user's behavior intention, and when it is determined that the probability of the user reaching the location of the smart electric bed within a preset time period is greater than a preset value, input the current time and user identity information into the scene prediction model and output the scene type;

[0006] Matching a first configuration scheme according to the scenario type, configuring the usage parameters of the smart electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical usage habits of different users;

[0007] Detecting the user's posture change data and the duration of each posture, analyzing the user's usage status according to the duration, adjusting the first configuration scheme according to the usage status analysis result, and generating a second configuration scheme;

[0008] The force tendency of the intelligent electric bed during use is predicted according to the user posture change data, the second configuration scheme is optimized according to the force tendency, and the use parameters of the intelligent electric bed are adjusted according to the optimized second configuration scheme.

[0009] Preferably, the detecting the user's behavioral intention includes:

[0010] Calculate the probability of the user arriving at the location of the smart electric bed within the preset time based on the user's walking direction and walking speed:

[0011]

[0012] In the formula, P represents the arrival probability, L0 represents the straight-line distance between the user's location and the location of the smart electric bed, θ represents the angle between the location of the smart electric bed and the user's walking direction with the user's location as the origin, and L t represents the user's location at time t, and v represents the user's walking speed.

[0013] Preferably, after outputting the scene type, the method further includes:

[0014] Match linkage control schemes according to scene types, and use linkage control schemes to control other smart home usage parameters;

[0015] Analyze user comfort based on linkage control results, and adjust other smart home usage parameters online according to the analysis results of user comfort; user comfort is:

[0016] G C =w1G H +w2G s ;

[0017]

[0018] In the formula, G C Score the user's comfort level, G H , G s They represent the environmental comfort score and the user's personalized comfort score respectively; w1 and w2 are weights; Q and Q0 are the scene illumination and standard illumination preset values ​​respectively; T is the average temperature of the scene, and d is the relative humidity of the scene.

[0019] Preferably, the adjusting the first configuration scheme according to the usage status analysis result includes:

[0020] Determine the change in the carrying capacity of the smart electric bed according to the change data of the contact area between the user and the smart electric bed and the user's flip angle during the posture adjustment process;

[0021] According to the changes in the load-bearing capacity of the smart electric bed, the load-bearing capacity, support angle, bed surface height and bed hardness of different parts of the user's body are adaptively adjusted.

[0022] Preferably, predicting the force tendency of the intelligent electric bed during use according to the user's posture change data, and optimizing the second configuration scheme according to the force tendency, includes:

[0023] Acquiring user posture change data, including a change in pressure on the smart electric bed during the user's posture change and a change in the contact area between the user and the smart electric bed;

[0024] According to the user posture change data, predict the direction of the user posture change to determine the corresponding force tendency of the bed, and obtain the user flip angle and flip number corresponding to the force tendency of the bed;

[0025] The degree of compatibility between the second configuration scheme and the user's usage status is determined according to the flip angle and the flip times. When the degree of compatibility does not meet the preset conditions, the second configuration scheme is optimized according to the force tendency of the bed body.

[0026] Preferably, after outputting the scene type, the method further includes:

[0027] When the scene type is unattended, determine whether it is necessary to enter the fault detection mode;

[0028] If so, the intelligent electric bed is diagnosed for faults, and an alarm is triggered when an abnormality is diagnosed;

[0029] If not, the intelligent electric bed is controlled to automatically shut down the power or switch to energy-saving mode.

[0030] Preferably, the scene prediction model is obtained based on convolutional neural network training.

[0031] In a second aspect, the present invention further provides an intelligent electric bed multi-scene adjustment control system based on artificial intelligence, the system comprising:

[0032] A scene type prediction unit is used to detect the user's behavior intention. When it is determined that the probability of the user reaching the location of the intelligent electric bed within a preset time period is greater than a preset value, the current time and user identity information are input into the scene prediction model to output the scene type.

[0033] A configuration scheme matching unit, used to match a first configuration scheme according to a scene type, and configure the use parameters of the intelligent electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical use habits of different users;

[0034] A configuration scheme adjustment unit, used to detect the user's posture change data and the duration of each posture, analyze the user's usage status according to the duration, adjust the first configuration scheme according to the usage status analysis result, and generate a second configuration scheme;

[0035] The optimization control unit is used to predict the force tendency of the intelligent electric bed during use according to the user's posture change data, optimize the second configuration scheme according to the force tendency, and adjust the use parameters of the intelligent electric bed according to the optimized second configuration scheme.

[0036] In a third aspect, the present invention further provides an electronic device comprising: a processor and a memory, wherein the memory is used to store computer program code, wherein the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1) The present invention can first detect the user's behavioral intention, and when the electric bed is not in use, control it to be in power-off or energy-saving mode to reduce energy consumption; before the user reaches the smart electric bed, by determining the arrival probability of the user reaching the location of the smart electric bed within a preset time period, and when it is determined that the probability value is greater than the preset value, the scene will be immediately identified to match the first configuration scheme according to the scene type, and the use parameters of the electric bed can be adjusted in advance to avoid starting the adjustment after the user arrives, so that the user can enter the smart use process as soon as possible, thereby improving the user experience.

[0040] 2) The scene prediction model mainly makes predictions based on the current time and user identity information. Usually, users' use of smart beds follows certain time rules, and the usage rules of different users are also different. Therefore, when the present invention recognizes that the user is about to arrive at the smart bed, it can quickly predict the scene type based on the current time and user identity information. Compared with scene recognition based on image recognition of user behavior, it reduces the prediction cost, and can predict and set the parameters of the electric bed in advance, speeding up the process of users entering use.

[0041] 3) After obtaining the first configuration scheme, the present invention will configure the use parameters of the intelligent electric bed according to the first configuration scheme, and the first configuration scheme is learned according to the historical use habits of different users, and can match the use needs of different users based on user preferences. Compared with the user issuing a control instruction to adjust the parameters before each use, the present invention is user-friendly and has a good user experience;

[0042] 4) During the user's use, it can detect the user's posture change data and the duration of each posture in real time, analyze the user's use status according to the duration, adjust the first configuration plan according to the use status analysis result, and predict the force tendency of the smart electric bed during the user's use according to the user's posture change data, and optimize the adjusted plan according to the force tendency. This method is equivalent to adaptively adjusting the bed parameters during use based on the force data, thereby ensuring the safety and rationality of user use and helping to maintain user health.

[0043] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0045] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0046] Figure 1 A schematic flow chart of a multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence provided by an embodiment of the present invention;

[0047] Figure 2 A schematic structural diagram of a multi-scene adjustment control system for an intelligent electric bed based on artificial intelligence provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to enable users in the technical field to better understand the solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technical users in the field without creative work are within the scope of protection of the present invention.

[0049] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by users of skill in the art that the embodiments described herein may be combined with other embodiments.

[0050] In addition, in order to better illustrate the present invention, numerous specific details are provided in the following detailed description. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0051] At present, the intelligence level of the intelligent electric bed in the use and regulation process needs to be improved, including switching between different users and being unable to adaptively adjust in different scenarios to meet user needs and ensure the user's safe use process. To this end, the present invention provides an intelligent electric bed multi-scenario adjustment and control method based on artificial intelligence, which can first match the parameter setting scheme that meets the user's habitual preferences according to the user scenario, and detect the force data and analyze the use status during use to adaptively adjust the bed parameters, thereby meeting the user's personalized experience, ensuring the user's use safety, high intelligence level, and good user experience.

[0052] See also Figure 1 , Figure 1 The present invention provides a flowchart of a multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence. Figure 1 As shown, a multi-scenario adjustment and control method of an intelligent electric bed based on artificial intelligence includes the following steps:

[0053] S10, detecting the user's behavior intention, and when it is determined that the probability of the user reaching the location of the smart electric bed within the preset time period is greater than a preset value, inputting the current time and user identity information into the scene prediction model, and outputting the scene type;

[0054] S20, matching a first configuration scheme according to the scenario type, and configuring the usage parameters of the intelligent electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical usage habits of different users;

[0055] S30, detecting the user's posture change data and the duration of each posture, analyzing the user's usage status according to the duration, adjusting the first configuration scheme according to the usage status analysis result, and generating a second configuration scheme;

[0056] S40, predicting the force tendency of the intelligent electric bed during use according to the user posture change data, optimizing the second configuration scheme according to the force tendency, and adjusting the use parameters of the intelligent electric bed according to the optimized second configuration scheme.

[0057] In this embodiment, the user's behavior intention is judged based on the arrival probability of the user reaching the location of the smart electric bed within a preset time period. When it is greater than the preset value, it means that the user will soon reach the smart electric bed within the preset time period. Otherwise, it is judged that the user may just pass through the space where the electric bed is located, and the target point of his behavior intention is not the smart electric bed. Usually the preset time period is a short time range, such as within 1 minute. If the time period is longer, it may cause the use mode of the electric bed to be started more in advance, resulting in power loss.

[0058] When it is determined that the user is about to arrive at the smart electric bed within a preset time period, this embodiment will first perform scene prediction and recognition to determine the scene type, and then match the parameter configuration scheme according to the scene type, that is, the first configuration scheme. In this way, the parameters of the electric bed can be adjusted in advance during the period when the user is walking but not yet reaching the electric bed. Compared with adjusting after the user arrives, it can ensure that the user enters the smart use process faster, thereby improving the user experience.

[0059] Among them, the prediction of scene type is mainly based on inputting the current time and user identity information into the scene prediction model to output the scene type. User identity information mainly includes user weight, height, gender, age, etc. The reason why user identity information is needed is that different users have different functional requirements and parameter comfort requirements for smart electric beds. For example, the elderly and children have different preferences for the softness and hardness of the bed and the height of the bed surface. The functions of using smart electric beds can include exercise punching in to lose weight, doing yoga, meditation, sleep, reading, etc. The bed usage parameters corresponding to each function are different, and the time information is mainly used to predict the use of the bed. It is understandable that the same user's habits of using smart beds are usually relatively fixed, such as sleeping at 11 o'clock every night, reading at 10 o'clock, and exercising at 8 o'clock in the morning. In this way, the type of scene used can be quickly predicted based on the current time information and user identity information.

[0060] In some embodiments, the scene prediction model is usually obtained based on convolutional neural network training. During training, a large amount of historical usage data can be used, including the user identity, usage time and usage purpose of the smart bed. The user identity and usage time data are used as model inputs, and the usage purpose, that is, the scene type, is used as output to train the model. After the number of iterations reaches a certain number, the model prediction accuracy is ensured to meet a preset recognition accuracy, and the scene prediction model can be generated. Among them, using a convolutional neural network to train the model is only a preferred implementation method. In other embodiments, other models, such as support vector machines, random forests and other networks, can also be used to train the scene prediction model.

[0061] It should be emphasized that the reason why the model is trained in advance to predict the scene type in this embodiment is that it is necessary to configure the parameters of the bed in advance according to the scene purpose during the period when it is determined that the user has not yet arrived at the smart electric bed. If the scene recognition method is adopted after the user arrives and based on the user's behavior, firstly, the parameters of the bed cannot be configured in advance, so that the user can enter the use mode only after the user arrives. This is relatively inefficient and the user experience will be poor. Secondly, this recognition method based on user behavior will greatly increase the training cost of the model, because it involves image recognition, and a large number of image features will be involved in training. The computational cost during training is relatively high. Once the number of image samples is insufficient or the quality is low, the recognition accuracy of the model cannot be guaranteed. Therefore, this embodiment chooses to identify the model based on user identity data and time data, which reduces the training and prediction costs, and can also pre-adjust the bed parameters, speed up the user's entry into the smart use process, and improve the user experience.

[0062] After matching the first configuration plan according to the scene type, the smart electric bed will automatically adjust the usage parameters of the bed according to the first configuration plan, where the first configuration plan is learned based on the historical usage habits of different users, including the support angle, bed surface height, and bed hardness preferred by different users in different usage scenarios.

[0063] In some embodiments, after obtaining the first configuration scheme, it can be sent to the user through a mobile terminal first, and then controlled after the user confirms it, or it can be controlled first. If the user feels uncomfortable or has other needs during the experience, the various functions of the bed can be remotely or locally controlled through interactive methods such as mobile terminals, voice assistants, remote controls or bedside control panels. The smart bed combines AI technology and adopts an intelligent control system, which enables the bed to accurately respond to user instructions or make decisions autonomously through built-in microprocessors, sensors and actuators.

[0064] After the initial parameters are adjusted, the user enters the intelligent use mode. In this process, the user's posture change data and the duration of each posture are detected, and the user's usage status is analyzed according to the duration, that is, the user's experience in this state is determined. For example, frequent changes in posture or short duration indicate that the current parameters of the bed may cause poor user experience. Therefore, when this problem occurs, the first configuration plan needs to be adjusted based on the usage status analysis results to generate a second configuration plan;

[0065] Furthermore, the force tendency of the smart electric bed during use is predicted based on the user's posture change data, and the second configuration scheme is optimized based on the force tendency. By predicting the force in advance, the safety of the user during use can be guaranteed, and joint strain caused by insufficient bearing capacity and poor fit can be avoided, and even safety accidents can be caused. Finally, the use parameters of the smart electric bed are adjusted according to the optimized second configuration scheme, which is equivalent to adaptively adjusting the bed parameters according to the use status and force tendency, that is, the safe use process of the smart bed can be guaranteed under scientific guidance, while also meeting user needs.

[0066] In some embodiments, detecting the user's behavioral intention includes:

[0067] Calculate the probability of the user arriving at the location of the smart electric bed within the preset time based on the user's walking direction and walking speed:

[0068]

[0069] In the formula, P represents the arrival probability, L0 represents the straight-line distance between the user's location and the location of the smart electric bed, θ represents the angle between the location of the smart electric bed and the user's walking direction with the user's location as the origin, and L t represents the user's location at time t, and v represents the user's walking speed.

[0070] In order to adjust the parameters of the intelligent electric bed in advance, this embodiment mainly predicts the user's behavior intention based on the user's behavior data. The user's behavior data includes the walking direction and walking speed. The walking direction determines whether the user is moving towards the location of the intelligent electric bed. θ represents the angle between the location of the intelligent electric bed and the user's walking direction with the user's location as the origin. When the user moves towards the direction of the intelligent electric bed, the angle is usually unchanged or fluctuates within a small range, that is, the user moves in a straight line or slightly adjusts the sitting position. The walking speed will also affect the probability of the user arriving at the location of the intelligent electric bed. It can be understood that the slower the user's speed and the longer it takes to walk to the front of the intelligent electric bed, the greater the probability of random events that may occur during this period, that is, the greater the risk of changing the direction of the user's behavior. Therefore, when the user moves at a faster speed, the probability of successfully arriving at the location of the intelligent electric bed will also increase. When it is determined that the arrival probability is greater than the preset value, it can be considered that the user's behavior target location is the intelligent electric bed.

[0071] Preferably, the two parameters of walking direction and walking speed can be obtained through the camera of the mobile terminal. For example, when it is detected that someone enters the room where the smart electric bed is located, the camera will automatically turn on and shoot the person's movement trajectory at preset intervals. The user's walking direction and speed can be obtained through the movement route, distance traveled and time spent.

[0072] In one embodiment, after outputting the scene type, the method further includes:

[0073] Match linkage control schemes according to scene types, and use linkage control schemes to control other smart home usage parameters;

[0074] Analyze user comfort based on linkage control results, and adjust other smart home usage parameters online according to the analysis results of user comfort; user comfort is:

[0075] G C =w1G H +w2G s ;

[0076]

[0077] In the formula, G C Score the user's comfort level, G H , G s They represent the environmental comfort score and the user's personalized comfort score respectively; w1 and w2 are weights; Q and Q0 are the scene illumination and standard illumination preset values ​​respectively; T is the average temperature of the scene, and d is the relative humidity of the scene.

[0078] In this embodiment, by accessing the smart home system, the smart electric bed can be linked with other smart devices, such as lights, air conditioners, curtains, and audio, to achieve a preset usage environment scene. For example, when the user sets the "bedtime mode", the bed will be adjusted to a suitable reading angle, and the lights will gradually dim and the music will be soft, which will help create a comfortable sleeping atmosphere. The "wake-up mode" may slowly raise the head of the bed at the scheduled wake-up time, accompanied by soft music and gradually lit lights, to achieve a natural waking experience. When exercising, the room needs to be relatively ventilated, maintain a comfortable temperature and humidity, and can be accompanied by the user's favorite music, which is more conducive to persisting in completing the exercise process.

[0079] It can be understood that in this embodiment, after other smart homes are controlled according to the linkage control scheme, the user's comfort will be detected and fed back. The environmental comfort score and the user's personalized comfort score are considered here. The environmental comfort score is mainly based on each scenario (the user's use of the smart bed at different times) to provide a scientific environmental scene configuration plan, such as the optimal temperature and humidity required for sleep, while the user's personalized comfort score is mainly evaluated based on the user's subjective feelings. The user comfort score can be obtained based on these two scores. If the score is good, the current linkage control scheme can be retained, and the linkage control will continue to be performed according to the scheme in the next linkage control. If the score is not ideal, the configuration parameters of each smart home in the linkage control can be optimized until the user's comfort is met.

[0080] In one embodiment, adjusting the first configuration scheme according to the usage status analysis result includes:

[0081] Determine the change in the bearing capacity of the smart electric bed according to the change in the force area of ​​contact between the user and the smart electric bed and the user's flip angle during the posture adjustment process;

[0082] According to the changes in the load-bearing capacity of the smart electric bed, the load-bearing capacity, support angle, bed surface height and bed hardness of different parts of the user's body are adaptively adjusted.

[0083] For ease of understanding, the following example uses a user sleeping on a bed:

[0084] Specifically, the contact force area can collect the user's sleeping position data on the bed through a pressure sensor preset in the inner layer of the bed, wherein a plurality of pressure sensors are arranged and evenly distributed in the inner layer of the bed. When the user's sleeping position changes, the pressure detected by the corresponding sensor increases or decreases, indicating that the user's sleeping position has changed. According to the duration of each sleeping position, that is, the stable duration of the force on the corresponding pressure sensor, the duration of the sleeping position corresponding to the sleeping position is obtained. When the duration of the sleeping position exceeds a preset threshold, such as 10 minutes, it is judged that the user has fallen asleep.

[0085] When the first configuration scheme is adjusted according to the usage status analysis result, that is, the bearing capacity of the bed under different sleeping states is adjusted in a targeted manner according to the sleep analysis result, wherein the adjustment value of the bearing capacity is:

[0086]

[0087] In the formula, F represents the adjustment value of the bed's bearing capacity, ΔS represents the contact area between the user and the bed, Indicates the user's flip angle during the user's sleeping posture adjustment process. ΔG represents the change in force on the user during the sleeping position flipping process.

[0088] Once F is obtained, adaptive adjustments can be made based on the load-bearing capacity, support angle, bed height, and bed hardness of different parts of the user's body.

[0089] Further, predicting the force tendency of the intelligent electric bed during use according to the user's posture change data, and optimizing the second configuration scheme according to the force tendency, includes:

[0090] Acquiring user posture change data, including a change in pressure on the smart electric bed during the user's posture change and a change in the contact area between the user and the smart electric bed;

[0091] According to the user's posture change data, the user's posture change direction is predicted to determine the corresponding force tendency of the bed, and the flip angle and flip number corresponding to the force tendency of the bed are obtained;

[0092] The degree of compatibility between the second configuration scheme and the user's usage status is determined according to the flip angle and the flip times. When the degree of compatibility does not meet the preset conditions, the second configuration scheme is optimized according to the force tendency of the bed body.

[0093] Taking the user's sleeping process as an example, the bed pressure change value and bed contact area change value during the user's sleeping position change process are calculated in combination with the user's sleeping position change data. For example, when changing from lying straight to lying sideways, the bed contact area decreases and the bed pressure at each contact position increases; the bed change difference is calculated by the bed pressure change before and after the sleeping position change, and the bed contact area change value is calculated by the bed contact area change before and after the sleeping position change. When the user's sleeping position change tends to be stable, the sleeping position force value after stabilization and the sleeping position force value before the sleeping position change are obtained for calculation. The bed force tendency is analyzed based on the difference in the sleeping position force value before and after the sleeping position change. According to the gradient change of the force value, the slope of the force change during the flipping process is calculated to obtain the force flipping angle. The number of user flipping times is counted according to the number of changes in the force increase and decrease of each pressure sensor, and then the degree of coordination with the user's use is judged according to the value, such as the degree of fit between the body and the bed and the user's sleeping comfort. If the value does not meet the preset conditions, the force tendency of the bed is required to optimize the second configuration scheme, and the smart electric bed is adjusted by changing the support angle, bed height and bed hardness. Specifically, the parameter adaptive adjustment process can be realized by an AI algorithm, which can automatically adjust the height, inclination angle and hardness of the bed according to the user's body shape, weight, sleeping posture changes and sleep monitoring data. For example, the bed can automatically raise the head position to relieve snoring, or adjust the waist support to relieve back pain. Preferably, the smart electric bed can also provide the function of local independent regulation. When more than one person uses the bed, it can be adjusted separately to meet the needs of different users. In addition, during control, its working mode will be continuously optimized according to user feedback and usage to achieve truly personalized sleep support.

[0094] In one embodiment, when the user uses the smart electric bed to sleep, the control method will also monitor and analyze the user's sleep. Various sensors, such as pressure sensors, biometric sensors, heart rate sensors, etc., are installed on the smart electric bed to monitor the user's sleep quality parameters in real time, such as heart rate, breathing rate, number of tossing, sleep stage (light sleep, deep sleep, REM sleep, etc.). These data are processed and analyzed by the AI ​​algorithm to evaluate the user's sleep health, identify sleep disorders (such as snoring, insomnia, sleep apnea, etc.) and provide personalized sleep improvement suggestions. In addition, the AI ​​algorithm can identify the user's sleep habits, preferences and potential health risks through deep learning of long-term sleep data. This information can be used to generate personalized sleep reports and provide improvement suggestions. When a user sleep report is generated, the user can connect with a professional medical and health consultant platform based on the report to provide users with professional sleep consultation and treatment plans.

[0095] In one embodiment, after outputting the scene type, the method further includes:

[0096] When the scene type is unattended, determine whether it is necessary to enter the fault detection mode;

[0097] If so, the intelligent electric bed is diagnosed for faults, and an alarm is triggered when an abnormality is diagnosed;

[0098] If not, the intelligent electric bed is controlled to automatically shut down the power or switch to energy-saving mode.

[0099] In this embodiment, when no one is using it, it is first determined whether to enter the fault detection mode. If yes, a detection is performed. If not, the smart electric bed is controlled to automatically shut down the power or switch to energy-saving mode to reduce the energy consumption of the bed. By utilizing the fault prediction and diagnosis capabilities of AI, the smart electric bed can self-detect hardware failures, software anomalies, or performance degradation, and send early warnings to users or manufacturers in a timely manner, facilitating preventive maintenance or remote firmware updates to ensure that the bed is always in optimal operating condition.

[0100] In summary, the method provided by the embodiment of the present invention has at least the following effects:

[0101] 1) The present invention can first detect the user's behavioral intention, and when the electric bed is not in use, control it to be in power-off or energy-saving mode to reduce energy consumption; before the user reaches the smart electric bed, by determining the arrival probability of the user reaching the location of the smart electric bed within a preset time period, and when it is determined that the probability value is greater than the preset value, the scene will be immediately identified to match the first configuration scheme according to the scene type, and the use parameters of the electric bed can be adjusted in advance to avoid starting the adjustment after the user arrives, so that the user can enter the smart use process as soon as possible, thereby improving the user experience.

[0102] 2) The scene prediction model mainly makes predictions based on the current time and user identity information. Usually, users' use of smart beds follows certain time rules, and the usage rules of different users are also different. Therefore, when the present invention recognizes that the user is about to arrive at the smart bed, it can quickly predict the scene type based on the current time and user identity information. Compared with scene recognition based on image recognition of user behavior, it reduces the prediction cost, and can predict and set the parameters of the electric bed in advance, speeding up the process of users entering use.

[0103] 3) After obtaining the first configuration scheme, the present invention will configure the use parameters of the intelligent electric bed according to the first configuration scheme, and the first configuration scheme is learned according to the historical use habits of different users, and can match the use needs of different users based on user preferences. Compared with the user issuing a control instruction to adjust the parameters before each use, the present invention is user-friendly and has a good user experience;

[0104] 4) During the user's use, it can detect the user's posture change data and the duration of each posture in real time, analyze the user's use status according to the duration, adjust the first configuration plan according to the use status analysis result, and predict the force tendency of the smart electric bed during the user's use according to the user's posture change data, and optimize the adjusted plan according to the force tendency. This method is equivalent to adaptively adjusting the bed parameters during use based on the force data, thereby ensuring the safety and rationality of user use and helping to maintain user health.

[0105] See also Figure 2 In some embodiments, the present invention further provides an artificial intelligence-based intelligent electric bed multi-scene adjustment control system, the system comprising:

[0106] The scene type prediction unit 100 is used to detect the user's behavior intention. When it is determined that the probability of the user reaching the location of the intelligent electric bed within a preset time period is greater than a preset value, the current time and the user's identity information are input into the scene prediction model to output the scene type.

[0107] A configuration scheme matching unit 200 is used to match a first configuration scheme according to a scene type, and configure the use parameters of the intelligent electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical use habits of different users;

[0108] The configuration scheme adjustment unit 300 is used to detect the user's posture change data and the duration of each posture, analyze the user's usage status according to the duration, adjust the first configuration scheme according to the usage status analysis result, and generate a second configuration scheme;

[0109] The optimization control unit 400 is used to predict the force tendency of the intelligent electric bed during use of the user according to the user posture change data, optimize the second configuration scheme according to the force tendency, and adjust the use parameters of the intelligent electric bed according to the optimized second configuration scheme.

[0110] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0111] The present invention also provides an electronic device, comprising: a processor and a memory, wherein the memory is used to store computer program code, the computer program code includes computer instructions, and when the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0112] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0113] Users of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical users can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0114] Technical users in the relevant field 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. Technical users in the relevant field can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0115] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0117] A user of ordinary skill in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

Claims

1. A multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence, characterized in that: The method comprises: Detect the user's behavior intention, and when it is determined that the probability of the user reaching the location of the smart electric bed within a preset time period is greater than a preset value, input the current time and user identity information into the scene prediction model and output the scene type; Matching a first configuration scheme according to the scenario type, configuring the usage parameters of the smart electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical usage habits of different users; Detecting the user's posture change data and the duration of each posture, analyzing the user's usage status according to the duration, adjusting the first configuration scheme according to the usage status analysis result, and generating a second configuration scheme; The adjusting the first configuration scheme according to the usage status analysis result includes: Determine the change in the carrying capacity of the smart electric bed according to the change data of the contact area between the user and the smart electric bed and the user's flip angle during the posture adjustment process; According to the changes in the load-bearing capacity of the smart electric bed, the load-bearing capacity, support angle, bed height and bed hardness of different parts of the user's body are adaptively adjusted; The force tendency of the intelligent electric bed during use is predicted according to the user posture change data, the second configuration scheme is optimized according to the force tendency, and the use parameters of the intelligent electric bed are adjusted according to the optimized second configuration scheme.

2. The multi-scenario adjustment and control method of an intelligent electric bed based on artificial intelligence according to claim 1 is characterized in that: The detecting of the user's behavior intention includes: Calculate the probability of the user arriving at the location of the smart electric bed within the preset time based on the user's walking direction and walking speed: ； In the formula, represents the arrival probability, Indicates the straight-line distance between the user's location and the location of the smart electric bed. It represents the angle between the position of the smart electric bed and the direction in which the user is walking, with the user's position as the origin. express The user's location at the moment, Indicates the user's walking speed.

3. The multi-scenario adjustment and control method of an intelligent electric bed based on artificial intelligence according to claim 1 is characterized in that: The predicting the force tendency of the intelligent electric bed during use of the user according to the user posture change data, and optimizing the second configuration scheme according to the force tendency, includes: Acquiring user posture change data, including a change in pressure on the smart electric bed during the user's posture change and a change in the contact area between the user and the smart electric bed; According to the user posture change data, predict the direction of the user posture change to determine the corresponding force tendency of the bed, and obtain the user flip angle and flip number corresponding to the force tendency of the bed; The degree of compatibility between the second configuration scheme and the user's usage status is determined according to the flip angle and the flip times. When the degree of compatibility does not meet the preset conditions, the second configuration scheme is optimized according to the force tendency of the bed body.

4. The multi-scenario adjustment and control method of an intelligent electric bed based on artificial intelligence according to claim 1 is characterized in that: After the output scene type, it also includes: When the scene type is unattended, determine whether it is necessary to enter the fault detection mode; If so, the intelligent electric bed is diagnosed for faults, and an alarm is triggered when an abnormality is diagnosed; If not, the intelligent electric bed is controlled to automatically shut down the power or switch to energy-saving mode.

5. The multi-scenario adjustment and control method of an intelligent electric bed based on artificial intelligence according to claim 1 is characterized in that: The scene prediction model is obtained based on convolutional neural network training.

6. An artificial intelligence-based intelligent electric bed multi-scene adjustment control system, characterized in that: The system comprises: A scene type prediction unit is used to detect the user's behavior intention. When it is determined that the probability of the user reaching the location of the intelligent electric bed within a preset time period is greater than a preset value, the current time and user identity information are input into the scene prediction model to output the scene type. A configuration scheme matching unit, used to match a first configuration scheme according to a scene type, and configure the use parameters of the intelligent electric bed according to the first configuration scheme, wherein the first configuration scheme is learned based on the historical use habits of different users; A configuration scheme adjustment unit, used to detect the user's posture change data and the duration of each posture, analyze the user's usage status according to the duration, adjust the first configuration scheme according to the usage status analysis result, and generate a second configuration scheme; The adjusting the first configuration scheme according to the usage status analysis result includes: Determine the change in the carrying capacity of the smart electric bed according to the change data of the contact area between the user and the smart electric bed and the user's flip angle during the posture adjustment process; According to the changes in the load-bearing capacity of the smart electric bed, the load-bearing capacity, support angle, bed height and bed hardness of different parts of the user's body are adaptively adjusted; The optimization control unit is used to predict the force tendency of the intelligent electric bed during use according to the user's posture change data, optimize the second configuration scheme according to the force tendency, and adjust the use parameters of the intelligent electric bed according to the optimized second configuration scheme.

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes the multi-scene adjustment and control method for an intelligent electric bed based on artificial intelligence as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the artificial intelligence-based multi-scene adjustment and control method for an intelligent electric bed as described in any one of claims 1 to 5.

Images