Multi-mode temperature control method, device, electronic device and storage medium

Abstract

The present invention discloses a multimodal temperature control method, device, electronic device and storage medium. The method includes obtaining first multimodal data that affects the temperature control of the device to be controlled from at least two dimensions, and preprocessing the multimodal data to obtain second multimodal data; extracting features from the second multimodal data and assigning weights, superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain the target temperature of the device to be controlled; inputting the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative updating until the loss function converges to obtain the target temperature prediction model. By adopting the technical solution of the embodiment of the present invention, the temperature change trend of the device to be controlled can be perceived in advance, so that the temperature of the device to be controlled can be adjusted in advance to avoid unnecessary energy waste.

Description

Technical Field

[0001] The present invention relates to the field of building control technology, and in particular to a multi-modal temperature control method, device, electronic equipment and storage medium. Background Art

[0002] In modern buildings, the temperature control of building equipment usually adopts manual mode and automatic mode to control the building temperature.

[0003] Manual mode is typically controlled manually by the user through the temperature controller panel, enabling controls such as turning the air conditioner on and off, setting the air conditioner fan speed, and operating mode. Once the air conditioner begins operating, it typically continues to operate in the specified state. Automatic mode is an intelligent operating mode for air conditioners that automatically adjusts its operating state and switches operating modes based on environmental changes. For example, when the temperature difference is large, the air conditioner will operate at a higher fan speed to quickly adjust the temperature. When the temperature difference is small, the fan speed will be reduced to maintain the temperature more gently while reducing noise and energy consumption. When the temperature is above the set comfort range, the air conditioner automatically switches to cooling mode to lower the indoor temperature. When the indoor temperature falls below the set range, the air conditioner switches to heating mode to raise the indoor temperature.

[0004] In manual mode, each temperature adjustment requires manual intervention. Automatic mode may not meet individual user needs, such as those who prefer a cooler or warmer environment. Furthermore, the temperature typically fluctuates within the system's default temperature (e.g., 26 degrees Celsius), which is set at the factory and cannot be changed by normal user operation. Summary of the Invention

[0005] The present invention provides a multimodal temperature control method, device, electronic device and storage medium to solve the problem that the automatic mode cannot meet personalized needs and cannot adaptively achieve temperature control.

[0006] According to one aspect of the present invention, a multi-modal temperature control method is provided, the method comprising:

[0007] Acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data;

[0008] Extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with a basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled;

[0009] The second multimodal data and the target temperature of the device to be controlled are input into a preset temperature prediction model for model training and iterative update until the loss function converges to obtain a target temperature prediction model.

[0010] According to another aspect of the present invention, there is provided a multi-modal temperature control device, the device comprising:

[0011] a multimodal data acquisition module, configured to acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data;

[0012] a multimodal data weighting module, configured to extract features from the second multimodal data and assign weights to the second multimodal data, and superimpose the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled;

[0013] The target temperature prediction model training module is used to input the second multimodal data and the target temperature of the device to be controlled into the preset temperature prediction model for model training and iterative update until the loss function converges to obtain the target temperature prediction model.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] at least one processor; and,

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the multi-modal temperature control method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the multi-modal temperature control method according to any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the computer program implements the multi-modal temperature control method according to any embodiment of the present invention.

[0020] The technical solution of the embodiment of the present invention obtains first multimodal data that affects the temperature control of the device to be controlled from at least two dimensions, preprocesses the multimodal data, and obtains second multimodal data; extracts features from the second multimodal data and assigns weights, superimposes the weighted second multimodal data with the basic set temperature of the device to be controlled, and obtains the target temperature of the device to be controlled; inputs the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining the target temperature prediction model. This solves the problem of being unable to meet personalized needs and unable to achieve adaptive temperature control in automatic mode, and achieves the beneficial effect of pre-sensing the temperature change trend of the device to be controlled, adjusting the temperature of the device to be controlled in advance, and avoiding unnecessary energy waste.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 This is a flow chart of a multi-mode temperature control method provided according to the first embodiment of the present invention.

[0024] Figure 2 This is a flow chart of a multi-mode temperature control method provided according to the second embodiment of the present invention.

[0025] Figure 3 3 is a schematic structural diagram of a multi-mode temperature control device provided according to embodiment 3 of the present invention.

[0026] Figure 4 It is a structural diagram of an electronic device provided by the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0028] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. It should be noted that the terms "first", "second", "target", "original", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including", "etc." and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1:

[0030] Figure 1 A flowchart of a multi-modal temperature control method is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the temperature of a device to be controlled is automatically adjusted according to multi-modal indoor and outdoor environmental conditions. The method can be executed by a multi-modal temperature control device. The multi-modal temperature control device can be implemented in the form of hardware and / or software. The multi-modal temperature control device can be configured in any electronic device with network communication function. Figure 1 As shown, the method includes:

[0031] S110 , obtaining first multimodal data that affects temperature control of the device to be controlled from at least two dimensions, and preprocessing the multimodal data to obtain second multimodal data.

[0032] The device to be controlled may refer to a device that needs to be temperature controlled in a building, for example, an air-conditioning device.

[0033] In an embodiment of the present invention, first multimodal data influencing the temperature control of a device to be controlled is obtained from at least two dimensions. The first multimodal data influencing the temperature control of the device to be controlled may refer to a change in the indoor temperature requirement due to a change in the first multimodal data, necessitating temperature control of the device to be controlled. The multimodal data includes, but is not limited to, indoor and outdoor temperature, indoor and outdoor humidity, the number of people indoors, indoor room dimensions, user preferences, and the outdoor temperature of the day.

[0034] The preprocessing may refer to validating the first multimodal data and expanding the data; for example, determining whether the first multimodal data is empty, determining whether the first multimodal data exceeds a preset numerical range, converting the first multimodal data type, and expanding the first multimodal data sample.

[0035] In an embodiment of the present invention, first multimodal data that affects the temperature control of the device to be controlled is obtained from at least two dimensions, and the multimodal data is preprocessed to obtain second multimodal data; and the second multimodal data is saved in a CSV format file for future use.

[0036] S120 , extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with a basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled.

[0037] The feature extraction may refer to obtaining features of the second multimodal data and performing normalization processing for subsequent weighted calculation. For example, feature extraction is performed on the indoor and outdoor temperatures obtained over a period of time, the changing trends of the indoor and outdoor temperatures are obtained, and normalization processing is performed to perform weighted processing on the indoor and outdoor temperatures. The weighted processing may refer to assigning weights to the second multimodal data, and the weighting may be assigned according to the importance of the second multimodal data; for example, in summer, if the user prefers coolness, the weight of the user's preference may be assigned relatively large, so that the temperature can be adjusted according to the user's preference.

[0038] The basic set temperature may refer to the original set temperature of the device to be controlled. For example, the basic set temperature of an air-conditioning device is usually 26°C. In an embodiment of the present invention, the weighted second multimodal data is superimposed on the basic set temperature to obtain the target temperature of the device to be controlled. For example, in winter, when the outdoor temperature is lower than the basic set temperature, the heating mode should be turned on to raise the indoor temperature to the set temperature. A weight is assigned to the outdoor temperature, and the weighted outdoor temperature is added to the basic set temperature to obtain the target temperature of the device to be controlled.

[0039] The target temperature may refer to a desired indoor temperature under the influence of the second multimodal data. In this embodiment of the present invention, the target temperature of the device to be controlled is obtained by assigning a weight to the second multimedia data and superimposing the weighted second multimodal data with the base set temperature of the device to be controlled.

[0040] S130 , inputting the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model.

[0041] The preset temperature prediction model may be a temperature prediction model based on a long short-term memory network. The model is trained by inputting the second multimodal data, the weights of the second multimodal data, and the target temperature of the device to be controlled into the preset temperature prediction model to obtain a converged target temperature prediction model. In embodiments of the present invention, the target temperature prediction model is used to predict the temperature of the device to be controlled at the next moment based on multimodal data affecting the indoor temperature, thereby achieving automatic temperature control of the device to be controlled.

[0042] An embodiment of the present invention provides a multimodal temperature control method. First multimodal data influencing the temperature control of a device to be controlled is acquired from at least two dimensions, and the multimodal data is preprocessed to obtain second multimodal data. Feature extraction and weighting are performed on the second multimodal data, and the weighted second multimodal data is superimposed on the basic set temperature of the device to be controlled to obtain a target temperature for the device to be controlled. The second multimodal data and the target temperature of the device to be controlled are input into a preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model. By adopting the technical solution of the embodiment of the present invention, the temperature change trend of the device to be controlled can be perceived in advance, thereby adjusting the temperature of the device to be controlled in advance and avoiding unnecessary energy waste.

[0043] Example 2:

[0044] Figure 2 This is a flow chart of a multi-mode temperature control method provided by the second embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment. The embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0045] S210: Acquire first multimodal data that affects temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data.

[0046] In this embodiment of the present invention, first multimodal data affecting the temperature control of the device to be controlled within a period of time is obtained from at least two dimensions, and the multimodal data is preprocessed to obtain second multimodal data.

[0047] As an optional but non-limiting implementation, the method of obtaining first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions and preprocessing the multimodal data to obtain second multimodal data includes but is not limited to steps A1-A2:

[0048] Step A1: Obtain first multimodal data that affects the temperature control of the device to be controlled from at least two dimensions; wherein the first multimodal data includes indoor and outdoor temperature, indoor and outdoor humidity, number of people indoors, indoor space dimensions, user preferences, and outdoor temperature conditions on the day.

[0049] Step A2: Preprocess the first multimodal data to obtain second multimodal data, and save the second multimodal data in a target file of a preset format; wherein the preprocessing includes determining whether the multimodal data is empty, determining whether the multimodal data exceeds a preset numerical range, multimodal data type conversion, and multimodal data sample expansion.

[0050] The system acquires first multimodal data from at least two dimensions that influence the temperature control of the device to be controlled. For example, a temperature sensor collects real-time indoor and outdoor temperatures, a humidity sensor collects indoor and outdoor humidity values, and a occupancy sensor collects the number of people in the room. This data is used to determine room size, user preferences (cold, normal, warm), the day's minimum and maximum outdoor temperatures, and the date. Real-time indoor and outdoor temperature and humidity are collected proactively at one-minute intervals, while the occupancy sensor automatically collects data when people pass by. Minimum and maximum temperatures are derived from online weather data.

[0051] After acquiring the first multimodal data, the first multimodal data is preprocessed to obtain the second multimodal data. For example, the first multimodal data is validated, and the validation includes determining whether the multimodal data is empty, determining whether the multimodal data exceeds a preset numerical range, and converting the multimodal data type; wherein, if the multimodal data is empty, it is necessary to collect it again; if the multimodal data exceeds the preset numerical range, it is necessary to determine whether the device is damaged; and convert the multimodal data to a floating point type or an integer. In addition, in order to enrich the data sample, the obtained first multimodal data is expanded using a linear interpolation method. Afterwards, the obtained second multimodal data is saved in a local CSV format file for use.

[0052] S220 , extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled.

[0053] Before feature extraction is performed on the second multimodal data, parameter initialization is also included; specifically, the weights of the influencing factors of indoor space size, indoor number of people, user preferences, outdoor temperature and humidity are initialized, the local historical data recording buffer is initialized (for example, recording 24 hours of data), and a learning rate is set for regular updating and adjustment of weights.

[0054] Extracting features from the second multimodal data and assigning weights thereto may comprise obtaining the second multimodal data from a CSV file, extracting features, and normalizing each of the obtained features for subsequent weighted calculation. Calculating the target temperature may comprise performing proportional weighting based on current input feature values ​​and weights, and superimposing the weights with a base set temperature to obtain the target temperature.

[0055] As an optional but non-limiting implementation, extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain the target temperature of the device to be controlled includes but is not limited to steps B1-B3:

[0056] Step B1: extracting features of the outdoor temperature included in the second multimodal data, and assigning corresponding weights to the outdoor temperature.

[0057] Step B2: Determine the difference between the outdoor temperature and the basic set temperature of the device to be controlled.

[0058] Step B3: Determine the first target temperature of the device to be controlled based on the difference, the weight assigned to the outdoor temperature, the mode coefficient, and the basic device temperature.

[0059] Among them, taking the second multimodal data including outdoor temperature as an example, a weight is assigned to the outdoor temperature, and the target temperature is determined. Read the current outdoor temperature, minimum temperature, maximum temperature and the date of the day, and fit the working mode that the current air conditioner should be turned on, heating, ventilation or cooling. For example, in spring, when the outdoor temperature is lower than the basic set temperature, the heating mode should be turned on to raise the indoor temperature to the set temperature; when the outdoor temperature is higher than the basic set temperature, the ventilation mode should be turned on to introduce external heat to raise the indoor temperature to the set temperature. The minimum and maximum temperatures are used to assist in determining the working mode of the air conditioner. If the maximum temperature is lower than the set temperature, the heating mode must be turned on.

[0060] Based on the air conditioning operating mode and the difference between the real-time outdoor temperature and the current temperature, the outdoor temperature characteristics are proportionally weighted. That is, the target temperature is equal to the basic set temperature plus the characteristic weighted value of the difference between the real-time outdoor temperature and the current real-time indoor temperature. The target temperature is dynamically adjusted to intelligently maintain indoor comfort while improving energy efficiency.

[0061] Optionally, the higher the outdoor temperature, the lower the target temperature; the lower the outdoor temperature, the higher the target temperature. The air conditioner operates in different modes. In cooling mode, the temperature difference is equal to the outdoor temperature minus the indoor temperature; in heating mode, the temperature difference is equal to the indoor temperature minus the outdoor temperature. By compensating the basic set temperature with the outdoor temperature, the temperature control system can more reasonably respond to different environmental conditions. The logic in cooling / heating mode is symmetrical but in opposite directions, specifically expressed as:

[0062] In cooling mode, the target temperature calculation formula can be expressed as:

[0063]

[0064] Among them, the Indicates the target temperature of the device to be controlled after dynamic adjustment; Indicates the basic set temperature of the device to be controlled; Indicates outdoor temperature; Indicates the weight given to the outdoor temperature. When the outside is hotter, the target temperature needs to be lowered further to offset the heat conduction. When it is cooler outside, the target temperature needs to be raised appropriately to avoid over-cooling.

[0065] In heating mode, the target temperature calculation formula can be expressed as:

[0066]

[0067] Among them, when When the outside is colder, the target temperature needs to be raised further to compensate for the heat loss. When it is warmer outside, the target temperature needs to be lowered appropriately to avoid overheating.

[0068] In summary, it can be determined that in cooling mode, Negatively correlated with the outdoor temperature difference, it should resist the outdoor high temperature and enhance the cooling effect; in heating mode, It is positively correlated with the outdoor temperature difference and should counteract the low outdoor temperature to enhance the heating effect. Among them, the weight determines the intensity of the outdoor temperature influence and needs to be calibrated through experiments or experience. The cooling and heating formulas are essentially the same logic with opposite signs, reflecting the duality of the modes. Therefore, the two formulas can be combined into a first target temperature calculation formula, and the mode coefficient is used to distinguish between heating mode and cooling mode. Among them, the calculation formula of the first target temperature is expressed as:

[0069]

[0070] Among them, the Indicates the first target temperature of the device to be controlled; Indicates the basic set temperature of the device to be controlled; Indicates outdoor temperature; Indicates the mode coefficient. In cooling mode, ; In heating mode, .

[0071] For example, taking the basic set temperature as 24°C and the outdoor temperature weight as 0.1, in cooling mode, the outdoor temperature is 32°C, and the first target temperature obtained is 23.2°C; in heating mode, the outdoor temperature is 10°C, and the first target temperature obtained is 25.4°C.

[0072] In the embodiment of the present invention, the outdoor temperature is used as an influencing factor affecting the temperature regulation of the device to be controlled, and the outdoor temperature is weighted to achieve temperature regulation of the device to be controlled.

[0073] As an optional but non-limiting implementation, the feature extraction and weighting of the second multimodal data, and the superposition of the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain the target temperature of the device to be controlled also include but are not limited to steps C1-C3:

[0074] Step C1: extracting features from the number of people indoors and the size of the indoor space included in the second multimodal data, and assigning corresponding weights to the number of people indoors and the size of the indoor space.

[0075] Step C2: Determine the second target temperature of the device to be controlled under different conditions of the number of people indoors based on the number of people indoors, the weight assigned to the number of people indoors, the current target temperature, and the first adjustment range; wherein the current target temperature refers to the target temperature of the device to be controlled obtained in the previous stage, and the first adjustment range refers to the maximum temperature adjustment range under different conditions of the number of people indoors.

[0076] Step C3: Or, based on the indoor space size, the indoor space size threshold that triggers temperature adjustment, the weight assigned to the indoor space size, the current target temperature and the second adjustment range, determine the third target temperature of the device to be controlled under different indoor space size conditions; wherein, the second adjustment range refers to the maximum temperature adjustment range under different indoor space size conditions.

[0077] After adjusting the temperature of the device to be controlled based on the outdoor temperature, the temperature can also be adjusted based on the number of people in the room. A weight is assigned to the number of people in the room, the current target temperature, and the first adjustment range to determine the second target temperature of the device to be controlled under different conditions of the number of people in the room. The second target temperature can be expressed as:

[0078]

[0079] in, It can refer to the second target temperature of the device to be controlled under different indoor occupancy conditions; It may refer to the target temperature of the device to be controlled obtained in the previous stage, and here it may refer to the first target temperature; Indicates the number of people in the room; Indicates the weight given by the number of people in the room; Indicates the maximum adjustment range, by which overcooling or overheating is avoided.

[0080] Human respiration heat has a certain impact on temperature, but this is assumed to be negligible when there are fewer than two people in the room. As the number of people in the room gradually increases, the impact of the number of people on the temperature will not exceed a threshold, assuming a maximum adjustment of 0.5 degrees. When there are more people, metabolic heat production increases, requiring stronger cooling or weaker heating.

[0081] The impact of indoor space dimensions on temperature is further calculated based on the number of people in the room. Weights are assigned to the indoor space dimensions, and based on the indoor space dimension threshold that triggers temperature adjustment, the current target temperature, and the second adjustment range, a third target temperature for the device to be controlled under different indoor space dimension conditions is determined. The third target temperature can be expressed as:

[0082]

[0083] in, Indicates the third target temperature of the device to be controlled under different indoor space size conditions; It may refer to the target temperature of the device to be controlled obtained in the previous stage, and here it may refer to the second target temperature; Indicates the current indoor space size, Indicates the indoor space size threshold that triggers temperature adjustment. Indicates the space size adjustment interval, Indicates the spatial size weight of each interval. When the indoor temperature is exceeded, When the temperature drops ℃; passed Calculate the number of temperature adjustments to determine the final temperature value to be adjusted, and the maximum temperature adjustment value does not exceed .

[0084] For example, , , , For example, determine the third target temperature. If the current indoor space size ,at this time , then there is no need to regulate the temperature of the controlled device. At this time, the third target temperature is the target temperature obtained in the previous stage, that is, the second target temperature. , , , that is, you need to adjust 0.15 , at this time the third target temperature is .like , , , that is, it needs to be adjusted according to the maximum adjustment range. At this time, the third target temperature is .

[0085] In the embodiment of the present invention, the target temperature of the device to be controlled is regulated according to the size of the indoor space, so that the indoor temperature is suitable for the corresponding space size, avoiding indoor overcooling or overheating caused by an overly large space.

[0086] As an optional but non-limiting implementation, the feature extraction and weighting of the second multimodal data, and the superposition of the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain the target temperature of the device to be controlled also include but are not limited to steps D1-D2:

[0087] Step D1: extracting features of user preferences included in the second multimodal data, and assigning corresponding weights to the user preferences; wherein the user preferences include preference for cold, preference for heat, and preference for moderate.

[0088] Step D2: Enumerate user preferences and determine the fourth target temperature of the device to be controlled under different user preference conditions based on the enumeration value, the weight assigned to the user preference, and the current target temperature; wherein, the enumeration value of the user's preference for heat is 1, the enumeration value of the user's preference for cold is -1, and the enumeration value of the user's preference for moderate is 0.

[0089] Among them, the proportional weighted value of the user's preferences is calculated. The default maximum adjustment range of the heat preference and cold preference parameters here is plus or minus 1 degree of the set temperature. The specific value will be dynamically adjusted according to the weight. Weights are assigned to user preferences, and user preferences are enumerated to determine the fourth target temperature of the device to be controlled under different user preference conditions. The fourth target temperature can be expressed as:

[0090]

[0091] in, Indicates the fourth target temperature of the device to be controlled under different user preference conditions. Here it refers to the third target temperature; Indicates the weight given to user preferences; represents the user preference coefficient, .

[0092] Optional, with , For example; when the user likes cold, the When the user likes moderate, the When the user likes cold, the .

[0093] In an embodiment of the present invention, by obtaining multimodal data that affects the temperature control of the device to be controlled and assigning weights to the multimodal data, when the multimodal data changes, the temperature of the device to be controlled will re-trigger real-time calculation to dynamically provide the latest suitable temperature for subsequent temperature adjustment.

[0094] Optionally, after each calculation of the appropriate temperature, an error is calculated between it and the real-time temperature to evaluate the performance of the model and update the weights, and the error is recorded in the historical data buffer.

[0095] In an optional solution of an embodiment of the present invention, the method further includes updating the base set temperature and multimodal data weights. The average value of the real-time temperature data of the controlled device recorded over a period of time (e.g., 24 hours) is obtained as the latest base set temperature. The multimodal data weights are updated based on the error between the target temperature and the real-time temperature cached in the historical data buffer and the feature weights. The weight update can be expressed as:

[0096]

[0097] in, The updated weight of the i-th multimodal data, Represents the weight of the i-th multimodal data before updating; represents the learning rate; Indicates the number of historical records of participation in extremes, such as data recorded in 24 hours; Indicates the error of the k-th record data; Indicates the normalized feature value of the kth record, such as the indoor space size and the number of people indoors, which need to be normalized to a reasonable range.

[0098] In the embodiment of the present invention, the weights of the multimodal data and the basic set temperature of the device to be controlled are updated at irregular intervals to determine a target temperature that is more suitable for the current indoor environmental conditions.

[0099] S230: Input the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative update until the loss function converges to obtain a target temperature prediction model.

[0100] After the target temperature of the device to be controlled is determined, the target temperature and the second multimodal data are input into a preset temperature prediction model for model training to obtain a converged target temperature prediction model.

[0101] As an optional but non-limiting implementation, the second multimodal data and the target temperature of the device to be controlled are input into a preset temperature prediction model for model training and iterative updating until the loss function converges to obtain the target temperature prediction model, including but not limited to steps E1-E3:

[0102] Step E1: constructing a preset temperature prediction model based on a long short-term memory network; wherein, the output value of the fully connected layer of the preset temperature prediction model is modified so that the number of output values ​​is consistent with the predicted length of the sequence sample.

[0103] Step E2: constructing a time series sample according to the second multimodal data and the target temperature of the device to be controlled.

[0104] Step E3: Input the time series samples into a preset temperature prediction model for model training and iterative update until the loss function converges to obtain a target temperature prediction model.

[0105] The process reads a CSV file and normalizes the features of the collected multimodal data by column to obtain the mean and standard deviation of the feature data. This data is then converted to a mean of 0 and a standard deviation of 1. This eliminates differences in dimensionality and numerical range between features, ensuring that they are on the same scale, improving model training effectiveness and accuracy. Secondly, the time information for each set (row) of data (e.g., 2025-01-20 14:30:00) is read and broken down into hours and specific dates to help the model understand temporal features and capture temporal patterns. The parsed time features are then concatenated with other numerical values ​​as input to construct time series samples for network model training.

[0106] A preset temperature prediction model based on a long short-term memory network is constructed. This is a multi-step prediction model that modifies the output value of the network's final output layer to determine the length of the predicted temperature for the device to be controlled. For example, modifying the output value of the output layer to 5 will predict the temperature of the device to be controlled for five future time points. Optionally, the number of output values ​​in the output layer must be consistent with the predicted length of the sequence sample. The formula can be expressed as:

[0107]

[0108] in, represents the predicted temperature at the i-th time point in the future, Represents the predicted length of the sequence sample.

[0109] The processed time series samples are input into the preset temperature prediction model for model training, and the MSE loss function (averaging the errors of 5 prediction steps) is used for iterative training. The loss function can be expressed as:

[0110]

[0111] Where n represents the number of samples, k represents the time step of prediction, represents the true value of the i-th sample at the j-th time point, Represents the predicted value of the i-th sample at the j-th time point.

[0112] In one optional solution of an embodiment of the present invention, after determining the target temperature prediction model, the trained target temperature prediction model must be verified. After obtaining the trained target temperature prediction model, it is verified using a test set. After repeated verification, a better network model is obtained. If the prediction effect is poor, the trained model parameters are modified and iterative training is repeated. After that, the current set of input features is simply input into the model, and the model will directly output the temperature prediction value for the next five time steps.

[0113] As shown in Tables 1 and 2, consider a simple time series dataset with temperature recorded every minute, used to predict the temperature five minutes into the future. If the time series length T = 10, the model will use the data from the previous 10 minutes to predict the temperature at the next time point. The model uses the data from time points 1 to 10 to predict the temperature at time points 11-15.

[0114] Table 1 Input time series samples

[0115] Time point 1 2 3 4 5 6 7 8 9 10 temperature 20 20.1 20.1 20.2 20.1 20.4 20.5 20.4 20.6 20.7

[0116] Table 2 Output time series samples

[0117] Time point 11 12 13 14 15 Predicted temperature 20.8 20.7 20.9 20.9 21.0

[0118] After validating the model, it needs to be converted and deployed. For example, the trained network model can be converted to ONNX format for deployment on the AIBox edge server platform.

[0119] The embodiment of the present invention determines a converged target temperature prediction model by training, iteratively updating, and verifying a preset temperature prediction model.

[0120] S240, energy consumption forecast.

[0121] After determining a target temperature prediction model, the target temperature prediction model is used to predict the temperature, and a PID algorithm is used to adjust the temperature of the device to be controlled to the predicted temperature to achieve energy savings. The PID algorithm performs calculations based on the input deviation value according to the functional relationship of proportional P, integral I, and differential D, and the calculation results are used to control the output. In this embodiment of the present invention, a preset energy consumption prediction model is constructed to adaptively adjust the temperature of the device to be controlled using the PID algorithm to save energy.

[0122] As an optional but non-limiting implementation, after obtaining the target temperature prediction model, the method further includes energy consumption prediction, specifically including but not limited to steps F1-F3:

[0123] Step F1: using the target temperature prediction model to predict the temperature of the device to be controlled at the next moment to obtain a predicted temperature.

[0124] Step F2: Input the predicted temperature and the real-time temperature at the current moment into a preset energy consumption prediction model to determine the minimum energy consumption and the predicted working state of the device to be controlled at the next moment.

[0125] Step F3: performing a temperature control operation on the device to be controlled according to the predicted working state.

[0126] Taking the predicted temperature for the next five minutes as an example, a target temperature prediction model is used to determine the predicted temperature for the next five minutes. This predicted temperature, along with the current real-time temperature, is then input into a preset energy consumption prediction model. The predicted temperature serves as the target temperature for the device to be controlled. Given a fixed air conditioner duty cycle and cooling capacity, a shortest path algorithm is used to calculate the minimum energy consumption and operating status (0-100) required to adjust the real-time temperature to the target temperature within five minutes. After determining the minimum energy consumption and operating status, assuming the air conditioner can increase or decrease the temperature by 2 degrees Celsius within five minutes at full speed, if the difference between the current real-time temperature and the target temperature is within 1 degree, the device to be controlled can either operate at full speed for two minutes to maintain the real-time temperature within the target temperature, and remain in standby mode for the remainder of the time. Alternatively, the device can operate at 70% of full speed (minimum energy consumption / total energy consumption for five minutes) for five minutes to achieve energy savings.

[0127] In the embodiment of the present invention, a target temperature prediction model is introduced to predict the temperature, so that the system can perceive the temperature change trend in advance, thereby making adjustments in advance to avoid unnecessary energy waste; based on the preset energy consumption prediction model and the temperature prediction results, intelligent control of the heating or cooling system is realized, energy use is optimized, and energy saving and consumption reduction are achieved.

[0128] In an embodiment of the present invention, a multimodal temperature control method is provided. Under the machine learning framework, the collected multimodal data is integrated, and an appropriate temperature setting value is given by adaptively allocating proportional weights, updating the weights, and performing weighted calculations. Secondly, the collected multimodal data is fed into a long short-term memory neural network model for temperature prediction, and temperature values ​​for future time periods can be obtained. Whether there are deviations can be sensed so that corresponding adjustment strategies can be made in advance. Finally, an energy consumption model is established based on the real-time temperature value and the temperature prediction value to achieve the goal of adjusting the real-time temperature to within the predicted temperature range within a specified time, minimizing the required energy consumption, and achieving the purpose of energy saving.

[0129] Example 3:

[0130] Figure 3 This is a schematic diagram of the structure of a multi-mode temperature control device provided in Example 3 of the present invention. Figure 3 As shown, the device includes:

[0131] A multimodal data acquisition module 310 is configured to acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data;

[0132] a multimodal data weighting module 320 for extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled;

[0133] The target temperature prediction model training module 330 is used to input the second multimodal data and the target temperature of the device to be controlled into the preset temperature prediction model for model training and iterative update until the loss function converges to obtain the target temperature prediction model.

[0134] Optional multimodal data acquisition module, specifically used for:

[0135] Acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions; wherein the first multimodal data includes indoor and outdoor temperature, indoor and outdoor humidity, number of people indoors, indoor space dimensions, user preferences, and outdoor temperature conditions on the day;

[0136] The first multimodal data is preprocessed to obtain second multimodal data, and the second multimodal data is saved in a target file in a preset format; wherein the preprocessing includes determining whether the multimodal data is empty, determining whether the multimodal data exceeds a preset numerical range, multimodal data type conversion, and multimodal data sample expansion.

[0137] Optional multimodal data weighting module, specifically used to:

[0138] performing feature extraction on the outdoor temperature included in the second multimodal data, and assigning a corresponding weight to the outdoor temperature;

[0139] Determine the difference between the outdoor temperature and the base set temperature of the equipment to be controlled;

[0140] Determining a first target temperature of the device to be controlled based on the difference, the weight assigned to the outdoor temperature, the mode coefficient, and the basic device temperature;

[0141] The calculation formula of the first target temperature is expressed as:

[0142]

[0143] Among them, the Indicates the first target temperature of the device to be controlled; Indicates the basic set temperature of the device to be controlled; Indicates outdoor temperature; represents the weight given to the outdoor temperature; Indicates the mode coefficient. In cooling mode, ; In heating mode, .

[0144] Optionally, the multimodal data weighting module is also used to:

[0145] performing feature extraction on the number of people indoors and the size of the indoor space included in the second multimodal data, and assigning corresponding weights to the number of people indoors and the size of the indoor space;

[0146] Determining a second target temperature of the device to be controlled under different conditions of the number of people in the room based on the number of people in the room, the weight assigned to the number of people in the room, the current target temperature, and the first adjustment range; wherein the current target temperature refers to the target temperature of the device to be controlled obtained in the previous stage, and the first adjustment range refers to the maximum temperature adjustment range under different conditions of the number of people in the room;

[0147] Alternatively, the third target temperature of the device to be controlled under different indoor space size conditions is determined based on the indoor space size, the indoor space size threshold that triggers temperature adjustment, the weight assigned to the indoor space size, the current target temperature, and the second adjustment range; wherein the second adjustment range refers to the maximum temperature adjustment range under different indoor space size conditions.

[0148] Optionally, the multimodal data weighting module is also used to:

[0149] Extracting features of user preferences included in the second multimodal data and assigning corresponding weights to the user preferences; wherein the user preferences include preference for cold, preference for heat, and preference for moderate;

[0150] User preferences are enumerated, and based on the enumeration values, the weights assigned to the user preferences, and the current target temperature, the fourth target temperature of the device to be controlled under different user preference conditions is determined; wherein, the enumeration value of the user's preference for heat is 1, the enumeration value of the user's preference for cold is -1, and the enumeration value of the user's preference for moderate is 0.

[0151] Optional target temperature prediction model training module, specifically used for:

[0152] Constructing a preset temperature prediction model based on a long short-term memory network; wherein, the output value of the fully connected layer of the preset temperature prediction model is modified so that the number of output values ​​is consistent with the predicted length of the sequence sample;

[0153] constructing a time series sample based on the second multimodal data and a target temperature of the device to be controlled;

[0154] The time series samples are input into a preset temperature prediction model for model training and iterative updating until the loss function converges to obtain a target temperature prediction model.

[0155] Optionally, after obtaining the target temperature prediction model, the device further includes an energy consumption prediction module, specifically configured to:

[0156] The target temperature prediction model is used to predict the temperature of the device to be controlled at the next moment to obtain a predicted temperature;

[0157] Input the predicted temperature and the real-time temperature at the current moment into a preset energy consumption prediction model to determine the minimum energy consumption and the predicted working state of the device to be controlled at the next moment;

[0158] A temperature control operation is performed on the device to be controlled according to the predicted working state.

[0159] The multimodal temperature control device provided in the embodiment of the present invention can execute the multimodal temperature control method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the multimodal temperature control method. For detailed process, please refer to the relevant operations of the multimodal temperature control method in the aforementioned embodiment.

[0160] Example 4:

[0161] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0162] like Figure 4 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0163] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0164] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the multi-modal temperature control method.

[0165] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0166] In some embodiments, the multimodal temperature control method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the multimodal temperature control method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the multimodal temperature control method in any other suitable manner (e.g., via firmware).

[0167] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0168] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0169] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0170] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0171] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0172] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0173] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0174] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A multi-modal temperature control method, characterized in that: The method comprises: Acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data; Extracting features from the second multimodal data and assigning weights, and superimposing the weighted second multimodal data with a basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled; Inputting the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model; The second multimodal data and the target temperature of the device to be controlled are input into a preset temperature prediction model for model training and iterative updating until the loss function converges to obtain the target temperature prediction model, including: Constructing a preset temperature prediction model based on a long short-term memory network; modifying the output value of a fully connected layer of the preset temperature prediction model so that the number of output values ​​is consistent with the predicted length of the time series sample; constructing a time series sample based on the second multimodal data and the target temperature of the device to be controlled; inputting the time series sample into the preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model; The step of extracting features from the second multimodal data and assigning weights to the second multimodal data, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain the target temperature of the device to be controlled includes: Extracting features from the outdoor temperature included in the second multimodal data and assigning a corresponding weight to the outdoor temperature; determining a difference between the outdoor temperature and a base set temperature of the device to be controlled; and determining a first target temperature of the device to be controlled based on the difference, the weight assigned to the outdoor temperature, the mode coefficient, and the base device temperature; The calculation formula of the first target temperature is expressed as: Among them, the Indicates the first target temperature of the device to be controlled; Indicates the basic set temperature of the device to be controlled; Indicates outdoor temperature; represents the weight given to the outdoor temperature; Indicates the mode coefficient. In cooling mode, ; In heating mode, .

2. The method according to claim 1, characterized in that The step of acquiring first multimodal data that affects the temperature control of the device to be controlled from at least two dimensions and preprocessing the multimodal data to obtain second multimodal data includes: Acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions; wherein the first multimodal data includes indoor and outdoor temperature, indoor and outdoor humidity, number of people indoors, indoor space dimensions, user preferences, and outdoor temperature conditions on the day; The first multimodal data is preprocessed to obtain second multimodal data, and the second multimodal data is saved in a target file in a preset format; wherein the preprocessing includes determining whether the multimodal data is empty, determining whether the multimodal data exceeds a preset numerical range, multimodal data type conversion, and multimodal data sample expansion.

3. The method according to claim 1, characterized in that The step of extracting features from the second multimodal data and assigning weights to the second multimodal data, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled, further comprising: performing feature extraction on the number of people indoors and the size of the indoor space included in the second multimodal data, and assigning corresponding weights to the number of people indoors and the size of the indoor space; Determining a second target temperature of the device to be controlled under different conditions of the number of people in the room based on the number of people in the room, the weight assigned to the number of people in the room, the current target temperature, and the first adjustment range; wherein the current target temperature refers to the target temperature of the device to be controlled obtained in the previous stage, and the first adjustment range refers to the maximum temperature adjustment range under different conditions of the number of people in the room; Alternatively, the third target temperature of the device to be controlled under different indoor space size conditions is determined based on the indoor space size, the indoor space size threshold that triggers temperature adjustment, the weight assigned to the indoor space size, the current target temperature, and the second adjustment range; wherein the second adjustment range refers to the maximum temperature adjustment range under different indoor space size conditions.

4. The method according to claim 1, wherein The step of extracting features from the second multimodal data and assigning weights to the second multimodal data, and superimposing the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled, further comprising: Extracting features of user preferences included in the second multimodal data and assigning corresponding weights to the user preferences; wherein the user preferences include preference for cold, preference for heat, and preference for moderate; User preferences are enumerated, and based on the enumeration values, the weights assigned to the user preferences, and the current target temperature, the fourth target temperature of the device to be controlled under different user preference conditions is determined; wherein, the enumeration value of the user's preference for heat is 1, the enumeration value of the user's preference for cold is -1, and the enumeration value of the user's preference for moderate is 0.

5. The method according to claim 1, wherein After obtaining the target temperature prediction model, the method further includes energy consumption prediction, specifically including: The target temperature prediction model is used to predict the temperature of the device to be controlled at the next moment to obtain a predicted temperature; Input the predicted temperature and the real-time temperature at the current moment into a preset energy consumption prediction model to determine the minimum energy consumption and the predicted working state of the device to be controlled at the next moment; A temperature control operation is performed on the device to be controlled according to the predicted working state.

6. A multi-mode temperature control device, characterized in that: The device comprises: a multimodal data acquisition module, configured to acquire first multimodal data affecting the temperature control of the device to be controlled from at least two dimensions, and preprocess the multimodal data to obtain second multimodal data; a multimodal data weighting module, configured to extract features from the second multimodal data and assign weights to the second multimodal data, and superimpose the weighted second multimodal data with the basic set temperature of the device to be controlled to obtain a target temperature of the device to be controlled; a target temperature prediction model training module, configured to input the second multimodal data and the target temperature of the device to be controlled into a preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model; The target temperature prediction model training module is specifically used to: Constructing a preset temperature prediction model based on a long short-term memory network; modifying the output value of a fully connected layer of the preset temperature prediction model so that the number of output values ​​is consistent with the predicted length of the time series sample; constructing a time series sample based on the second multimodal data and the target temperature of the device to be controlled; inputting the time series sample into the preset temperature prediction model for model training and iterative updating until the loss function converges, thereby obtaining a target temperature prediction model; The multimodal data weighting module is specifically used to: Extracting features from the outdoor temperature included in the second multimodal data and assigning a corresponding weight to the outdoor temperature; determining a difference between the outdoor temperature and a base set temperature of the device to be controlled; and determining a first target temperature of the device to be controlled based on the difference, the weight assigned to the outdoor temperature, the mode coefficient, and the base device temperature; The calculation formula of the first target temperature is expressed as: Among them, the Indicates the first target temperature of the device to be controlled; Indicates the basic set temperature of the device to be controlled; Indicates outdoor temperature; represents the weight given to the outdoor temperature; Indicates the mode coefficient. In cooling mode, ; In heating mode, .

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the multi-modal temperature control method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the multi-modal temperature control method according to any one of claims 1 to 5 when executed.

Images