Curtain wall intelligent control method and device based on behavior recognition, equipment and medium

Abstract

The invention relates to a curtain wall intelligent control method and device based on behavior recognition, equipment and a medium, and the method comprises the steps: obtaining a space use state and corresponding scene data, and judging whether a current space is in an adjustable time period or not according to the change characteristics of the scene data; under the condition that the current space is the adjustable time period, behavior triggering features are extracted from the change features, then the activity state of the personnel is recognized, and a corresponding control intention is determined according to the activity state; according to the control intention, calling a control target corresponding to an adjustment constraint condition from a preset control intention library, and generating a control instruction; and executing the control instruction, and returning a result according to the corresponding action state to form a triggering condition of the next round of recognition. The curtain wall control method has the effect of improving curtain wall control accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent building control, and in particular to a curtain wall intelligent control method, device, equipment and medium based on behavior recognition. Background Art

[0002] At present, intelligent curtain wall systems have gradually been applied to high-end buildings, hotels, office spaces and other scenarios to achieve automated shading, lighting and ventilation control to improve environmental comfort and energy saving effects.

[0003] Existing intelligent curtain wall control methods are usually based on automatic control of light intensity, temperature and humidity or time preset strategies. Although some systems support manual adjustment or sensor linkage control, they generally rely on static environmental parameters or single trigger conditions for adjustment decisions. They lack the dynamic adaptability of shading and ventilation linkage control, which can easily lead to problems such as control response delays, execution logic mismatch, and discontinuous adjustment experience.

[0004] The above-mentioned existing technical solutions have the following defects: the existing curtain wall control method cannot accurately match the control intention in dynamic scene perception, so there is room for improvement. Summary of the Invention

[0005] In order to improve the accuracy of curtain wall control, the present application provides a curtain wall intelligent control method, device, equipment and medium based on behavior recognition.

[0006] The above-mentioned invention objective of this application is achieved through the following technical solutions: A curtain wall intelligent control method based on behavior recognition, the method comprising: Obtaining the space usage status and corresponding scene data, and determining whether the current space is in an adjustable period based on the change characteristics of the scene data; In the case where the current space is an adjustable time period, extracting behavior trigger features from the change features, thereby identifying the activity status of personnel, and determining corresponding control intentions according to the activity status; According to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library, and a control instruction is generated; Execute the control instruction and return the result according to the corresponding action state to form the trigger condition for the next round of recognition.

[0007] By adopting the above technical solution, by obtaining the space usage status and the corresponding scene data, and judging whether the current space is in an adjustable period based on the change characteristics of the scene data, it is possible to realize dynamic identification of the space environment status and perception of the change trend, thereby ensuring that the curtain wall control action is only performed within the time window with response value, effectively avoiding resource waste and control mis-touch; by extracting behavior trigger characteristics and identifying the activity status of personnel under the premise that the space is in an adjustable period, it is possible to actively perceive the user's real behavior, thereby matching a control intention with a higher human-machine fit; by calling the control target in the preset control intention library according to the control intention and generating control instructions, the control strategy can have situational adaptability and strategic flexibility, thereby improving the targetedness of shading and ventilation control and the level of system intelligent response; by executing control instructions and using the action status feedback results to form the trigger conditions for the next round of identification, it is possible to build a closed-loop link of behavior perception and control decision-making, thereby enhancing the continuity, stability and feedback error correction capabilities of the system operation.

[0008] In one example, the present application may be further configured as follows: determining whether the current space is in an adjustable period based on the change characteristics of the scene data specifically includes: Performing fitting processing on the scene data within a preset time sliding window, constructing a change function of the scene data, and obtaining a change feature of the scene data; When the change characteristic satisfies monotonically increasing or monotonically decreasing, and the fluctuation amplitude of the change characteristic is lower than a preset fluctuation threshold, it is determined that the current space is an adjustable period.

[0009] By adopting the above technical solution, by fitting the scene data within a preset time sliding window and constructing a change function, the changing trend characteristics of the spatial state can be extracted, avoiding misjudgment caused by short-term fluctuation interference, thereby improving the accuracy and robustness of adjustable time period identification; by determining the adjustable state under the condition that the changing trend satisfies monotonicity and the fluctuation amplitude is lower than the threshold, it can ensure that the control strategy is executed in a stable scenario, thereby reducing system false triggering and unnecessary energy consumption, and improving the timeliness adaptability of the control logic.

[0010] In one example, the present application may be further configured as follows: extracting behavior trigger features from the change features, thereby identifying the activity status of the personnel, and determining the corresponding control intention according to the activity status, specifically including: By performing window segmentation on the short-term fluctuation signal in the change feature, the disturbance frequency in each segment is compared with the historical stability baseline to extract the disturbance segment associated with the behavior as the behavior trigger feature; The behavior trigger feature is compared with a preset behavior judgment rule, and when the activity state is identified, the control intention is determined according to a preset association logic between the activity state and the control intention.

[0011] By adopting the above technical solution, by performing segmented analysis on the short-term fluctuation signals in the change characteristics and comparing the disturbance frequency in each segment with the historical stability baseline, it is possible to extract disturbance segments with behavioral characteristic significance, thereby achieving accurate judgment of personnel behavior activities; by conditionally comparing the extracted behavior trigger characteristics with preset rules and determining the control intention accordingly, it is possible to achieve adaptive mapping between behavioral states and control intentions, thereby improving the responsiveness and pertinence of the control strategy to changes in specific scenarios.

[0012] In one example, the present application may be further configured as follows: comparing the disturbance frequency in each segment with the historical stability baseline to extract the disturbance segment associated with the behavior as the behavior trigger feature, specifically including: Collecting disturbance signal information in the segments and performing frequency statistics to obtain the disturbance frequency; The disturbance frequency is subjected to segment-by-segment difference analysis with the historical stability baseline of the corresponding time period, and target segments whose deviation exceeds a set deviation threshold are extracted as the disturbance segments.

[0013] By adopting the above technical solution, by collecting disturbance signal information in segments and performing frequency statistics, we can effectively obtain behavioral disturbance frequency indicators within the time segment, thereby providing a quantitative basis for behavioral change trends; by comparing the disturbance frequency with the historical stability baseline and extracting segments with significant deviations as behavioral association data, we can accurately identify behavioral intervention characteristics, thereby improving the discrimination and reliability of behavior recognition.

[0014] In one example, the present application may be further configured as follows: calling the control target corresponding to the adjustment constraint condition from a preset control intention library according to the control intention, and generating a control instruction, specifically including: Retrieving a control parameter range corresponding to the control intention, and screening the control parameters in combination with the space usage status to obtain an adjustment target set; A difference analysis is performed on the current device state according to the adjustment target set, and a control rhythm is generated based on the control strategy, thereby constructing the control instruction.

[0015] By adopting the above technical solution, by retrieving the control parameter range corresponding to the control intention and screening it in combination with the space usage status, it is possible to dynamically screen out unexecutable or inappropriate adjustment strategies under current conditions, so that the control target is more in line with the current environment and user needs; by performing differential analysis on the current device status according to the adjustment target set, and generating control rhythm and control amplitude in combination with the control strategy, flexible adjustment and gradual control can be achieved, thereby avoiding user discomfort or abnormal equipment load caused by sudden adjustment changes, and improving the smoothness and experience of control execution.

[0016] In one example, the present application may be further configured as follows: performing a difference analysis on the current device state according to the adjustment target set, generating a control rhythm based on a control strategy, and then constructing the control instruction, specifically including: Calculating the difference between the adjustment target set and the current device state value, classifying the difference into intervals, and determining the control rhythm according to the interval classification result; Based on the control rhythm, a corresponding control duration and a target change step are generated, and then the control instruction is generated.

[0017] By adopting the above technical solution, by calculating the difference between the adjustment target and the current equipment status and classifying the intervals, the adjustment level required for the current adjustment can be clarified, thereby providing a basic basis for the subsequent control rhythm selection and improving the accuracy of control decisions; by generating the control duration and target change step size based on the classification results, and constructing control instructions accordingly, it is possible to achieve self-adaptation of response time and adjustment amplitude in different adjustment scenarios, thereby improving the system's adaptability to changing scenarios and intelligent execution capabilities.

[0018] The second object of the present invention is achieved through the following technical solutions: A curtain wall intelligent control device based on behavior recognition, the device comprising: A state perception module is used to obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the change characteristics of the scene data; A behavior recognition module is used to extract behavior trigger features from the change features when the current space is an adjustable time period, thereby identifying the activity status of the personnel and determining the corresponding control intention according to the activity status; A strategy generation module is used to call the control target corresponding to the adjustment constraint condition from the preset control intention library according to the control intention and generate a control instruction; The execution feedback module is used to execute the control instruction and return the result according to the corresponding action state to form the trigger condition for the next round of recognition.

[0019] By adopting the above technical solution, by obtaining the space usage status and the corresponding scene data, and judging whether the current space is in an adjustable period based on the change characteristics of the scene data, it is possible to realize dynamic identification of the space environment status and perception of the change trend, thereby ensuring that the curtain wall control action is only performed within the time window with response value, effectively avoiding resource waste and control mis-touch; by extracting behavior trigger characteristics and identifying the activity status of personnel under the premise that the space is in an adjustable period, it is possible to actively perceive the user's real behavior, thereby matching a control intention with a higher human-machine fit; by calling the control target in the preset control intention library according to the control intention and generating control instructions, the control strategy can have situational adaptability and strategic flexibility, thereby improving the targetedness of shading and ventilation control and the level of system intelligent response; by executing control instructions and using the action status feedback results to form the trigger conditions for the next round of identification, it is possible to build a closed-loop link of behavior perception and control decision-making, thereby enhancing the continuity, stability and feedback error correction capabilities of the system operation.

[0020] The third objective of this application is achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned curtain wall intelligent control method based on behavior recognition are implemented.

[0021] The fourth objective of this application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned curtain wall intelligent control method based on behavior recognition.

[0022] In summary, this application has the following beneficial technical effects: 1. By acquiring the space usage status and corresponding scene data, and judging whether the current space is in an adjustable period based on the changing characteristics of the scene data, it is possible to dynamically identify the space environment status and perceive the changing trend, thereby ensuring that the curtain wall control action is only performed within the time window with response value, effectively avoiding resource waste and control errors; by extracting behavior trigger features and identifying the activity status of personnel under the premise that the space is in an adjustable period, it is possible to actively perceive the user's real behavior, thereby matching control intentions with greater human-machine compatibility; by calling the control targets in the preset control intention library and generating control instructions based on the control intention, the control strategy can have situational adaptability and strategic flexibility, thereby improving the pertinence of shading and ventilation control and the level of system intelligent response; by executing control instructions and using the action status feedback results to form the trigger conditions for the next round of identification, it is possible to build a closed-loop link between behavior perception and control decision-making, thereby enhancing the continuity, stability and feedback error correction capabilities of the system operation; 2. By fitting the scene data within a preset time sliding window and constructing a change function, the changing trend characteristics of the spatial state can be extracted, avoiding misjudgments caused by short-term fluctuations, thereby improving the accuracy and robustness of identifying the adjustable period. By determining the adjustable state under the conditions that the changing trend satisfies monotonicity and the fluctuation amplitude is below the threshold, it can ensure that the control strategy is executed in a stable scenario, thereby reducing system false triggering and unnecessary energy consumption, and improving the timeliness and adaptability of the control logic. 3. By performing segmented analysis on the short-term fluctuation signals in the change characteristics and comparing the disturbance frequency within each segment with the historical stability baseline, it is possible to extract disturbance segments with behavioral characteristic significance, thereby achieving accurate judgment of personnel behavior activities; by conditionally comparing the extracted behavior trigger characteristics with preset rules and determining the control intention accordingly, it is possible to achieve adaptive mapping between behavioral states and control intentions, thereby improving the responsiveness and pertinence of the control strategy to specific scenario changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in the curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S20 in the curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S21 in the curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 5This is a flowchart for implementing step S30 in the curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 6 This is a flowchart for implementing step S32 in the curtain wall intelligent control method based on behavior recognition in one embodiment of the present application; Figure 7 This is a principle block diagram of a curtain wall intelligent control device based on behavior recognition in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below with reference to the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a curtain wall intelligent control method based on behavior recognition, which specifically includes the following steps: S10: Obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the change characteristics of the scene data.

[0026] Specifically, by collecting environmental parameters and personnel status information related to the space usage status, a scene data set for the current time period is constructed, and based on the changing trend of the data set, it is judged whether the current space state has continuous and stable adjustment significance, thereby determining whether to enter the control pre-process.

[0027] S20: When the current space is an adjustable time period, behavior triggering features are extracted from the change features to identify the activity status of the personnel and determine the corresponding control intention according to the activity status.

[0028] Specifically, after determining that the current space has the adjustment conditions, the feature information related to the disturbance changes in the scene data is extracted, the main activity types of people in the current space are identified, and the control intention applicable to the current scene is determined in combination with the preset mapping relationship between behavior and control.

[0029] S30: According to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library, and a control instruction is generated.

[0030] Specifically, based on the control intent, the matching adjustment strategy template is called, and the executable control target is determined in combination with the current environmental status, equipment capabilities and control constraints. Then, a control instruction containing action content and rhythm parameters is generated according to the control target.

[0031] S40: Execute the control instruction and return the result according to the corresponding action state to form the trigger condition for the next round of recognition.

[0032] Specifically, the control instructions are sent to the corresponding control device to complete the specific adjustment action, and the action status feedback of the device is collected after the execution is completed. The feedback result serves as the trigger basis for updating behavior recognition and control strategy judgment, and is used to start the next round of decision-making process.

[0033] In one embodiment, if Figure 2 As shown, in step S10, that is, according to the change characteristics of the scene data, it is determined whether the current space is in the adjustable period, specifically including: S11: Perform fitting processing on the scene data within a preset time sliding window, construct a change function of the scene data, and obtain change characteristics of the scene data.

[0034] Specifically, by setting a sliding time window of fixed length, the continuous time period information in the scene data is extracted, and the data such as light intensity, air temperature and humidity or gas concentration within the time period are interpolated and smoothed. The change trend function of the time period is constructed by polynomial fitting. The change direction of the fitting function is determined by calculating the first-order derivative of the fitting function at different sampling points, and the positive and negative change trends of the derivatives are further obtained as the change characteristics of the scene data, so as to be used subsequently to judge whether there is a state trend with continuous adjustment significance.

[0035] S12: When the change feature satisfies a monotonically increasing or monotonically decreasing state and the fluctuation amplitude of the change feature is lower than a preset fluctuation threshold, the current space is determined to be an adjustable period.

[0036] Specifically, after obtaining the changing characteristics of the scene data, whether it is in a monotonically rising or falling state is determined by analyzing whether its first-order derivative is continuously positive or negative in the sliding window. At the same time, the difference between the maximum and minimum values of the original data in the time window is calculated and compared with the set fluctuation amplitude threshold. When the data change shows a monotonic trend and the fluctuation amplitude is lower than the threshold, it is considered that the current environmental state is relatively stable and suitable for executing control instructions, and the time period is marked as an adjustable period.

[0037] In one embodiment, if Figure 3 As shown, in step S20, the behavior trigger feature is extracted from the change feature, and then the activity state of the person is identified, and the corresponding control intention is determined according to the activity state, which specifically includes: S21: By segmenting the short-term fluctuation signal in the change feature into windows, the disturbance frequency in each segment is compared with the historical stability baseline to extract the disturbance fragment associated with the behavior as the behavior trigger feature.

[0038] Specifically, the time series signal corresponding to the change feature is first divided into several adjacent segments according to the set window length. The number of changes of the disturbance signal per unit time in each segment is counted to calculate the disturbance frequency. At the same time, the historical state sequence of the corresponding time period is called to establish a stability baseline. The baseline represents the feature changes when there is no human activity. The amplitude deviation between the disturbance frequency of the current segment and the stability baseline is calculated. When the deviation is greater than the set threshold, it is considered that there is a potential behavior trigger signal in the current segment, and the segment is extracted as the behavior trigger feature required for subsequent behavior recognition.

[0039] S22: Conditionally compare the behavior triggering feature with the preset behavior judgment rule, and when the activity state is identified, determine the control intention according to the preset association logic between the activity state and the control intention.

[0040] Specifically, the extracted behavior trigger features are matched one by one with the pre-established behavior judgment conditions to determine whether the features meet the judgment criteria of a certain behavior label in terms of time density, frequency amplitude, duration, etc. When the conditions are met, the corresponding personnel activity status is identified. At the same time, the control intention in the current scenario is determined based on the control logic pointed to by the activity status in the preset control intention mapping table. The control intention is used to guide the selection of subsequent adjustment strategies.

[0041] In one embodiment, if Figure 4 As shown, in step S21, the disturbance frequency in each segment is compared with the historical stability baseline to extract the disturbance segment associated with the behavior as the behavior trigger feature, specifically including: S211: Collect disturbance signal information in the segment and perform frequency statistics to obtain disturbance frequency.

[0042] Specifically, the sampling value of the disturbance signal is extracted in each time segment and the number of times the sampling value changes is counted. The disturbance count per unit time in each segment is divided by the time length to calculate the disturbance frequency of the segment. This frequency is used to measure the degree of change in environmental disturbance caused by human activities and provide a basic indicator for subsequent behavior trigger feature identification.

[0043] S212: Perform segment-by-segment difference analysis on the disturbance frequency and the historical stability baseline of the corresponding time period, and extract target segments whose deviation exceeds a set deviation threshold as disturbance segments.

[0044] Specifically, the historical disturbance frequency under the same conditions as the current segment time period is called as the stability baseline, the disturbance frequency of the current segment is subtracted from the baseline and the difference is recorded. The difference is compared with the set deviation threshold to determine whether the segment deviates significantly from the normal state. When the difference is greater than the threshold, the current segment is marked as a target disturbance segment and retained for further analysis of the behavioral state.

[0045] In one embodiment, if Figure 5 As shown, in step S30, that is, according to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library, and a control instruction is generated, which specifically includes: S31: Retrieve the control parameter range corresponding to the control intention, and filter the control parameters in combination with the space usage status to obtain an adjustment target set.

[0046] Specifically, according to the currently generated control intention, the corresponding control parameter set is searched in the control strategy index table. The parameter set includes control variables such as shading angle, color change depth, ventilation opening and closing ratio, etc. At the same time, combined with the current space usage status, it is judged whether it is in an executable state. If it is currently occupied and the external light is strong, the control parameters with too high light transmittance are screened out, and only the adjustment targets that can meet the shading requirements under this condition are retained to form the target set for subsequent decision-making.

[0047] S32: Perform difference analysis on the current device state according to the adjustment target set, generate a control rhythm based on the control strategy, and then construct a control instruction.

[0048] Specifically, the differences between each control target value in the adjustment target set and the current equipment status are calculated and quantitatively evaluated. The corresponding rhythm mode in the control strategy is selected according to the amplitude range of the difference, including slow change, rapid adjustment or segmented execution. After the control rhythm is determined, a control instruction containing the target value, execution time and response type is generated for each control target. The control instruction will be used to drive the shading or ventilation equipment to perform the corresponding adjustment action.

[0049] In one embodiment, if Figure 6 As shown, in step S32, the current device state is subjected to difference analysis according to the adjustment target set, and a control rhythm is generated based on the control strategy, and then a control instruction is constructed, which specifically includes: S321: Calculate the difference between the adjustment target set and the current device state value, classify the difference into intervals, and determine the control rhythm according to the interval classification result.

[0050] Specifically, the numerical difference between each target value and the current device status value is first calculated, and the size of the difference is compared with multiple preset rhythm thresholds to determine which category the difference belongs to: gradual change, small adjustment, or jump adjustment. According to the classification result, the corresponding control rhythm is selected, such as slow linear change, graded advancement, or one-time rapid execution.

[0051] S322: Based on the control rhythm, generate a corresponding control duration and target change step size, and then generate a control instruction.

[0052] Specifically, according to the selected control rhythm, the length of the single adjustment time corresponding to the rhythm and the target change of each step are determined. On this basis, a complete control instruction including the adjustment target, change amplitude, duration and expected feedback state is constructed, and the control instruction is added to the control queue in a serial manner, ready for action execution and feedback verification.

[0053] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0054] In one embodiment, a curtain wall intelligent control device based on behavior recognition is provided, and the curtain wall intelligent control device based on behavior recognition corresponds one-to-one with the curtain wall intelligent control method based on behavior recognition in the above embodiment. Figure 7 As shown in the figure, the curtain wall intelligent control device based on behavior recognition includes a state perception module, a behavior recognition module, a strategy generation module, and an execution feedback module. The detailed description of each functional module is as follows: The state perception module is used to obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the changing characteristics of the scene data; The behavior recognition module is used to extract behavior trigger features from the change features when the current space is an adjustable time period, and then identify the activity status of the personnel and determine the corresponding control intention based on the activity status; The strategy generation module is used to call the control target corresponding to the adjustment constraint condition from the preset control intention library according to the control intention and generate the control instruction; The execution feedback module is used to execute control instructions and return results according to the corresponding action status to form the trigger conditions for the next round of recognition.

[0055] Optionally, the state perception module specifically includes: The fitting processing submodule is used to perform fitting processing on the scene data within a preset time sliding window, construct a change function of the scene data, and obtain the change characteristics of the scene data; The trend judgment submodule is used to judge that the current space is an adjustable period when the change feature satisfies monotonically rising or monotonically falling and the fluctuation amplitude of the change feature is lower than the preset fluctuation threshold.

[0056] Optionally, the behavior recognition module specifically includes: The disturbance analysis submodule is used to segment the short-term fluctuation signal in the change feature into windows, compare the disturbance frequency in each segment with the historical stability baseline, and extract the disturbance fragments associated with the behavior as the behavior trigger feature; The intention generation submodule is used to conditionally compare the behavior triggering features with the preset behavior judgment rules, and when the activity state is identified, determine the control intention based on the preset association logic between the activity state and the control intention.

[0057] Optionally, the disturbance analysis submodule specifically includes: A frequency statistics unit is used to collect disturbance signal information in the segment and perform frequency statistics to obtain the disturbance frequency; The difference comparison unit is used to perform segment-by-segment difference analysis on the disturbance frequency and the historical stability baseline of the corresponding time period, and extract the target segments whose deviation exceeds the set deviation threshold as the disturbance segments.

[0058] Optionally, the strategy generation module specifically includes: The parameter screening submodule is used to retrieve the control parameter range corresponding to the control intention and screen the control parameters in combination with the space usage status to obtain the adjustment target set; The instruction generation submodule is used to perform differential analysis on the current device status according to the adjustment target set, generate the control rhythm based on the control strategy, and then construct the control instruction.

[0059] Optionally, the instruction generation submodule specifically includes: a rhythm determination unit, configured to calculate the difference between the adjustment target set and the current device state value, classify the difference into intervals, and determine the control rhythm based on the interval classification result; The step size construction unit generates the corresponding control duration and target change step size based on the control rhythm, and then generates the control instructions.

[0060] For the specific definition of the curtain wall intelligent control device based on behavior recognition, please refer to the definition of the curtain wall intelligent control method based on behavior recognition above, which will not be repeated here. The various modules in the above-mentioned curtain wall intelligent control device based on behavior recognition can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0061] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, memory, network interface and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a curtain wall intelligent control method based on behavior recognition is implemented.

[0062] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed: Obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the changing characteristics of the scene data; When the current space is an adjustable time period, the behavior trigger features are extracted from the change features to identify the activity status of the personnel and determine the corresponding control intention according to the activity status; According to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library and the control instruction is generated; Execute the control instructions and return the results according to the corresponding action status to form the trigger conditions for the next round of recognition.

[0063] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the changing characteristics of the scene data; When the current space is an adjustable time period, the behavior trigger features are extracted from the change features to identify the activity status of the personnel and determine the corresponding control intention according to the activity status; According to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library and the control instruction is generated; Execute the control instructions and return the results according to the corresponding action status to form the trigger conditions for the next round of recognition.

[0064] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0065] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0066] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A curtain wall intelligent control method based on behavior recognition, characterized in that: The method comprises: Obtaining the space usage status and corresponding scene data, and determining whether the current space is in an adjustable period based on the change characteristics of the scene data; In the case where the current space is an adjustable time period, extracting behavior trigger features from the change features, thereby identifying the activity status of the personnel, and determining the corresponding control intention according to the activity status; According to the control intention, the control target corresponding to the adjustment constraint condition is called from the preset control intention library, and a control instruction is generated; Execute the control instruction and return the result according to the corresponding action state to form the trigger condition for the next round of recognition.

2. The curtain wall intelligent control method based on behavior recognition according to claim 1 is characterized in that: The determining, based on the change characteristics of the scene data, whether the current space is in an adjustable period specifically includes: Performing fitting processing on the scene data within a preset time sliding window, constructing a change function of the scene data, and obtaining a change feature of the scene data; When the change characteristic satisfies monotonically increasing or monotonically decreasing, and the fluctuation amplitude of the change characteristic is lower than a preset fluctuation threshold, it is determined that the current space is an adjustable period.

3. The curtain wall intelligent control method based on behavior recognition according to claim 1 is characterized in that: The extracting of the behavior trigger feature from the change feature, thereby identifying the activity state of the personnel, and determining the corresponding control intention according to the activity state, specifically includes: By performing window segmentation on the short-term fluctuation signal in the change feature, the disturbance frequency in each segment is compared with the historical stability baseline to extract the disturbance segment associated with the behavior as the behavior trigger feature; The behavior trigger feature is compared with a preset behavior judgment rule, and when the activity state is identified, the control intention is determined according to a preset association logic between the activity state and the control intention.

4. The curtain wall intelligent control method based on behavior recognition according to claim 3 is characterized in that: The comparison of the disturbance frequency in each segment with the historical stability baseline to extract the disturbance segment associated with the behavior as the behavior triggering feature specifically includes: Collecting disturbance signal information in the segments and performing frequency statistics to obtain the disturbance frequency; The disturbance frequency is subjected to segment-by-segment difference analysis with the historical stability baseline of the corresponding time period, and target segments whose deviation exceeds a set deviation threshold are extracted as the disturbance segments.

5. The curtain wall intelligent control method based on behavior recognition according to claim 1 is characterized in that: The control intention is to call the control target corresponding to the adjustment constraint condition from the preset control intention library and generate a control instruction, which specifically includes: Retrieving a control parameter range corresponding to the control intention, and screening the control parameters in combination with the space usage status to obtain an adjustment target set; A difference analysis is performed on the current device state according to the adjustment target set, and a control rhythm is generated based on the control strategy, thereby constructing the control instruction.

6. The curtain wall intelligent control method based on behavior recognition according to claim 5 is characterized in that: The difference analysis of the current device state according to the adjustment target set is performed, and the control rhythm is generated based on the control strategy, and then the control instruction is constructed, which specifically includes: Calculating the difference between the adjustment target set and the current device state value, classifying the difference into intervals, and determining the control rhythm according to the interval classification result; Based on the control rhythm, a corresponding control duration and a target change step are generated, and then the control instruction is generated.

7. A curtain wall intelligent control device based on behavior recognition, characterized in that: The device comprises: A state perception module is used to obtain the space usage status and corresponding scene data, and determine whether the current space is in an adjustable period based on the change characteristics of the scene data; A behavior recognition module is used to extract behavior trigger features from the change features when the current space is an adjustable time period, thereby identifying the activity status of the personnel and determining the corresponding control intention according to the activity status; A strategy generation module is used to call the control target corresponding to the adjustment constraint condition from the preset control intention library according to the control intention and generate a control instruction; The execution feedback module is used to execute the control instruction and return the result according to the corresponding action state to form the trigger condition for the next round of recognition.

8. The curtain wall intelligent control device based on behavior recognition according to claim 7 is characterized in that: The state perception module specifically includes: A fitting processing submodule, configured to perform fitting processing on the scene data within a preset time sliding window, construct a change function of the scene data, and obtain a change feature of the scene data; The trend judgment submodule is used to judge that the current space is an adjustable period when the change feature satisfies monotonically rising or monotonically falling and the fluctuation amplitude of the change feature is lower than a preset fluctuation threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the curtain wall intelligent control method based on behavior recognition as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the curtain wall intelligent control method based on behavior recognition as described in any one of claims 1 to 6 are implemented.

Images