Comfort assessment method and apparatus for air conditioner, and device and storage medium

Abstract

The present application relates to the technical field of air conditioners, and in particular to a comfort assessment method and apparatus for an air conditioner, and a device and a storage medium. In the present application, current running data of an air conditioner and user operation behavior information are acquired, a comfort assessment is performed on the current running data and the user operation behavior information by means of a trained comfort assessment model to obtain comfort assessment data, and finally, a current comfort assessment result of the air conditioner is determined on the basis of a preset comfort measurement interval combined with the comfort assessment data.

Description

Air conditioner comfort evaluation method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202311086751.5 filed on August 25, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of air conditioners, and in particular to a method, device, equipment and storage medium for evaluating the comfort level of an air conditioner. Background Art

[0003] In traditional technology, in order to improve the user experience when using air conditioning, users generally control the various components of the air conditioner to make the indoor environment reach the user's expected comfort level. However, the current comfort measurement indicators for individual users using air conditioners are too one-sided, making the comfort evaluation of the air conditioner during operation not very accurate.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Technical issues

[0005] The main purpose of this application is to provide a method, device, equipment and storage medium for evaluating the comfort level of an air conditioner, aiming to solve the technical problem in the prior art of low accuracy in evaluating the comfort level of a user when using an air conditioner. Technical Solutions

[0006] To achieve the above objectives, the present application provides a method for evaluating the comfort level of an air conditioner, the method comprising the following steps:

[0007] When the air conditioner is running, obtaining current operating data of the air conditioner and user operation behavior information;

[0008] Determining comfort evaluation data corresponding to the current operation data and the user operation behavior information through a trained comfort evaluation model; and

[0009] The current comfort evaluation of the air conditioner is determined according to a preset comfort metric interval and the comfort evaluation data.

[0010] In one embodiment, before determining the current comfort evaluation of the air conditioner according to the preset comfort metric interval and the comfort evaluation data, the method further includes:

[0011] Obtain a training data sample set;

[0012] Performing comfort evaluation based on the training data sample set using a trained comfort evaluation model to obtain multiple evaluated comfort levels; and

[0013] The multiple evaluated comfort levels are divided into ranges to obtain preset comfort measurement intervals.

[0014] In one embodiment, dividing the multiple evaluated comfort levels into ranges to obtain preset comfort measurement intervals includes:

[0015] Counting the distribution intervals of the plurality of comfort evaluations;

[0016] Filtering the plurality of comfort evaluation distribution intervals based on a preset first ratio threshold and a preset second ratio threshold; and

[0017] The evaluated comfort levels corresponding to the filtered distribution intervals are marked based on the preset comfort metric to obtain a preset comfort metric interval, and the preset first ratio threshold is less than the second ratio threshold.

[0018] In one embodiment, obtaining a training data sample set includes:

[0019] When a user operation behavior is detected, an abnormal data sample, a first comfort data sample, and a second comfort data sample are acquired, wherein the abnormal data sample is current operating data of the air conditioner, the first comfort data sample is operating data of the air conditioner after a first time interval, and the second comfort data sample is operating data of the air conditioner after a second time interval, wherein the first time interval is less than the second time interval; and

[0020] A training data sample set is generated according to the abnormal data sample, the first comfort data sample, and the second comfort data sample.

[0021] In one embodiment, generating a training data sample set according to the abnormal data sample, the first comfort data sample, and the second comfort data sample includes:

[0022] Determining the interval length of the abnormal data samples;

[0023] When the interval duration is greater than or equal to a preset duration, constructing triplet data according to the abnormal data sample, the first comfort data sample, and the second comfort data sample; and

[0024] A training data sample set is generated according to the triple data.

[0025] In one embodiment, determining the current comfort evaluation of the air conditioner according to the preset comfort metric interval and the comfort evaluation data includes:

[0026] When the comfort evaluation data is within a preset comfort metric interval, the current comfort level of the air conditioner is determined according to the preset comfort metric and the comfort evaluation data.

[0027] In one embodiment, the air conditioner comfort evaluation method further includes:

[0028] When the comfort evaluation data is outside a preset comfort metric range, proportionally adjusting the comfort evaluation data to obtain target comfort evaluation data; and

[0029] The current comfort level of the air conditioner is determined according to a preset comfort metric and the target comfort level evaluation data.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a comfort evaluation device for an air conditioner, the comfort evaluation device for an air conditioner comprising:

[0031] An acquisition module, configured to acquire current operating data of the air conditioner and user operation behavior information when the air conditioner is running;

[0032] an evaluation module, configured to determine comfort evaluation data corresponding to the current operation data and the user operation behavior information through a trained comfort evaluation model; and

[0033] An evaluation module is used to determine a current comfort evaluation of the air conditioner according to a preset comfort metric interval and the comfort evaluation data.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a comfort evaluation device for an air conditioner, wherein the comfort evaluation device for an air conditioner includes: a memory, a processor, and a comfort evaluation program for an air conditioner stored on the memory and executable on the processor, wherein the comfort evaluation program for the air conditioner is configured to implement the steps of the comfort evaluation method for the air conditioner as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a comfort evaluation program for an air conditioner is stored. When the comfort evaluation program for an air conditioner is executed by a processor, the steps of the comfort evaluation method for an air conditioner as described above are implemented. Beneficial effects

[0036] The present application discloses a comfort evaluation method for an air conditioner, the comfort evaluation method for an air conditioner comprising: when the air conditioner is running, obtaining current operating data and user operation behavior information of the air conditioner; determining comfort evaluation data corresponding to the current operating data and the user operation behavior information through a trained comfort evaluation model; determining the current comfort evaluation of the air conditioner according to a preset comfort metric interval and the comfort evaluation data. Compared with the prior art, the present application obtains the current operating data and user operation behavior information of the air conditioner, and performs comfort evaluation on the current operating data and user operation behavior information through a trained comfort evaluation model to obtain comfort evaluation data, and finally determines the current comfort evaluation result of the air conditioner according to the preset comfort metric interval combined with the comfort evaluation data, thereby avoiding the technical problem in the prior art of low accuracy of comfort evaluation when a user uses an air conditioner, and improving the comprehensiveness of the comfort evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] FIG1 is a schematic diagram of the structure of an air conditioner comfort evaluation device in a hardware operating environment according to an embodiment of the present application;

[0038] FIG2 is a flow chart of a first embodiment of a method for evaluating the comfort level of an air conditioner according to the present invention;

[0039] FIG3 is a flow chart of a second embodiment of the method for evaluating the comfort level of an air conditioner according to the present invention;

[0040] FIG4 is a structural block diagram of the first embodiment of the comfort evaluation device for an air conditioner of the present application.

[0041] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. Modes for Carrying Out the Invention

[0042] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0043] Refer to Figure 1, which is a schematic diagram of the structure of an air conditioner comfort evaluation device in the hardware operating environment involved in an embodiment of the present application.

[0044] As shown in Figure 1, the air conditioner comfort assessment device may include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. The user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may include a standard wired interface or a wireless interface (such as a Wireless Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also be a storage device independent of the processor 1001.

[0045] Those skilled in the art will appreciate that the structure shown in FIG1 does not limit the comfort evaluation device for an air conditioner, and may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0046] As shown in FIG1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a comfort evaluation program for an air conditioner.

[0047] In the comfort evaluation device of the air conditioner shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the comfort evaluation device of the air conditioner of this application can be set in the comfort evaluation device of the air conditioner, and the comfort evaluation device of the air conditioner calls the comfort evaluation program of the air conditioner stored in the memory 1005 through the processor 1001, and executes the comfort evaluation method of the air conditioner of this application.

[0048] The present application provides a method for evaluating the comfort level of an air conditioner. Referring to FIG. 2 , FIG. 2 is a flow chart of a first embodiment of the method for evaluating the comfort level of an air conditioner proposed in the present application.

[0049] In one embodiment, the method for evaluating the comfort level of an air conditioner comprises the following steps:

[0050] Step S10: When the air conditioner is running, current operating data of the air conditioner and user operation behavior information are obtained.

[0051] It should be noted that the method proposed in this application can be performed by the air conditioner device, which has functions such as data processing, data communication, and program execution. It can also be other devices with the same or similar functions, and this application does not limit this. For ease of explanation, this application uses the air conditioner controller as an example.

[0052] It should be noted that in the existing technology, there are two main directions for measuring air-conditioning comfort: the application level and the theoretical level. At the application level, indicators such as temperature reaching time, temperature maintenance effect, windless feeling, and low noise are often used as comfort measurement indicators; at the theoretical level, PMV is an indicator generally accepted by the industry. In addition, there are a series of measurement indicators such as effective temperature ET, equivalent temperature, synthetic temperature, new effective temperature, and standard effective temperature SET.

[0053] Among them, since the comfort measurement indicators at the application level are too one-sided, only certain indicators that affect comfort are selected as the measurement basis, which is far from being able to truly measure people's comfort during air-conditioning operation; while the indicators in theoretical research relatively comprehensively measure the thermal comfort of air conditioning, but the acquisition of these indicators requires the support of a series of precise instruments or expensive equipment, so they cannot be actually applied to daily air-conditioning thermal comfort measurement, resulting in the low accuracy of existing technologies for comfort assessment.

[0054] It can be understood that the air conditioner operating data includes but is not limited to: environmental information, operating condition information and user setting information, among which the environmental information includes indoor ambient temperature, indoor ambient humidity and outdoor thermal environment information, among which the operating condition information includes fan speed, throttling element opening and windshield opening, among which the user setting information includes user-set temperature and air conditioner operating mode, among which this application does not impose specific restrictions on this.

[0055] User operation behavior information includes but is not limited to: power on, power off, temperature adjustment, mode adjustment, wind speed adjustment, and windshield direction adjustment. Evaluating comfort through user operation behavior information can make the model more adaptable and more personalized.

[0056] In one embodiment, when the air conditioner is running, the operating data of the air conditioner and the user operation behavior information can be collected at preset periods, and the periodic characteristics in the air conditioner operating data can be extracted: including but not limited to environmental information, working condition information and user setting information, etc. The preset period can be 30s or 1min, and can also be set by the user. This application does not impose specific restrictions on this.

[0057] Step S20: Determine the comfort evaluation data corresponding to the current operation data and the user operation behavior information through the trained comfort evaluation model.

[0058] It should be noted that the trained comfort evaluation model can be a model based on metric learning, which is mainly used to calculate the comfort data corresponding to the air conditioner operation data and user operation behavior information, such as metric learning methods such as LMNN, NCA or TripletNetwork. This application does not impose specific restrictions on this.

[0059] Among them, metric learning mainly maps samples to a low-dimensional space by learning a metric, so that the distance between similar samples is as small as possible and the distance between heterogeneous samples is as large as possible. Therefore, when training the model, it is necessary to combine comfortable samples and uncomfortable samples for model training.

[0060] Step S30: determining the current comfort evaluation of the air conditioner according to a preset comfort metric interval and the comfort evaluation data.

[0061] It is understandable that due to the large amount of operating data and user operation behavior information reported by the air conditioner, the output of the trained comfort assessment model is discrete. In order to accurately determine the category of the input data, this application limits the threshold range of the comfort metric by pre-setting the comfort metric interval, thereby reducing the difficulty of comfort assessment caused by extreme data.

[0062] In one embodiment, when the air conditioner is turned on and running, information such as the environment, working conditions, and user operation behavior reported during the operation of the air conditioner is obtained, and after feature extraction, the above information is input into a trained comfort assessment model to obtain a model output (i.e., comfort assessment data). Finally, the model output (i.e., comfort assessment data) is range-processed based on a preset comfort metric interval, and the final current moment comfort is combined with the comfort metric to determine whether the current comfort evaluation is comfortable or uncomfortable.

[0063] Furthermore, the step S30 includes:

[0064] When the comfort evaluation data is within a preset comfort metric interval, the current comfort level of the air conditioner is determined according to the preset comfort metric and the comfort evaluation data.

[0065] It should be noted that when the calculated comfort evaluation data is within the preset comfort measurement range, it means that the comfort evaluation data is relatively reasonable, and the comfort evaluation can be performed according to the position of the comfort evaluation data in the preset comfort measurement range. For example: the calculated comfort evaluation data Si=0.75, the preset comfort measurement range is [-1~1], which means that under the current operating data of the air conditioner, the user is relatively comfortable, where -1 is the uncomfortable side and 1 is the comfortable side.

[0066] When the comfort evaluation data is outside a preset comfort metric range, proportionally adjusting the comfort evaluation data to obtain target comfort evaluation data;

[0067] The current comfort level of the air conditioner is determined according to a preset comfort metric and the target comfort level evaluation data.

[0068] In one embodiment, the proportional adjustment of the comfort assessment data may be performed by scaling the data proportionally according to a certain ratio so that the target comfort assessment data falls within a preset comfort measurement range, and the scaled value is calculated as the comfort at the current moment. For example: Si=2, the range [15%-85%] is [-1, 1], then the preset comfort measurement range is adjusted to obtain a range [5%-95%] of [-2, 2]. This application does not impose any specific restrictions on this.

[0069] This application obtains the current operating data of the air conditioner and user operation behavior information, and performs comfort evaluation on the current operating data and user operation behavior information through a trained comfort evaluation model to obtain comfort evaluation data. Finally, the current comfort evaluation result of the air conditioner is determined based on a pre-set comfort metric interval combined with the comfort evaluation data. This avoids the technical problem in the existing technology of low accuracy of comfort evaluation when users use air conditioners, and improves the comprehensiveness of comfort evaluation.

[0070] Refer to FIG3 , which is a flow chart of a second embodiment of a method for evaluating the comfort level of an air conditioner proposed in this application.

[0071] Based on the first embodiment above, in one embodiment, before step S30, the method further includes:

[0072] Step S210: Obtain a training data sample set.

[0073] It should be noted that the training data sample set includes the operating data of the air conditioner collected every specific period (30 seconds) when the air conditioner is running, the operating data of the air conditioner when there is user operation information, the operating data of the air conditioner after there is user operation information and a first time interval, and the operating data of the air conditioner after there is user operation information and a second time interval, wherein the first time interval is less than the second time interval, for example: the first time interval is set to half an hour, and the second time interval is set to one hour. This application does not impose specific restrictions on this.

[0074] Furthermore, the obtaining of a training data sample set includes:

[0075] When a user operation behavior is detected, an abnormal data sample, a first comfort data sample, and a second comfort data sample are acquired, wherein the abnormal data sample is current operating data of the air conditioner, the first comfort data sample is operating data of the air conditioner after a first time interval, and the second comfort data sample is operating data of the air conditioner after a second time interval, wherein the first time interval is less than the second time interval;

[0076] A training data sample set is generated according to the abnormal data sample, the first comfort data sample, and the second comfort data sample.

[0077] In one embodiment, when the user performs an operation, data is collected additionally; the reported data during the additional operation is marked as an uncomfortable sample Ui, or the average of multiple data close to the operation time point is marked as an uncomfortable sample Ui, such as the label is 0; if there is no additional operation within two hours after the user's operation, the data at a fixed time interval (such as 30 minutes) after the operation (i.e., the first comfortable data sample) and the data after the operation (such as 60 minutes) (i.e., the second comfortable data sample) are marked as comfort samples Ci0, Ci1. If the label is 1, similarly, one data or multiple data close to the time point can be averaged.

[0078] Step S220: performing comfort evaluation based on the training data sample set using the trained comfort evaluation model to obtain multiple evaluated comfort levels.

[0079] It can be understood that multiple evaluated comfort levels refer to the comfort parameter values ​​obtained by performing comfort evaluation on each data sample in the acquired training data sample set through a trained comfort evaluation model. Since the data in the training data sample set can come from multiple operation information of different devices and different users, it is discrete in form. After the comfort evaluation is performed, the multiple evaluated comfort levels obtained are also discrete. In order to improve the efficiency of model training, this application can divide the range of multiple evaluated comfort levels, eliminate some extreme data, and then continue iterative training.

[0080] Furthermore, generating a training data sample set according to the abnormal data sample, the first comfort data sample, and the second comfort data sample includes:

[0081] Determining the interval length of the abnormal data samples;

[0082] When the interval duration is greater than or equal to a preset duration, constructing triplet data according to the abnormal data sample, the first comfort data sample, and the second comfort data sample;

[0083] A training data sample set is generated according to the triple data.

[0084] It should be noted that in order to improve the accuracy of classification during model training and make the distance between data of the same type closer and the distance between data of different types farther, during model training, the data input into the comfort assessment model in the form of triple data can be used for model training to achieve the purpose of increasing the distance between data of different types (comfortable / uncomfortable, Ui and Ci0) and shortening the distance between data of the same type (comfortable / comfortable, Ci0 and Ci1).

[0085] Among them, the interval length of the abnormal data sample is greater than the preset time length, which means that the interval length of the abnormal data sample is greater than two hours, that is, there is no user operation within two hours, then the abnormal data sample is marked as Ui, and the data of the fixed first market (30 minutes) and the data of the second interval (60 minutes) are marked as the first comfortable data sample Ci0 and the second comfortable data sample Ci1, and finally the triplet [Ui, Ci0, Ci1] is generated.

[0086] Step S230: Divide the multiple evaluated comfort levels into ranges to obtain preset comfort measurement intervals.

[0087] In one embodiment, the preset comfort metric interval can be set to [-1~1], where 1 is the comfortable side and -1 is the uncomfortable side. This application does not impose any specific restrictions on this.

[0088] Furthermore, the plurality of evaluated comfort levels are divided into ranges to obtain preset comfort measurement intervals, including:

[0089] Counting the distribution intervals of the plurality of comfort evaluations;

[0090] screening the plurality of comfort evaluation distribution intervals based on a preset first ratio threshold and a preset second ratio threshold;

[0091] The evaluated comfort levels corresponding to the filtered distribution intervals are marked based on the preset comfort metric to obtain a preset comfort metric interval, and the preset first ratio threshold is less than the second ratio threshold.

[0092] In one embodiment, the distribution range of multiple evaluated comfort levels is 0-100%. At this time, the 5-95% part can be retained, the remaining part can be eliminated, and [-1~1] can be used as the preset comfort metric to proportionally mark the evaluated comfort levels of the 5-95% part, so as to facilitate the subsequent determination of specific evaluations.

[0093] The present application obtains the operating data of the air conditioner when there is operation information as an abnormal data sample, the operating data after a first time interval as a first comfort data sample, and the operating data after a second time interval as a second comfort data sample, so that the distance between data of the same type is closer and the distance between data of different types is farther, thereby improving the accuracy of classification and the efficiency of model training, and dividing the obtained evaluated comfort into ranges, so that in actual application, the comfort evaluation result can be directly obtained according to the calculation result, which is more convenient and quick, and improves the user experience.

[0094] In addition, the present application also proposes a storage medium on which a comfort evaluation program for an air conditioner is stored. When the comfort evaluation program for an air conditioner is executed by a processor, the steps of the comfort evaluation method for an air conditioner as described above are implemented.

[0095] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0096] 4 , which is a structural block diagram of a first embodiment of a comfort evaluation device for an air conditioner according to the present application.

[0097] As shown in FIG4 , the air conditioner comfort evaluation device proposed in this application includes:

[0098] The acquisition module 10 is used to acquire the current operation data of the air conditioner and the user operation behavior information when the air conditioner is running.

[0099] The evaluation module 20 is configured to determine the comfort evaluation data corresponding to the current operation data and the user operation behavior information through a trained comfort evaluation model.

[0100] The evaluation module 30 is configured to determine a current comfort evaluation of the air conditioner according to a preset comfort metric interval and the comfort evaluation data.

[0101] In one embodiment, the evaluation module 30 is further used to obtain a training data sample set; perform comfort evaluation based on the training data sample set using a trained comfort evaluation model to obtain multiple evaluated comfort levels; and divide the multiple evaluated comfort levels into ranges to obtain preset comfort measurement intervals.

[0102] In one embodiment, the evaluation module 30 is further used to count the distribution intervals of the multiple evaluated comfort levels; filter the distribution intervals of the multiple evaluated comfort levels based on a preset first ratio threshold and a preset second ratio threshold; and mark the evaluated comfort levels corresponding to the filtered distribution intervals based on a preset comfort metric to obtain a preset comfort metric interval, wherein the preset first ratio threshold is less than the second ratio threshold.

[0103] In one embodiment, the evaluation module 30 is further used to obtain an abnormal data sample, a first comfort data sample, and a second comfort data sample when a user operation behavior is detected, wherein the abnormal data sample is the current operating data of the air conditioner, the first comfort data sample is the operating data of the air conditioner after a first time interval, and the second comfort data sample is the operating data of the air conditioner after a second time interval, and the first time interval is less than the second time interval; and a training data sample set is generated based on the abnormal data sample, the first comfort data sample, and the second comfort data sample.

[0104] In one embodiment, the evaluation module 30 is further used to determine the interval duration of the abnormal data samples; when the interval duration is greater than or equal to the preset duration, construct triplet data based on the abnormal data samples, the first comfort data samples and the second comfort data samples; and generate a training data sample set based on the triplet data.

[0105] In one embodiment, the evaluation module 30 is further configured to determine the current comfort level of the air conditioner according to a preset comfort metric and the comfort level evaluation data when the comfort level evaluation data is within a preset comfort metric range.

[0106] In one embodiment, the evaluation module 30 is further used to proportionally adjust the comfort assessment data to obtain target comfort assessment data when the comfort assessment data is outside a preset comfort metric range; and determine the current comfort of the air conditioner based on the preset comfort metric and the target comfort assessment data.

[0107] This application obtains the current operating data of the air conditioner and the user's operating behavior information, and performs a comfort evaluation on the current operating data and the user's operating behavior information through a trained comfort evaluation model to obtain comfort evaluation data. Finally, the current comfort evaluation result of the air conditioner is determined based on a pre-set comfort metric interval combined with the comfort evaluation data. This avoids the technical problem in the prior art of low accuracy in comfort evaluation when users use air conditioners, and improves the comprehensiveness of comfort evaluation.

[0108] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and they can be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0109] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present application. In specific applications, technicians in this field can make settings as needed, and the present application does not impose any restrictions on this.

[0110] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In actual applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of this embodiment scheme, and no restrictions are imposed here.

[0111] In addition, for technical details not fully described in this embodiment, please refer to the comfort evaluation method for the air conditioner provided in any embodiment of the present application, and will not be repeated here.

[0112] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0113] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of this application.

[0115] The above are merely optional embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for evaluating the comfort level of an air conditioner, wherein: The comfort evaluation method of the air conditioner comprises: When the air conditioner is running, obtaining current operating data of the air conditioner and user operation behavior information; Determining the comfort evaluation data corresponding to the current operation data and the user operation behavior information through a trained comfort evaluation model; and The current comfort evaluation of the air conditioner is determined according to the preset comfort metric interval and the comfort evaluation data.

2. The method for evaluating the comfort level of an air conditioner according to claim 1, wherein: Before determining the current comfort evaluation of the air conditioner according to the preset comfort metric interval and the comfort evaluation data, the method further includes: Obtain a sample set of training data; Performing comfort evaluation based on the training data sample set using a trained comfort evaluation model to obtain multiple evaluation comforts; and The multiple evaluated comfort levels are divided into ranges to obtain preset comfort measurement intervals.

3. The method for evaluating the comfort level of an air conditioner according to claim 2, wherein: The step of dividing the multiple evaluated comfort levels into ranges to obtain a preset comfort measurement interval includes: Counting the distribution intervals of the plurality of comfort evaluations; Screening the plurality of distribution intervals for evaluating comfort based on a preset first ratio threshold and a preset second ratio threshold; and The evaluated comfort levels corresponding to the filtered distribution intervals are marked based on the preset comfort metric to obtain a preset comfort metric interval, wherein the preset first ratio threshold is less than the second ratio threshold.

4. The method for evaluating the comfort level of an air conditioner according to claim 2, wherein: The step of obtaining a training data sample set includes: When a user operation behavior is detected, an abnormal data sample, a first comfort data sample, and a second comfort data sample are acquired, wherein the abnormal data sample is current operation data of the air conditioner, the first comfort data sample is operation data of the air conditioner after a first time interval, and the second comfort data sample is operation data of the air conditioner after a second time interval, wherein the first time interval is less than the second time interval; and A training data sample set is generated according to the abnormal data sample, the first comfort data sample and the second comfort data sample.

5. The method for evaluating the comfort level of an air conditioner according to claim 4, wherein: The generating a training data sample set according to the abnormal data sample, the first comfort data sample and the second comfort data sample comprises: Determining the interval length of the abnormal data samples; When the interval duration is greater than or equal to a preset duration, constructing triple data according to the abnormal data sample, the first comfort data sample and the second comfort data sample; and A training data sample set is generated according to the triple data.

6. The method for evaluating the comfort level of an air conditioner according to any one of claims 1 to 5, wherein: The step of determining the current comfort evaluation of the air conditioner according to the preset comfort metric interval and the comfort evaluation data comprises: When the comfort evaluation data is within a preset comfort metric interval, the current comfort level of the air conditioner is determined according to the preset comfort metric and the comfort evaluation data.

7. The method for evaluating the comfort level of an air conditioner according to claim 6, wherein: The comfort evaluation method of the air conditioner further comprises: When the comfort evaluation data is outside a preset comfort measurement interval, proportionally adjusting the comfort evaluation data to obtain target comfort evaluation data; and The current comfort level of the air conditioner is determined according to a preset comfort metric and the target comfort level evaluation data.

8. A comfort evaluation device for an air conditioner, wherein: The comfort evaluation device of the air conditioner comprises: An acquisition module, used for acquiring current operation data of the air conditioner and user operation behavior information when the air conditioner is running; An evaluation module, used to determine the comfort evaluation data corresponding to the current operation data and the user operation behavior information through a trained comfort evaluation model; and An evaluation module is used to determine a current comfort evaluation of the air conditioner according to a preset comfort metric interval and the comfort evaluation data.

9. A comfort evaluation device for an air conditioner, wherein: The air conditioner comfort evaluation device includes: a memory, a processor, and an air conditioner comfort evaluation program stored in the memory and executable on the processor, wherein the air conditioner comfort evaluation program is configured to implement the air conditioner comfort evaluation method as described in any one of claims 1 to 7.

10. A storage medium, wherein: The storage medium stores a comfort evaluation program for the air conditioner, and when the comfort evaluation program for the air conditioner is executed by the processor, the comfort evaluation method for the air conditioner as claimed in any one of claims 1 to 7 is implemented.

Images