Intelligent door and window control system with autonomous learning function

Abstract

The invention discloses an intelligent door and window control system with an autonomous learning function, and relates to the technical field of door and window control. The intelligent door and window control system with the autonomous learning function comprises a behavior acquisition module used for acquiring a plurality of historical opening behavior sequences and a plurality of historical closing behavior sequences of a user; the time period determination module is used for determining a habit time period of the user according to each historical opening behavior sequence and each historical closing behavior sequence; the time period monitoring module is used for monitoring the habit time periods according to the habit time periods and determining the habit keeping degree of the user in the habit time periods; and the door and window control module is used for sending a door and window control signal to control the door and window to move under the condition that the habit retention degree is not within the preset retention degree range. According to the intelligent door and window control system with the autonomous learning function, the intelligent control effect of doors and windows can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of door and window control, and in particular to an intelligent door and window control system with an autonomous learning function. Background Art

[0002] With the improvement of life concepts, the intelligent development of doors and windows in buildings is increasingly valued by residents. The development of smart doors and windows can bring residents high-quality lighting and ventilation experience, and bring beneficial effects such as energy saving, comfort, and health.

[0003] The existing intelligent door and window control system realizes automatic control of doors and windows by allowing users to pre-set the opening and closing times of doors and windows.

[0004] However, the intelligent door and window control system can only control the doors and windows through pre-set opening and closing times, and the intelligent control effect is poor. Summary of the invention

[0005] The embodiment of the present invention provides an intelligent door and window control system with an autonomous learning function, which can improve the intelligent control effect of doors and windows.

[0006] According to a first aspect of an embodiment of the present invention, there is provided an intelligent door and window control system with an autonomous learning function, comprising:

[0007] A behavior acquisition module is used to acquire multiple historical opening behavior sequences and multiple historical closing behavior sequences of the user, wherein the historical opening behavior sequence includes the number of times the user opened doors and windows in each time period in the historical period, and the historical closing behavior sequence includes the number of times the user closed doors and windows in each time period in the historical period;

[0008] A time period determination module is used to determine the user's habitual time period according to each historical opening behavior sequence and each historical closing behavior sequence. The habitual time period is a time period in which the user has regular door and window control behaviors;

[0009] The time period monitoring module is used to monitor the habit time period for each habit time period and determine the habit retention degree of the user in the habit time period. The habit retention degree is used to characterize the degree to which the user maintains the door and window control behavior in the habit time period;

[0010] The door and window control module is used to send a door and window control signal to control the movement of the door and window when the habitual retention degree is not within the preset retention degree range.

[0011] In the intelligent door and window control system with autonomous learning function provided by the embodiment of the present invention, the behavior acquisition module acquires multiple historical opening behavior sequences and multiple historical closing behavior sequences of the user, and then the time period determination module obtains the user's habitual time period by learning the user's habit of opening and closing doors and windows in the historical period. Then, the time period monitoring module monitors each habitual time period to determine whether the user breaks the habit of opening and closing doors and windows. In the case where the user breaks the habit of opening and closing doors and windows, it is determined that the user has not moved the doors and windows in time due to forgetfulness or busyness, so the door and window control module sends a door and window control signal to control the doors and windows to move automatically. In this way, the embodiment of the present invention can control the doors and windows to move automatically when the user does not move the doors and windows in time, thereby improving the intelligent control effect of doors and windows. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 A schematic diagram of the structure of an intelligent door and window control system with autonomous learning function provided by one embodiment of the present invention;

[0014] Figure 2 A schematic diagram of the structure of a time period determination module provided by an embodiment of the present invention;

[0015] Figure 3 A schematic diagram of the structure of a door and window control module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation, structure, features and effects of an intelligent door and window control system with autonomous learning function proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0019] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0020] With the improvement of life concepts, the intelligent development of doors and windows in buildings is increasingly valued by residents. The development of smart doors and windows can bring residents high-quality lighting and ventilation experience, and bring beneficial effects such as energy saving, comfort, and health.

[0021] The existing intelligent door and window control system realizes automatic control of doors and windows by users setting the opening time and closing time of doors and windows in advance. However, the intelligent door and window control system can only control doors and windows through the pre-set opening time and closing time, and the intelligent control effect is poor.

[0022] The purpose of the present invention is to provide an intelligent door and window control system with an autonomous learning function. In the intelligent door and window control system with an autonomous learning function provided by the embodiment of the present invention, the behavior acquisition module acquires multiple historical opening behavior sequences and multiple historical closing behavior sequences of the user, and then the time period determination module obtains the user's habitual time period by learning the user's opening and closing habits of doors and windows in the historical period. Then, the time period monitoring module monitors each habitual time period to determine whether the user breaks the habit of opening and closing doors and windows. In the case where the user breaks the habit of opening and closing doors and windows, it is determined that the user has not moved the doors and windows in time due to forgetfulness or busyness, so the door and window control module sends a door and window control signal to control the doors and windows to move automatically. In this way, the embodiment of the present invention can control the doors and windows to move automatically when the user does not move the doors and windows in time, thereby improving the intelligent control effect of doors and windows.

[0023] The following describes a specific embodiment of an intelligent door and window control system with autonomous learning function provided by an embodiment of the present invention.

[0024] like Figure 1 As shown, a schematic diagram of the structure of an intelligent door and window control system with autonomous learning function is provided. The intelligent door and window control system with autonomous learning function 100 comprises a behavior acquisition module 110 , a time period determination module 120 , a time period monitoring module 130 and a door and window control module 140 .

[0025] The behavior acquisition module 110 is used to obtain multiple historical opening behavior sequences and multiple historical closing behavior sequences of the user. The historical opening behavior sequence includes the number of times the user opened doors and windows in each time period during the historical period, and the historical closing behavior sequence includes the number of times the user closed doors and windows in each time period during the historical period.

[0026] In this embodiment, the historical opening behavior sequence and the historical closing behavior sequence respectively include the number of times the user opened and closed the doors and windows in each time period in the historical period. For example, the length of the historical period can be one day, and the length of the time period can be 4 hours, that is, one day is divided into 6 time periods.

[0027] As an example, the behavior acquisition module 110 records the user's daily door and window opening behavior data and door and window closing behavior data over a period of time through the door opening and closing detection sensors of the smart doors and windows.

[0028] Then, the collected door and window opening behavior data and door and window closing behavior data are grouped according to the length of the preset time period, and the number of door and window opening behaviors and the number of door and window closing behaviors in each group are counted, so as to form multiple historical opening behavior sequences and multiple historical closing behavior sequences in chronological order.

[0029] The time period determination module 120 is used to determine the user's habitual time period according to each historical opening behavior sequence and each historical closing behavior sequence. The habitual time period is a time period in which the user has regular door and window control behaviors.

[0030] In this embodiment, the habitual time period is used to characterize the time period in which the user has regular door and window control behaviors. For example, after getting up in the morning and before going to bed at night can be the habitual time period.

[0031] The door and window control behavior is used to characterize the control behavior of the door and window. For example, the door and window control behavior may include the door and window opening behavior and the door and window closing behavior.

[0032] As an example, the time period determination module 120 uses a machine learning algorithm (such as a clustering algorithm, time series analysis, etc.) to analyze the historical opening behavior sequence and the historical closing behavior sequence to identify the user's door and window control behavior patterns in different time periods.

[0033] Then, according to the result of the door and window control behavior pattern recognition, the habitual time period in which the user has regular door and window control behavior is determined.

[0034] The time period monitoring module 130 is used to monitor each habit time period and determine the user's habit maintenance degree in the habit time period. The habit maintenance degree is used to characterize the degree to which the user maintains the door and window control behavior in the habit time period.

[0035] In this embodiment, the habit retention degree is used to characterize the degree to which the user maintains the door and window control behavior in the habitual time period. For example, the greater the habit retention degree, the more the user maintains the habit of the door and window control behavior; the smaller the habit retention degree, the less the user maintains the habit of the door and window control behavior.

[0036] As an example, the time period monitoring module 130 monitors the user's door and window control behavior in real time for each habitual time period through the door opening and closing detection sensor of the smart door and window. The user's door and window control behavior data monitored in real time is compared with the historical opening behavior sequence and the historical closing behavior sequence to calculate the user's habit retention degree in the habitual time period. Specifically, this can be achieved by calculating indicators such as behavior frequency and behavior consistency.

[0037] The door and window control module 140 is used to send a door and window control signal to control the movement of the door and window when the habitual retention degree is not within the preset retention degree range.

[0038] In this embodiment, a reasonable preset retention range is set according to the desired door and window control effect, wherein the preset retention range can be adjusted according to the personalized needs of the user.

[0039] When the habit retention degree monitored in real time is not within the preset retention range, the system generates a corresponding door and window control signal. Then, the generated control signal is sent to the controller of the smart door and window, and the controller performs the corresponding door and window control operation. Specifically, when the door and window are in the open state, the door and window closing behavior is executed; when the door and window are in the closed state, the door and window opening behavior is executed.

[0040] In the intelligent door and window control system with autonomous learning function provided by the present embodiment, the behavior acquisition module acquires multiple historical opening behavior sequences and multiple historical closing behavior sequences of the user, and then the time period determination module obtains the user's habitual time period by learning the user's habit of opening and closing doors and windows in the historical period. Then, the time period monitoring module monitors each habitual time period to determine whether the user breaks the habit of opening and closing doors and windows. In the case where the user breaks the habit of opening and closing doors and windows, it is determined that the user has not moved the doors and windows in time due to forgetfulness or busyness, so the door and window control module sends a door and window control signal to control the doors and windows to move automatically. In this way, the embodiment of the present invention can control the doors and windows to move automatically when the user does not move the doors and windows in time, thereby improving the intelligent control effect of doors and windows.

[0041] As an optional embodiment, the behavior acquisition module 110 is specifically used for:

[0042] Obtain the user's historical opening behavior data and historical closing behavior data in multiple historical periods. The historical opening behavior data has a corresponding opening timestamp, and the historical closing behavior data has a corresponding closing timestamp;

[0043] For each historical period, respectively perform: based on the opening timestamp of each historical opening behavior data and the closing timestamp of each historical closing behavior data in the historical period, count the number of door and window openings and the number of door and window closings in each time period in the historical period;

[0044] For each historical period, the following are performed: sorting the number of times each door and window is opened in chronological order to obtain a historical opening behavior sequence; and sorting the number of times each door and window is closed in chronological order to obtain a historical closing behavior sequence.

[0045] In this embodiment, the behavior acquisition module 110 obtains historical opening behavior data and historical closing behavior data from the data source through an API interface, database query or file import, and cleans the collected data to remove duplicate, erroneous or invalid records.

[0046] Then, determine the length of the time period to be counted, such as every hour, every two hours, or every three hours. And divide the entire historical period into multiple continuous time periods according to the length of the time period. For each time period, according to the opening timestamp of the historical opening behavior data and the closing timestamp of the historical closing behavior data, filter out the historical opening behavior data and the historical closing behavior data within the time period respectively.

[0047] Then, the filtered historical opening behavior data and historical closing behavior data are counted to calculate the number of door and window openings and door and window closings in each time period. Specifically, the statistics can be implemented using an aggregate function (such as COUNT) in a database query or a data structure (such as a dictionary or a hash table) in a programming language.

[0048] Finally, for each historical period, the number of door and window openings and door and window closings obtained are sorted in chronological order to obtain a historical opening behavior sequence and a historical closing behavior sequence. Specifically, the sorting can be achieved using a sorting algorithm in a programming language (such as quick sort, merge sort, etc.) or an ORDER BY clause in a database query.

[0049] Through this embodiment, the historical opening behavior data and the historical closing behavior data in the historical period can be effectively counted to form a historical opening behavior sequence and a historical closing behavior sequence. This helps to accurately screen out the user's habitual time period based on the historical opening behavior sequence and the historical closing behavior sequence. In this way, the user's habitual time period can be effectively supervised, and the intelligent control effect of doors and windows can be improved.

[0050] As an optional embodiment, Figure 2 As shown, the time period determination module 120 specifically includes the following units:

[0051] The priority determination unit 121 is used to determine the user's habit priority in each time period in each historical period according to each historical opening behavior sequence and each historical closing behavior sequence. The habit priority is used to characterize the concentration of the user's door and window control behavior in the time period;

[0052] A regularity determination unit 122, for determining the habit regularity of each time period according to the habit priority of each time period of the user in each historical period, wherein the habit regularity is used to characterize the degree of regular door and window control behavior of the user;

[0053] The time period determining unit 123 is used to determine the time period corresponding to the habit regularity as the habit time period when the habit regularity is within a preset regularity range.

[0054] In this embodiment, the habit priority is used to characterize the degree of concentration of the user's door and window control behaviors in a time period. For example, if the user opens the doors and windows after getting up in the morning and closes them before going to bed at night, the habit priority of the time period after getting up in the morning and before going to bed at night is higher.

[0055] The habit regularity is used to characterize the degree to which the user has regular door and window control behaviors. For example, if the user opens the doors and windows after getting up in the morning and closes them before going to bed at night every day, the habit retention degree in the time period after getting up in the morning and before going to bed at night is relatively high.

[0056] As an example, the priority determination unit 121 calculates the total number of door and window opening behaviors and door and window closing behaviors for each time period in each historical period based on each historical opening behavior sequence and each historical closing behavior sequence. Then, a habit priority is assigned to each time period based on the total number of door and window opening behaviors and door and window closing behaviors in each time period. The habit priority can be a score obtained by normalization, and a higher score indicates a more concentrated door and window control behavior in the time period. For example, a simple count, frequency, or more complex statistical methods (such as entropy, standard deviation, etc.) can be used to calculate the habit priority.

[0057] The regularity determination unit 122 divides the habit priorities of the same time period in all historical periods into a group, and obtains the habit priority of each time period in all historical periods. Then, according to the habit priority of the time period in all historical periods, the habit regularity of each time period is calculated. The habit regularity can be measured by calculating the stability or consistency of the habit priority between different historical periods. For example, it can be evaluated using indicators such as variance, standard deviation or correlation coefficient.

[0058] The time period determination unit 123 sets a preset regularity range, and the preset regularity range is used to filter out multiple time periods with the most regular user behavior. Then, the habit regularity of each time period is compared with the preset regularity range; if the habit regularity of a time period is within the preset regularity range, the time period is determined as the user's habitual time period.

[0059] Through this embodiment, the historical opening behavior sequence and the historical closing behavior sequence are effectively analyzed, so as to accurately screen out the user's habitual time period. This is helpful for subsequent effective supervision of the user's habitual time period. When the user fails to move the doors and windows in time due to forgetfulness or busyness, the doors and windows can be controlled to move automatically, which can improve the intelligent control effect of the doors and windows.

[0060] As an optional embodiment, the priority determination unit 121 is specifically configured to:

[0061] For each historical period, perform the following steps:

[0062] Statistically process the target historical opening behavior sequence and the target historical closing behavior sequence to obtain the target door and window opening times and target door and window closing times in each time period within the target historical period, as well as the total number of door and window control behaviors within the target historical period. The target historical opening behavior sequence and the target historical closing behavior sequence are the historical opening behavior sequence and the historical closing behavior sequence corresponding to the target historical period.

[0063] The number of times each target door and window is opened, the number of times each target door and window is closed, and the total number of door and window control behaviors are used to determine the user's habit priority in each time period within the target historical period.

[0064] In this embodiment, the habit priority can be specifically determined by the following formula 1:

[0065]

[0066] In formula 1, a t,d Used to characterize the habit priority of the tth time period in the dth historical period. t It is used to represent the number of times doors and windows are opened in the tth time period in the dth historical period, gt A is used to represent the number of door and window closings in the tth time period in the dth historical period. d Used to represent the total number of door and window control behaviors in the dth historical period.

[0067] Among them, f t +g t It is used to represent the sum of the number of door and window openings and the number of door and window closings in the t-th time period in the d-th historical period, that is, the number of door and window control behaviors in the t-th time period in the d-th historical period; It is used to represent the ratio of the number of door and window control behaviors in the tth time period within the dth historical period to the total number of door and window control behaviors in the dth historical period. The larger the ratio, the more concentrated the door and window control behaviors are in this time period, and the greater the habit priority of this time period.

[0068] Through this embodiment, by analyzing the historical opening behavior sequence and the historical closing behavior sequence, the user's habit priority of each time period in each historical period can be determined. This helps to determine the habit time period according to the habit priority in the future, thereby improving the intelligent control effect of doors and windows.

[0069] As an optional embodiment, the regularity determination unit 122 is specifically configured to:

[0070] For each time period, perform the following steps:

[0071] Using the habit priorities of the target time periods in each historical period, determine the first habit priority difference of the target time periods in adjacent historical periods, where the target time period is any time period;

[0072] Using the habit priorities of the target time period in each historical period, determine the average of the first habit priorities of the target time period;

[0073] The habit regularity of the target time period is determined by using the first habit priority difference values ​​and the first habit priority mean value.

[0074] In this embodiment, the habit regularity can be specifically determined by the following formula 2:

[0075]

[0076] In formula 2, k t Used to characterize the habit regularity of the t-th time period, a t,d It is used to characterize the habit priority of the t-th time period in the d-th historical period, a t,d+1 It is used to characterize the habit priority of the tth time period within the d+1th historical period, and D is used to characterize the number of historical periods.

[0077] in, It is used to represent the mean value of the habit priority of the t-th time period in each historical period. The larger the mean value of the habit priority, the higher the overall habit priority of the t-th time period, and the greater the habit regularity of the t-th time period; It is used to represent the sum of the absolute values ​​of the habit priority differences in the t-th time period within adjacent historical periods. The larger the value, the lower the variability of the habit priority in the t-th time period, and the greater the habit regularity in the t-th time period.

[0078] Through this embodiment, according to the habit priority of each time period in each historical period, the habit regularity of each time period can be accurately determined, which is helpful to subsequently filter out the habit time period according to the habit regularity, thereby improving the intelligent control effect of doors and windows.

[0079] As an optional embodiment, the time period monitoring module 130 is specifically configured to:

[0080] Determine the average of the second habit priorities of the habit time periods by using the habit priorities of the habit time periods in the current period and the habit priorities of the habit time periods in a preset number of historical periods;

[0081] The difference between the habit priority of the habit time period in the current period and the mean of the second habit priority is taken, and the absolute value is obtained to obtain the difference of the second habit priority;

[0082] The second habit priority difference is used to determine the habit retention degree of the user in the habit time period in the current period.

[0083] In this embodiment, the habit retention degree can be specifically determined by the following formula 3:

[0084]

[0085] In formula 3, k t’ It is used to characterize the habit retention degree in the tth time period within the current period z, a t,z Used to characterize the habit priority of the t-th time period within the current period z. It is used to characterize the average value of the habit priority of the t-th time period in a preset number of historical periods. For example, the average value of the habit priority of the t-th time period in the first 10 historical periods can be calculated.

[0086] in, It is used to characterize the degree of difference between the habit priority of the tth time period in the current period and the habit priority of the tth time period in the historical period. The larger the value, the greater the difference between the habit priority of the tth time period in the current period and the habit priority of the tth time period in the historical period, and the smaller the habit retention degree.

[0087] Through this embodiment, the habit time period is monitored, and the degree of habit maintenance of the user in the habit time period can be accurately determined, so as to judge whether the user breaks the habit of opening and closing doors and windows. This helps to control the doors and windows to move automatically when the user fails to move the doors and windows in time due to forgetfulness or busyness, and can improve the intelligent control effect of doors and windows.

[0088] As an alternative embodiment, see Figure 3 The door and window control module 140 shown specifically includes the following units:

[0089] The environment acquisition unit 141 is used to acquire the environment parameter sequence from the most recent door and window movement moment to the current moment when the habit retention degree is not within the preset retention degree range;

[0090] An environment analysis unit 142 is used to determine the environment jump value of the habitual time period according to the environment parameter sequence;

[0091] The door and window control unit 143 is used to send a door and window control signal to control the movement of the door and window when the environment jump value in the customary time period is within a preset abnormal range.

[0092] In this embodiment, the environmental parameter sequence includes indoor environmental parameters at multiple moments. For example, the environmental parameter may include at least one of a temperature value and a humidity value.

[0093] The environment jump value is used to characterize the degree of abnormal change of the indoor environment. For example, in the customary time period when the doors and windows should be closed, the user does not close the doors and windows, and the degree of abnormal change of the indoor environment is relatively large.

[0094] As an example, when it is detected that the habit retention degree of the habit time period is not within the preset retention degree range, the environment acquisition unit 141 acquires the environment parameter data from the last door or window movement to the current moment through the environment sensor, thereby forming an environment parameter sequence.

[0095] Then, the environment analysis unit 142 analyzes the environment parameter sequence and calculates the environment jump value within the customary time period. For example, the environment jump value can be determined according to the change amount or change rate of the environment parameters at adjacent time points.

[0096] Finally, the door and window control unit 143 sets a preset abnormal range and compares the calculated environment jump value of the customary time period with the preset abnormal range. If the environment jump value is within the preset abnormal range, it is considered that the current environmental state is abnormal and the door and window state needs to be adjusted to cope with it. Then, the door and window control unit 143 generates and sends the corresponding door and window control signal to the controller of the smart door and window, and the controller performs the corresponding door and window control operation.

[0097] If the environment jump value is not within the preset abnormal range, the current environment state is considered normal, and it is determined that the phenomenon of breaking the habit of opening and closing doors and windows at this time is intentional by the user, so there is no need to control the doors and windows to move.

[0098] Through this embodiment, when the habit retention degree is not within the preset retention degree range, the abnormality degree of the indoor environment is further determined according to the environmental parameter sequence. Therefore, it is possible to accurately judge whether the phenomenon of breaking the opening and closing habit of doors and windows at this time is intentional by the user according to the abnormality degree of the indoor environment, thereby improving the accuracy of intelligent control of doors and windows.

[0099] As an optional embodiment, the environment analysis unit 142 is specifically configured to:

[0100] Using the environmental parameter sequence, determining the sequence length and sequence information entropy of the environmental parameter sequence;

[0101] The sequence duration and sequence information entropy are used to determine the environmental jump value of the habitual time period.

[0102] In this embodiment, the sequence duration is the difference between the end time and the start time of the environmental parameter sequence, and the information entropy is used to characterize the uncertainty of the occurrence of each possible environmental event corresponding to the environmental parameter sequence.

[0103] As an example, the environment jump value may be specifically determined by the following formula 4:

[0104] C t =I(w t )*s t Formula 4

[0105] In formula 4, C t It is used to characterize the environmental jump value of the tth time period, I(w t ) is used to characterize the sequence information entropy of the environmental parameter sequence corresponding to the t-th time period, s t The sequence length used to characterize the environmental parameter sequence corresponding to the t-th time period.

[0106] Among them, the larger the sequence information entropy, the more unstable the changes in the environmental parameters in the environmental parameter sequence, and the larger the environmental jump value; the longer the sequence duration, the longer the time the user did not take the door and window control behavior, that is, the greater the possibility that the user did not move the doors and windows in time due to forgetfulness or busyness, and the larger the environmental jump value.

[0107] Through this embodiment, the abnormal degree of the indoor environment is accurately determined according to the sequence duration and sequence information entropy of the environmental parameter sequence. Therefore, it is possible to accurately judge whether the phenomenon of breaking the habit of opening and closing doors and windows at this time is intentional by the user according to the abnormal degree of the indoor environment, thereby improving the accuracy of intelligent control of doors and windows.

[0108] As an optional embodiment, the door and window control module 100 further includes the following units:

[0109] A damping value acquisition unit, used to acquire the damping value at each moment during the movement of the door and window;

[0110] The door and window return unit is used to send a door and window return signal when the damping value is greater than the corresponding damping value threshold, so as to control the door and window to return to the state before the movement;

[0111] The result feedback unit is used to send the door and window control result to the user when each damping value is not greater than the corresponding damping value threshold.

[0112] In this embodiment, damping sensors are installed on the moving parts of doors and windows (such as window sashes, door frames, etc.). These sensors can be force sensors, displacement sensors or acceleration sensors, which can directly or indirectly measure the damping force or resistance during the movement process.

[0113] The damping sensor is connected to the damping value acquisition unit in a wired or wireless manner, and the damping value acquisition unit acquires the damping value detected by the damping sensor in real time during the movement of the door or window.

[0114] Then, a reasonable damping value threshold is set according to the specifications, materials, use environment and other factors of the doors and windows. The damping value threshold can be fixed or dynamically adjusted (such as according to environmental factors such as temperature and humidity). At the same time, the door and window return unit compares the damping value obtained in real time with the set damping value threshold.

[0115] If the damping value obtained in real time is greater than the corresponding damping value threshold, it is considered that human blocking behavior has occurred at this time, and the door and window return unit sends a door and window return signal to the controller to stop the current movement of the door and window and control the door and window to return to the state before movement.

[0116] If the damping values ​​obtained in real time are not greater than the corresponding damping value threshold, it is considered that there has been no human intervention, and the doors and windows can be controlled normally. At this time, after the doors and windows are controlled to move, the door and window control results are fed back to the customer. Specifically, the door and window control results may include failure to open and close the doors / windows in time, resulting in low / high real-time indoor temperature and humidity, and the automatic opening and closing of the doors and windows has been completed.

[0117] Through this embodiment, the damping value at each moment is obtained in real time during the movement of the door and window, so as to judge whether human intervention occurs according to the damping value at each moment, thereby ensuring that the intelligent control of the door and window can meet the needs of the user and improve the accuracy of the intelligent control of the door and window.

[0118] As an optional embodiment, the door and window control module 100 further includes the following units:

[0119] A damping value analysis unit, used to determine a damping value average by using the damping value at the current moment and the damping values ​​at each historical moment;

[0120] The threshold value analysis unit is used to determine the damping value threshold value corresponding to the damping value at the current moment by using the damping value mean value and the preset damping value coefficient.

[0121] In this embodiment, the damping value threshold can be specifically determined by the following formula 5:

[0122]

[0123] In Formula 5, F is used to represent the damping value threshold. k is used to represent the preset damping value coefficient. For example, the preset damping value coefficient may be 1.5. f(v) is used to represent the damping value at time v, and T is used to represent the number of acquisition moments in the door and window movement process.

[0124] in, It is used to represent the average damping value at the current moment and the historical moment. The larger the average damping value, the larger the damping value in the historical door pushing process, and the larger the damping value threshold at the current moment.

[0125] Through this embodiment, the damping value at the current moment and the damping values ​​at each historical moment are used to determine the average damping value. Then, according to the average damping value and the preset damping value coefficient, the damping value threshold at the current moment is set. In this way, by adjusting the damping value threshold in real time, it is possible to more accurately determine whether human intervention occurs. This ensures that the intelligent control of doors and windows can meet the needs of users and improves the accuracy of the intelligent control of doors and windows.

[0126] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0127] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0128] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. An intelligent door and window control system with autonomous learning function, characterized in that: The system comprises: A behavior acquisition module, used to acquire multiple historical opening behavior sequences and multiple historical closing behavior sequences of a user, wherein the historical opening behavior sequences include the number of times the user opened doors and windows in each time period in the historical period, and the historical closing behavior sequences include the number of times the user closed doors and windows in each time period in the historical period; A time period determination module, used to determine the user's habitual time period according to each of the historical opening behavior sequences and each of the historical closing behavior sequences, wherein the habitual time period is a time period in which the user has regular door and window control behaviors; A time period monitoring module, for monitoring each of the habit time periods, and determining the degree of habit maintenance of the user in the habit time period, wherein the habit maintenance degree is used to characterize the degree to which the user maintains the door and window control behavior in the habit time period; The door and window control module is used to send a door and window control signal to control the movement of the door and window when the habitual retention degree is not within a preset retention degree range.

2. The intelligent door and window control system with autonomous learning function according to claim 1 is characterized in that: The behavior acquisition module is specifically used for: Acquire historical opening behavior data and historical closing behavior data of the user in multiple historical periods, wherein the historical opening behavior data has a corresponding opening timestamp, and the historical closing behavior data has a corresponding closing timestamp; For each of the historical periods, respectively executing: based on the opening timestamps of each of the historical opening behavior data and the closing timestamps of each of the historical closing behavior data in the historical period, counting the number of door and window openings and the number of door and window closings in each time period in the historical period; For each of the historical periods, respectively: sorting the number of times each of the doors and windows are opened in chronological order to obtain the historical opening behavior sequence; sorting the number of times each of the doors and windows are closed in chronological order to obtain the historical closing behavior sequence.

3. The intelligent door and window control system with autonomous learning function according to claim 1 is characterized in that: The time period determination module specifically includes the following units: A priority determination unit, for determining the user's habit priority for each time period in each of the historical periods according to each of the historical opening behavior sequences and each of the historical closing behavior sequences, wherein the habit priority is used to characterize the concentration of the user's door and window control behavior in the time period; A regularity determination unit, used to determine the habit regularity of each time period according to the habit priority of each time period of the user in each historical period, wherein the habit regularity is used to characterize the degree of regularity of the door and window control behavior of the user; The time period determination unit is used to determine the time period corresponding to the habit regularity as the habit time period when the habit regularity is within a preset regularity range.

4. The intelligent door and window control system with autonomous learning function according to claim 3 is characterized in that: The priority determination unit is specifically used to: For each of the historical periods, perform the following steps: Statistically processing the target historical opening behavior sequence and the target historical closing behavior sequence to obtain the target door and window opening times and the target door and window closing times in each time period within the target historical period, and the total number of door and window control behaviors within the target historical period, wherein the target historical opening behavior sequence and the target historical closing behavior sequence are the historical opening behavior sequence and the historical closing behavior sequence corresponding to the target historical period; The habit priority of the user in each time period within the target historical period is determined by using the number of times each target door and window is opened, the number of times each target door and window is closed, and the total number of door and window control behaviors.

5. The intelligent door and window control system with autonomous learning function according to claim 3 is characterized in that: The regularity determination unit is specifically used for: For each of the time periods, perform the following steps respectively: Determine the first habit priority difference of the target time periods in adjacent historical periods by using the habit priority of the target time periods in each of the historical periods, the target time period being any one of the time periods; Determine the average first habit priority of the target time period by using the habit priorities of the target time period in each of the historical periods; The habit regularity of the target time period is determined by using the first habit priority difference values ​​and the first habit priority mean value.

6. The intelligent door and window control system with autonomous learning function according to claim 1 is characterized in that: The time period monitoring module is specifically used for: Determine a second habit priority average of the habit time period by using the habit priority of the habit time period in the current period and the habit priorities of the habit time period in a preset number of historical periods; The habit priority of the habit time period in the current period is subtracted from the average of the second habit priority and the absolute value is taken to obtain the second habit priority difference; The second habit priority difference is used to determine the user's habit retention degree for the habit time period in the current period.

7. The intelligent door and window control system with autonomous learning function according to claim 1 is characterized in that: The door and window control module specifically includes the following units: An environment acquisition unit, configured to acquire a sequence of environment parameters from the most recent door and window movement moment to the current moment when the habit retention degree is not within a preset retention degree range; An environment analysis unit, configured to determine an environment jump value of the habitual time period according to the environment parameter sequence; The door and window control unit is used to send a door and window control signal to control the movement of the door and window when the environment jump value in the habitual time period is within a preset abnormal range.

8. The intelligent door and window control system with autonomous learning function according to claim 7 is characterized in that: The environmental analysis unit is specifically used for: Using the environmental parameter sequence, determining a sequence duration and a sequence information entropy of the environmental parameter sequence; The environment jump value of the habitual time period is determined by using the sequence duration and the sequence information entropy.

9. The intelligent door and window control system with autonomous learning function according to claim 7, characterized in that: The door and window control module also includes the following units: A damping value acquisition unit, used to acquire the damping value at each moment during the movement of the door and window; A door and window return unit, used to send a door and window return signal when the damping value is greater than the corresponding damping value threshold, so as to control the door and window to return to the state before the movement; The result feedback unit is used to send the door and window control result to the user when each of the damping values ​​is not greater than the corresponding damping value threshold.

10. The intelligent door and window control system with autonomous learning function according to claim 9, characterized in that: The door and window control module also includes the following units: A damping value analysis unit, used to determine a damping value mean by using the damping value at the current moment and the damping values ​​at each historical moment; A threshold value analysis unit is used to determine the damping value threshold value corresponding to the damping value at the current moment by using the damping value mean and a preset damping value coefficient.

Images