[0021] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.
[0022] The following describes the user behavior self-learning air conditioning system control method proposed by the embodiments of the present invention and the user behavior self-learning air conditioning system implementing the method with reference to the accompanying drawings.
[0023] figure 1 It is a flow chart of the control method of the user behavior self-learning air conditioning system according to the embodiment of the present invention. The user behavior self-learning air conditioning system includes at least one air conditioner, a communication device, and an intelligent control device that communicates with each air conditioner through the communication device, that is, at least one air conditioner communicates with the intelligent control device through the communication device. The method can adopt CAN bus communication or serial communication. The intelligent control device includes an information collection module, an information processing module and a behavior prediction module. like figure 1 As shown, the control method includes the following steps:
[0024] S1: The information collection module collects the user's control information on each air conditioner in real time to form a user behavior database.
[0025] Wherein, the control information includes control objects, control time points and control instructions.
[0026] It should be noted that the control object may refer to the identification information of the air conditioner, the control instruction may refer to an instruction input by the user to the corresponding air conditioner, such as a start-up instruction or a shutdown instruction, etc., and the control time point may refer to the user receiving the control instruction. The time point of the input command, so that for each control object (air conditioner), the control command input by the user and the control time point of receiving the control command are collected in real time and stored in the corresponding location, thereby forming a user behavior database.
[0027] Specifically, the information collection module can collect the control instructions received by the air conditioner and the corresponding control time points for each air conditioner used by the user, such as the power-on command and the corresponding power-on time, the power-off command and the corresponding power-off time, so that A user behavior database cached in the last N days that is updated in real time.
[0028] For example, assuming that the user behavior self-learning air conditioning system includes air conditioner 1 and air conditioner 2, the user inputs a start command to air conditioner 1 at time point 1, a temperature setting command to air conditioner 1 at time point 2, and At time point 3, a shutdown command is input to the air conditioner 1 . Then the user inputs the start-up command to the air conditioner 2 at time point 4, the wind gear setting command to the air conditioner 2 at time point 5, and the shutdown command to the air conditioner 2 at time point 6, which can be formed as shown in Table 1 below. Shown user behavior database:
[0029] Table 1
[0030]
[0031] It should be understood that the above examples only illustrate some control instructions, and the user behavior database may also include other control instructions.
[0032] S2: The information processing module analyzes and processes the user behavior database to obtain user behavior rules, and generates a user behavior model according to the user behavior rules.
[0033] Wherein, the user behavior model includes the running time period of each air conditioner, the operating parameters of each air conditioner in each time period, and the usage probability of each air conditioner in each time period.
[0034]That is to say, after the user behavior database is cached, it can first be judged whether there are at least M (M greater than 0 and less than or equal to N) valid records cached in the user behavior database, if not, then continue to cache the user behavior database; if yes, Then divide the running time of the air conditioner into multiple time periods, and then calculate the use probability and corresponding operating parameters of each air conditioner in each time period according to the selected part of the behavior database and through statistical analysis, as User Behavior Model.
[0035] For example, divide the running time of the air conditioner into 24 time periods in a day, that is, each hour is regarded as a time period, assuming that from 8:00 pm to 9:00 pm, the air conditioner runs in cooling mode during this hour. 54 minutes, then the use probability of the air conditioner during this time period is 54/60=90%, and the operation mode is cooling mode.
[0036] S3: The behavior prediction module predicts the user's control behavior on each air conditioner according to the user behavior model to generate corresponding control parameters, so as to control the corresponding air conditioners according to the corresponding control parameters.
[0037] That is to say, in each time period, the behavior prediction module can obtain the control parameters of each air conditioner in the corresponding time period according to the user behavior model, and control the corresponding air conditioners according to the control parameters.
[0038] According to a specific embodiment of the present invention, such as figure 2 As shown, the behavior prediction module predicts the user's control behavior for each air conditioner according to the user behavior model to generate corresponding control parameters, specifically including: the behavior prediction module calculates the current time period for each air conditioner according to the user behavior model and the current time period and judge the usage probability of each air conditioner in the current time period; if the usage probability of any air conditioner in the current time period is greater than or equal to the preset start-up threshold, the behavior prediction module will generate a command to control the start-up of the air conditioner Control parameters; if the usage probability of any air conditioner in the current time period is less than or equal to the preset shutdown threshold, the behavior prediction module will generate control parameters to control the shutdown of the air conditioner.
[0039] As mentioned above, in the control method of the embodiment of the present invention, first, in the process of the user controlling the air conditioner, the user's control behavior is collected and stored through the information collection module; and then the information processing module analyzes the collected user's control behavior To calculate the use probability of each air conditioner in each time period to form a user behavior model; finally, at the beginning of each time period, the behavior prediction module obtains the use probability of each air conditioner in the current time period according to the user behavior model, and The usage probability is compared with the start/stop threshold, and the air conditioner is controlled to start/shut down according to the comparison result.
[0040] Therefore, the control method of the embodiment of the present invention adopts machine learning and behavior prediction technology, collects and stores the behavior data of the user using the air conditioner, and then conducts statistical analysis based on time to obtain the user behavior law, and controls the air conditioner according to the user behavior law . Therefore, through repeated collection and processing, user behavior self-learning can be realized, user behavior can be effectively predicted, and the air conditioner is made intelligent and practical. Great convenience and experience.
[0041] The control method of the embodiment of the present invention will be described in detail below by taking the control of turning on and off the air conditioner as an example.
[0042] For each air conditioner used by the user, the start-up instruction received by the air conditioner and the corresponding start-up time, shutdown instruction and corresponding turn-off time are collected, thereby forming a real-time updated cache database of the last ten days.
[0043] Divide the time when the user uses each air conditioner to determine the running time period of each air conditioner, for example, one hour. The information processing module calculates the time period for each air conditioner in a day through statistical analysis based on at least three valid records in the cache database of the last ten days. The frequency of use of each air conditioner in one hour is used to determine the probability of use of each air conditioner in each hour of the day, which is used as the user's behavior model for using the air conditioner.
[0044] Every hour, the behavior prediction module calculates the use probability of each air conditioner in the current time period according to the user's air conditioner use behavior model and the current time period. When the use probability is greater than or equal to the preset power-on threshold such as 80%, The corresponding air conditioner is controlled to be turned on, and when the usage probability is less than or equal to a preset shutdown threshold such as 20%, the corresponding air conditioner is controlled to be turned off.
[0045] More specifically, such as figure 2 As shown, the control method of the embodiment of the present invention includes the following steps:
[0046] S101: Collect and cache the behavior information of users using each air conditioner in real time to form a user behavior database.
[0047] S102: Determine whether the user behavior database caches valid records for at least 3 days.
[0048] If yes, execute step S103; if no, return to step S101.
[0049] S103: Analyze the cached user behavior database, calculate the usage probability of each air conditioner in each time period, and generate a user behavior model.
[0050] S104: Determine whether it is the start time point of each time period.
[0051] If yes, execute step S105; if no, return to step S101.
[0052] S105: Obtain and calculate the use probability of each air conditioner in the current time period according to the user behavior model.
[0053] S106: Control the air conditioners whose usage probability is greater than or equal to 80% to be turned on, and control the air conditioners whose usage probability is less than or equal to 20% to be turned off.
[0054] Further, according to an embodiment of the present invention, the control method of the user behavior self-learning air conditioning system further includes: updating the user behavior model in real time.
[0055] That is to say, after the user behavior model is generated, the user's control information on the air conditioner can be continuously collected through the information collection module, and then the user behavior model can be modified through the information processing module, so that the user behavior model can be continuously improved, thereby realizing user behavior machine learning and automatic optimization.
[0056] Specifically, after the predictive control of the behavior prediction module is completed, the collection operation of the information collection module will continue, and the use probability of each air conditioner in each time period will be recalculated by the information processing module to modify the user behavior model.
[0057] It should be noted that the user can adjust the prediction results in the user behavior model. The information collection module can also collect the user's adjustment instructions on the forecast results. When the user adjusts the forecast results, the information processing module can judge whether there is an abnormality in the use probability of each air conditioner in each time period. If there is an abnormality, pass The preset penalty factor penalizes the abnormal usage probability, and the corresponding usage probability is corrected according to the doubling of the preset penalty factor to further optimize the user behavior model.
[0058] It should be understood that the relationship between the air conditioner, the communication device and the intelligent control device described in the above embodiments is a logical relationship, the communication device can be physically integrated with the air conditioner, and the intelligent control device can also be physically integrated with the air conditioner In other words, in terms of physical implementation, the system composed of air conditioners, communication devices and intelligent control devices can be adjusted or changed appropriately.
[0059] In addition, it should be noted that the time period for the information collection module to cache the user behavior database, the time period for the information processing module to calculate the user behavior model, and the startup threshold/shutdown threshold set by the behavior prediction module can all be determined according to actual application scenarios. Appropriate adjustments.
[0060] In summary, according to the control method of the user behavior self-learning air-conditioning system proposed in the embodiment of the present invention, the user's control information on each air conditioner is collected in real time through the information collection module to form a user behavior database, and the user behavior is collected through the information processing module. The behavior database is analyzed and processed to obtain user behavior rules, and then generate user behavior models according to user behavior rules. The control parameters control the corresponding air conditioners. Therefore, this method automatically optimizes user behavior rules through continuous learning, can effectively predict user behavior, and intelligently control air conditioners according to user behavior rules, for example, it can intelligently turn on/off the air conditioner that the user wants to turn on/off. It brings better convenience and experience, and this method has strong practicability, and also provides a useful exploration for the intelligent development of home appliances.
[0061] In order to implement the methods of the foregoing embodiments, the embodiments of the present invention further propose a user behavior self-learning air conditioning system.
[0062] image 3 is a schematic block diagram of a user behavior self-learning air conditioning system according to an embodiment of the present invention. like image 3 As shown, the user behavior self-learning air conditioning system includes: at least one air conditioner 10 , a communication device 20 , and an intelligent control device 30 .
[0063] Wherein, the communication device 20 is connected with each air conditioner; the intelligent control device 30 is connected with the communication device 20 to communicate with each air conditioner through the communication device 20 . In other words, at least one air conditioner 10 communicates with the intelligent control device 30 through the communication device 20 , and the communication method can be CAN bus communication or serial communication.
[0064] The intelligent control device 30 includes an information collection module 301, an information processing module 302 and a behavior prediction module 303, wherein the information collection module 301 is used to collect the user's control information on each air conditioner in real time to form a user behavior database, and the information processing module 302 uses To analyze the user behavior database to obtain user behavior rules, and generate a user behavior model according to the user behavior rules, the behavior prediction module 303 is used to predict the user's control behavior for each air conditioner according to the user behavior model to generate corresponding control parameters, to Control the corresponding air conditioner according to the corresponding control parameters.
[0065] Wherein, the control information includes control objects, control time points and control instructions.
[0066] It should be noted that the control object may refer to the identification information of the air conditioner, the control instruction may refer to an instruction input by the user to the corresponding air conditioner, such as a start-up instruction or a shutdown instruction, etc., and the control time point may refer to the user receiving the control instruction. The time point of the input command, so for each control object (air conditioner), the information collection module 301 collects the control command input by the user in real time and the control time point of receiving the control command and stores them in the corresponding position, thereby forming a user behavior database .
[0067] Specifically, the information collection module 301 can collect control commands received by the air conditioner and corresponding control time points for each air conditioner used by the user, such as a power-on command and the corresponding power-on time, a power-off command and the corresponding power-off time, Thus, a user behavior database cached in the last N days that is updated in real time is formed.
[0068] For example, assuming that the user behavior self-learning air conditioning system includes air conditioner 1 and air conditioner 2, the user inputs a start command to air conditioner 1 at time point 1, a temperature setting command to air conditioner 1 at time point 2, and At time point 3, a shutdown command is input to the air conditioner 1 . Then the user inputs a startup command to the air conditioner 2 at time point 4, a wind gear setting command to the air conditioner 2 at time point 5, and a shutdown command to the air conditioner 2 at time point 6, so that the information collection module 301 can form a The user behavior database shown in Table 1 below:
[0069] Table 1
[0070]
[0071] It should be understood that the above examples only illustrate some control instructions, and the user behavior database may also include other control instructions.
[0072] Wherein, the user behavior model includes the running time period of each air conditioner, the operating parameters of each air conditioner in each time period, and the usage probability of each air conditioner in each time period.
[0073] That is to say, after caching the user behavior database, the information processing module 302 can first judge whether there are at least M (M is greater than 0 and less than or equal to N) valid records cached in the user behavior database, if not, then the information collection module 301 continues Cache the user behavior database; if yes, the information processing module 302 divides the running time of the air conditioner into multiple time periods, and then calculates the time period of each air conditioner in each time period according to the selected part of the behavior database and through statistical analysis. The probability of use and the corresponding operating parameters are used as a user behavior model.
[0074] For example, divide the running time of the air conditioner into 24 time periods in a day, that is, each hour is regarded as a time period, assuming that from 8:00 pm to 9:00 pm, the air conditioner runs in cooling mode during this hour. 54 minutes, then the use probability of the air conditioner during this time period is 54/60=90%, and the operation mode is cooling mode.
[0075] According to a specific embodiment of the present invention, the behavior prediction module 303 further judges and calculates the use probability of each air conditioner in the current time period according to the user behavior model and the current time period, and calculates the use probability of each air conditioner in the current time period Judgment, wherein, if the use probability of any air conditioner in the current time period is greater than or equal to the preset startup threshold, the behavior prediction module 303 generates control parameters for controlling the startup of the air conditioner; if the use probability of any air conditioner in the current time period If it is less than or equal to the preset shutdown threshold, the behavior prediction module 303 generates control parameters for controlling the shutdown of the air conditioner.
[0076] As mentioned above, in the system of the embodiment of the present invention, first, in the process of the user controlling the air conditioner, the user's control behavior is collected and stored through the information collection module 301; then the information processing module 302 performs the collected user control behavior Analyze to calculate the use probability of each air conditioner in each time period to form a user behavior model; finally, at the beginning of each time period, the behavior prediction module 303 obtains the use probability of each air conditioner in the current time period according to the user behavior model , and compare the usage probability with the start/shutdown threshold, and control the start/shutdown of the air conditioner according to the comparison result.
[0077] Therefore, the system of the embodiment of the present invention adopts machine learning and behavior prediction technology to collect and store the behavior data of users using the air conditioner, and then conduct statistical analysis based on time to obtain the user behavior law, and control the air conditioner according to the user behavior law. Therefore, through repeated collection and processing, user behavior self-learning can be realized, user behavior can be effectively predicted, and the air conditioner is made intelligent and practical. Great convenience and experience.
[0078] The system of the embodiment of the present invention will be described in detail below by taking the control of turning on and off the air conditioner as an example.
[0079] For each air conditioner used by the user, the information collection module 301 collects the start-up command received by the air conditioner and the corresponding start-up time, the shutdown command and the corresponding shutdown time, thereby forming a real-time updated cache database of the last ten days.
[0080] The time when the user uses each air conditioner is divided to determine the running time of each air conditioner, for example, one hour, and the information processing module 303 calculates the time period within a day through statistical analysis based on at least three valid records in the cache database of the last ten days. The frequency of use of each air conditioner in each hour is used to determine the use probability of each air conditioner in each hour of the day, which is used as the user's behavior model for using the air conditioner.
[0081] Every hour, the behavior prediction module 303 calculates the use probability of each air conditioner in the current time period according to the user's air conditioner use behavior model and the current time period, when the use probability is greater than or equal to the preset power-on threshold such as 80% , control the corresponding air conditioner to turn on, and when the usage probability is less than or equal to a preset shutdown threshold such as 20%, control the corresponding air conditioner to turn off.
[0082] Further, according to an embodiment of the present invention, the intelligent control device 30 is also used to update the user behavior model in real time.
[0083] That is to say, after the user behavior model is generated, the user's control information on the air conditioner can be continuously collected through the information collection module 301, and then the user behavior model can be modified through the information processing module 302, so that the user behavior model can be continuously improved, thereby realizing user behavior Machine learning and automatic optimization.
[0084] Specifically, after the predictive control of the behavior prediction module 303 is completed, the collection operation of the information collection module 301 will continue, and the use probability of each air conditioner in each time period will be recalculated through the information processing module 302 to modify the user behavior model .
[0085] It should be noted that the user can adjust the prediction results in the user behavior model. The information collection module 301 can also collect the user's adjustment instruction on the prediction result. When the user adjusts the prediction result, the information processing module 302 can judge whether the usage probability of each air conditioner in each time period is abnormal. Abnormal uses the preset penalty factor to punish the abnormal usage probability, and the corresponding usage probability is corrected by doubling the preset penalty factor to further optimize the user behavior model.
[0086] It should be understood that the relationship between the air conditioner, the communication device 20 and the intelligent control device 30 described in the above embodiments is a logical relationship, the communication device 20 can be physically integrated with the air conditioner, and the intelligent control device 30 can also be in It is physically integrated with the air conditioner, that is, in terms of physical realization, the system composed of the air conditioner, the communication device 20 and the intelligent control device 30 can be adjusted or changed appropriately.
[0087] In addition, it should be noted that the duration of the information collection module 301 caching the user behavior database, the time period divided by the information processing module 302 to calculate the user behavior model, and the startup threshold/shutdown threshold set by the behavior prediction module 303 can all be based on actual conditions. Appropriate adjustments are made to the application scenario.
[0088] In summary, according to the user behavior self-learning air-conditioning system proposed in the embodiment of the present invention, the user's control information on each air conditioner is collected in real time through the information collection module to form a user behavior database, and the user behavior database is processed through the information processing module. Analyze and process to obtain user behavior rules, and then generate a user behavior model according to the user behavior rules. Finally, the behavior prediction module predicts the user's control behavior for each air conditioner according to the user behavior model to generate corresponding control parameters to control the air conditioner according to the corresponding control parameters. corresponding air conditioner. Therefore, the system automatically optimizes user behavior rules through continuous learning, can effectively predict user behavior, and intelligently control air conditioners according to user behavior rules. Bring better convenience and experience, and the system has strong practicability, and also provides useful exploration for the intelligent development of home appliances.
[0089] In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Back", "Left", "Right", "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise", "Axial", The orientation or positional relationship indicated by "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the referred device or element Must be in a particular orientation, be constructed in a particular orientation, and operate in a particular orientation, and therefore should not be construed as limiting the invention.
[0090] In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.
[0091] In the present invention, unless otherwise clearly specified and limited, terms such as "installation", "connection", "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrated; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components or the interaction relationship between two components, unless otherwise specified limit. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention according to specific situations.
[0092] In the present invention, unless otherwise clearly specified and limited, the first feature may be in direct contact with the first feature or the first and second feature may be in direct contact with the second feature through an intermediary. touch. Moreover, "above", "above" and "above" the first feature on the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. "Below", "beneath" and "beneath" the first feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is less horizontally than the second feature.
[0093] In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.
[0094] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention, those skilled in the art can make the above-mentioned The embodiments are subject to changes, modifications, substitutions and variations.