Heating energy-saving method and device based on big data analysis, storage medium and computer program product

Abstract

The invention discloses a heating energy-saving method and device based on big data analysis, a storage medium and a computer program product, and relates to the field of intelligent heating systems.The heating energy-saving method based on big data analysis comprises the steps that historical heating parameters corresponding to multiple first heating devices in a target time period are obtained; clustering processing is conducted on the cooling rate and the target water temperature according to the indoor temperature and the outdoor temperature, clustering results are obtained, target heating parameters are screened out from the clustering results, and multiple target heating parameters are obtained; linear regression data analysis is carried out according to the multiple target heating parameters, and a first common relation model is generated according to an analysis result; and according to the target indoor temperature, the outdoor temperature prediction data of the first target area in the first time period and the first common relation model, the minimum target water temperature of second heating equipment in the first target area in the first time period is determined.

Description

Technical Field

[0001] This application relates to the field of intelligent heating systems, and more specifically, to a heating energy-saving method and device, storage medium, and computer program product based on big data analysis. Background Technology

[0002] Within the existing technological framework, most devices equipped with temperature sensors can directly acquire indoor and outdoor temperature data. This data is crucial for the automated control of these devices, allowing them to adjust their operating states, such as water temperature, based on real-time ambient temperature to maintain a preset comfortable indoor temperature. Furthermore, operational data, such as the rate of water temperature change, is extensively recorded and analyzed to optimize device performance and energy efficiency. Technological advancements in this field, such as the optimization of data processing algorithms and the development of intelligent control strategies, have significantly improved the response speed and energy-saving performance of intelligent heating systems.

[0003] However, for devices without temperature sensors, directly acquiring indoor temperature data becomes quite difficult, limiting their ability to achieve automated temperature regulation. Traditionally, the operating status adjustments of such devices often rely on manual operation by the user or are based on preset schedules, failing to intelligently respond to changes in the external environment.

[0004] There is no effective solution yet for the problem that heating boilers without temperature sensors cannot automatically adjust to the target water temperature that meets the user's room temperature requirements while achieving energy-saving effects. Summary of the Invention

[0005] This application provides a heating energy-saving method and device, storage medium and computer program product based on big data analysis, to at least solve the problem in the prior art that heating boilers without temperature sensors cannot automatically adjust to the target water temperature that meets the user's room temperature requirements while achieving energy-saving effects.

[0006] According to one embodiment of this application, a heating energy-saving method based on big data analysis is provided, comprising: acquiring historical heating parameters corresponding to multiple first heating devices within a target time period, wherein the historical heating parameters include: indoor temperature corresponding to the first heating device, outdoor temperature of a first target area, cooling rate, target water temperature of the first heating device, the time difference between the target time period and the current time being less than a first threshold, the first heating device being equipped with a temperature sensor, the multiple first heating devices being located in the first target area, and the temperature sensor being used at least to collect the indoor temperature; clustering the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain clustering results, and filtering out target heating parameters from the clustering results to obtain multiple A plurality of target heating parameters are defined, wherein the target heating parameters are at least used to indicate the maximum cooling rate for maintaining a target water temperature under the same outdoor and indoor temperatures. The plurality of first heating devices correspond one-to-one with the plurality of target heating parameters. Linear regression data analysis is performed based on the plurality of target heating parameters, and a first common relationship model is generated based on the analysis results. The first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate, and the target water temperature. The minimum target water temperature of a second heating device in the first target area is determined within the first time period based on the target indoor temperature, the predicted outdoor temperature data of the first target area within the first time period, and the first common relationship model. The second heating device is not equipped with the temperature sensor.

[0007] In an exemplary embodiment, before obtaining historical heating parameters corresponding to multiple first heating devices within a target time period, the method further includes: determining the start and end points of the indoor temperature decrease from the indoor temperature data of the first heating devices; calculating a first cooling rate corresponding to a second time period based on a first temperature and a first timestamp corresponding to the start point, and a second temperature and a second timestamp corresponding to the end point, wherein the first timestamp is the start timestamp of the second time period, and the second timestamp is the end timestamp of the second time period; and converting the multiple first cooling rates into multiple second cooling rates corresponding to multiple third time periods using a weighted average algorithm, wherein the multiple third time periods correspond one-to-one with the multiple second cooling rates, and the historical heating parameters include the multiple second cooling rates.

[0008] In an exemplary embodiment, clustering the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain a clustering result includes: grouping the historical heating parameters according to the indoor temperature and the outdoor temperature to obtain multiple groups of first heating parameters, wherein the multiple groups of first heating parameters correspond to the same parameter category as the historical heating parameters, and the indoor temperature and the outdoor temperature corresponding to the multiple first sub-heating parameters included in each group of first heating parameters are all the same; for the multiple first sub-heating parameters of each group of first heating parameters, removing discrete points in the multiple first sub-heating parameters according to the target water temperature and the second cooling rate to obtain multiple filtered first sub-heating parameters, wherein the second cooling rate corresponding to the discrete point is greater than a first preset threshold or less than a second preset threshold, the first preset threshold and the second preset threshold are determined by the multiple first sub-heating parameters; and determining the multiple filtered first sub-heating parameters as the clustering result.

[0009] In an exemplary embodiment, selecting target heating parameters from the clustering results includes: grouping the clustering results according to the target water temperature to obtain multiple groups of second heating parameters, wherein the multiple groups of second heating parameters have the same parameter category as the clustering results, and the multiple second sub-heating parameters included in each group of second heating parameters correspond to the same target water temperature; for the multiple second sub-heating parameters of each group of second heating parameters, filtering the multiple second sub-heating parameters according to the second cooling rate to obtain multiple filtered second sub-heating parameters, wherein the second cooling rate corresponding to the multiple filtered second sub-heating parameters is greater than a third preset threshold, the third preset threshold being determined by the multiple second sub-heating parameters; and determining the multiple filtered second sub-heating parameters as the target heating parameters.

[0010] In an exemplary embodiment, before performing linear regression data analysis based on the plurality of target heating parameters and generating a first common relationship model based on the analysis results, the method further includes: if the target second cooling rate corresponding to the target third time period in the plurality of third time periods is not obtained, determining the third cooling rate corresponding to the first heating device in the fourth time period as the target second cooling rate, thereby obtaining the plurality of second cooling rates, wherein the fourth time period is an adjacent time period of the target third time period; if the third cooling rate is not obtained, determining the plurality of fourth cooling rates corresponding to the second target region as the plurality of second cooling rates, wherein the second target region includes the first target region; if the plurality of fourth cooling rates are not obtained, determining the plurality of fifth cooling rates corresponding to the third target region as the plurality of second cooling rates, wherein the third target region includes the second target region.

[0011] In an exemplary embodiment, after performing linear regression data analysis based on the plurality of target heating parameters and generating a first common relationship model based on the analysis results, the method further includes: obtaining multiple sets of sixth cooling rates corresponding to the plurality of target heating parameters, and multiple outdoor temperatures corresponding to the plurality of target heating parameters, wherein the plurality of target heating parameters correspond one-to-one with the multiple sets of sixth cooling rates, and each set of sixth cooling rates includes the plurality of second cooling rates corresponding to the first heating device; given the multiple sets of sixth cooling rates and the multiple outdoor temperatures, performing linear regression analysis on the multiple sets of sixth cooling rates and the multiple outdoor temperatures with the multiple sets of sixth cooling rates as targets and the multiple outdoor temperatures as feature parameters to obtain a second common relationship model, wherein the plurality of target heating parameters correspond one-to-one with the multiple sets of target heating parameters and the multiple outdoor temperatures as feature parameters. The second public relation model is used to indicate the relationship between the cooling rate and the outdoor temperature in the first target area; if the multiple sets of sixth cooling rates or the multiple outdoor temperatures are not obtained, the third public relation model corresponding to the second target area is determined as the second public relation model, wherein the second target area includes the first target area, and the third public relation model is used to indicate the relationship between the cooling rate and the outdoor temperature in the second target area; if the third public relation model is not obtained, the fourth public relation model corresponding to the third target area is determined as the second public relation model, wherein the third target area includes the second target area, and the fourth public relation model is used to indicate the relationship between the cooling rate and the outdoor temperature in the third target area.

[0012] In an exemplary embodiment, determining the minimum target water temperature of a second heating device in the first target area within the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area within the first time period, and the first public relationship model includes: determining a fifth public relationship model based on the second public relationship model and the first public relationship model; and predicting the target water temperature of the second heating device within the first time period based on the target indoor temperature, the outdoor temperature prediction data, and the fifth public relationship model.

[0013] According to another embodiment of this application, a heating energy-saving device based on big data analysis is also provided, comprising: an acquisition module, configured to acquire historical heating parameters corresponding to multiple first heating devices within a target time period, wherein the historical heating parameters include: indoor temperature corresponding to the first heating device, outdoor temperature of a first target area, cooling rate, target water temperature of the first heating device, the time difference between the target time period and the current time being less than a first threshold, the first heating device being equipped with a temperature sensor, the multiple first heating devices being located in the first target area, and the temperature sensor being used at least to collect the indoor temperature; and a processing module, configured to perform clustering processing on the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain clustering results, and to filter out target heating parameters from the clustering results to obtain multiple A target heating parameter is defined, wherein the target heating parameter is at least used to indicate the maximum cooling rate for maintaining the target water temperature under the same outdoor and indoor temperatures, and the plurality of first heating devices correspond one-to-one with the plurality of target heating parameters; a data analysis module is used to perform linear regression data analysis based on the plurality of target heating parameters, and generate a first common relationship model based on the analysis results, wherein the first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature; a determination module is used to determine the minimum target water temperature of the second heating device in the first target area in the first target area in the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area in the first time period and the first common relationship model, wherein the second heating device is not equipped with the temperature sensor.

[0014] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described heating energy-saving method based on big data analysis when it is run.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the methods described in various embodiments of this application.

[0016] This application first obtains historical heating parameters corresponding to multiple first heating devices in a first target area. Each first heating device is equipped with a temperature sensor. The historical heating parameters include: indoor temperature, outdoor temperature, cooling rate, and target water temperature. The temperature sensor is used to collect at least the indoor temperature. Then, the cooling rate and target water temperature are clustered based on the indoor and outdoor temperatures to obtain clustering results. Target heating parameters are then selected from the clustering results to obtain multiple maximum cooling rates used to maintain the target water temperature under the same indoor and outdoor temperature conditions. Next, linear regression data analysis is performed on these multiple target heating parameters to obtain a first common relationship model corresponding to the multiple target heating parameters. This first common relationship model indicates the correlation between indoor temperature, outdoor temperature, cooling rate, and target water temperature. Finally, the minimum target water temperature of a second heating device in the first target area within the first time period is determined based on the target indoor temperature, the predicted outdoor temperature data of the first target area within a first time period, and the first common relationship model. The second heating device is not equipped with the aforementioned temperature sensor. The above solution involves collecting and analyzing historical operating data from heating users equipped with temperature sensors, including indoor temperature, outdoor temperature, and cooling rate. A linear regression model is then used to establish the relationship between the target water temperature and these factors. This model is applied to heating users without temperature sensors. By combining the current indoor and outdoor temperature data reported by the users with a common formula, the target heating water temperature for a future period is predicted. This solves the problem in related technologies where heating boilers without temperature sensors cannot automatically adjust to a target water temperature that meets user room temperature requirements while achieving energy savings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal for a heating energy-saving method based on big data analysis, according to an embodiment of this application.

[0020] Figure 2 This is a flowchart of a heating energy-saving method based on big data analysis according to an embodiment of this application;

[0021] Figure 3This is a distribution coordinate diagram of a set of first heating parameters according to an embodiment of this application;

[0022] Figure 4 This is a distribution coordinate diagram of a set of clustered first heating parameters according to an embodiment of this application;

[0023] Figure 5 This is a flowchart of a heating temperature prediction method based on linear regression according to an embodiment of this application;

[0024] Figure 6 This is a structural block diagram of a heating energy-saving device based on big data analysis according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] The methods and embodiments provided in this application can be executed on a computer terminal or similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal for a heating energy-saving method based on big data analysis, according to an embodiment of this application. Figure 1 As shown, a computer terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor (MPU) or a field-programmable gate array (FPGA)) and a memory 104 for storing data are also shown. The computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the heating energy-saving method based on big data analysis in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0029] The computer terminal uses a wireless network provided by a communications provider. In one example, transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0030] This embodiment provides a heating energy-saving method based on big data analysis. Figure 2 This is a flowchart of a heating energy-saving method based on big data analysis according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps S202-S208:

[0031] Step S202: Obtain historical heating parameters corresponding to multiple first heating devices within the target time period, wherein the historical heating parameters include: the indoor temperature corresponding to the first heating device, the outdoor temperature of the first target area, the cooling rate, the target water temperature of the first heating device, the time difference between the target time period and the current time is less than a first threshold, the first heating device is equipped with a temperature sensor, the multiple first heating devices are all located in the first target area, and the temperature sensor is used at least to collect the indoor temperature;

[0032] Step S204: Cluster the cooling rate and the target water temperature according to the indoor temperature and the outdoor temperature to obtain clustering results, and filter out target heating parameters from the clustering results to obtain multiple target heating parameters. The target heating parameters are used to indicate at least the maximum cooling rate for maintaining the target water temperature under the same outdoor temperature and indoor temperature conditions. The multiple first heating devices correspond one-to-one with the multiple target heating parameters.

[0033] Step S206: Perform linear regression data analysis based on the multiple target heating parameters, and generate a first common relationship model based on the analysis results. The first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature.

[0034] Step S208: Determine the minimum target water temperature of the second heating device in the first target area during the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relationship model, wherein the second heating device is not equipped with the temperature sensor.

[0035] Through the above steps, firstly, historical heating parameters corresponding to multiple first heating devices in the first target area are obtained. Each first heating device is equipped with a temperature sensor. The historical heating parameters include: indoor temperature, outdoor temperature, cooling rate, and target water temperature. The temperature sensor is used to collect at least the indoor temperature. Then, the cooling rate and target water temperature are clustered based on the indoor and outdoor temperatures to obtain clustering results. Target heating parameters are then selected from the clustering results to obtain multiple maximum cooling rates used to maintain the target water temperature under the same indoor and outdoor temperature conditions. Next, linear regression data analysis is performed on these multiple target heating parameters to obtain a first common relationship model corresponding to the multiple target heating parameters. This first common relationship model indicates the correlation between indoor temperature, outdoor temperature, cooling rate, and target water temperature. Finally, the minimum target water temperature of a second heating device in the first target area within the first time period is determined based on the target indoor temperature, the predicted outdoor temperature data for the first target area within the first time period, and the first common relationship model. The second heating device is not equipped with the aforementioned temperature sensor. The above solution involves collecting and analyzing historical operating data from heating users equipped with temperature sensors, including indoor temperature, outdoor temperature, and cooling rate. A linear regression model is then used to establish the relationship between the target water temperature and these factors. This model is applied to heating users without temperature sensors. By combining the current indoor and outdoor temperature data reported by the users with a common formula, the target heating water temperature for a future period is predicted. This solves the problem in related technologies where heating boilers without temperature sensors cannot automatically adjust to a target water temperature that meets user room temperature requirements while achieving energy savings.

[0036] Optionally, before obtaining the historical heating parameters corresponding to multiple first heating devices within the target time period, the method further includes: determining the start and end points of the indoor temperature decrease from the indoor temperature data of the first heating devices; calculating a first cooling rate corresponding to the second time period based on the first temperature and first timestamp corresponding to the start point, and the second temperature and second timestamp corresponding to the end point, wherein the first timestamp is the start timestamp of the second time period, and the second timestamp is the end timestamp of the second time period; and using a weighted average algorithm to convert the multiple first cooling rates into multiple second cooling rates corresponding to multiple third time periods, wherein the multiple third time periods correspond one-to-one with the multiple second cooling rates, and the historical heating parameters include the multiple second cooling rates.

[0037] In this embodiment, firstly, an intelligent algorithm identifies the start and end times of the indoor temperature drop in the device with a temperature sensor (the aforementioned first heating device). This process utilizes "inflection point detection" technology, aiming to accurately capture key moments of temperature change from time-series data. Next, the cooling rate of the time period corresponding to the start and end times (the aforementioned second time period) is calculated using the formula: Cooling rate = (Starting temperature - Ending temperature) / ((Ending timestamp - Starting timestamp) / 1000 / 60), which represents the temperature drop per minute. Then, a weighted average algorithm is used to process the cooling rates of one or more second time periods within a specific time period (the aforementioned third time period), transforming them into an average value matching the specific time cycle. This not only smooths out data fluctuations but also enhances the "robustness" and "accuracy" of the prediction model by assigning different weights to the data from different second time periods. It should be noted that the aforementioned third time period can be based on real-world standard hours (0-23), for example, the 00-hour period is 00:00:00-00:59:59.

[0038] It should be noted that inflection point detection technology, as a key technology in data analysis and signal processing, is mainly used to identify points in time series data where trends or patterns undergo significant changes. Mathematically, an inflection point is usually defined as the zero of the first derivative of a function or the extreme point of its second derivative, meaning that at these points, the rate of change of the data undergoes a crucial turning point. In practical applications, such as temperature monitoring in this embodiment, inflection point detection can accurately capture the moment when the temperature begins to rise or fall, which is crucial for analyzing equipment efficiency, predicting energy demand, and optimizing control strategies.

[0039] Optionally, clustering is performed on the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain clustering results. This includes: grouping the historical heating parameters according to the indoor temperature and the outdoor temperature to obtain multiple groups of first heating parameters, wherein the multiple groups of first heating parameters correspond to the same parameter category as the historical heating parameters, and the indoor temperature and the outdoor temperature corresponding to the multiple first sub-heating parameters included in each group of first heating parameters are all the same; for the multiple first sub-heating parameters of each group of first heating parameters, discrete points in the multiple first sub-heating parameters are removed according to the target water temperature and the second cooling rate to obtain multiple filtered first sub-heating parameters, wherein the second cooling rate corresponding to the discrete point is greater than a first preset threshold or less than a second preset threshold, and the first preset threshold and the second preset threshold are determined by the multiple first sub-heating parameters; and the multiple filtered first sub-heating parameters are determined as the clustering results.

[0040] In this embodiment, the historical heating parameters are first divided into multiple groups of primary heating parameters based on the similarity between indoor and outdoor temperatures, through data grouping. Figure 3 This is a coordinate graph showing the distribution of one set of primary heating parameters from multiple sets, corresponding to an indoor temperature of 19°C and an outdoor temperature of 1°C. The horizontal axis represents the cooling rate, and the vertical axis represents the target water temperature. Subsequently, discrete points are eliminated by setting a "first preset threshold" and a "second preset threshold" for the cooling rate. This allows the system to identify and remove outliers that deviate from the normal range. Finally, the filtered primary heating parameters are grouped into cluster results. Figure 4 for Figure 3 The distribution coordinates of the first set of heating parameters after clustering.

[0041] It should be noted that the first and second preset thresholds mentioned above are dynamically determined based on the distribution of cooling rate in historical data. By analyzing the relationship between target water temperature and cooling rate in multiple first sub-heating parameters, data points that significantly deviate from the normal trend of group changes are identified, and thresholds are set based on these. The maximum standard value is the first preset threshold, and the minimum standard value is the second preset threshold.

[0042] Optionally, selecting target heating parameters from the clustering results includes: grouping the clustering results according to the target water temperature to obtain multiple groups of second heating parameters, wherein the multiple groups of second heating parameters have the same parameter category as the clustering results, and the multiple second sub-heating parameters included in each group of second heating parameters correspond to the same target water temperature; for the multiple second sub-heating parameters of each group of second heating parameters, filtering the multiple second sub-heating parameters according to the second cooling rate to obtain multiple filtered second sub-heating parameters, wherein the second cooling rate corresponding to the multiple filtered second sub-heating parameters is greater than a third preset threshold, the third preset threshold being determined by the multiple second sub-heating parameters; and determining the multiple filtered second sub-heating parameters as the target heating parameters.

[0043] The purpose of this embodiment is to determine the minimum target water temperature that can maintain the user's selected indoor temperature. Since the target water temperature range is large (30-80°C), but the indoor temperature range is small (0-30°C), the indoor temperature may only increase by 1 degree Celsius for every several degrees the target water temperature rises, which is also the case in nature. Therefore, choosing the lowest target water temperature to maintain the user's selected indoor temperature can achieve energy saving. In this embodiment, firstly, based on the key indicator of the target water temperature, the clustering results generated in the previous step are regrouped to obtain multiple groups of second heating parameters, where the target water temperature is the same for each group of second heating parameters. Subsequently, a secondary screening mechanism based on the second cooling rate is introduced. This involves setting a third preset threshold to filter out the largest portion of the cooling rate within each target water temperature, for example, a maximum cooling rate of 20%, which is equivalent to selecting the rightmost 20% of the data in each target temperature row. This step is crucial for energy saving. Finally, the data after secondary grouping and secondary screening are determined as the target heating parameters, providing high-quality input for subsequent prediction model training.

[0044] Optionally, before performing linear regression data analysis based on the plurality of target heating parameters and generating a first common relationship model based on the analysis results, the method further includes: if the target second cooling rate corresponding to the target third time period in the plurality of third time periods is not obtained, determining the third cooling rate corresponding to the first heating device in the fourth time period as the target second cooling rate, thereby obtaining the plurality of second cooling rates, wherein the fourth time period is an adjacent time period of the target third time period; if the third cooling rate is not obtained, determining the plurality of fourth cooling rates corresponding to the second target region as the plurality of second cooling rates, wherein the second target region includes the first target region; if the plurality of fourth cooling rates are not obtained, determining the plurality of fifth cooling rates corresponding to the third target region as the plurality of second cooling rates, wherein the third target region includes the second target region.

[0045] In this embodiment, firstly, when the system fails to obtain the target second cooling rate data within a specific third time period, the third cooling rate recorded by the first heating device in the adjacent fourth time period is used as a substitute to fill the target third time period. This operation follows the principle of time series smoothing, utilizing the temporal correlation of device operating data and filling gaps through data interpolation or data extrapolation techniques to ensure data continuity. If the required third cooling rate cannot be provided even in the fourth time period, the system collects all available fourth cooling rate data from the second target region, including the first target region, to form a comprehensive dataset. The most relevant data is then selected as the target second cooling rate, where the second target region can be a corresponding city. If the second target region also fails to meet the data requirements, the scope is expanded to a third target region, which is a broader area encompassing the second target region, potentially the entire country. In this case, the system uses the fifth cooling rate data nationwide as a basis and, through benchmark data mapping technology, selects the data point closest to the device operating characteristics within the first target region as the target second cooling rate. This strategy not only overcomes geographical limitations but also demonstrates the ability to find common patterns in large-scale datasets, providing a wider range of reference points for prediction models and improving their generalization ability and prediction accuracy.

[0046] Optionally, after performing linear regression data analysis based on the multiple target heating parameters and generating a first common relationship model based on the analysis results, the method further includes: obtaining multiple sets of sixth cooling rates corresponding to the multiple target heating parameters, and multiple outdoor temperatures corresponding to the multiple target heating parameters, wherein the multiple target heating parameters correspond one-to-one with the multiple sets of sixth cooling rates, and each set of sixth cooling rates includes the multiple second cooling rates corresponding to the first heating device; given the multiple sets of sixth cooling rates and the multiple outdoor temperatures, performing linear regression analysis on the multiple sets of sixth cooling rates and the multiple outdoor temperatures with the multiple sets of sixth cooling rates as targets and the multiple outdoor temperatures as feature parameters to obtain a second common relationship model, wherein the second... A public relations model is used to indicate the relationship between the cooling rate and the outdoor temperature in the first target area. If the multiple sets of sixth cooling rates or the multiple outdoor temperatures are not obtained, the third public relations model corresponding to the second target area is determined as the second public relations model, wherein the second target area includes the first target area, and the third public relations model is used to indicate the relationship between the cooling rate and the outdoor temperature in the second target area. If the third public relations model is not obtained, the fourth public relations model corresponding to the third target area is determined as the second public relations model, wherein the third target area includes the second target area, and the fourth public relations model is used to indicate the relationship between the cooling rate and the outdoor temperature in the third target area.

[0047] This embodiment illustrates how to further analyze the relationship between cooling rate and outdoor temperature to enhance the environmental adaptability and prediction accuracy of the prediction model. First, the sixth cooling rate and corresponding outdoor temperature corresponding to the target heating parameter are collected. This process provides the foundational data for constructing the second public relationship model. Data alignment and feature selection ensure the accuracy and effectiveness of the analysis of the relationship between cooling rate and outdoor temperature. Subsequently, through linear regression analysis, using the collected multiple sets of sixth cooling rates and multiple outdoor temperature data, the second public relationship model is constructed. This formula reveals the linear relationship between the equipment cooling rate and outdoor temperature within the first target area. Furthermore, when multiple sets of sixth cooling rates or multiple outdoor temperatures within the first target area are unavailable, a third public relationship model for the second target area (which could be the corresponding city) is used as a substitute. When a third public relationship model for the second target area is unavailable, a fourth public relationship model for the third target area (which could be the entire country) is used as a substitute. This embodiment further improves the model's generalization ability and prediction accuracy.

[0048] Optionally, determining the minimum target water temperature of the second heating device in the first target area within the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area within the first time period, and the first public relationship model includes: determining a fifth public relationship model based on the second public relationship model and the first public relationship model; and predicting the target water temperature of the second heating device within the first time period based on the target indoor temperature, the outdoor temperature prediction data, and the fifth public relationship model.

[0049] In this embodiment, the construction of the fifth common relationship model is first mentioned. This model is based on a comprehensive analysis of the second common relationship model (reflecting the relationship between the cooling rate and the outdoor temperature) and the first common relationship model (used to predict the target water temperature). Specifically, the cooling rate in the second common relationship model can be represented by the outdoor temperature, and then substituted into the first common relationship model. The cooling rate in the first common relationship model is then replaced with an expression related to the outdoor temperature, resulting in a new fifth common relationship model. This formula is updated and calculated weekly. Next, the target indoor temperature, outdoor temperature prediction data, and the fifth common relationship model are used to predict the target water temperature, thus solving the problem in related technologies where heating boilers without temperature sensors cannot automatically adjust to a target water temperature that meets the user's room temperature requirements while achieving energy savings.

[0050] In another optional embodiment, this application provides a heating temperature prediction method based on linear regression, involving data processing flows for users with and without temperature sensors, such as... Figure 5 As shown, it includes:

[0051] I. User flow with temperature sensor:

[0052] 1. Raw data collection: Collect data including current indoor temperature, current water temperature of the mac, and outdoor temperature.

[0053] 2. Cooling rate calculation: Determine the start and end points of temperature reduction from the second-level reported data of the equipment, and calculate the cooling rate (hourly dimension).

[0054] 3. Data cleaning and feature extraction: Clean the raw reported data and extract effective feature parameters, including indoor temperature, outdoor temperature, cooling rate, etc.

[0055] 4. Cluster analysis: Cluster the indoor temperature, outdoor temperature and target water temperature in the historical data, screen out the densest sample points, and further select the largest 20% cooling rate in the target water temperature to achieve energy saving effect.

[0056] 5. Linear regression modeling: Based on the cleaned data and cluster analysis results, multinomial linear regression is performed to obtain a common prediction formula for the target water temperature.

[0057] II. User flow without temperature sensor:

[0058] 1. Data Collection: Collect current water temperature and outdoor temperature data from the Mac of users without temperature sensors.

[0059] 2. Cooling rate calculation: For users without a temperature sensor, the cooling rate is calculated based on the current water temperature. If the cooling rate is not available, the average cooling rate of the city or the country is used to approximate the cooling rate.

[0060] 3. Modeling the relationship between cooling rate and outdoor temperature: For each user without a temperature sensor, a linear regression is performed based on their daily cooling rate and outdoor temperature to obtain the formula for the relationship between cooling rate and outdoor temperature. If no formula is obtained, the average formula for the corresponding city or the whole country is used instead.

[0061] 4. Prediction Result Generation: Substitute the outdoor temperature prediction data of users without temperature sensors into the formula relating cooling rate to outdoor temperature, and combine it with the common prediction formula for target water temperature obtained from users with temperature sensors to predict the target water temperature for a period of time in the future.

[0062] In the above embodiments, using the basic algorithm of linear regression maximizes overall computational efficiency and makes it easier to implement prediction functions for massive numbers of users. The system cleverly obtains effective basic data for temperature prediction by summarizing patterns from users with data and transferring them to users without data. It also cleverly finds the theoretical basis for energy saving by analyzing different temperature ranges, achieving energy saving while making predictions. Furthermore, it improves prediction accuracy by transforming uncontrollable factors into controllable ones through feature transformation.

[0063] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0064] This embodiment also provides a heating energy-saving device based on big data analysis, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0065] Figure 6 This is a structural block diagram of an optional heating energy-saving device based on big data analysis, according to an embodiment of this application. Figure 6 As shown, it includes:

[0066] The acquisition module 62 is used to acquire historical heating parameters corresponding to the first heating device in the first target area. The first heating device is equipped with a temperature sensor. The historical heating parameters include: indoor temperature, outdoor temperature, cooling rate, and target water temperature. The temperature sensor is used to collect at least the indoor temperature.

[0067] Processing module 64 is used to perform clustering processing on the cooling rate and the target water temperature to obtain clustering results, and to filter out target heating parameters from the clustering results;

[0068] Data analysis module 66 is used to perform multinomial linear regression on multiple target heating parameters corresponding to multiple first heating devices in the first target area to obtain a first common relationship model corresponding to multiple target heating parameters, wherein the first common relationship model is used to indicate the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature;

[0069] The determination module 68 is used to predict the target water temperature of the second heating device in the first target area during the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relationship model, wherein the second heating device is not equipped with the temperature sensor.

[0070] Through the above embodiments, firstly, historical heating parameters corresponding to multiple first heating devices in the first target area are obtained. Each first heating device is equipped with a temperature sensor. The historical heating parameters include: indoor temperature, outdoor temperature, cooling rate, and target water temperature. The temperature sensor is used at least to collect indoor temperature data. Then, the cooling rate and target water temperature are clustered based on the indoor and outdoor temperatures to obtain clustering results. Target heating parameters are then selected from the clustering results to obtain multiple maximum cooling rates used to maintain the target water temperature under the same indoor and outdoor temperature conditions. Next, linear regression data analysis is performed on these multiple target heating parameters to obtain a first common relationship model corresponding to the multiple target heating parameters. This first common relationship model indicates the correlation between indoor temperature, outdoor temperature, cooling rate, and target water temperature. Finally, the minimum target water temperature of a second heating device in the first target area within the first time period is determined based on the target indoor temperature, the predicted outdoor temperature data of the first target area within the first time period, and the first common relationship model. The second heating device is not equipped with the aforementioned temperature sensor. The above solution involves collecting and analyzing historical operating data from heating users equipped with temperature sensors, including indoor temperature, outdoor temperature, and cooling rate. A linear regression model is then used to establish the relationship between the target water temperature and these factors. This model is applied to heating users without temperature sensors. By combining the current indoor and outdoor temperature data reported by the users with a common formula, the target heating water temperature for a future period is predicted. This solves the problem in related technologies where heating boilers without temperature sensors cannot automatically adjust to a target water temperature that meets user room temperature requirements while achieving energy savings.

[0071] Optionally, the acquisition module 62 is further configured to determine the start and end points of the indoor temperature decrease from the indoor temperature data of the first heating device; calculate the first cooling rate corresponding to the second time period based on the first temperature and first timestamp corresponding to the start point, and the second temperature and second timestamp corresponding to the end point, wherein the first timestamp is the start timestamp of the second time period, and the second timestamp is the end timestamp of the second time period; and use a weighted average algorithm to convert multiple first cooling rates into multiple second cooling rates corresponding to multiple third time periods, wherein the multiple third time periods correspond one-to-one with the multiple second cooling rates, and the historical heating parameters include the multiple second cooling rates.

[0072] In this embodiment, firstly, an intelligent algorithm identifies the start and end times of the indoor temperature drop in the device with a temperature sensor (the aforementioned first heating device). This process utilizes "inflection point detection" technology, aiming to accurately capture key moments of temperature change from time-series data. Next, the cooling rate of the time period corresponding to the start and end times (the aforementioned second time period) is calculated using the formula: Cooling rate = (Starting temperature - Ending temperature) / ((Ending timestamp - Starting timestamp) / 1000 / 60), which represents the temperature drop per minute. Then, a weighted average algorithm is used to process the cooling rates of one or more second time periods within a specific time period (the aforementioned third time period), transforming them into an average value matching the specific time cycle. This not only smooths out data fluctuations but also enhances the "robustness" and "accuracy" of the prediction model by assigning different weights to the data from different second time periods. It should be noted that the aforementioned third time period can be based on real-world standard hours (0-23), for example, the 00-hour period is 00:00:00-00:59:59.

[0073] It should be noted that inflection point detection technology, as a key technology in data analysis and signal processing, is mainly used to identify points in time series data where trends or patterns undergo significant changes. Mathematically, an inflection point is usually defined as the zero of the first derivative of a function or the extreme point of its second derivative, meaning that at these points, the rate of change of the data undergoes a crucial turning point. In practical applications, such as temperature monitoring in this embodiment, inflection point detection can accurately capture the moment when the temperature begins to rise or fall, which is crucial for analyzing equipment efficiency, predicting energy demand, and optimizing control strategies.

[0074] Optionally, the processing module 64 is further configured to group the historical heating parameters according to the indoor temperature and the outdoor temperature to obtain multiple groups of first heating parameters, wherein the multiple groups of first heating parameters correspond to the same parameter category as the historical heating parameters, and the indoor temperature and the outdoor temperature corresponding to the multiple first sub-heating parameters included in each group of first heating parameters are the same; for the multiple first sub-heating parameters of each group of first heating parameters, discrete points in the multiple first sub-heating parameters are removed according to the target water temperature and the second cooling rate to obtain multiple filtered first sub-heating parameters, wherein the second cooling rate corresponding to the discrete point is greater than a first preset threshold or less than a second preset threshold, the first preset threshold and the second preset threshold are determined by the multiple first sub-heating parameters; and the multiple filtered first sub-heating parameters are determined as clustering results.

[0075] In this embodiment, historical heating parameters are first grouped into multiple groups of primary heating parameters based on the similarity of indoor and outdoor temperatures. Then, discrete points are eliminated; by setting a "first preset threshold" and a "second preset threshold" for the cooling rate, the system can identify and remove outliers that deviate from the normal range. Finally, the selected primary heating parameters are used as the clustering result.

[0076] It should be noted that the first and second preset thresholds mentioned above are dynamically determined based on the distribution of cooling rate in historical data. By analyzing the relationship between target water temperature and cooling rate in multiple first sub-heating parameters, data points that significantly deviate from the normal trend of group changes are identified, and thresholds are set based on these. The maximum standard value is the first preset threshold, and the minimum standard value is the second preset threshold.

[0077] Optionally, the processing module 64 is further configured to group the clustering results according to the target water temperature to obtain multiple groups of second heating parameters, wherein the multiple groups of second heating parameters have the same parameter category as the clustering results, and the target water temperature of the multiple second sub-heating parameters included in each group of second heating parameters is the same; for the multiple second sub-heating parameters of each group of second heating parameters, the multiple second sub-heating parameters are filtered according to the second cooling rate to obtain multiple filtered second sub-heating parameters, wherein the second cooling rate corresponding to the multiple filtered second sub-heating parameters is greater than a third preset threshold, and the third preset threshold is determined by the multiple second sub-heating parameters; and the multiple filtered second sub-heating parameters are determined as the target heating parameters.

[0078] The purpose of this embodiment is to determine the minimum target water temperature that can maintain the user's selected indoor temperature. Since the target water temperature range is large (30-80°C), but the indoor temperature range is small (0-30°C), the indoor temperature may only increase by 1 degree Celsius for every several degrees the target water temperature rises, which is also the case in nature. Therefore, choosing the lowest target water temperature to maintain the user's selected indoor temperature can achieve energy saving. In this embodiment, firstly, based on the key indicator of the target water temperature, the clustering results generated in the previous step are regrouped to obtain multiple groups of second heating parameters, where the target water temperature is the same for each group of second heating parameters. Subsequently, a secondary screening mechanism based on the second cooling rate is introduced. This involves setting a third preset threshold to filter out the largest portion of the cooling rate within each target water temperature, for example, a maximum cooling rate of 20%, which is equivalent to selecting the rightmost 20% of the data in each target temperature row. This step is crucial for energy saving. Finally, the data after secondary grouping and secondary screening are determined as the target heating parameters, providing high-quality input for subsequent prediction model training.

[0079] Optionally, the data analysis module 66 is further configured to, when the target second cooling rate corresponding to the target third time period in the plurality of third time periods is not obtained, determine the third cooling rate corresponding to the first heating device in the fourth time period as the target second cooling rate, thereby obtaining the plurality of second cooling rates, wherein the fourth time period is an adjacent time period to the target third time period; when the third cooling rate is not obtained, determine the plurality of fourth cooling rates corresponding to the second target region as the plurality of second cooling rates, wherein the second target region includes the first target region; when the plurality of fourth cooling rates are not obtained, determine the plurality of fifth cooling rates corresponding to the third target region as the plurality of second cooling rates, wherein the third target region includes the second target region.

[0080] In this embodiment, firstly, when the system fails to obtain the target second cooling rate data within a specific third time period, the third cooling rate recorded by the first heating device in the adjacent fourth time period is used as a substitute to fill the target third time period. This operation follows the principle of time series smoothing, utilizing the temporal correlation of device operating data and filling gaps through data interpolation or data extrapolation techniques to ensure data continuity. If the required third cooling rate cannot be provided even in the fourth time period, the system collects all available fourth cooling rate data from the second target region, including the first target region, to form a comprehensive dataset. The most relevant data is then selected as the target second cooling rate, where the second target region can be a corresponding city. If the second target region also fails to meet the data requirements, the scope is expanded to a third target region, which is a broader area encompassing the second target region, potentially the entire country. In this case, the system uses the fifth cooling rate data nationwide as a basis and, through benchmark data mapping technology, selects the data point closest to the device operating characteristics within the first target region as the target second cooling rate. This strategy not only overcomes geographical limitations but also demonstrates the ability to find common patterns in large-scale datasets, providing a wider range of reference points for prediction models and improving their generalization ability and prediction accuracy.

[0081] Optionally, the data analysis module 66 is further configured to acquire multiple sets of sixth cooling rates corresponding to multiple target heating parameters, and multiple outdoor temperatures corresponding to multiple target heating parameters, wherein each of the multiple target heating parameters corresponds one-to-one with the multiple sets of sixth cooling rates, and each set of sixth cooling rates includes the multiple second cooling rates corresponding to the first heating device; upon acquiring the multiple sets of sixth cooling rates and the multiple outdoor temperatures, a linear regression analysis is performed on the multiple sets of sixth cooling rates and the multiple outdoor temperatures as feature parameters to obtain a second common relationship model, wherein the second common relationship model is used to indicate the first target area. The relationship between cooling rate and outdoor temperature; in the absence of the multiple sets of sixth cooling rates or the multiple outdoor temperatures, the third public relation model corresponding to the second target area is determined as the second public relation model, wherein the second target area includes the first target area, and the third public relation model is used to indicate the relationship between cooling rate and outdoor temperature in the second target area; in the absence of the third public relation model, the fourth public relation model corresponding to the third target area is determined as the second public relation model, wherein the third target area includes the second target area, and the fourth public relation model is used to indicate the relationship between cooling rate and outdoor temperature in the third target area.

[0082] This embodiment illustrates how to further analyze the relationship between cooling rate and outdoor temperature to enhance the environmental adaptability and prediction accuracy of the prediction model. First, the sixth cooling rate and corresponding outdoor temperature corresponding to the target heating parameter are collected. This process provides the foundational data for constructing the second public relationship model. Data alignment and feature selection ensure the accuracy and effectiveness of the analysis of the relationship between cooling rate and outdoor temperature. Subsequently, through linear regression analysis, using the collected multiple sets of sixth cooling rates and multiple outdoor temperature data, the second public relationship model is constructed. This formula reveals the linear relationship between the equipment cooling rate and outdoor temperature within the first target area. Furthermore, when multiple sets of sixth cooling rates or multiple outdoor temperatures within the first target area are unavailable, a third public relationship model for the second target area (which could be the corresponding city) is used as a substitute. When a third public relationship model for the second target area is unavailable, a fourth public relationship model for the third target area (which could be the entire country) is used as a substitute. This embodiment further improves the model's generalization ability and prediction accuracy.

[0083] Optionally, the aforementioned determining module 68 is further configured to determine a fifth public relations model based on the second public relations model and the first public relations model; and to predict the target water temperature of the second heating equipment within the first time period based on the target indoor temperature, the outdoor temperature prediction data, and the fifth public relations model.

[0084] In this embodiment, the construction of the fifth common relationship model is first mentioned. This model is based on a comprehensive analysis of the second common relationship model (reflecting the relationship between the cooling rate and the outdoor temperature) and the first common relationship model (used to predict the target water temperature). Specifically, the cooling rate in the second common relationship model can be represented by the outdoor temperature, and then substituted into the first common relationship model. The cooling rate in the first common relationship model is then replaced with an expression related to the outdoor temperature, resulting in a new fifth common relationship model. This formula is updated and calculated weekly. Next, the target indoor temperature, outdoor temperature prediction data, and the fifth common relationship model are used to predict the target water temperature, thus solving the problem in related technologies where heating boilers without temperature sensors cannot automatically adjust to a target water temperature that meets the user's room temperature requirements while achieving energy savings.

[0085] Embodiments of this application also provide a storage medium including a stored program, wherein the program executes any of the methods described above when it is run.

[0086] Optionally, in this embodiment, the storage medium may be configured to store program code for performing the following steps:

[0087] S1, Obtain historical heating parameters corresponding to multiple first heating devices within a target time period, wherein the historical heating parameters include: the indoor temperature corresponding to the first heating device, the outdoor temperature of the first target area, the cooling rate, the target water temperature of the first heating device, the time difference between the target time period and the current time is less than a first threshold, the first heating device is equipped with a temperature sensor, the multiple first heating devices are all located in the first target area, and the temperature sensor is used at least to collect the indoor temperature;

[0088] S2, cluster the cooling rate and the target water temperature according to the indoor temperature and the outdoor temperature to obtain clustering results, and filter out target heating parameters from the clustering results to obtain multiple target heating parameters. The target heating parameters are used to indicate at least the maximum cooling rate used to maintain the target water temperature under the same outdoor temperature and indoor temperature conditions. The multiple first heating devices correspond one-to-one with the multiple target heating parameters.

[0089] S3, perform linear regression data analysis based on the multiple target heating parameters, and generate a first common relationship model based on the analysis results, wherein the first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature;

[0090] S4, determine the minimum target water temperature of the second heating device in the first target area during the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relations model, wherein the second heating device is not equipped with the temperature sensor.

[0091] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0092] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium storing the computer program product, wherein the computer program, when executed by a processor, implements the steps of the methods described in various embodiments of this application.

[0093] Optionally, in this embodiment, the computer program described above can be configured to perform the following steps when executed by the processor:

[0094] S1, Obtain historical heating parameters corresponding to multiple first heating devices within a target time period, wherein the historical heating parameters include: the indoor temperature corresponding to the first heating device, the outdoor temperature of the first target area, the cooling rate, the target water temperature of the first heating device, the time difference between the target time period and the current time is less than a first threshold, the first heating device is equipped with a temperature sensor, the multiple first heating devices are all located in the first target area, and the temperature sensor is used at least to collect the indoor temperature;

[0095] S2, cluster the cooling rate and the target water temperature according to the indoor temperature and the outdoor temperature to obtain clustering results, and filter out target heating parameters from the clustering results to obtain multiple target heating parameters. The target heating parameters are used to indicate at least the maximum cooling rate used to maintain the target water temperature under the same outdoor temperature and indoor temperature conditions. The multiple first heating devices correspond one-to-one with the multiple target heating parameters.

[0096] S3, perform linear regression data analysis based on the multiple target heating parameters, and generate a first common relationship model based on the analysis results, wherein the first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature;

[0097] S4, determine the minimum target water temperature of the second heating device in the first target area during the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relations model, wherein the second heating device is not equipped with the temperature sensor.

[0098] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0099] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0100] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A heating energy-saving method based on big data analysis, characterized in that, include: The historical heating parameters corresponding to multiple first heating devices within a target time period are obtained. The historical heating parameters include: the indoor temperature corresponding to the first heating device, the outdoor temperature of the first target area, the cooling rate, the target water temperature of the first heating device, the time difference between the target time period and the current time being less than a first threshold, the first heating device being equipped with a temperature sensor, the multiple first heating devices being located in the first target area, and the temperature sensor being used at least to collect the indoor temperature. Clustering is performed on the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain clustering results. Target heating parameters are then selected from the clustering results to obtain multiple target heating parameters. The target heating parameters are used to indicate at least the maximum cooling rate used to maintain the target water temperature under the same outdoor and indoor temperatures. The multiple first heating devices correspond one-to-one with the multiple target heating parameters. Linear regression data analysis is performed based on the multiple target heating parameters, and a first common relationship model is generated based on the analysis results. The first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature. The minimum target water temperature of the second heating device in the first target area during the first time period is determined based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relations model, wherein the second heating device is not equipped with the temperature sensor.

2. The heating energy-saving method based on big data analysis according to claim 1, characterized in that, Before obtaining the historical heating parameters corresponding to multiple first heating devices within the target time period, the method further includes: determining the start point and end point of the indoor temperature decrease from the indoor temperature data of the first heating devices; The first cooling rate corresponding to the second time period is calculated based on the first temperature and first timestamp corresponding to the start point, and the second temperature and second timestamp corresponding to the end point, wherein the first timestamp is the start timestamp of the second time period, and the second timestamp is the end timestamp of the second time period; A weighted average algorithm is used to convert multiple first cooling rates into multiple second cooling rates corresponding to multiple third time periods, wherein the multiple third time periods correspond one-to-one with the multiple second cooling rates, and the historical heating parameters include the multiple second cooling rates.

3. The heating energy-saving method based on big data analysis according to claim 2, characterized in that, Clustering is performed on the cooling rate and the target water temperature based on the indoor temperature and the outdoor temperature to obtain clustering results, including: The historical heating parameters are grouped according to the indoor temperature and the outdoor temperature to obtain multiple groups of first heating parameters. The multiple groups of first heating parameters have the same parameter category as the historical heating parameters. The indoor temperature and the outdoor temperature of the multiple first sub-heating parameters included in each group of first heating parameters are the same. For each set of first heating parameters, multiple first sub-heating parameters are selected. Discrete points in the multiple first sub-heating parameters are eliminated according to the target water temperature and the second cooling rate to obtain multiple first sub-heating parameters after filtering. The second cooling rate corresponding to the discrete point is greater than a first preset threshold or less than a second preset threshold. The first preset threshold and the second preset threshold are determined by the multiple first sub-heating parameters. The selected first sub-heating parameters are determined as clustering results.

4. The heating energy-saving method based on big data analysis according to claim 3, characterized in that, Target heating parameters are selected from the clustering results, including: The clustering results are grouped according to the target water temperature to obtain multiple groups of second heating parameters. The multiple groups of second heating parameters have the same parameter category as the clustering results, and the multiple second sub-heating parameters contained in each group of second heating parameters have the same target water temperature. For each group of second heating parameters, multiple second sub-heating parameters are filtered according to the second cooling rate to obtain multiple filtered second sub-heating parameters. The second cooling rate corresponding to the multiple filtered second sub-heating parameters is greater than a third preset threshold, and the third preset threshold is determined by the multiple second sub-heating parameters. The selected second sub-heating parameters are determined as the target heating parameters.

5. The heating energy-saving method based on big data analysis according to claim 2, characterized in that, Before performing linear regression data analysis based on the multiple target heating parameters and generating a first public relations model based on the analysis results, the method further includes: If the target second cooling rate corresponding to the target third time period in the plurality of third time periods is not obtained, the third cooling rate corresponding to the first heating device in the fourth time period is determined as the target second cooling rate, and the plurality of second cooling rates are obtained, wherein the fourth time period is an adjacent time period of the target third time period. In the absence of the third cooling rate, the plurality of fourth cooling rates corresponding to the second target region are determined as the plurality of second cooling rates, wherein the second target region includes the first target region; In the absence of the plurality of fourth cooling rates, the plurality of fifth cooling rates corresponding to the third target region are determined as the plurality of second cooling rates, wherein the third target region includes the second target region.

6. The heating energy-saving method based on big data analysis according to claim 4, characterized in that, After performing linear regression data analysis based on the multiple target heating parameters and generating a first common relationship model based on the analysis results, the method further includes: Multiple sets of sixth cooling rates corresponding to multiple target heating parameters are obtained, as well as multiple outdoor temperatures corresponding to multiple target heating parameters. The multiple target heating parameters correspond one-to-one with the multiple sets of sixth cooling rates, and each set of sixth cooling rates includes the multiple second cooling rates corresponding to the first heating device. Given the multiple sets of sixth cooling rates and the multiple outdoor temperatures, a linear regression analysis is performed on the multiple sets of sixth cooling rates and the multiple outdoor temperatures as the target and the multiple outdoor temperatures as the feature parameters to obtain a second common relationship model. The second common relationship model is used to indicate the relationship between the cooling rate and the outdoor temperature in the first target area. In the absence of the multiple sets of sixth cooling rates or the multiple outdoor temperatures, the third public relation model corresponding to the second target area is determined as the second public relation model, wherein the second target area includes the first target area, and the third public relation model is used to indicate the relationship between the cooling rate and the outdoor temperature in the second target area. In the absence of the third public relations model, the fourth public relations model corresponding to the third target area is determined as the second public relations model, wherein the third target area includes the second target area, and the fourth public relations model is used to indicate the relationship between the cooling rate and the outdoor temperature in the third target area.

7. The heating energy-saving method based on big data analysis according to claim 6, characterized in that, Based on the target indoor temperature, the predicted outdoor temperature data of the first target area during the first time period, and the first public relations model, the minimum target water temperature of the second heating device in the first target area during the first time period is determined, including: A fifth public relations model is determined based on the second public relations model and the first public relations model; The minimum target water temperature of the second heating device during the first time period is determined based on the target indoor temperature, the predicted outdoor temperature data, and the fifth public relations model.

8. A heating energy-saving device based on big data analysis, characterized in that, include: The acquisition module is used to acquire historical heating parameters corresponding to multiple first heating devices within a target time period. The historical heating parameters include: the indoor temperature corresponding to the first heating device, the outdoor temperature of the first target area, the cooling rate, the target water temperature of the first heating device, the time difference between the target time period and the current time being less than a first threshold, the first heating device being equipped with a temperature sensor, the multiple first heating devices being located in the first target area, and the temperature sensor being used to collect the indoor temperature at least. The processing module is used to perform clustering processing on the cooling rate and the target water temperature according to the indoor temperature and the outdoor temperature to obtain clustering results, and to filter out target heating parameters from the clustering results to obtain multiple target heating parameters. The target heating parameters are used to indicate at least the maximum cooling rate for maintaining the target water temperature under the same outdoor temperature and indoor temperature conditions. The multiple first heating devices correspond one-to-one with the multiple target heating parameters. The data analysis module is used to perform linear regression data analysis based on the multiple target heating parameters, and generate a first common relationship model based on the analysis results. The first common relationship model is used to determine the correlation between the indoor temperature, the outdoor temperature, the cooling rate and the target water temperature. The determination module is used to determine the minimum target water temperature of the second heating device in the first target area during the first time period based on the target indoor temperature, the outdoor temperature prediction data of the first target area during the first time period, and the first public relationship model, wherein the second heating device is not equipped with the temperature sensor.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images