Air conditioning method and device and air conditioning equipment

Abstract

The invention relates to an air conditioning method and device and air conditioning equipment. The method comprises the steps of obtaining user behavior data and environment data in a target area, determining an air conditioning strategy of the air conditioning equipment based on the user behavior data, the environment data and preset user preference data, and adjusting the working state of the air conditioning equipment based on the air conditioning strategy. By adopting the method, the air conditioning precision can be improved.

Description

Technical Field

[0001] The present application relates to the field of air conditioning technology, and in particular to an air conditioning method, an apparatus, an air conditioning device, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the development of smart home appliances, air purifiers have gradually become one of the most commonly used home appliances. An air purifier is an appliance that purifies the air through filtration, electrical purification, or a combination of the two. It can effectively absorb polluted gases, particles, and harmful bacteria and viruses.

[0003] The working mode of traditional air purifiers is usually simple and modular. The working mode is pre-set in the controller. Users can control the air purifier to work with a fixed wind speed, humidification amount, lighting, etc. by selecting a specific working mode.

[0004] However, the working modes of air purifiers in traditional solutions are often limited. It is difficult to meet users' needs for air improvement only through the existing working modes. In addition, users have little understanding of the air environment and do not understand how to adjust the working parameters of the air purifier to meet their needs. In other words, the existing air conditioning methods have the problem of low accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide an air conditioning method, device, equipment, computer equipment, computer-readable storage medium and computer program product that can improve the air conditioning accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides an air conditioning method, comprising:

[0007] Obtain user behavior data and environmental data in the target area;

[0008] Determining an air conditioning strategy for an air conditioning device based on the user behavior data, the environmental data, and preset user preference data;

[0009] Based on the air conditioning strategy, the working state of the air conditioning equipment is adjusted.

[0010] In a second aspect, the present application also provides an air conditioning device, comprising:

[0011] Data acquisition module, used to obtain user behavior data and environmental data in the target area;

[0012] a parameter determination module, configured to determine an air conditioning strategy of an air conditioning device based on the user behavior data, the environmental data, and preset user preference data;

[0013] The air conditioning module is used to adjust the working state of the air conditioning equipment based on the air conditioning strategy.

[0014] In the third aspect, the present application also provides an air conditioning device, including a controller, and a data acquisition device and an air purification device connected to the controller, the data acquisition device being used to collect and send user behavior data and environmental data in a target area to the controller, and the controller being used to control the air purification device to adjust the air environment of the target area based on the air conditioning method described in any one of the air conditioning embodiments.

[0015] In a fourth aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in any one of the air conditioning embodiments when executing the computer program.

[0016] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in any one of the air conditioning embodiments.

[0017] In a sixth aspect, the present application further provides a computer program product, including a computer program, which implements the steps in any one of the air conditioning embodiments when executed by a processor.

[0018] The above-mentioned air conditioning method, device, air conditioning equipment, computer equipment, computer-readable storage medium and computer program product are different from the traditional solution in which the air purifier only provides limited working modes. This solution obtains user behavior data and environmental data, and formulates an air conditioning strategy based on the user behavior data, environmental data and preset user preference data, wherein the user preference data reflects the user's personalized needs for the air environment, the environmental data in the target area reflects the actual conditions of the current air environment, the user behavior data reflects the user's activities in the target area, and the user's preferences for the air conditioning strategy. The above-mentioned parameters provide reliable data support for formulating air conditioning parameters, so that a more personalized air conditioning strategy that better meets user needs can be formulated. Finally, based on the air conditioning strategy, the working state of the air conditioning equipment is adjusted, which can improve the accuracy of air conditioning and better meet the user's needs for air conditioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is an application environment diagram of an air conditioning method in an embodiment;

[0021] Figure 2 is a schematic flow chart of an air conditioning method in one embodiment;

[0022] Figure 3 is a schematic flow chart of an air conditioning method in another embodiment;

[0023] Figure 4 is a schematic flow chart of an air conditioning method in yet another embodiment;

[0024] Figure 5 A schematic diagram of a flow chart of an air conditioning method in yet another embodiment;

[0025] Figure 6 A schematic diagram of a flow chart of an air conditioning method in another embodiment;

[0026] Figure 7 A schematic diagram of a flow chart of an air conditioning method in a detailed embodiment;

[0027] Figure 8 is a decision logic diagram of an air conditioning decision model in one embodiment;

[0028] Fig. 9 is a structural block diagram of an air conditioning device in one embodiment;

[0029] Fig.10 is a structural block diagram of an air conditioning device in one embodiment;

[0030] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The air conditioning method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the data acquisition device 102 communicates with the controller 104 via a network. The data storage system can store data that the controller 104 needs to process. The data storage system can be integrated on the controller 104, or placed on the cloud or other network servers.

[0033] Specifically, the data collection device 102 may collect user behavior data and environmental data in the target area in real time, and send the data to the controller 104. The controller 104 determines the air conditioning strategy of the air conditioning equipment based on the user behavior data, environmental data and preset user preference data, and then adjusts the working state of the air conditioning equipment based on the air conditioning strategy.

[0034] Among them, the data acquisition device 102 can be but is not limited to various sensing devices, such as temperature sensors, humidity sensors, infrared sensors, etc. The controller 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0035] In an exemplary embodiment, Figure 2 As shown, an air conditioning method is provided, which is applied to Figure 1 The controller 104 in the embodiment is taken as an example to illustrate, and the following steps are included:

[0036] S100, obtaining user behavior data and environment data in a target area.

[0037] The target area refers to the area that needs to be air-conditioned, which is the specific spatial range where the air-conditioning equipment works, such as the room where the air-conditioning equipment is located. User behavior data refers to various behavioral information of users in the target area, such as the operation of the air-conditioning equipment by the user in the target area, the activities of the user in the target area, etc. Environmental data includes but is not limited to air quality-related indicators, temperature, humidity, light intensity, wind speed and other data in the target area.

[0038] Exemplarily, user behavior data and environmental data in the target area can be collected through various sensors or other monitoring means. For example, infrared sensors can be used to monitor the activities of users in the target area to collect user behavior data in the target area, and air quality sensors, temperature sensors, humidity sensors, wind speed sensors, light sensors, etc. can be used to collect environmental data in the target area.

[0039] S200, determining an air conditioning strategy of an air conditioning device based on user behavior data, environmental data, and preset user preference data.

[0040] Among them, the preset user preference data is pre-set data for air conditioning equipment, reflecting the user's preference for air quality and the way the air conditioning equipment adjusts the air. For example, the user may prefer that the air humidity in the target area is maintained at 40%-50%, or the user prefers that the air outlet of the air conditioning equipment is facing people when adjusting the air. The air conditioning strategy is a customized solution for how the air conditioning equipment operates to meet user needs and environmental requirements, including but not limited to the wind speed, operating power, whether to turn on heating, whether to turn on humidification, working mode, etc. of the air conditioning equipment. Air conditioning equipment includes but is not limited to air purifiers, air conditioners and other equipment that can adjust parameters such as air temperature, humidity, and cleanliness.

[0041] For example, based on user behavior data, the user's activity intensity, stay area, operations taken on air conditioning equipment in different time periods can be analyzed, and based on environmental data, the air quality indicators (such as formaldehyde concentration, PM2.5 concentration, etc.), temperature, humidity, light intensity and other environmental characteristics in the target area can be analyzed. The above different combinations of environmental characteristics will affect the formulation of air conditioning strategies. In addition, user preference data needs to be considered, which can be pre-input by the user through the interactive device on the air conditioning device when the user starts the air conditioning device, or pre-input to the server through other terminals, so as to understand the user's specific preferences for air freshness, temperature, humidity, air conditioning equipment working mode, etc.

[0042] Furthermore, after the above analysis, an air conditioning strategy can be formulated by rule matching or model prediction, etc. For example, an air conditioning rule is formulated in advance, and the above analysis results are matched with the air conditioning rule. For example, if the environmental data shows that the temperature in the target area is 10 degrees Celsius, the user behavior data shows that the user is active in the room, and the user preference data preset by the user shows that the user's favorite indoor temperature is 25 degrees Celsius, then the air conditioning strategy formulated according to the air conditioning rule can be to control the air conditioning device to turn on the heating and adjust the indoor temperature to 25 degrees Celsius.

[0043] In addition, an air conditioning strategy can also be formulated through a deep learning model. Specifically, the analysis results obtained by analyzing the user behavior data, environmental data, and preset user preference data are input into a trained air conditioning decision model. The air conditioning decision model is trained based on historical user behavior data, historical environmental data, and historical user preference data, and has fully learned the relationship between the above data and the final air conditioning strategy. Therefore, after the above analysis results are input into the trained air conditioning decision model, the air conditioning model will output an air conditioning strategy that meets user needs. In addition, the user behavior data, environmental data, and preset user preference data can also be directly input into the trained air conditioning decision model, and the air conditioning decision model performs operations such as feature extraction and strategy formulation to output an air conditioning strategy.

[0044] S300: Adjust the working state of the air conditioning equipment based on the air conditioning strategy.

[0045] Continuing from the above embodiment, after obtaining the air conditioning strategy, the server can convert the air conditioning strategy into specific instructions that the air conditioning equipment can understand and execute. For example, if the air conditioning strategy is to adjust the temperature of the target area to 25 degrees Celsius and maintain the humidity at 50%, the server can correspondingly send control instructions to the air conditioning equipment such as "set the temperature to 25 degrees Celsius" and "adjust to a specific humidification mode".

[0046] After receiving the control instructions sent by the server, the air conditioning equipment can adjust its own working state by adjusting operating parameters such as the compressor operating frequency, fan speed, and heating temperature to implement the air conditioning strategy.

[0047] The above-mentioned air conditioning method, device, air conditioning equipment, computer equipment, computer-readable storage medium and computer program product are different from the traditional solution in which the air purifier only provides limited working modes. This solution obtains user behavior data and environmental data, and formulates an air conditioning strategy based on the user behavior data, environmental data and preset user preference data, wherein the user preference data reflects the user's personalized needs for the air environment, the environmental data in the target area reflects the actual conditions of the current air environment, the user behavior data reflects the user's activities in the target area, and the user's preferences for the air conditioning strategy. The above-mentioned parameters provide reliable data support for formulating air conditioning parameters, so that a more personalized air conditioning strategy that better meets user needs can be formulated. Finally, based on the air conditioning strategy, the working state of the air conditioning equipment is adjusted, which can improve the accuracy of air conditioning and better meet the user's needs for air conditioning.

[0048] In one embodiment, Figure 3 As shown, S200 includes:

[0049] S210, using user activity data, environmental data and preset user preference data in the target area as input, calling a preset air conditioning decision model to determine a temperature adjustment strategy, an air supply strategy and a humidity adjustment strategy.

[0050] S220: Determine an air conditioning strategy for the air conditioning equipment according to the temperature conditioning strategy, the air supply strategy, and the humidity conditioning strategy.

[0051] Among them, the user behavior data in the target area includes the user activity data in the target area, and the preset air conditioning decision model is trained based on historical user activity data, historical environmental data and historical user preference data. The user activity data characterizes the specific activities of users in the target area, such as whether they are moving, stationary, or in an activity area. The temperature adjustment strategy refers to a scheme for adjusting the temperature of the target area, such as raising or lowering the temperature to a specific value, or dynamically adjusting the temperature according to certain rules. The air supply strategy includes but is not limited to the air supply direction and air supply intensity. The air supply direction refers to the direction in which the air conditioning equipment blows air, such as upward air supply, downward air supply, left air supply, right air supply or multi-angle air supply, etc. The air supply intensity refers to the wind force of the air delivered by the air conditioning equipment, which can be measured by indicators such as wind speed. The preset air conditioning decision model is an intelligent decision model based on a deep learning neural network. A composite neural network of CNN and LSTM can be used to convert the data input into the preset air conditioning decision model into a time series format, so as to better understand and predict user behavior and formulate an air conditioning strategy that better meets user needs.

[0052] Specifically, the preset air decision model is trained based on historical user activity data, historical environmental data, and historical preference data. During the training process, the air decision model learns the association between different combinations of historical user activity data, historical environmental data, and historical preference data and corresponding air conditioning strategies. The user activity data, environmental data, and preset user preference data in the target area can be used as inputs to the preset air decision model. The preset air decision model can determine the temperature control strategy, air supply strategy, humidity control strategy, etc. based on the above input data and the rules learned during the training process, and determine the air conditioning strategy of the air conditioning equipment by combining the temperature control strategy, air supply strategy, and humidity control strategy.

[0053] For example, a user purchases an air conditioning device, which may be a certain air purifier product. When purchasing the product, a preset air conditioning decision model has been deployed in the controller of the air purifier, which may be a neural network that can be used to make decisions. The user only needs to input user preference data on the operating system corresponding to the air purifier product, such as preferred temperature, humidity, wind speed and other parameters. The sensor device of the air purifier will collect user activity data and environmental data in the target area. The controller will use the user activity data, environmental data and user preference data in the target area as input, call the preset air conditioning decision model to make decisions, and then adjust the working state of the air conditioning device.

[0054] Assume that the user presets the temperature to 24 degrees Celsius, prefers the wind to blow towards people, the user presets the humidity to 80%, has no requirements for noise, the target area is his home, the outdoor weather is cloudy, the indoor temperature is 22 degrees Celsius, the air circulation is good, and the air humidity is 60%. At this time, the user turns on the air purifier, and the air purifier will automatically collect and make decisions based on environmental data and user activity data. Specifically, due to the low temperature in the environmental data, the temperature adjustment strategy of the air purifier can be to heat the resistance wire so that the temperature of the target area rises slowly. If the temperature of the target area reaches the user's preset temperature, the air purifier stops heating the resistance wire. Since the user prefers the wind to blow towards people, the infrared sensor in the air purifier will collect and feed back the user activity data, which can be the biological activity in the target area, to the preset air conditioning decision model. The preset air conditioning strategy model can judge the distance and direction of the user from the air purifier in the decision-making process. As one of the decision-making bases, the air supply strategy of the air purifier can be to control the air supply direction to always be the direction of the user, or if the user is close to the air purifier, then within the wind force range, strengthen the air supply to the user's direction. Since the humidity in the target area is lower than the user-preset humidity, after the preset air conditioning model decision, the humidity adjustment strategy can be to turn on the humidification system of the air purifier, and use ultrasonic oscillation technology to break up the water in the water storage box in the humidification system into very fine water mist particles, and then blow them out through the fan to achieve the humidification effect. When it is detected that the humidity in the target area reaches the user-preset humidity, the humidification system is stopped.

[0055] In this embodiment, based on the different preferences of each user as well as real-time user activities and environmental conditions, with the help of a trained air conditioning decision model, a more accurate and personalized air conditioning strategy can be obtained, thereby improving the control accuracy of the air conditioning equipment and making the air conditioning results more in line with user needs.

[0056] In one embodiment, Figure 4 As shown, after S220, the method further includes:

[0057] S230: Update the air conditioning strategy based on the autonomous operation data of the air conditioning equipment.

[0058] S300 includes:

[0059] S310: Adjust the working state of the air conditioning equipment based on the updated air conditioning strategy.

[0060] Among them, user behavior data includes autonomous operation data for air conditioning equipment. Autonomous operation data refers to data generated by users actively operating air conditioning equipment, such as users manually adjusting the wind speed level, heating level, and switching specific functions of air conditioning equipment (such as turning on the humidification function).

[0061] Specifically, the air conditioning strategy is determined by user activity data, environmental data, and preset user preference data, but it may still not fully meet the needs of the user. The user's autonomous operation data for the air conditioning device reflects the user's willingness to adjust the current air environment. Therefore, it is necessary to update the determined air conditioning strategy based on the autonomous operation data to better meet the actual needs of the user. For example, if the user manually increases the temperature of the air conditioning device from the set 25 degrees Celsius to 26 degrees Celsius, or adjusts the wind speed gear of the air conditioning device from a low gear to a high gear, the controller of the air conditioning device will update the air conditioning strategy based on the above autonomous operation data.

[0062] For example, in the rainy season, the weather is dull, the air is humid, and the ventilation is not very good. If the user does not know enough about the product when just purchasing the air conditioning device, he / she may input the user preference data that does not meet the actual needs, for example, the user inputs the need for the air-heating system of the air conditioning device and hopes that the wind will blow towards people. However, in fact, when using the air conditioning device to adjust the air, the user thinks that the air-heating system of the air conditioning device is not needed and does not like the wind blowing towards people, which leads to the user often actively turning off the air-heating system of the air conditioning device and actively operating so that the wind does not blow towards people. In addition, due to the stuffy climate, poor air circulation, and poor indoor air quality, the user actively turns on the negative ion generator of the air conditioning device many times to make the air fresher. At this time, the user's "turning off the air-heating system", "letting the wind not blow towards people", and "turning on the negative ion generator" all belong to the user's autonomous operation data for the air conditioning device in this embodiment, and the air conditioning device will update the air conditioning strategy accordingly according to the autonomous operation data.

[0063] In this embodiment, by timely responding to the user's autonomous operation and timely updating the air conditioning strategy according to the autonomous operation data, the air conditioning strategy can better meet the user's needs, making the air conditioning strategy more personalized and improving the air conditioning accuracy.

[0064] In one embodiment, Figure 5 As shown, the method also includes:

[0065] S410, when receiving the autonomous operation data, record the autonomous operation data and the environmental data in the current target area.

[0066] S420, when the number of times the autonomous operation data is received is greater than a preset threshold, the preset air conditioning decision model is trained using the recorded autonomous operation data and the recorded environmental data as training data to update the air conditioning decision model.

[0067] Following the above embodiment, when the controller of the air conditioning device receives the user's autonomous operation data, the controller will synchronously record the autonomous operation data and the environmental data in the current target area. In general, the data collected by the data acquisition device of the air conditioning device will be fed back to the controller so that the air conditioning decision model deployed in the controller can make decisions. However, if the user has an operation adjustment on the air conditioning device at a certain moment, that is, sends the autonomous operation data to the controller, it means that the user's demand and the air conditioning strategy output by the air conditioning decision model at this time have deviated. The environmental data and the user's autonomous operation data at this time can be further normalized and converted into a time series for storage. For example, at a certain moment, the user switches the wind speed of the air conditioning device from a low gear to a high gear. At this time, the controller will record the user's autonomous operation data, and also record the environmental data such as the temperature, humidity, and air quality index in the current target area. The environmental data is normalized and converted into a time series and stored, providing a data basis for the subsequent training of the air conditioning decision model.

[0068] Furthermore, each time the user's autonomous operation data for the air conditioning equipment is recorded, the data will be recorded. However, scattered, single operations often do not have regularity and reference, and there is a possibility of accidental touches. If the air conditioning decision model is trained again every time the autonomous operation data is received, the power consumption of the controller may increase, and the training effect is not satisfactory. Therefore, in this embodiment, a quantity threshold is pre-set. When the number of times the controller receives autonomous operation data is greater than the preset quantity threshold, it means that enough autonomous operation data has been accumulated at this time, which can trigger the training of the preset air conditioning strategy model. Specifically, the preset air conditioning decision model is trained using the recorded autonomous operation data and the corresponding environmental data as training data. During the training process, the air conditioning decision model will learn which air conditioning strategy the user prefers in different environments, thereby adjusting its own decision logic.

[0069] In addition, in addition to the number of times the autonomous operation data is received being greater than the preset quantity threshold, if the user's operation of the air conditioning equipment becomes frequent in a short period of time, or even the user actively operates the air conditioning equipment almost every time the air conditioning equipment is used, that is, when the frequency at which the controller receives the autonomous operation data is greater than the preset frequency threshold, the training of the preset air conditioning strategy model can also be triggered, and the received autonomous operation data and the corresponding environmental data can be converted into time series data. The air conditioning strategy model will continue to be based on the received time series data, and will continue to better understand the user's preferences based on the characteristics reflected by these time series data, understand the difference between the decision logic required by the user and the existing neural network weights of the air conditioning strategy model, and optimize its own neural network weights, thereby optimizing its own decision-making ability, and backing up new neural network weights.

[0070] In this embodiment, by continuously collecting the user's autonomous operation data and combining it with environmental data to train the air conditioning decision model, the air conditioning decision model can gradually adapt to the user's unique behavior patterns and preferences. In this way, the air conditioning decision model can adaptively meet the user's changing needs and flexibly serve the user, so that the final air conditioning strategy is more in line with the user's actual needs.

[0071] In one embodiment, Figure 6 As shown, the method also includes:

[0072] S430, backing up the preset air conditioning decision model, and after each update of the air conditioning decision model, backing up the updated air conditioning decision model to obtain backup data.

[0073] Following the above embodiment, backing up the preset air conditioning decision model is equivalent to retaining the initial version of the air conditioning decision model, and after each update of the air conditioning decision model, the updated air conditioning decision model needs to be backed up. Model backup refers to backing up and saving the neural network weights of the air conditioning decision model deployed in the air conditioning equipment when it leaves the factory, as well as the neural network weights of various versions of the air conditioning decision model during the user's use of the air conditioning equipment. If the user is not satisfied with the updated air conditioning strategy during the use of the air conditioning equipment, the backup data can be used to restore to a certain historical version of the air conditioning model without making corrections to the inappropriate neural network weights. For example, if the air conditioning equipment has a situation where the prediction effect becomes worse after the air conditioning decision model is updated, causing abnormal operation of the air conditioning equipment, etc., it can quickly trace back to the historical version of the air conditioning decision model so that the air conditioning equipment can operate normally.

[0074] Specifically, the backup data of different versions of the air conditioning decision model can be stored through devices such as solid-state hard drives, or the backup data can be uploaded to a cloud server using cloud storage, which not only provides a larger storage space, but also enables the backup data to be obtained from the cloud server when the local storage device is damaged. In addition, when backing up different versions of the air conditioning decision model, the backup time, model update content, update reason and other information of each version of the air conditioning decision model can be recorded, and a specific version identifier can be added to it, so that users can quickly find the correct version of the air conditioning decision model when tracing back.

[0075] In this embodiment, by backing up the preset air conditioning decision model and each updated air conditioning decision model, the user can quickly and conveniently trace the current air conditioning decision model back to the historical version of the air conditioning decision model, thereby reducing the training cost invested in the wrong model, and making the air conditioning decision model more in line with user needs and improving air conditioning accuracy.

[0076] In one embodiment, Figure 7 As shown, the method also includes:

[0077] S440, receiving a backtracking instruction for the air conditioning decision model, the backtracking instruction carrying a model version identifier, and based on the backup data, backtracking the current air conditioning decision model to the air conditioning decision model corresponding to the model version identifier.

[0078] Among them, the backtracking instruction is used to restore the air conditioning decision model to a specific historical version. The model version identifier is an identifier used to uniquely determine the air conditioning decision model version in the backup data. It can be a digital number, timestamp, version name, etc. The corresponding backup model can be accurately found through this identifier.

[0079] Specifically, the user can send a backtracking instruction for the air conditioning decision model to the controller of the air conditioning device through the interactive device of the air conditioning device. The backtracking instruction carries a specific model version identifier. For example, the user selects "Backtrack Model" through the system setting interface of the interactive device of the air conditioning device, and specifies to backtrack to the version corresponding to a certain timestamp. At this time, the timestamp can be used as the model version identifier. The user clicks "Backtrack Model" through a touch operation, which is regarded as issuing a backtracking instruction. After receiving the backtracking instruction, the controller of the air conditioning device searches for the air conditioning decision model corresponding to the model version identifier in the backup data, and loads the air conditioning decision model corresponding to the model version identifier into the system to replace the existing air conditioning decision model to achieve model backtracking.

[0080] For example, the user will continuously update and back up the air conditioning decision model during use, and the neural network weights of the air conditioning decision model will continue to change with the user's use, and continue to approach the user's needs. However, during the update process of the air conditioning decision model, some training deviations may occasionally occur, resulting in the air conditioning strategy obtained by the updated air conditioning decision model being less able to meet the user's needs than before the update. At this time, the user can trace the air conditioning decision model back to the previous version or any historical version based on the backup data. In addition, the user's preferences are not static, and there are certain regular changes in environmental data throughout the year. If the user's use of air conditioning equipment is relatively stable every year, the air conditioning equipment can form a working paradigm unique to the user. For example, when the rainy season is about to come in a certain year, the user believes that the air conditioning decision model deployed in the air conditioning equipment during the rainy season of the previous year can well meet his air conditioning needs, so the user can directly trace the air conditioning decision model back to the version of the rainy season of the previous year based on the backup data, saving the resources required to update the current air conditioning decision model.

[0081] In this embodiment, the user can backtrack the air conditioning decision model deployed in the air conditioning device to a historical version by sending a backtracking instruction, so that the backtracked air conditioning decision model can better meet user needs and improve air conditioning accuracy.

[0082] In order to make a clearer description of the air conditioning method provided by the present application, the following is a Figure 7 and one A detailed embodiment is explained, and the detailed embodiment includes the following steps:

[0083] S100, obtaining user behavior data and environment data in a target area.

[0084] S210, using user activity data, environmental data and preset user preference data in the target area as input, calling a preset air conditioning decision model to determine a temperature adjustment strategy, an air supply strategy and a humidity adjustment strategy.

[0085] S220: Determine an air conditioning strategy for the air conditioning equipment according to the temperature conditioning strategy, the air supply strategy, and the humidity conditioning strategy.

[0086] S230: Update the air conditioning strategy based on the autonomous operation data of the air conditioning equipment.

[0087] S310: Adjust the working state of the air conditioning equipment based on the updated air conditioning strategy.

[0088] S410, when receiving the autonomous operation data, record the autonomous operation data and the environmental data in the current target area.

[0089] S420, when the number of times the autonomous operation data is received is greater than a preset threshold, the preset air conditioning decision model is trained using the recorded autonomous operation data and the recorded environmental data as training data to update the air conditioning decision model.

[0090] S430, backing up the preset air conditioning decision model, and after each update of the air conditioning decision model, backing up the updated air conditioning decision model to obtain backup data.

[0091] S440, receiving a backtracking instruction for the air conditioning decision model, the backtracking instruction carrying a model version identifier, and based on the backup data, backtracking the current air conditioning decision model to the air conditioning decision model corresponding to the model version identifier.

[0092] The air conditioning decision model can be a neural network, and its decision logic can be as follows: Figure 8 As shown, the input data are environmental data (temperature, humidity, airflow, biology, lighting) and user preference data of user personalized settings. In addition, user activity data can also be used as input data of the neural network (not shown in the figure), and the output data are temperature adjustment strategy (electric heating), humidity adjustment strategy (humidification), air supply strategy (wind speed, wind direction). In addition, the output data can also be whether the air conditioning equipment needs to be muted, etc.

[0093] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0094] Based on the same inventive concept, the embodiment of the present application also provides an air conditioning device for implementing the air conditioning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more air conditioning device embodiments provided below can refer to the limitations of the air conditioning method above, and will not be repeated here.

[0095] In an exemplary embodiment, Fig. 9As shown, an air conditioning device 500 is provided, including: a data acquisition module 510, a parameter determination module 520 and an air conditioning module 530:

[0096] The data acquisition module 510 is used to acquire user behavior data and environmental data in the target area.

[0097] The parameter determination module 520 is used to determine the air conditioning strategy of the air conditioning device based on the user behavior data, the environmental data and the preset user preference data.

[0098] The air conditioning module 530 is used to adjust the working state of the air conditioning equipment based on the air conditioning strategy.

[0099] It can be understood that the air conditioning device 500 provided in this embodiment is a device integrated with multiple logic units or modules that perform specific functions, and is not a common device for conditioning air.

[0100] In one embodiment, the parameter determination module 520 is used to take user activity data, environmental data and preset user preference data in the target area as input, call a preset air conditioning decision model, determine the temperature adjustment strategy, air supply strategy and humidity adjustment strategy, and determine the air conditioning strategy of the air conditioning equipment based on the temperature adjustment strategy, air supply strategy and humidity adjustment strategy, wherein the preset air conditioning decision model is trained based on historical user activity data, historical environmental data and historical user preference data.

[0101] In one embodiment, the air conditioning device 500 is further used to update the air conditioning strategy based on the autonomous operation data of the air conditioning equipment, and the air conditioning module 530 is further used to adjust the working state of the air conditioning equipment based on the updated air conditioning strategy.

[0102] In one embodiment, the air conditioning device 500 is also used to record the autonomous operation data and the environmental data in the current target area when receiving the autonomous operation data. When the number of times the autonomous operation data is received is greater than a preset threshold value, the recorded autonomous operation data and the recorded environmental data are used as training data to train the preset air conditioning decision model to update the air conditioning decision model.

[0103] In one embodiment, the air conditioning device 500 is further used to back up a preset air conditioning decision model, and after each update of the air conditioning decision model, back up the updated air conditioning decision model to obtain backup data.

[0104] In one embodiment, the air conditioning device 500 is also used to receive a backtracking instruction for the air conditioning decision model, the backtracking instruction carries a model version identifier, and based on the backup data, backtracks the current air conditioning decision model to the air conditioning decision model corresponding to the model version identifier.

[0105] Each module in the above air conditioning device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0106] In one embodiment, Fig.10 As shown, an air conditioning device 600 is provided, including a controller 610, and a data acquisition device 620 and an air purification device 630 connected to the controller 610. The data acquisition device 620 is used to collect and send user behavior data and environmental data in the target area to the controller 610. The controller 610 is used to control the air purification device 630 to adjust the air environment of the target area based on the steps in any one of the above-mentioned air conditioning method embodiments.

[0107] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as user behavior data, environmental data and preset user preference data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an air conditioning method is implemented.

[0108] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned air conditioning method embodiment when executing the computer program.

[0110] 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 steps in the above-mentioned air conditioning method embodiment are implemented.

[0111] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps in the above-mentioned air conditioning method embodiment when executed by a processor.

[0112] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0113] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0115] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An air conditioning method, characterized in that: The method comprises: Obtain user behavior data and environmental data in the target area; Determining an air conditioning strategy for an air conditioning device based on the user behavior data, the environmental data, and preset user preference data; Based on the air conditioning strategy, the working state of the air conditioning equipment is adjusted.

2. The method according to claim 1, characterized in that The user behavior data in the target area includes user activity data in the target area, and determining the air conditioning strategy of the air conditioning device based on the user behavior data, the environmental data and preset user preference data includes: Taking the user activity data in the target area, the environmental data and the preset user preference data as input, calling a preset air conditioning decision model to determine a temperature adjustment strategy, an air supply strategy and a humidity adjustment strategy; Determining an air conditioning strategy for an air conditioning device according to the temperature adjustment strategy, the air supply strategy, and the humidity adjustment strategy; The preset air conditioning decision model is trained based on historical user activity data, historical environmental data and historical user preference data.

3. The method according to claim 2, characterized in that The user behavior data also includes autonomous operation data for the air conditioning device. After determining the air conditioning strategy of the air conditioning device according to the temperature adjustment strategy, the air supply strategy and the humidity adjustment strategy, the method further includes: updating the air conditioning strategy based on autonomous operation data for the air conditioning device; The step of adjusting the working state of the air conditioning equipment based on the air conditioning strategy includes: Based on the updated air conditioning strategy, the working state of the air conditioning equipment is adjusted.

4. The method according to claim 3, characterized in that The method further comprises: When receiving the autonomous operation data, recording the autonomous operation data and environmental data in the current target area; When the number of times the autonomous operation data is received is greater than a preset threshold, the preset air conditioning decision model is trained using the recorded autonomous operation data and the recorded environmental data as training data to update the air conditioning decision model.

5. The method according to claim 4, characterized in that The method further comprises: The preset air conditioning decision model is backed up, and after each update of the air conditioning decision model, the updated air conditioning decision model is backed up to obtain backup data.

6. The method according to claim 5, characterized in that The method further comprises: receiving a backtracking instruction for an air conditioning decision model, wherein the backtracking instruction carries a model version identifier; Based on the backup data, the current air conditioning decision model is traced back to the air conditioning decision model corresponding to the model version identifier.

7. An air conditioning device, characterized in that: The device comprises: Data acquisition module, used to obtain user behavior data and environmental data in the target area; a parameter determination module, configured to determine an air conditioning strategy of an air conditioning device based on the user behavior data, the environmental data, and preset user preference data; The air conditioning module is used to adjust the working state of the air conditioning equipment based on the air conditioning strategy.

8. An air conditioning device, characterized in that: The device includes a controller, and a data acquisition device and an air purification device connected to the controller, the data acquisition device is used to collect and send user behavior data and environmental data in the target area to the controller, and the controller is used to execute the steps of the air conditioning method described in any one of claims 1 to 6, and control the air purification device to adjust the air environment of the target area.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images