Model training method and device based on user comfort

Abstract

The invention discloses a model training method and device based on user comfort, and the method comprises the steps: determining a physiological condition data packet of a first user, the physiological condition data packet of the first user comprising a plurality of physiological condition data of the first user; determining a comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user; the physiological condition data packet of the first user and the comfort control parameter set of the first user are input into a to-be-trained initial comfort model for model training, a comfort model corresponding to the first user is obtained, and the comfort model is used for calculating input first physiological condition data of the first user; and obtaining a first comfort control parameter of the air conditioner for the first user. Therefore, the training accuracy of the comfort model can be improved, and the comfort requirement of the user can be better met through the comfort control parameters output by the comfort model.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a model training method and device based on user comfort. Background Art

[0002] As people's demand for quality of life becomes higher and higher, air conditioners that can improve people's quality of life are gradually penetrating into people's daily lives. For example, when users have comfort needs, comfort air conditioners can be used to adjust the environmental parameters around the users (such as temperature) to make the users feel comfortable.

[0003] At present, the environmental control parameters of comfort air conditioners are usually set based on the experience of experts. However, in practical applications, the comfort control parameters of air conditioners set by expert experience only consider the commonalities of multiple users, but do not consider individual differences, which easily leads to the inability to adapt to individual comfort needs. It can be seen that it is particularly important to propose a new training method for comfort models to meet the comfort needs of users. Summary of the invention

[0004] The present invention provides a model training method and device based on user comfort, which can improve the training accuracy of the comfort model and help the comfort control parameters output by the comfort model to better meet the user's comfort needs.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a model training method based on user comfort, the method comprising:

[0006] determining a physiological condition data packet of the first user, where the physiological condition data packet of the first user includes a plurality of physiological condition data of the first user;

[0007] determining, according to the physiological condition data packet of the first user, a comfort control parameter set of the air conditioner for the first user, wherein each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user;

[0008] The physiological condition data packet of the first user and the comfort control parameter set of the first user are input into the initial comfort model to be trained for model training to obtain a comfort model corresponding to the first user. The comfort model is used to calculate the input first physiological condition data of the first user to obtain the first comfort control parameter of the air conditioner for the first user.

[0009] As an optional implementation manner, in the first aspect of the present invention, detecting whether the first user sends a data packet upload instruction of the first user;

[0010] When a data packet upload instruction sent by the first user is detected, determining whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction;

[0011] When it is determined that at least one first data matching the physiological condition of the first user exists in all the uploaded data in the uploaded data packet, all the first data matching the physiological condition of the first user are determined as the physiological condition data packet of the first user.

[0012] As an optional implementation manner, in the first aspect of the present invention, when it is determined that none of the uploaded data in the uploaded data packet indicated by the data packet upload instruction contains first data matching the physiological condition of the first user, the step of determining the physiological condition data packet of the first user includes:

[0013] According to all the uploaded data in the uploaded data packet and the preset physiological condition association relationship, at least one second data having a correlation degree greater than or equal to a preset correlation degree with the physiological condition of the first user is screened out from all the uploaded data;

[0014] All the second data and the physiological condition association relationships are calculated to obtain third data matching the physiological condition of the first user, and the third data is determined as the physiological condition data packet of the first user.

[0015] As an optional implementation, in the first aspect of the present invention, the air conditioner has a corresponding model trading platform, and the model trading platform is used to provide at least one of the trained comfort models to platform users in the model trading platform for trading, and the platform users include at least one of the first users as a model seller user and at least one second user as a model buyer user;

[0016] And, the method further comprises:

[0017] When the model trading platform receives a comfort control demand of any second user for the air conditioner, a data packet matching instruction corresponding to the second user is generated according to the acquired second physiological condition data of the second user;

[0018] According to the data packet matching instruction corresponding to the second user, a physiological condition data packet matching the data packet matching instruction of the second user is screened out from the input data of the model input interface of all first comfort models uploaded to the model trading platform as a target physiological condition data packet corresponding to the second user;

[0019] Determine a first comfort model corresponding to the target physiological condition data packet corresponding to the second user as a second comfort model corresponding to the second user. The second comfort model is used to calculate the input second physiological condition data of the second user to obtain a second comfort control parameter of the air conditioner for the second user.

[0020] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0021] For the first comfort model corresponding to each of the first users of the model trading platform, detecting whether there is a third user who trades with the first comfort model among all the second users of the model trading platform;

[0022] When it is detected that there is a third user who has traded the first comfort model among all the second users, obtaining the model transaction status of the third users for the first comfort model, wherein the model transaction status includes the number of the third users and the transaction times of the corresponding third users;

[0023] According to the model transaction situation corresponding to the first comfort model, the transaction information corresponding to the first comfort model is generated, and the transaction information corresponding to the first comfort model includes the transaction profit information of the first user corresponding to the first comfort model.

[0024] As an optional implementation manner, in the first aspect of the present invention, generating transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model includes:

[0025] Acquire a first platform transaction level of a first user corresponding to the first comfort model, and a second platform transaction level of each of the third users included in the model transaction situation;

[0026] According to the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all the third users, and the transaction times of all the third users, respectively calculate the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each of the third users, and the transaction commission information of the model trading platform for the first comfort model;

[0027] The transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of all the third users, and the transaction commission information of the model trading platform for the first comfort model are determined as the transaction information corresponding to the first comfort model.

[0028] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0029] Acquire the model transaction status corresponding to each of the first comfort models in the model transaction platform;

[0030] Comparing the model transaction situations corresponding to all the first comfort models to obtain comparison results of all the first comfort models;

[0031] Based on the comparison results of all the first comfort models, the model trading platform generates model recommendation parameters for all the first comfort models, and the model recommendation parameters are used to trigger the model trading platform to recommend a model to any of the second users based on the model recommendation parameters when receiving the model trading demand of the second user.

[0032] The second aspect of the present invention discloses a model training device based on user comfort, the device comprising:

[0033] A determination module, configured to determine a physiological condition data packet of the first user, wherein the physiological condition data packet of the first user includes a plurality of physiological condition data of the first user;

[0034] The determination module is further used to determine a comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user, wherein each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user;

[0035] A training module is used to input the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user. The comfort model is used to calculate the input first physiological condition data of the first user, so as to obtain the first comfort control parameter of the air conditioner for the first user.

[0036] As an optional implementation, in the second aspect of the present invention, the manner in which the determining module determines the physiological condition data packet of the first user specifically includes:

[0037] Detecting whether the first user sends a data packet upload instruction of the first user;

[0038] When a data packet upload instruction sent by the first user is detected, determining whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction;

[0039] When it is determined that at least one first data matching the physiological condition of the first user exists in all the uploaded data in the uploaded data packet, all the first data matching the physiological condition of the first user are determined as the physiological condition data packet of the first user.

[0040] As an optional implementation, in the second aspect of the present invention, when it is determined that none of the uploaded data in the uploaded data packet indicated by the data packet upload instruction contains the first data matching the physiological condition of the first user, the manner in which the determination module determines the physiological condition data packet of the first user specifically includes:

[0041] According to all the uploaded data in the uploaded data packet and the preset physiological condition association relationship, at least one second data having a correlation degree greater than or equal to a preset correlation degree with the physiological condition of the first user is screened out from all the uploaded data;

[0042] All the second data and the physiological condition association relationships are calculated to obtain third data matching the physiological condition of the first user, and the third data is determined as the physiological condition data packet of the first user.

[0043] As an optional implementation, in the second aspect of the present invention, the air conditioner has a corresponding model trading platform, and the model trading platform is used to provide at least one of the trained comfort models to platform users in the model trading platform for trading, and the platform users include at least one of the first users as a model seller user and at least one second user as a model buyer user;

[0044] And, the device also includes:

[0045] a generating module, configured to generate a data packet matching instruction corresponding to the second user according to the acquired second physiological condition data of the second user when the model trading platform receives a comfort control demand of any second user for the air conditioner;

[0046] a screening module, configured to screen out, according to the data packet matching instruction corresponding to the second user, a physiological condition data packet that matches the data packet matching instruction of the second user from the input data of the model input interface of all first comfort models uploaded to the model trading platform as a target physiological condition data packet corresponding to the second user;

[0047] The determination module is also used to determine the first comfort model corresponding to the target physiological condition data packet corresponding to the second user, as the second comfort model corresponding to the second user. The second comfort model is used to calculate the input second physiological condition data of the second user to obtain the second comfort control parameters of the air conditioner for the second user.

[0048] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0049] a detection module, configured to detect, for a first comfort model corresponding to each of the first users of the model trading platform, whether there is a third user who trades with the first comfort model among all the second users of the model trading platform;

[0050] an acquisition module, configured to, when detecting that there is a third user among all the second users who has traded the first comfort model, acquire the model transaction status of the third user for the first comfort model, wherein the model transaction status includes the number of the third users and the number of transactions of the corresponding third users;

[0051] The generating module is further used to generate transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model, and the transaction information corresponding to the first comfort model includes transaction profit information of the first user corresponding to the first comfort model.

[0052] As an optional implementation, in the second aspect of the present invention, the generation module generates the transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model, specifically including:

[0053] Acquire a first platform transaction level of a first user corresponding to the first comfort model, and a second platform transaction level of each of the third users included in the model transaction situation;

[0054] According to the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all the third users, and the transaction times of all the third users, respectively calculate the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each of the third users, and the transaction commission information of the model trading platform for the first comfort model;

[0055] The transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of all the third users, and the transaction commission information of the model trading platform for the first comfort model are determined as the transaction information corresponding to the first comfort model.

[0056] As an optional implementation, in the second aspect of the present invention, the acquisition module is further used to acquire the model transaction status corresponding to each of the first comfort models in the model transaction platform;

[0057] And, the device also includes:

[0058] A comparison module, used for comparing the model transaction situations corresponding to all the first comfort models, and obtaining the comparison results of all the first comfort models;

[0059] The generation module is further used to generate model recommendation parameters of the model trading platform for all the first comfort models based on the comparison results of all the first comfort models, and the model recommendation parameters are used to trigger the model trading platform to recommend a model to any second user based on the model recommendation parameters when receiving the model trading demand of any second user.

[0060] The third aspect of the present invention discloses another model training device based on user comfort, the device comprising:

[0061] A memory storing executable program code;

[0062] a processor coupled to the memory;

[0063] The processor calls the executable program code stored in the memory to execute the model training method based on user comfort disclosed in the first aspect of the present invention.

[0064] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the model training method based on user comfort disclosed in the first aspect of the present invention.

[0065] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0066] In an embodiment of the present invention, a physiological condition data packet of a first user is determined, and the physiological condition data packet of the first user includes multiple physiological condition data of the first user; according to the physiological condition data packet of the first user, a comfort control parameter set of the air conditioner for the first user is determined, and each comfort control parameter contained in the comfort control parameter set meets the comfort requirements of the first user; the physiological condition data packet of the first user and the comfort control parameter set of the first user are input into the initial comfort model to be trained for model training, and a comfort model corresponding to the first user is obtained, and the comfort model is used to calculate the first physiological condition data of the input first user to obtain the first comfort control parameter of the air conditioner for the first user. It can be seen that the implementation of the present invention can accurately determine the comfort control parameter set of the air conditioner for the first user according to the determined physiological condition data packet of the first user, and input the physiological condition data packet of the first user and the accurately determined comfort control parameter set of the first user into the initial comfort model to be trained for model training, and obtain the comfort model corresponding to the first user, which can improve the training accuracy of the comfort model, thereby facilitating the accuracy of controlling the air conditioner to adjust the user's surrounding environment through the comfort control parameters output by the accurately trained comfort model, so as to better meet the user's comfort requirements, and can also improve the user's experience of using the air conditioner and improve the user's usage viscosity. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0068] Figure 1 It is a schematic diagram of a scenario to which a model training method based on user comfort disclosed in an embodiment of the present invention is applicable;

[0069] Figure 2 It is a flowchart of a model training method based on user comfort disclosed in an embodiment of the present invention;

[0070] Figure 3 It is a flowchart of another model training method based on user comfort disclosed in an embodiment of the present invention;

[0071] Figure 4 It is a structural schematic diagram of a model training device based on user comfort disclosed in an embodiment of the present invention;

[0072] Figure 5 is a structural schematic diagram of another model training device based on user comfort disclosed in an embodiment of the present invention;

[0073] Figure 6 It is a structural schematic diagram of another model training device based on user comfort disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0076] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0077] The present invention discloses a model training method and device based on user comfort, which can accurately determine the comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user determined, and input the physiological condition data packet of the first user and the comfort control parameter set of the first user accurately determined into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user, which can improve the training accuracy of the comfort model, thereby facilitating the accuracy of controlling the air conditioner to adjust the user's surrounding environment through the comfort control parameters output by the accurately trained comfort model, so as to better meet the user's comfort requirements, and also can improve the user's experience of using the air conditioner and improve the user's usage viscosity. The following are detailed descriptions.

[0078] In order to better understand the model training method and device based on user comfort described in the present invention, firstly, a home scene to which the model training method based on user comfort is applicable is described. Specifically, the scene diagram of the home scene can be as follows: Figure 1 As shown, Figure 1 is a schematic diagram of a home scene applicable to a model training method based on user comfort disclosed in an embodiment of the present invention, such as Figure 1 As shown, a smart air conditioner is placed in the home scene, and there is a user in the home scene.

[0079] It should be noted that Figure 1 The scene diagram shown is only for showing one of the scenes to which the model training method and device based on user comfort are applicable, and it is not used to limit other scenes to which the model training method and device based on user comfort are applicable, and Figure 1 The smart air conditioner involved in Figure 1 The scene schematic diagram shown does not limit the shape, size, and location of the smart air conditioner; Figure 1 There is no restriction on whether the users and other related objects involved exist and their existence form.

[0080] Embodiment 1

[0081] See also Figure 2 , Figure 2 is a flow chart of a model training method based on user comfort disclosed in an embodiment of the present invention. Figure 2 The described user comfort-based model training method can be applied to a user comfort-based model training device, wherein the device may include a training device or a training server, wherein the training server may include a cloud server or a local server, which is not limited in the embodiments of the present invention. Figure 2 As shown, the user comfort-based model training method based on user comfort may include the following operations:

[0082] 101. Determine a physiological condition data packet of a first user.

[0083] In an embodiment of the present invention, the physiological condition data packet of the first user includes multiple physiological condition data of the first user. Among them, each physiological condition data of the first user has a corresponding data collection time, and the physiological condition data corresponding to each data collection time (such as: within the past 72 hours) may include the weight of the first user during the data collection time, the height of the first user during the data collection time, the height-to-weight ratio of the first user during the data collection time, the metabolic rate of the first user during the data collection time, and the temperature sensitivity coefficient of the first user during the data collection time, etc. One or more combinations are not limited in the embodiment of the present invention.

[0084] 102. Determine a set of comfort control parameters of the air conditioner for the first user according to the physiological condition data packet of the first user.

[0085] In an embodiment of the present invention, a comfort control parameter set includes multiple comfort control parameters of the air conditioner. The comfort control parameters may include a combination of one or more of a comfort temperature control parameter, a comfort air volume control parameter, and a comfort humidity control parameter. Each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user. The comfort requirement may include a combination of one or more of a comfort temperature requirement, a comfort air volume requirement, and a comfort humidity requirement of the first user, which is not limited in the embodiment of the present invention.

[0086] 103. Input the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained to perform model training, so as to obtain a comfort model corresponding to the first user.

[0087] In an embodiment of the present invention, the comfort model is used to calculate the first physiological condition data of the first user input to obtain the first comfort control parameter of the air conditioner for the first user. The first comfort control parameter is used to control the air conditioner to adjust the environment around the first user according to the first comfort control parameter, so that the adjustment result of the air conditioner on the environment around the first user meets the target comfort requirement corresponding to the first physiological condition data of the first user, which is not limited in the embodiment of the present invention.

[0088] It can be seen that the implementation Figure 2 The described model training method based on user comfort can accurately determine the comfort control parameter set of the air conditioner for the first user according to the determined physiological condition data packet of the first user, and input the physiological condition data packet of the first user and the accurately determined comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user, which can improve the training accuracy of the comfort model, thereby facilitating improving the accuracy of controlling the air conditioner to adjust the user's surrounding environment through the comfort control parameters output by the accurately trained comfort model, so as to better meet the user's comfort needs, and can also enhance the user's experience of using the air conditioner and improve the user's usage stickiness.

[0089] In an optional embodiment, determining the comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user in the above step 102 may include:

[0090] For each physiological condition data in the physiological condition data packet of the first user, determining, according to the physiological condition data, a comfort requirement corresponding to the physiological condition data;

[0091] Determining a comfort control parameter corresponding to the physiological condition data according to a comfort requirement corresponding to the physiological condition data;

[0092] The comfort control parameters corresponding to all the physiological condition data of the first user are determined as all the parameters of the comfort control parameter set of the air conditioner for the first user.

[0093] It can be seen that this optional embodiment can accurately determine the corresponding comfort requirement based on each physiological condition data of the determined physiological condition data packet of the first user, and determine the comfort control parameters corresponding to the physiological condition data based on the comfort requirement corresponding to the accurately determined physiological condition data, which can improve the accuracy and reliability of determining the comfort control parameters corresponding to each physiological condition data, and improve the accuracy and reliability of determining the comfort control parameters of the air conditioner for the first user.

[0094] In another optional embodiment, after inputting the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained for model training in the above step 103 to obtain the comfort model corresponding to the first user, the method may further include:

[0095] Acquiring current physiological condition data of the first user;

[0096] determining a current comfort requirement of the first user according to the current physiological condition data of the first user;

[0097] Inputting the current physiological condition data of the first user into the comfort model corresponding to the first user to perform parameter calculation to obtain the current comfort control parameters corresponding to the first user;

[0098] Verifying a current comfort control parameter corresponding to the first user according to the current comfort requirement of the first user;

[0099] When the verification is passed, the current comfort control parameters are output to the air conditioner;

[0100] When the verification fails, the current comfort control parameters are corrected according to the current comfort requirement of the first user to obtain the corrected current comfort control parameters, and the corrected current comfort control parameters are output to the air conditioner.

[0101] In the embodiment of the present invention, when the air conditioner receives the current comfort control parameter or the corrected current comfort control parameter, it can adjust the environmental parameters around the first user according to the received comfort control parameter so that the first user feels comfortable.

[0102] In an embodiment of the present invention, optionally, when the verification fails, the current physiological condition data of the first user and the corrected current comfort control parameters can be input into the comfort model of the first user for re-training to obtain a re-trained comfort model, so that the re-trained comfort model can better meet the needs of the first user.

[0103] It can be seen that this optional embodiment can determine the current comfort demand of the first user based on the acquired current physiological condition data of the first user, and input the current physiological condition data of the first user into the comfort model corresponding to the first user, output the current comfort control parameters corresponding to the first user, and verify the current comfort control parameters corresponding to the first user according to the current comfort demand of the first user; when the verification passes, the current comfort control parameters are directly output to the air conditioner; when the verification fails, the current comfort control parameters are first corrected and then the corrected current comfort control parameters are output to the air conditioner, which can improve the output accuracy and flexibility of the comfort control parameters that need to be output to the air conditioner, thereby facilitating improving the accuracy of the air conditioning environment adjustment through accurately output comfort control parameters, and then facilitating meeting the current comfort demand of the first user through the environmental parameters accurately adjusted by the air conditioner.

[0104] Embodiment 2

[0105] See also Figure 3 , Figure 3 1 is a flow chart of a method for training a model based on user comfort disclosed in an embodiment of the present invention. Figure 3 The described user comfort-based model training method can be applied to a user comfort-based model training device, wherein the device may include a training device or a training server, wherein the training server may include a cloud server or a local server, and the embodiment of the present invention is not limited thereto. Figure 3 As shown, the user comfort-based model training method based on user comfort may include the following operations:

[0106] 201. Detect whether a first user sends a data packet upload instruction of the first user.

[0107] In the embodiment of the present invention, optionally, the data packet upload instruction of the first user may be an instruction corresponding to the data packet uploaded by the first user to the input interface of the initial comfort model to be trained. When the data packet upload instruction sent by the first user is detected, step 202 is triggered; when it is detected that the first user has not sent the data packet upload instruction of the first user, this process may be terminated.

[0108] 202. Determine whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction.

[0109] In an embodiment of the present invention, when the judgment result of step 202 is yes (that is, when it is determined that there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet), step 203 is triggered for execution; when the judgment result of step 202 is no, this process can be terminated.

[0110] 203. Determine all first data matching the physiological condition of the first user as a physiological condition data packet of the first user.

[0111] 204. Determine a set of comfort control parameters of the air conditioner for the first user according to the physiological condition data packet of the first user.

[0112] 205. Input the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained to perform model training, so as to obtain a comfort model corresponding to the first user.

[0113] In the embodiment of the present invention, for other descriptions in step 203 to step 205, please refer to the detailed description of step 101 to step 103 in the first embodiment, and the embodiment of the present invention will not be repeated.

[0114] It can be seen that the implementation Figure 3 The described model training method based on user comfort can accurately determine the comfort control parameter set of the air conditioner for the first user according to the determined physiological condition data packet of the first user, and input the physiological condition data packet of the first user and the accurately determined comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user, which can improve the training accuracy of the comfort model, thereby facilitating the accuracy of controlling the air conditioner to adjust the user's surrounding environment through the comfort control parameters output by the accurately trained comfort model, so as to better meet the user's comfort requirements, and also improve the user's use experience of the air conditioner and improve the user's use viscosity. In addition, it can also determine whether there is at least one first data matching the physiological condition of the first user in all the uploaded data in the uploaded data packet indicated by the data packet upload instruction when the first user sends its data packet upload instruction, and when it is determined that there is at least one first data matching the physiological condition of the first user, all the first data are determined as the physiological condition data packet of the first user, which can improve the accuracy of determining the physiological condition data packet of the first user, thereby facilitating improving the training accuracy of the comfort model through the accurately determined physiological condition data packet.

[0115] In an optional embodiment, when it is determined in the above step 202 that none of the uploaded data in the uploaded data packet indicated by the data packet upload instruction contains the first data matching the physiological condition of the first user, determining the physiological condition data packet of the first user may include:

[0116] According to all the uploaded data in the uploaded data packet and the preset physiological condition association relationship, at least one second data having a correlation degree greater than or equal to a preset correlation degree with the physiological condition of the first user is screened out from all the uploaded data;

[0117] All second data and physiological condition associations are calculated to obtain third data matching the physiological condition of the first user, and the third data is determined as the physiological condition data packet of the first user.

[0118] In the embodiment of the present invention, optionally, the preset physiological condition association relationship may represent the association relationship between each uploaded data in all uploaded data in the uploaded data package and the physiological condition of the user corresponding to the uploaded data. Optionally, the preset association degree may be 70%, 80%, or any other set value, which is not limited in the embodiment of the present invention.

[0119] It can be seen that this optional embodiment can, when there is no physiological condition data packet in the data packet uploaded by the first user, accurately screen out at least one second data whose correlation with the first user's physiological condition is greater than or equal to the preset correlation degree from all the uploaded data based on all the data uploaded by the first user and the preset physiological condition correlation relationship, and calculate all the accurately screened second data and physiological condition correlation relationships to obtain third data matching the first user's physiological condition as the first user's physiological condition data packet. This can improve the accuracy and flexibility of determining the data packet corresponding to the first user's physiological condition, and reduce the occurrence of errors in the subsequently determined comfort control parameter set of the first user due to the first user not uploading the physiological condition data packet.

[0120] In another optional embodiment, there is a corresponding model trading platform for the air conditioner, and the model trading platform is used to provide at least one trained comfort model to platform users in the model trading platform for trading, and the platform users include at least one first user as a model seller user and at least one second user as a model buyer user. And, the method may also include:

[0121] When the model trading platform receives a comfort control demand for air conditioning from any second user, a data packet matching instruction corresponding to the second user is generated according to the acquired second physiological condition data of the second user;

[0122] According to the data packet matching instruction corresponding to the second user, a physiological condition data packet matching the data packet matching instruction of the second user is screened out from the input data of the model input interface of all first comfort models uploaded to the model trading platform as a target physiological condition data packet corresponding to the second user;

[0123] A first comfort model corresponding to the target physiological condition data packet corresponding to the second user is determined as a second comfort model corresponding to the second user.

[0124] In the embodiment of the present invention, the second comfort model is used to calculate the input second physiological condition data of the second user to obtain the second comfort control parameter of the air conditioner for the second user.

[0125] In the embodiment of the present invention, optionally, the first user may be an old user who has used the air conditioner or other air conditioners of the same type as the air conditioner. The second user may be a new user of the type of the air conditioner who has not used the air conditioner (i.e., a user who has not undergone comfort model training). Optionally, the comfort regulation demand of the second user for the air conditioner may be to adjust the control parameters of the air conditioner to the regulation demand corresponding to the comfort control parameters required to meet the comfort demand of the second user, which is not limited in the embodiment of the present invention.

[0126] It can be seen that this optional embodiment can generate a data packet matching instruction corresponding to the second user based on the physiological condition data of the second user when the second user who has not undergone comfort model training has a comfort regulation demand, and according to the data packet matching instruction corresponding to the second user, filter out the target physiological condition data packet matching the second user from the input data of the model input interface of all first comfort models of the model trading platform, which can improve the screening accuracy of the target physiological condition data packet corresponding to the second user, reduce the occurrence of screening of target physiological condition data packets that do not need to be screened, and determine the first comfort model corresponding to the target physiological condition data packet in the model trading platform as the second comfort model corresponding to the second user, which can improve the determination accuracy and speed of the second comfort model, thereby facilitating the output of the second comfort control parameters of the air conditioner for the second user through the accurately screened second comfort model to meet the comfort regulation demand of the second user, thereby facilitating improving the second user's usage experience and usage stickiness.

[0127] In this optional embodiment, as an optional implementation, the method may further include:

[0128] For a first comfort model corresponding to each first user of the model trading platform, detecting whether there is a third user who trades with the first comfort model among all second users of the model trading platform;

[0129] When it is detected that there is a third user who has traded the first comfort model among all the second users, obtaining the model transaction status of the third user for the first comfort model;

[0130] Transaction information corresponding to the first comfort model is generated according to the model transaction situation corresponding to the first comfort model.

[0131] In the embodiment of the present invention, the model transaction situation may include the number of third users and the number of transactions of the corresponding third users. Optionally, the transaction information corresponding to the first comfort model may include the transaction profit information of the first user corresponding to the first comfort model. Among them, the transaction profit information of the first user may include the transaction income information of the first user (such as: information on the amount of income that matches the transaction model), and may also include the transaction discount information of the first user (such as: discount information corresponding to the purchase of goods provided by the platform to the first user), which is not limited in the embodiment of the present invention.

[0132] It can be seen that this optional implementation can, for the first comfort model corresponding to each first user of the model trading platform, generate transaction information corresponding to the first comfort model based on the model transaction information of the acquired third user when it is detected that a third user has traded the first comfort model. This can improve the accuracy of the generation of transaction information, thereby facilitating increasing the enthusiasm and interest of users in using the model trading platform to trade models through transaction information, and is conducive to improving the convenience of trading comfort models through the provided model trading platform.

[0133] In this optional implementation, optionally, generating transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model may include:

[0134] Obtaining a first platform transaction level of a first user corresponding to the first comfort model, and a second platform transaction level of each third user included in the model transaction situation;

[0135] According to the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all third users, and the transaction times of all third users, respectively calculate the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each third user, and the transaction commission information of the model trading platform for the first comfort model;

[0136] The transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of all third users, and the transaction commission information of the model trading platform for the first comfort model are determined as the transaction information corresponding to the first comfort model.

[0137] In an embodiment of the present invention, optionally, the first platform transaction level of the first user can be used to indicate the level corresponding to the first preferential strength that the first user can obtain when selling goods (such as: comfort model) on the model trading platform, and the second platform transaction level of the third user can be used to indicate the level corresponding to the second preferential strength that the second user can obtain when purchasing goods (such as: comfort model) on the model trading platform, and the embodiment of the present invention does not limit this.

[0138] It can be seen that this optional implementation can also calculate the transaction information corresponding to the first comfort model based on the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all third users, and the number of transactions of all third users (the transaction information corresponding to the first comfort model may include the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each third user, and the transaction commission information of the model transaction platform for the first comfort model), which can improve the calculation accuracy and reliability of the transaction information corresponding to the first comfort model.

[0139] In this optional embodiment, as another optional implementation, the method may further include:

[0140] Obtaining the model transaction status corresponding to each first comfort model in the model transaction platform;

[0141] Compare the model transaction situations corresponding to all the first comfort models to obtain the comparison results of all the first comfort models;

[0142] According to the comparison results of all the first comfort models, the model trading platform generates model recommended parameters for all the first comfort models.

[0143] In an embodiment of the present invention, the model recommendation parameter is used to trigger the model trading platform to recommend a model to any second user according to the model recommendation parameter when receiving a model trading demand from the second user. Optionally, the comparison results of all first comfort models may include the ranking results of the model trading situations corresponding to all first comfort models. For example, assuming that the total number of transactions of the first comfort model A, the first comfort model B, and the first comfort model C (the total number of transactions may include the number of transaction users and the number of transactions for each transaction user) are 5, 2, and 1 respectively, the model trading platform may choose to give priority to recommending the first comfort model A.

[0144] It can be seen that this optional implementation method can compare the model transaction situations corresponding to all the first comfort models in the acquired model trading platform, obtain the comparison results of all the first comfort models, and generate the model recommendation parameters of the model trading platform for all the first comfort models according to the comparison results of all the first comfort models, which can improve the generation accuracy of the model recommendation parameters, thereby facilitating improving the model recommendation accuracy of the model trading platform through accurately generated model recommendation parameters, and facilitating improving the intelligence level of the model trading platform in providing services to platform users.

[0145] Embodiment 3

[0146] See also Figure 4 , Figure 4 1 is a schematic diagram of a structure of a user comfort-based model training device disclosed in an embodiment of the present invention. Figure 4 The user comfort-based model training device described may include a training device or a training server, wherein the training server may include a cloud server or a local server, which is not limited in the embodiment of the present invention. Figure 4 As shown, the model training device based on user comfort may include:

[0147] The determination module 301 is used to determine a physiological condition data packet of a first user, where the physiological condition data packet of the first user includes a plurality of physiological condition data of the first user.

[0148] The determination module 301 is further used to determine a comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user, and each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user.

[0149] The training module 302 is used to input the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user. The comfort model is used to calculate the first physiological condition data of the input first user, so as to obtain the first comfort control parameter of the air conditioner for the first user.

[0150] It can be seen that the implementation Figure 4The described model training device based on user comfort can accurately determine the comfort control parameter set of the air conditioner for the first user according to the determined physiological condition data packet of the first user, and input the physiological condition data packet of the first user and the accurately determined comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user, which can improve the training accuracy of the comfort model, thereby facilitating improving the accuracy of controlling the air conditioner to adjust the user's surrounding environment through the comfort control parameters output by the accurately trained comfort model, so as to better meet the user's comfort needs, and can also enhance the user's experience of using the air conditioner and improve the user's usage stickiness.

[0151] In an optional embodiment, the manner in which the determining module 301 determines the physiological condition data packet of the first user may specifically include:

[0152] Detecting whether the first user sends a data packet upload instruction of the first user;

[0153] When a data packet upload instruction sent by the first user is detected, determining whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction;

[0154] When it is determined that at least one first data matching the physiological condition of the first user exists in all the uploaded data in the uploaded data packet, all the first data matching the physiological condition of the first user are determined as the physiological condition data packet of the first user.

[0155] It can be seen that this optional embodiment can determine whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction when the first user sends his data packet upload instruction, and when it is determined that there is at least one first data matching the physiological condition of the first user, all the first data are determined as the physiological condition data packet of the first user, which can improve the accuracy of determining the physiological condition data packet of the first user, thereby facilitating improving the training accuracy of the comfort model through accurately determined physiological condition data packets.

[0156] In this optional embodiment, as an optional implementation manner, when it is determined that none of the uploaded data in the uploaded data packet indicated by the data packet upload instruction contains the first data matching the physiological condition of the first user, the manner in which the determination module 301 determines the physiological condition data packet of the first user may specifically include:

[0157] According to all the uploaded data in the uploaded data packet and the preset physiological condition association relationship, at least one second data having a correlation degree greater than or equal to a preset correlation degree with the physiological condition of the first user is screened out from all the uploaded data;

[0158] All second data and physiological condition associations are calculated to obtain third data matching the physiological condition of the first user, and the third data is determined as the physiological condition data packet of the first user.

[0159] It can be seen that this optional implementation can, when there is no physiological condition data packet in the data packet uploaded by the first user, accurately screen out at least one second data whose correlation with the physiological condition of the first user is greater than or equal to the preset correlation from all the uploaded data, based on all the data uploaded by the first user and the preset physiological condition correlation relationship, and calculate all the accurately screened second data and physiological condition correlation relationships to obtain third data matching the physiological condition of the first user. This data packet serves as the physiological condition data packet of the first user, and can improve the accuracy and flexibility of determining the data packet corresponding to the physiological condition of the first user, and reduce the occurrence of errors in the comfort control parameter set of the first user subsequently determined due to the first user not uploading the physiological condition data packet.

[0160] In another optional embodiment, there is a corresponding model trading platform for the air conditioner, and the model trading platform is used to provide at least one comfort model trained by the training module 302 to platform users in the model trading platform for trading, and the platform users include at least one first user as a model seller user and at least one second user as a model buyer user. And, Figure 5 As shown, the device may also include:

[0161] The generating module 303 is used to generate a data packet matching instruction corresponding to the second user according to the acquired second physiological condition data of the second user when the model trading platform receives the comfort control demand of any second user for the air conditioner;

[0162] A screening module 304 is used to screen out a physiological condition data packet that matches the data packet matching instruction of the second user from the input data of the model input interface of all first comfort models uploaded to the model trading platform according to the data packet matching instruction corresponding to the second user, as a target physiological condition data packet corresponding to the second user;

[0163] The determination module 301 is also used to determine the first comfort model corresponding to the target physiological condition data packet corresponding to the second user, as the second comfort model corresponding to the second user. The second comfort model is used to calculate the input second physiological condition data of the second user to obtain the second comfort control parameters of the air conditioner for the second user.

[0164] It can be seen that this optional embodiment can generate a data packet matching instruction corresponding to the second user based on the physiological condition data of the second user when the second user who has not undergone comfort model training has a comfort regulation demand, and according to the data packet matching instruction corresponding to the second user, filter out the target physiological condition data packet matching the second user from the input data of the model input interface of all first comfort models of the model trading platform, which can improve the screening accuracy of the target physiological condition data packet corresponding to the second user, reduce the occurrence of screening of target physiological condition data packets that do not need to be screened, and determine the first comfort model corresponding to the target physiological condition data packet in the model trading platform as the second comfort model corresponding to the second user, which can improve the accuracy and speed of determining the second comfort model, thereby facilitating the output of the second comfort control parameters of the air conditioner for the second user through the accurately screened second comfort model, so as to meet the comfort regulation demand of the second user, and further help to improve the second user's usage experience and usage stickiness.

[0165] In this optional embodiment, as an optional implementation, as Figure 5 As shown, the device may also include:

[0166] The detection module 305 is used to detect, for each first user of the model trading platform, whether there is a third user who trades the first comfort model among all second users of the model trading platform;

[0167] The acquisition module 306 is used to acquire the model transaction status of the third user for the first comfort model when it is detected that there is a third user who trades the first comfort model among all the second users, and the model transaction status includes the number of third users and the number of transactions of the corresponding third users;

[0168] The generation module 303 is further used to generate transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model, and the transaction information corresponding to the first comfort model includes transaction profit information of the first user corresponding to the first comfort model.

[0169] It can be seen that this optional implementation can, for the first comfort model corresponding to each first user of the model trading platform, generate transaction information corresponding to the first comfort model based on the model transaction information of the acquired third user when it is detected that a third user has traded the first comfort model. This can improve the accuracy of the generation of transaction information, thereby facilitating increasing the enthusiasm and interest of users in using the model trading platform to trade models through transaction information, and is conducive to improving the convenience of trading comfort models through the provided model trading platform.

[0170] In this optional implementation, optionally, the generation module 303 generates the transaction information corresponding to the first comfort model according to the model transaction situation corresponding to the first comfort model in a manner that specifically includes:

[0171] Obtaining a first platform transaction level of a first user corresponding to the first comfort model, and a second platform transaction level of each third user included in the model transaction situation;

[0172] According to the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all third users, and the transaction times of all third users, respectively calculate the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each third user, and the transaction commission information of the model trading platform for the first comfort model;

[0173] The transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of all third users, and the transaction commission information of the model trading platform for the first comfort model are determined as the transaction information corresponding to the first comfort model.

[0174] It can be seen that this optional implementation can also calculate the transaction information corresponding to the first comfort model based on the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all third users, and the number of transactions of all third users (the transaction information corresponding to the first comfort model may include the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each third user, and the transaction commission information of the model transaction platform for the first comfort model), which can improve the calculation accuracy and reliability of the transaction information corresponding to the first comfort model.

[0175] In this optional embodiment, as another optional implementation, the acquisition module 306 is further used to acquire the model transaction situation corresponding to each first comfort model in the model transaction platform;

[0176] And, if Figure 5 As shown, the device may also include:

[0177] A comparison module 307 is used to compare the model transaction situations corresponding to all the first comfort models to obtain the comparison results of all the first comfort models;

[0178] The generation module 303 is also used to generate model recommendation parameters of the model trading platform for all first comfort models based on the comparison results of all first comfort models. The model recommendation parameters are used to trigger the model trading platform to recommend a model to any second user based on the model recommendation parameters when receiving the model trading demand of the second user.

[0179] It can be seen that this optional implementation method can compare the model transaction situations corresponding to all the first comfort models in the acquired model trading platform, obtain the comparison results of all the first comfort models, and generate the model recommendation parameters of the model trading platform for all the first comfort models according to the comparison results of all the first comfort models, which can improve the generation accuracy of the model recommendation parameters, thereby facilitating improving the model recommendation accuracy of the model trading platform through accurately generated model recommendation parameters, and facilitating improving the intelligence level of the model trading platform in providing services to platform users.

[0180] Embodiment 4

[0181] See also Figure 6 , Figure 6 FIG. 1 is a schematic diagram of a structure of another user comfort-based model training device disclosed in an embodiment of the present invention. Figure 6 As shown, the user comfort-based model training device based on user comfort may include:

[0182] A memory 401 storing executable program codes;

[0183] a processor 402 coupled to the memory 401;

[0184] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the model training method based on user comfort described in the first embodiment of the present invention or the second embodiment of the present invention.

[0185] Embodiment 5

[0186] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the model training method based on user comfort described in Embodiment 1 or Embodiment 2 of the present invention.

[0187] Embodiment 6

[0188] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the user comfort-based model training method based on user comfort described in Example 1 or Example 2.

[0189] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0190] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0191] Finally, it should be noted that the user comfort-based model training method and device disclosed in the embodiment of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A model training method based on user comfort, characterized in that: The method comprises: Determine a physiological condition data packet of a first user, where the physiological condition data packet of the first user includes a plurality of physiological condition data of the first user; determining, according to the physiological condition data packet of the first user, a comfort control parameter set of the air conditioner for the first user, wherein each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user; The physiological condition data packet of the first user and the comfort control parameter set of the first user are input into the initial comfort model to be trained for model training to obtain a comfort model corresponding to the first user. The comfort model is used to calculate the input first physiological condition data of the first user to obtain the first comfort control parameter of the air conditioner for the first user.

2. The model training method based on user comfort according to claim 1, characterized in that: The step of determining the physiological condition data packet of the first user includes: Detecting whether the first user sends a data packet upload instruction of the first user; When a data packet upload instruction sent by the first user is detected, determining whether there is at least one first data matching the physiological condition of the first user among all the uploaded data in the uploaded data packet indicated by the data packet upload instruction; When it is determined that at least one first data matching the physiological condition of the first user exists in all the uploaded data in the uploaded data packet, all the first data matching the physiological condition of the first user are determined as the physiological condition data packet of the first user.

3. The model training method based on user comfort according to claim 2, characterized in that: When it is determined that none of the uploaded data in the uploaded data packet indicated by the data packet upload instruction contains first data matching the physiological condition of the first user, the step of determining the physiological condition data packet of the first user includes: According to all the uploaded data in the uploaded data packet and the preset physiological condition association relationship, at least one second data having a correlation degree greater than or equal to a preset correlation degree with the physiological condition of the first user is screened out from all the uploaded data; All the second data and the physiological condition association relationships are calculated to obtain third data matching the physiological condition of the first user, and the third data is determined as the physiological condition data packet of the first user.

4. The model training method based on user comfort according to any one of claims 1 to 3, characterized in that: The air conditioner has a corresponding model trading platform, and the model trading platform is used to provide at least one of the trained comfort models to platform users in the model trading platform for trading, and the platform users include at least one of the first users as a model seller user and at least one second user as a model buyer user; And, the method further comprises: When the model trading platform receives a comfort control demand of any second user for the air conditioner, a data packet matching instruction corresponding to the second user is generated according to the acquired second physiological condition data of the second user; According to the data packet matching instruction corresponding to the second user, a physiological condition data packet matching the data packet matching instruction of the second user is screened out from the input data of the model input interface of all first comfort models uploaded to the model trading platform as a target physiological condition data packet corresponding to the second user; Determine a first comfort model corresponding to the target physiological condition data packet corresponding to the second user as a second comfort model corresponding to the second user. The second comfort model is used to calculate the input second physiological condition data of the second user to obtain a second comfort control parameter of the air conditioner for the second user.

5. The model training method based on user comfort according to claim 4, characterized in that: The method further comprises: For the first comfort model corresponding to each of the first users of the model trading platform, detecting whether there is a third user who trades with the first comfort model among all the second users of the model trading platform; When it is detected that there is a third user who has traded the first comfort model among all the second users, obtaining the model transaction status of the third users for the first comfort model, wherein the model transaction status includes the number of the third users and the transaction times of the corresponding third users; According to the model transaction situation corresponding to the first comfort model, the transaction information corresponding to the first comfort model is generated, and the transaction information corresponding to the first comfort model includes the transaction profit information of the first user corresponding to the first comfort model.

6. The model training method based on user comfort according to claim 5, characterized in that: The generating, according to the model transaction situation corresponding to the first comfort model, the transaction information corresponding to the first comfort model comprises: Acquire a first platform transaction level of a first user corresponding to the first comfort model, and a second platform transaction level of each of the third users included in the model transaction situation; According to the first platform transaction level of the first user corresponding to the first comfort model, the second platform transaction levels of all the third users, and the transaction times of all the third users, respectively calculate the transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of each of the third users, and the transaction commission information of the model trading platform for the first comfort model; The transaction profit information of the first user corresponding to the first comfort model, the transaction consumption information of all the third users, and the transaction commission information of the model trading platform for the first comfort model are determined as the transaction information corresponding to the first comfort model.

7. The model training method based on user comfort according to claim 5 or 6, characterized in that: The method further comprises: Acquire the model transaction status corresponding to each of the first comfort models in the model transaction platform; Comparing the model transaction situations corresponding to all the first comfort models to obtain comparison results of all the first comfort models; Based on the comparison results of all the first comfort models, the model trading platform generates model recommendation parameters for all the first comfort models, and the model recommendation parameters are used to trigger the model trading platform to recommend a model to any of the second users based on the model recommendation parameters when receiving the model trading demand of the second user.

8. A model training device based on user comfort, characterized in that: The device comprises: A determination module, configured to determine a physiological condition data packet of a first user, wherein the physiological condition data packet of the first user includes a plurality of physiological condition data of the first user; The determination module is further configured to determine a comfort control parameter set of the air conditioner for the first user according to the physiological condition data packet of the first user, wherein each comfort control parameter included in the comfort control parameter set meets the comfort requirement of the first user; A training module is used to input the physiological condition data packet of the first user and the comfort control parameter set of the first user into the initial comfort model to be trained for model training, so as to obtain the comfort model corresponding to the first user. The comfort model is used to calculate the input first physiological condition data of the first user, so as to obtain the first comfort control parameter of the air conditioner for the first user.

9. A model training device based on user comfort, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the user comfort-based model training method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, which, when called, are used to execute the model training method based on user comfort as described in any one of claims 1-7.

Images