AI smart home control system based on spatial awareness

Abstract

The invention discloses an AI smart home control system based on spatial awareness. The AI smart home control system comprises a controller, a monitoring system and a millimeter wave radar management system, the monitoring system determines a first position of the target object, determines video data of the target object at the first position, and performs behavior analysis according to the video data to obtain a target behavior; when the target behavior is a sleep behavior, the millimeter-wave radar management system determines millimeter-wave radars whose distance to the first position is smaller than a preset distance, and a millimeter-wave radars are obtained; acquiring monitoring data of a preset time period corresponding to each millimeter-wave radar in the a millimeter-wave radars to obtain a monitoring data sets; the controller determines a sleep abnormality degree value of the target object according to the a monitoring data sets; and when the sleep abnormity degree value is greater than a preset threshold value, performing alarm operation. According to the embodiment of the invention, abnormal sleep monitoring can be carried out on the elderly, so that the old-age care monitoring quality is ensured.

Description

Technical Field

[0001] The present application relates to the field of smart home technology or the field of Internet technology, and specifically to an AI smart home control system based on spatial perception. Background Art

[0002] With the development of the aging trend, elderly care has become a focus of social attention, especially for the elderly who are alone. Once they encounter abnormal breathing during sleep, if they are not monitored in the first time, the consequences will be disastrous. Therefore, how to monitor the abnormal sleep of the elderly to ensure the quality of elderly care needs to be solved urgently. Summary of the invention

[0003] The embodiment of the present application provides an AI smart home control system based on spatial perception, which can monitor the abnormal sleep of the elderly to ensure the quality of elderly care.

[0004] The embodiment of the present application provides an AI smart home control system based on space perception, and the AI ​​smart home control system based on space perception includes: a controller, a monitoring system and a millimeter wave radar management system, and the millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1; wherein,

[0005] The monitoring system is used to determine a first position of a target object, determine video data of the target object at the first position, and perform behavior analysis based on the video data to obtain a target behavior;

[0006] The millimeter-wave radar management system is used to determine, when the target behavior is a sleeping behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance, to obtain a millimeter-wave radars, where a is a positive integer less than or equal to k;

[0007] Acquire monitoring data of a preset time period corresponding to each of the a millimeter-wave radars to obtain a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data, and heart rate data;

[0008] The controller is used to determine the sleep abnormality level value of the target object according to the a monitoring data sets; when the sleep abnormality level value is greater than a preset threshold, perform an alarm operation.

[0009] The implementation of the embodiments of the present application has the following beneficial effects:

[0010] It can be seen that the AI ​​smart home control system based on spatial perception described in the embodiment of the present application includes: a controller, a monitoring system and a millimeter-wave radar management system. The millimeter-wave radar management system includes k millimeter-wave radars, each millimeter-wave radar corresponds to a position, k is an integer greater than 1, the monitoring system determines the first position of the target object, determines the video data of the target object at the first position, performs behavior analysis based on the video data, and obtains the target behavior. When the target behavior is sleep behavior, the millimeter-wave radar management system determines the millimeter-wave radar whose distance from the first position is less than a preset distance, obtains a millimeter-wave radars, a is a positive integer less than or equal to k, obtains the monitoring data of the preset time period corresponding to each of the a millimeter-wave radars, and obtains a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data data, heart rate data, the controller determines the sleep abnormality value of the target object according to a monitoring data set; when the sleep abnormality value is greater than a preset threshold, an alarm operation is performed. First, the target object can be tracked and identified by video, and the first position of the target object and the video data of the target object at the first position can be determined. Behavior analysis is performed according to the video data to obtain the target behavior. Second, when the target behavior is sleep behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance can be determined, and a millimeter-wave radar is obtained. The accuracy of millimeter-wave radar data collection can be guaranteed, and the accuracy of subsequent sleep abnormality detection can be guaranteed. Third, when the sleep abnormality value is greater than the preset threshold, it means that an abnormality occurs during the sleep process of the elderly, and an alarm operation can be performed. The alarm operation is performed at the first time, thereby ensuring the safety of the elderly. Furthermore, the elderly can be monitored for sleep abnormalities to ensure the quality of elderly care. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 It is a structural diagram of an AI smart home control system based on space perception provided in an embodiment of the present application;

[0013] Figure 2 It is a flowchart of an AI smart home control method based on space perception provided in an embodiment of the present application;

[0014] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] 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. 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0017] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0018] The embodiments of the present application are described in detail below.

[0019] See also Figure 1 , Figure 1 is a structural diagram of an AI intelligent control system based on space perception provided by an embodiment of the present application. As shown in the figure, the AI ​​intelligent control system based on space perception includes: a controller, a monitoring system and a millimeter wave radar management system. The millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1; wherein,

[0020] The monitoring system is used to determine a first position of a target object, determine video data of the target object at the first position, and perform behavior analysis based on the video data to obtain a target behavior;

[0021] The millimeter-wave radar management system is used to determine, when the target behavior is a sleeping behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance, to obtain a millimeter-wave radars, where a is a positive integer less than or equal to k;

[0022] Acquire monitoring data of a preset time period corresponding to each of the a millimeter-wave radars to obtain a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data, and heart rate data;

[0023] The controller is used to determine the sleep abnormality level value of the target object according to the a monitoring data sets; when the sleep abnormality level value is greater than a preset threshold, perform an alarm operation.

[0024] In a specific implementation, the target object may be an elderly person, and the elderly person may refer to a specific object, or may refer to a person older than a preset age, and the preset age may be preset or set by the system by default. For example, the specific object may be preset by the user or set by the system by default. For example, an AI smart home control system based on spatial perception may record an image of a specific object to register the specific object.

[0025] The AI ​​smart home control system based on spatial perception may include a controller, a monitoring system and a millimeter wave radar management system. The millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1. The monitoring system may include multiple cameras, and the multiple cameras may be distributed in various spaces of the AI ​​smart home control system based on spatial perception, and each camera may correspond to a position. The controller, the monitoring system and the millimeter wave radar management system are connected in communication.

[0026] Among them, the monitoring system can determine the first position of the target object, for example, it can track and identify the target object through video, and determine the first position of the target object. Then, the video data of the target object at the first position can be determined, and behavior analysis can be performed based on the video data to obtain the target behavior. Specifically, the video data can be segmented to obtain a related image of the target object, and features can be extracted from the related image to obtain related features. Behavior recognition can be performed based on the related features to obtain the target behavior. The related features can include at least one of the following: feature points, feature behaviors, feature vectors, feature values, feature patterns, etc., which are not limited here. The related features can include features of at least one part of the target object, and the part can include at least one of the following: eyes, face, nose, arms, legs, stomach, etc., which are not limited here.

[0027] The preset distance may be preset or set by the system by default. The preset time period may be preset or set by the system by default. For example, the preset time period may be a time period before the sleep behavior is identified, or the preset time period may be a time period before the current moment.

[0028] Next, when the target behavior is sleeping behavior, the millimeter-wave radar management system can also determine the millimeter-wave radars whose distance from the first position is less than a preset distance, and obtain a millimeter-wave radars, where a is a positive integer less than or equal to k. Since the greater the distance, the greater the corresponding delay and interference, therefore, if the distance from the first position is less than the preset distance, the accuracy of millimeter-wave radar data collection can be guaranteed, and the accuracy of subsequent sleep abnormality detection can be guaranteed.

[0029] Among them, the monitoring data of the millimeter wave radar includes at least one of the following: breathing data, blood pressure data, blood oxygen data, heart rate data, etc., which are not limited here.

[0030] Furthermore, the millimeter-wave radar management system can obtain monitoring data of a preset time period corresponding to each of a millimeter-wave radars to obtain a monitoring data set, each monitoring data set can include at least one monitoring data, and each type of monitoring data can include at least one monitoring data.

[0031] The preset threshold value may be preset or set by system default.

[0032] In a specific implementation, the controller can be used to determine the sleep abnormality value of the target object according to a monitoring data set. When the sleep abnormality value is greater than a preset threshold, it means that the elderly person has an abnormality during sleep, and the abnormality may include at least one of the following: shortness of breath, myocardial infarction, heart failure, etc., which are not limited here. Then, an alarm operation can be performed, thereby performing an alarm operation in the first place, thereby ensuring the safety of the elderly person.

[0033] The alarm operation may include at least one of the following: vibration prompt, voice prompt, calling relevant personnel or reporting to the police, etc., which are not limited here.

[0034] Optionally, the controller is further specifically used for:

[0035] Obtain target underlying disease information of the target subject;

[0036] Determine the preset threshold corresponding to the target underlying disease information.

[0037] In the specific implementation, the mapping relationship between the preset basic disease information and the threshold can be pre-stored, and then the target basic disease information of the target object can be obtained, and then the preset threshold corresponding to the target basic disease information can be determined based on the mapping relationship. In this way, the corresponding threshold can be adapted based on the actual basic disease condition of the elderly, which helps to improve the accuracy of the alarm and also helps to improve the efficiency of elderly care.

[0038] Optionally, in determining the sleep abnormality level value of the target object according to the a monitoring data sets, the controller is specifically configured to:

[0039] Determine a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each monitoring data set in the a monitoring data sets, to obtain a first fitting straight lines and a first fitting curve segments;

[0040] Obtaining the absolute values ​​of the slopes of the a first fitting straight lines to obtain a absolute values;

[0041] Determine the abnormality degree value corresponding to each absolute value of the a absolute values ​​to obtain a abnormality degree values;

[0042] Determine the distances between the a millimeter-wave radars and the first position to obtain a first distances;

[0043] Determine the extreme value of each of the a first fitting curve segments to obtain a extreme value sets;

[0044] Determine the standard deviations corresponding to the a extreme value sets to obtain a standard deviations;

[0045] Determine corresponding weights according to the a first distances and the a standard deviations to obtain a weights;

[0046] A weighted operation is performed based on the a abnormality degree values ​​and the a weight values ​​to obtain the sleep abnormality degree value.

[0047] In a specific implementation, since the monitoring data set may include multiple monitoring data, each monitoring data corresponds to a collection time, and thus, the multiple monitoring data and their corresponding collection times may be regarded as multiple coordinate points, which are mapped to a coordinate system, in which the horizontal axis of the coordinate point is time and the vertical axis is the monitoring data. Then, fitting may be performed based on the multiple coordinate points to determine the corresponding first fitting straight line and the first fitting curve segment corresponding to the preset time period, and thus a first fitting straight lines and a first fitting curve segments may be obtained.

[0048] Among them, the slopes of a first fitting straight line are obtained, and then the absolute values ​​of the corresponding slopes are taken to obtain a absolute values, and the absolute values ​​reflect the degree of abnormal change. Then, the abnormality degree value corresponding to each absolute value in the a absolute values ​​is determined to obtain a abnormality degree values. Specifically, the mapping relationship between the preset absolute value and the abnormality degree value can be pre-stored, and then, the abnormality degree value corresponding to each absolute value in the a absolute values ​​can be determined based on the mapping relationship to obtain a abnormality degree values.

[0049] Next, the distances between a millimeter-wave radars and the first position can be determined to obtain a first distances. Different distances result in different interference to the millimeter-wave radars, and the credibility of the corresponding sleep abnormality degree values ​​is different. Therefore, the extreme values ​​of each of the a first fitting curve segments can be determined to obtain a extreme value sets. Each extreme value set can include multiple extreme values, and the multiple extreme values ​​can include maximum values ​​and minimum values.

[0050] Furthermore, a standard deviation operation can be performed on each extreme value set in the a extreme value sets to obtain a standard deviations. The standard deviation reflects the volatility of the degree of abnormal sleep and also reflects the credibility of the value of the degree of abnormal sleep.

[0051] Next, the corresponding weights are determined according to a first distances and a standard deviations to obtain a weights. That is, on the one hand, at different distances, the interference to the millimeter-wave radar is different, and the credibility of the corresponding sleep abnormality degree value is different. On the other hand, the standard deviation reflects the volatility of the sleep abnormality degree and also reflects the credibility of the sleep abnormality degree value. Then, the distance and standard deviation can be used to deeply optimize the weights so that the weight depth conforms to the actual situation. Finally, a weighted operation can be performed based on a abnormality degree values ​​and a weights to obtain the sleep abnormality degree value, which helps to ensure accurate assessment of the sleep abnormality degree value and then achieve accurate alarm, that is, the sleep abnormality of the elderly can be monitored to ensure the quality of elderly care.

[0052] Optionally, each monitoring data set includes multiple monitoring data; determining a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each monitoring data set in the a monitoring data sets to obtain a first fitting straight lines and a first fitting curve segments includes:

[0053] Determine each type of monitoring data in the second monitoring data set to be fitted, and obtain a plurality of fitting straight lines and a plurality of fitting curve segments;

[0054] Acquiring target physical condition data of the target object;

[0055] determining a plurality of weights corresponding to the target physical condition data;

[0056] Determine a first fitting straight line corresponding to the second monitoring data set according to the multiple weights and the multiple fitting straight lines;

[0057] A first fitting curve segment corresponding to the second monitoring data set is determined according to the multiple weights and the multiple fitting curve segments.

[0058] Among them, each monitoring data set includes multiple monitoring data, each monitoring data corresponds to a data type, and the data type may include at least one of the following: respiratory data type, blood pressure data type, blood oxygen data type, heart rate data type, etc., which are not limited here.

[0059] In a specific implementation, when there are multiple monitoring data, each type of monitoring data in the second monitoring data set can be fitted to obtain multiple fitting straight lines and multiple fitting curve segments, and each type of monitoring data corresponds to a fitting straight line and a fitting curve segment.

[0060] Next, the target physical condition data of the target object can also be obtained. The weights of the monitoring data of each dimension corresponding to different physical condition data are different. Then, the mapping relationship between the preset physical condition data and the weight set can be pre-stored, and then the target weight set corresponding to the target physical condition data can be determined based on the mapping relationship. The target weight set includes multiple weights, and the sum of the multiple weights is 1. These fitting straight lines are superimposed according to the multiple weights and multiple fitting straight lines to obtain the first fitting straight line corresponding to the second monitoring data set. Correspondingly, multiple weights and multiple fitting curve segments can also be superimposed to obtain the first fitting curve segment corresponding to the second monitoring data set. In this way, based on the physical condition data of the elderly, the fitting conditions of multiple dimensions can be deeply integrated to obtain accurate fitting results.

[0061] Optionally, in the aspect of determining corresponding weights according to the a first distances and the a standard deviations to obtain a weights, the controller is specifically configured to:

[0062] Determine a weight corresponding to each of the a first distances to obtain a first weights;

[0063] Determine the optimization parameters corresponding to the a standard deviations to obtain a optimization parameters;

[0064] The a first weights are optimized according to the a optimization parameters to obtain the a weights.

[0065] In a specific implementation, a mapping relationship between a preset distance and a weight can be pre-stored, and then, a weight corresponding to each of a first distances can be determined based on the mapping relationship to obtain a first weight. Then, a mapping relationship between a preset standard deviation and an optimization parameter can be pre-stored, and then, an optimization parameter corresponding to each of a standard deviations can be determined based on the mapping relationship to obtain a optimization parameters. Then, the corresponding first weight in a first weights is optimized according to the a optimization parameters to obtain a weight. Specifically, the optimized weight = (1 + optimization parameter) * first weight. On the one hand, at different distances, the interference to the millimeter-wave radar is different, and the credibility of the corresponding sleep abnormality degree value is different. On the other hand, the standard deviation reflects the volatility of the sleep abnormality degree and also reflects the credibility of the sleep abnormality degree value. Then, the distance and standard deviation can be used to deeply optimize the weight so that the weight depth conforms to the actual situation, thereby helping to ensure accurate assessment of the sleep abnormality degree value, and then, to achieve accurate alarm, that is, the sleep abnormality monitoring of the elderly can be performed to ensure the quality of elderly care.

[0066] Optionally, each of the k millimeter-wave radars corresponds to an environmental sensor; and in determining the a weights according to the a second distances, the controller is specifically configured to:

[0067] Optimizing the a first weights according to the a optimization parameters to obtain a second weights;

[0068] Acquire environmental parameters of environmental sensors corresponding to the a millimeter-wave radars to obtain a environmental parameters;

[0069] Determine a fine-tuning parameter corresponding to each of the a environmental parameters to obtain a fine-tuning parameters;

[0070] Corresponding second weights among the a second weights are fine-tuned according to the a fine-tuning parameters to obtain the a weights.

[0071] In a specific implementation, each of the k millimeter-wave radars corresponds to an environmental sensor. The environmental sensor can be integrated with the corresponding millimeter-wave radar. The environmental sensor can be used to detect environmental parameters. The environmental parameters may include at least one of the following: ambient brightness, ambient humidity, ambient temperature, magnetic field interference intensity, ambient noise, etc., which are not limited here.

[0072] In a specific implementation, a first weights may be optimized according to a optimization parameters to obtain a second weights, that is, second weight = (1 + optimization parameter) * first weight.

[0073] Furthermore, the environmental parameters of the environmental sensors corresponding to a millimeter-wave radars can be obtained to obtain a environmental parameters. The mapping relationship between the preset environmental parameters and the fine-tuning parameters can also be pre-stored. Then, the fine-tuning parameters corresponding to each of the a environmental parameters can be determined based on the mapping relationship to obtain a fine-tuning parameters. Then, the corresponding second weights in the a second weights are fine-tuned according to the a fine-tuning parameters to obtain a weights, that is, the optimized weight = (1 + fine-tuning parameter) * second weight. Not only the different distances, but also the different interferences to the millimeter-wave radars, the corresponding credibility of the abnormal sleep degree values ​​is different. The standard deviation reflects the volatility of the abnormal sleep degree and also reflects the credibility of the abnormal sleep degree value. Then, the weights are deeply optimized by using the distance and standard deviation, and the environmental impact is taken into consideration to further optimize the weights so that the weight depth conforms to the actual situation, thereby helping to ensure accurate assessment of the abnormal sleep degree value, and then, to achieve accurate alarm, that is, the abnormal sleep of the elderly can be monitored to ensure the quality of elderly care.

[0074] Optionally, the above step of determining the first fitting straight line and the first fitting curve segment corresponding to the preset time period according to each monitoring data set in the a monitoring data sets to obtain a first fitting straight lines and a first fitting curve segments may include the following steps:

[0075] Determine a target distance between a first millimeter-wave radar and the first position; the first millimeter-wave radar is a millimeter-wave radar corresponding to a first monitoring data set; the first monitoring data set is any monitoring data set among the a monitoring data sets;

[0076] Determining a first magnetic field interference parameter of the first millimeter-wave radar;

[0077] Determining first attribute information of the first millimeter-wave radar;

[0078] Determining a first noise reduction algorithm corresponding to the first magnetic field interference parameter;

[0079] Determining a first algorithm parameter of the first noise reduction algorithm corresponding to the first attribute information;

[0080] determining a first feedback adjustment parameter corresponding to the target distance;

[0081] Performing feedback adjustment on the first algorithm parameter according to the first feedback adjustment parameter to obtain a second algorithm parameter;

[0082] Performing denoising processing on the first monitoring data set according to the first denoising algorithm and the second algorithm parameters to obtain a target first monitoring data set;

[0083] A first fitting straight line and a first fitting curve segment corresponding to the first millimeter-wave radar are determined according to the target first monitoring data set.

[0084] In a specific implementation, the first millimeter wave radar is a millimeter wave radar corresponding to the first monitoring data set, and the first monitoring data set is any monitoring data set among the a monitoring data sets. The target distance between the first millimeter wave radar and the first position can be determined, and the first magnetic field interference parameter of the first millimeter wave radar can also be determined.

[0085] In a specific implementation, the first attribute information of the first millimeter wave radar may be determined. The first attribute information may include at least one of the following: the model of the first millimeter wave radar, the hardware parameters of the first millimeter wave radar, the software parameters of the first millimeter wave radar, the manufacturer of the first millimeter wave radar, the accuracy of the first millimeter wave radar, the anti-interference performance of the first millimeter wave radar, etc., which are not limited here, and the first attribute information reflects the performance of the first millimeter wave radar.

[0086] Furthermore, a mapping relationship between preset magnetic field interference parameters and noise reduction algorithms can be pre-stored, and then, a first noise reduction algorithm corresponding to the first magnetic field interference parameters can be determined based on the mapping relationship, so that a noise reduction algorithm adapted to the environmental magnetic field interference can be obtained. The mapping relationship between the preset millimeter-wave radar attribute information and the algorithm parameters of the first noise reduction algorithm can also be pre-stored. The algorithm parameters are used to control the noise reduction effect of the first noise reduction algorithm. The noise reduction effect may include at least one of the following: noise reduction speed, noise reduction degree, noise reduction area, etc., which are not limited here. Furthermore, the first algorithm parameters of the first noise reduction algorithm corresponding to the first attribute information can be determined based on the mapping relationship.

[0087] Next, the mapping relationship between the preset distance and the feedback adjustment parameter can be pre-stored, and then the first feedback adjustment parameter corresponding to the target distance can be determined based on the mapping relationship, and then the first algorithm parameter is feedback-adjusted according to the first feedback adjustment parameter to obtain the second algorithm parameter, that is, the second algorithm parameter = (1 + first feedback adjustment parameter) * first algorithm parameter. The distance reflects the degree of masking of the content of the information itself by noise to a certain extent. The greater the distance, the greater the degree of masking, and vice versa. The first monitoring data set is denoised according to the first noise reduction algorithm and the second algorithm parameter to obtain the target first monitoring data set, and the first fitting straight line and the first fitting curve segment corresponding to the first millimeter-wave radar are determined according to the target first monitoring data set. In this way, the algorithm parameters can be feedback-adjusted again based on the depth of the degree of masking of the content of the information itself by noise, so as to further ensure the deep noise reduction of the noise reduction algorithm, thereby deeply ensuring the noise reduction performance, which helps to improve the accuracy of the monitoring data of the millimeter-wave radar.

[0088] It can be seen that the AI ​​smart home control system based on spatial perception described in the embodiment of the present application includes: a controller, a monitoring system and a millimeter-wave radar management system. The millimeter-wave radar management system includes k millimeter-wave radars, each millimeter-wave radar corresponds to a position, k is an integer greater than 1, the monitoring system determines the first position of the target object, determines the video data of the target object at the first position, performs behavior analysis based on the video data, and obtains the target behavior. When the target behavior is sleep behavior, the millimeter-wave radar management system determines the millimeter-wave radar whose distance from the first position is less than a preset distance, obtains a millimeter-wave radars, a is a positive integer less than or equal to k, obtains the monitoring data of the preset time period corresponding to each of the a millimeter-wave radars, and obtains a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data data, heart rate data, the controller determines the sleep abnormality value of the target object according to a monitoring data set; when the sleep abnormality value is greater than a preset threshold, an alarm operation is performed. First, the target object can be tracked and identified by video, and the first position of the target object and the video data of the target object at the first position can be determined. Behavior analysis is performed according to the video data to obtain the target behavior. Second, when the target behavior is sleep behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance can be determined, and a millimeter-wave radar is obtained. The accuracy of millimeter-wave radar data collection can be guaranteed, and the accuracy of subsequent sleep abnormality detection can be guaranteed. Third, when the sleep abnormality value is greater than the preset threshold, it means that an abnormality occurs during the sleep process of the elderly, and an alarm operation can be performed. The alarm operation is performed at the first time, thereby ensuring the safety of the elderly. Furthermore, the elderly can be monitored for sleep abnormalities to ensure the quality of elderly care.

[0089] See also Figure 2 , Figure 2 It is a flow chart of an AI smart home control method based on space perception provided in an embodiment of the present application, which is applied to an AI smart home control system based on space perception. The AI ​​smart home control system based on space perception includes: a controller, a monitoring system and a millimeter wave radar management system. The millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1; the AI ​​smart home control method based on space perception includes:

[0090] 201. Determine a first position of a target object, determine video data of the target object at the first position, and perform behavior analysis based on the video data to obtain a target behavior.

[0091] 202. When the target behavior is sleeping behavior, determine a millimeter-wave radar whose distance from the first position is less than a preset distance, and obtain a millimeter-wave radars, where a is a positive integer less than or equal to k.

[0092] 203. Acquire monitoring data of a preset time period corresponding to each of the a millimeter-wave radars to obtain a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data, and heart rate data.

[0093] 204. Determine a sleep abnormality level of the target object according to the a monitoring data sets; and perform an alarm operation when the sleep abnormality level is greater than a preset threshold.

[0094] The specific description of the above steps 201 to 204 can refer to the above Figure 1 The relevant description in will not be repeated here.

[0095] It can be seen that the AI ​​smart home control method based on space perception described in the embodiment of the present application is based on the AI ​​smart home control system based on space perception. The AI ​​smart home control system based on space perception includes: a controller, a monitoring system and a millimeter wave radar management system. The millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, k is an integer greater than 1, the monitoring system determines the first position of the target object, determines the video data of the target object at the first position, performs behavior analysis based on the video data, and obtains the target behavior. When the target behavior is sleeping behavior, the millimeter wave radar management system determines the millimeter wave radar whose distance from the first position is less than the preset distance, obtains a millimeter wave radars, a is a positive integer less than or equal to k, obtains the monitoring data of the preset time period corresponding to each millimeter wave radar in the a millimeter wave radars, and obtains a monitoring data set; the monitoring data includes at least one of the following: call breathing data, blood pressure data, blood oxygen data, and heart rate data. The controller determines the sleep abnormality level of the target object based on a monitoring data set; when the sleep abnormality level is greater than a preset threshold, an alarm operation is performed. First, the target object can be tracked and identified by video, and the first position of the target object and the video data of the target object at the first position can be determined. Behavior analysis is performed based on the video data to obtain the target behavior. Second, when the target behavior is sleep behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance can be determined, and a millimeter-wave radar can be obtained. The accuracy of millimeter-wave radar data collection can be guaranteed, and the accuracy of subsequent sleep abnormality detection can be guaranteed. Third, when the sleep abnormality level is greater than the preset threshold, it means that an abnormality occurs during the sleep process of the elderly, and an alarm operation can be performed at the first time, thereby ensuring the safety of the elderly. Furthermore, the elderly can be monitored for sleep abnormalities to ensure the quality of elderly care.

[0096] In accordance with the above embodiment, please refer to Figure 3 , Figure 3 : is a structural schematic diagram of an electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. In the embodiment of the present application, the electronic device is applied to an AI smart home control system based on spatial perception. The AI ​​smart home control system based on spatial perception includes: a controller, a monitoring system and a millimeter wave radar management system. The millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1; the program includes instructions for executing the following steps:

[0097] Determine a first position of a target object, determine video data of the target object at the first position, and perform behavior analysis based on the video data to obtain a target behavior;

[0098] When the target behavior is a sleeping behavior, determine a millimeter-wave radar whose distance from the first position is less than a preset distance, and obtain a millimeter-wave radars, where a is a positive integer less than or equal to k;

[0099] Acquire monitoring data of a preset time period corresponding to each of the a millimeter-wave radars to obtain a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data, and heart rate data;

[0100] Determine the sleep abnormality level of the target object according to the a monitoring data sets; and perform an alarm operation when the sleep abnormality level is greater than a preset threshold.

[0101] Optionally, in determining the sleep abnormality level of the target object according to the a monitoring data sets, the program includes instructions for executing the following steps:

[0102] Determine a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each monitoring data set in the a monitoring data sets, to obtain a first fitting straight lines and a first fitting curve segments;

[0103] Obtaining the absolute values ​​of the slopes of the a first fitting straight lines to obtain a absolute values;

[0104] Determine the abnormality degree value corresponding to each absolute value of the a absolute values ​​to obtain a abnormality degree values;

[0105] Determine the distances between the a millimeter-wave radars and the first position to obtain a first distances;

[0106] Determine the extreme value of each of the a first fitting curve segments to obtain a extreme value sets;

[0107] Determine the standard deviations corresponding to the a extreme value sets to obtain a standard deviations;

[0108] Determine corresponding weights according to the a first distances and the a standard deviations to obtain a weights;

[0109] A weighted operation is performed based on the a abnormality degree values ​​and the a weight values ​​to obtain the sleep abnormality degree value.

[0110] Optionally, in the aspect of determining corresponding weights according to the a first distances and the a standard deviations to obtain a weights, the program includes instructions for executing the following steps:

[0111] Determine a weight corresponding to each of the a first distances to obtain a first weights;

[0112] Determine the optimization parameters corresponding to the a standard deviations to obtain a optimization parameters;

[0113] The a first weights are optimized according to the a optimization parameters to obtain the a weights.

[0114] Optionally, each of the k millimeter-wave radars corresponds to an environmental sensor; in terms of optimizing the a first weights according to the a optimization parameters to obtain the a weights, the program includes instructions for performing the following steps:

[0115] Optimizing the a first weights according to the a optimization parameters to obtain a second weights;

[0116] Acquire environmental parameters of environmental sensors corresponding to the a millimeter-wave radars to obtain a environmental parameters;

[0117] Determine a fine-tuning parameter corresponding to each of the a environmental parameters to obtain a fine-tuning parameters;

[0118] Corresponding second weights among the a second weights are fine-tuned according to the a fine-tuning parameters to obtain the a weights.

[0119] Optionally, the program further includes instructions for executing the following steps:

[0120] Obtain target underlying disease information of the target subject;

[0121] Determine the preset threshold corresponding to the target underlying disease information.

[0122] Optionally, in the aspect of determining a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each of the a monitoring data sets to obtain a first fitting straight lines and a first fitting curve segments, the program includes instructions for executing the following steps:

[0123] Determine a target distance between a first millimeter-wave radar and the first position; the first millimeter-wave radar is a millimeter-wave radar corresponding to a first monitoring data set; the first monitoring data set is any monitoring data set among the a monitoring data sets;

[0124] Determining a first magnetic field interference parameter of the first millimeter-wave radar;

[0125] Determining first attribute information of the first millimeter-wave radar;

[0126] Determining a first noise reduction algorithm corresponding to the first magnetic field interference parameter;

[0127] Determining a first algorithm parameter of the first noise reduction algorithm corresponding to the first attribute information;

[0128] determining a first feedback adjustment parameter corresponding to the target distance;

[0129] Performing feedback adjustment on the first algorithm parameter according to the first feedback adjustment parameter to obtain a second algorithm parameter;

[0130] Performing denoising processing on the first monitoring data set according to the first denoising algorithm and the second algorithm parameters to obtain a target first monitoring data set;

[0131] A first fitting straight line and a first fitting curve segment corresponding to the first millimeter-wave radar are determined according to the target first monitoring data set.

[0132] It can be seen that the electronic device described in the embodiment of the present application is applied to an AI smart home control system based on spatial perception. The AI ​​smart home control system based on spatial perception includes: a controller, a monitoring system and a millimeter-wave radar management system. The millimeter-wave radar management system includes k millimeter-wave radars, each millimeter-wave radar corresponds to a position, k is an integer greater than 1, the monitoring system determines the first position of the target object, determines the video data of the target object at the first position, performs behavior analysis based on the video data, and obtains the target behavior. When the target behavior is sleep behavior, the millimeter-wave radar management system determines the millimeter-wave radar whose distance from the first position is less than a preset distance, obtains a millimeter-wave radars, a is a positive integer less than or equal to k, obtains monitoring data of a preset time period corresponding to each of the a millimeter-wave radars, and obtains a monitoring data set; the monitoring data includes at least one of the following: breathing data, Blood pressure data, blood oxygen data, heart rate data, the controller determines the sleep abnormality level of the target object based on a monitoring data set; when the sleep abnormality level is greater than a preset threshold, an alarm operation is performed. First, the target object can be tracked and identified through video, and the first position of the target object and the video data of the target object at the first position can be determined. Behavior analysis is performed based on the video data to obtain the target behavior. Second, when the target behavior is sleep behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance can be determined, and a millimeter-wave radar can be obtained. The accuracy of millimeter-wave radar data collection can be guaranteed, and the accuracy of subsequent sleep abnormality detection can be guaranteed. Third, when the sleep abnormality level is greater than the preset threshold, it means that an abnormality has occurred during the sleep process of the elderly, and an alarm operation can be performed at the first time, thereby ensuring the safety of the elderly. Furthermore, the elderly can be monitored for sleep abnormalities to ensure the quality of elderly care.

[0133] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0134] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0135] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0136] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] In the several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0138] The units described as separate components above may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0140] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0141] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0142] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An AI smart home control system based on space perception, characterized in that: The AI ​​smart home control system based on spatial perception includes: a controller, a monitoring system and a millimeter wave radar management system, wherein the millimeter wave radar management system includes k millimeter wave radars, each millimeter wave radar corresponds to a position, and k is an integer greater than 1; wherein, The monitoring system is used to determine a first position of a target object, determine video data of the target object at the first position, and perform behavior analysis based on the video data to obtain a target behavior; The millimeter-wave radar management system is used to determine, when the target behavior is a sleeping behavior, a millimeter-wave radar whose distance from the first position is less than a preset distance, to obtain a millimeter-wave radars, where a is a positive integer less than or equal to k; Acquire monitoring data of a preset time period corresponding to each of the a millimeter-wave radars to obtain a monitoring data set; the monitoring data includes at least one of the following: respiratory data, blood pressure data, blood oxygen data, and heart rate data; The controller is used to determine the sleep abnormality level value of the target object according to the a monitoring data sets; when the sleep abnormality level value is greater than a preset threshold, perform an alarm operation.

2. The AI ​​smart home control system based on spatial perception according to claim 1 is characterized in that: In determining the sleep abnormality level of the target object according to the a monitoring data sets, the controller is specifically used to: Determine a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each monitoring data set in the a monitoring data sets, to obtain a first fitting straight lines and a first fitting curve segments; Obtaining the absolute values ​​of the slopes of the a first fitting straight lines to obtain a absolute values; Determine the abnormality degree value corresponding to each absolute value of the a absolute values ​​to obtain a abnormality degree values; Determine the distances between the a millimeter-wave radars and the first position to obtain a first distances; Determine the extreme value of each of the a first fitting curve segments to obtain a extreme value sets; Determine the standard deviations corresponding to the a extreme value sets to obtain a standard deviations; Determine corresponding weights according to the a first distances and the a standard deviations to obtain a weights; A weighted operation is performed based on the a abnormality degree values ​​and the a weight values ​​to obtain the sleep abnormality degree value.

3. The AI ​​smart home control system based on spatial perception according to claim 2 is characterized in that: In the aspect of determining corresponding weights according to the a first distances and the a standard deviations to obtain a weights, the controller is specifically used to: Determine a weight corresponding to each of the a first distances to obtain a first weights; Determine the optimization parameters corresponding to the a standard deviations to obtain a optimization parameters; The a first weights are optimized according to the a optimization parameters to obtain the a weights.

4. The AI ​​smart home control system based on space perception according to claim 3 is characterized in that: Each of the k millimeter-wave radars corresponds to an environmental sensor; in terms of optimizing the a first weights according to the a optimization parameters to obtain the a weights, the controller is specifically used to: Optimizing the a first weights according to the a optimization parameters to obtain a second weights; Acquire environmental parameters of environmental sensors corresponding to the a millimeter-wave radars to obtain a environmental parameters; Determine a fine-tuning parameter corresponding to each of the a environmental parameters to obtain a fine-tuning parameters; Corresponding second weights among the a second weights are fine-tuned according to the a fine-tuning parameters to obtain the a weights.

5. The AI ​​smart home control system based on space perception according to any one of claims 1 to 4, characterized in that: The controller is also specifically used for: Obtain target underlying disease information of the target subject; Determine the preset threshold corresponding to the target underlying disease information.

6. The AI ​​smart home control system based on space perception according to any one of claims 2 to 4, characterized in that: The step of determining a first fitting straight line and a first fitting curve segment corresponding to the preset time period according to each of the a monitoring data sets to obtain a first fitting straight lines and a first fitting curve segments includes: Determine a target distance between a first millimeter-wave radar and the first position; the first millimeter-wave radar is a millimeter-wave radar corresponding to a first monitoring data set; the first monitoring data set is any monitoring data set among the a monitoring data sets; Determining a first magnetic field interference parameter of the first millimeter-wave radar; Determining first attribute information of the first millimeter-wave radar; Determining a first noise reduction algorithm corresponding to the first magnetic field interference parameter; Determining a first algorithm parameter of the first noise reduction algorithm corresponding to the first attribute information; determining a first feedback adjustment parameter corresponding to the target distance; Performing feedback adjustment on the first algorithm parameter according to the first feedback adjustment parameter to obtain a second algorithm parameter; Performing denoising processing on the first monitoring data set according to the first denoising algorithm and the second algorithm parameters to obtain a target first monitoring data set; A first fitting straight line and a first fitting curve segment corresponding to the first millimeter-wave radar are determined according to the target first monitoring data set.

Images