A bathing facility energy-saving control method and system based on big data analysis

Abstract

The application discloses a kind of based on big data analysis's bathing facility energy-saving control method and system, it is related to energy-saving control technical field, including first collection and store bath multi-dimensional data and temperature adjustment influence factor;Then build and iterate bath decision tree algorithm, traverse and obtain water temperature regulation method and automatically regulate water temperature after;Finally, according to temperature adjustment influence factor, judge whether iteration algorithm, decide whether to update water temperature regulation method.The application is by collecting multi-dimensional bath data, calculates impurity degree using decision tree algorithm in combination with temperature adjustment influence factor, selects the feature with strong certainty as parent node to divide data, accurately identifies preferred water temperature interval, dynamically triggers algorithm iteration according to user temperature adjustment frequency, maintains stability for zero time, resets refinement for multiple times, timely corrects strategy, reduces artificial temperature adjustment and energy consumption, improves energy-saving effect.

Description

Technical Field

[0001] This invention relates to the field of energy-saving control technology, specifically to an energy-saving control method and system for bathing facilities based on big data analysis. Background Technology

[0002] With the increasing global emphasis on carbon emission control and green development, reducing the energy consumption of bathing facilities is a necessary measure to implement energy conservation and emission reduction policies and fulfill social responsibility. Especially in high-frequency usage scenarios such as hotels, schools, and public bathhouses, long-term high energy consumption not only increases operating costs but also contradicts sustainable development goals. However, traditional bathing facilities rely on manual temperature adjustment based on human experience and lack real-time collection and intelligent analysis of multi-dimensional data such as traffic flow, time of day, and water temperature demand. This makes it impossible to accurately match the appropriate water temperature, forcing users to frequently adjust the temperature manually, thus increasing the energy consumption of bathing facilities. Summary of the Invention

[0003] Technical problems to be solved

[0004] To address the shortcomings of existing technologies, this invention provides an energy-saving control method and system for bathing facilities based on big data analysis. This solves the problem that traditional bathing facilities rely on manual experience for adjustment and lack real-time collection and intelligent analysis of multi-dimensional data such as traffic flow, time period, and water temperature requirements, resulting in water temperature that cannot accurately match user needs, requiring users to frequently adjust the temperature manually, thus increasing the facility's energy consumption.

[0005] Technical solution

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method and system for energy-saving control of bathing facilities based on big data analysis, comprising the following specific steps and modules: Step 1: collecting and storing multi-dimensional bathing data and temperature-regulating influencing factors; Step 2: constructing and iterating a bathing decision tree algorithm, and obtaining a water temperature regulation method after traversal, and automatically regulating the water temperature according to the water temperature regulation method; Step 3: judging whether the bathing decision tree algorithm should iterate based on the temperature-regulating influencing factors. If it is judged to be iterating, the algorithm is iterated and the water temperature regulation method is updated; if it is judged not to iterate, the water temperature regulation method is not updated.

[0007] Furthermore, the specific steps of constructing and iterating the bathing decision tree algorithm are as follows: S1: Perform a comprehensive calculation based on the Gini coefficient division criterion and the temperature regulation influencing factor, determine a certain feature data as the parent node, and automatically divide the child nodes belonging to the parent node. S2: According to Before further dividing to obtain child nodes, first determine Can it continue to be divided? S3: If it can continue to be divided, then further divide the other feature data according to the parent node to obtain child nodes. If it cannot continue to be divided, obtain leaf nodes. S4: Repeat S1 to S3 until it can no longer be divided, so that the algorithm is completed. Then iterate the updated bathing multidimensional data and temperature regulation influencing factors according to S1 to S3.

[0008] Furthermore, the specific method for obtaining the parent node is as follows: The multidimensional bathing data includes feature data, and the feature data includes sub-features. One type of feature data is the hot water temperature for each bath. Based on the Gini coefficient classification criterion and the temperature regulation influence factor, the various sub-features of the feature data are comprehensively calculated to obtain the sub-impurity degree of each type of sub-feature. The sub-impurity degree of each type of sub-feature is weighted and summed according to the number of each type of sub-feature to obtain the impurity degree. The impurity degree of each feature data is compared by bubble sort to obtain the feature data with the lowest impurity degree. The feature data with the lowest impurity degree is taken as the parent node.

[0009] Furthermore, the specific method for obtaining the sub-impurity degree of each type of sub-feature is as follows: ;in, Sub-impurity degree representing various sub-characteristics This represents the total probability. Indicates the types of sub-features in the feature data. This indicates the first random draw to the [number]th [item]. The probability of sub-features, This indicates the first random draw to the [number]th [item]. Sub-features are replaced, and a second random sample is drawn to the first sub-feature. The probability of sub-features, This represents the sum of probabilities that two random samplings of all category sub-features will result in the same category. This represents the probability of getting different categories from two random draws. This indicates the temperature regulation influencing factor.

[0010] Furthermore, the specific method for obtaining the impurity level is as follows: ;in, Indicates impurity level. Indicates the types of sub-features in the feature data. This indicates the number of features in each category. Sub-impurity degree representing various sub-characteristics.

[0011] Furthermore, the aforementioned according to Before further dividing to obtain child nodes, first determine The specific steps to determine whether further partitioning is possible are as follows: S1: Calculate the impurity level of each feature data; S2: Compare the impurity levels of each feature data using bubble sort to obtain the feature data with the lowest impurity level. S3: If Impurity level less than If the impurity level is low, further separation can be performed. Impurity degree greater than or equal to If the impurity level is too high, further classification is not possible.

[0012] Furthermore, the specific steps for determining whether to iterate the bathing decision tree algorithm based on the temperature adjustment influencing factor are as follows: S1: Detect and count the number of times the user adjusts the water temperature each time they bathe, and record it as the number of times the user is satisfied with the temperature; S2: If the number of times the user is satisfied with the temperature is zero, then the algorithm is not iterated locally; if the number of times the user is satisfied with the temperature is greater than zero, then the algorithm is iterated again until the child nodes are no longer divided.

[0013] Furthermore, the specific steps for iterating the algorithm again are as follows: S1: Sort the impurity level of each feature data by quicksort to obtain the feature data with the smallest impurity level, and use this feature data as the root node; S2: Continue to divide the root node as the parent node until it can no longer be divided, so that the algorithm iteration is completed.

[0014] Furthermore, the specific steps for sorting the impurity level of each feature data using quick sort are as follows: S1: Randomly select the impurity level of a feature data as the baseline feature data; S2: Arrange the feature data with an impurity level less than or equal to the baseline feature data to the left of the baseline feature data, and arrange the feature data with an impurity level greater than the baseline feature data to the right of the baseline feature data; S3: Repeat S1 to S2 until the sorting is complete.

[0015] Furthermore, the system includes a multi-dimensional data acquisition and storage module, a bathing strategy analysis and control module, and a user operation feedback correction module. The multi-dimensional data acquisition and storage module collects and stores multi-dimensional bathing data and temperature control influencing factors. The bathing strategy analysis and control module constructs and iterates a bathing decision tree algorithm, traverses it to obtain a water temperature control method, and automatically controls the water temperature according to this method. The user operation feedback correction module determines whether the bathing decision tree algorithm needs iteration based on the temperature control influencing factors. If iteration is indicated, the algorithm is iterated and the water temperature control method is updated; otherwise, the water temperature control method is not updated.

[0016] Beneficial effects

[0017] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0018] 1. By collecting multi-dimensional bathing data, the impurity of the feature data is calculated by combining the decision tree algorithm with the temperature adjustment influencing factor. The feature data with the strongest determinism is selected first as the parent node and the data is divided. The user's preferred water temperature range is accurately identified, reducing the energy waste caused by frequent manual temperature adjustment and reducing facility energy consumption from the source.

[0019] 2. The algorithm is dynamically triggered to iterate based on the number of times the user adjusts the temperature. If the number of temperature adjustments is zero, the algorithm remains stable. If the number of adjustments is greater than zero, the root node is reset and the division is refined through quick sorting. The water temperature control strategy is corrected in real time. This mechanism avoids the time-consuming process of iterating again based on historical data and can update the rules in a timely manner according to user needs, continuously improving the energy-saving effect.

[0020] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0021] Figure 1 This invention relates to a flowchart of an energy-saving control method for bathing facilities based on big data analysis.

[0022] Figure 2 This invention relates to a structural diagram of an energy-saving control system for bathing facilities based on big data analysis. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0025] like Figure 1 As shown, this embodiment of the invention provides an energy-saving control method for bathing facilities based on big data analysis, including the following specific steps:

[0026] Step 1: Collect multi-dimensional bathing data and the number of times users adjust the water temperature during each bath. This multi-dimensional bathing data includes the time period of each bath, the amount of hot water used, and the water temperature. These parameters constitute the feature data of the multi-dimensional bathing data, which includes various sub-features. The multi-dimensional bathing data is then cleaned to remove missing and redundant values, improving its quality. This data is then stored to obtain historical data, which is used to build the algorithm and iterate the algorithm after each update. The reason for using historical data instead of real-time data for algorithm iteration is to ensure data accuracy by collecting a large amount of multi-dimensional bathing data, thus preventing a decrease in algorithm accuracy.

[0027] Step 2: Based on historical data and the number of times users adjust the water temperature during each shower, construct and iterate a shower decision tree algorithm. The number of times users adjust the water temperature during each shower is recorded as the temperature adjustment influencing factor. The temperature adjustment influencing factor only affects the hot water temperature during each shower. By traversing the shower decision tree algorithm, a water temperature control method is obtained, and the water temperature is automatically controlled according to the water temperature control method.

[0028] The specific steps for constructing and iterating the bathing decision tree algorithm are as follows:

[0029] S1: Based on the Gini coefficient classification criterion and temperature regulation influencing factors, a comprehensive calculation is performed to determine a certain characteristic data as the parent node, and child nodes belonging to that parent node are automatically classified. The Gini coefficient is suitable for rapid partitioning of large amounts of data;

[0030] S2: According to Before further dividing to obtain child nodes, first determine Can we continue dividing it?

[0031] S3: If it can be further divided, it means that there are few impurities in the feature data. Based on the parent node, other feature data are further divided to obtain child nodes. If it cannot be further divided, leaf nodes are obtained. Among them, the child nodes that cannot be further divided are recorded as leaf nodes.

[0032] S4: Repeat S1 to S3 until no further division is possible, thus completing the algorithm construction. Then, iterate the updated historical data and temperature regulation influencing factors according to S1 to S3.

[0033] The specific method for obtaining the parent node is as follows:

[0034] Based on the Gini coefficient classification criterion and temperature regulation influence factor, the various sub-features of the feature data are standardized and comprehensively calculated to obtain the sub-impurity degree of each sub-feature. The sub-impurity degrees of each sub-feature are then weighted and summed according to the number of each type of sub-feature to obtain the impurity degree. Since the proportion of identical sub-features is high in feature data with low impurity degree and low in feature data with high impurity degree, the impurity degree of each feature data is compared by bubble sort to obtain the feature data with the lowest impurity degree. The feature data with the lowest impurity degree is taken as the parent node. This means that continuing to divide the child nodes through this parent node can reduce the invalid division of child nodes or the division of child nodes with small effect. The child nodes are other feature data, which improves the accuracy and efficiency of the division. This is because the feature data with the lowest impurity degree has the strongest determinism.

[0035] The specific methods for obtaining the sub-impurity degree of various sub-features are as follows:

[0036] ;

[0037] in, Sub-impurity degree representing various sub-characteristics This represents the total probability. Indicates the types of sub-features in the feature data. This indicates the first random draw to the [number]th [item]. The probability of sub-features, This indicates the first random draw to the [number]th [item]. Sub-features are replaced, and a second random sample is drawn to the first sub-feature. The probability of a sub-feature, since each sub-feature is mutually exclusive, This represents the sum of probabilities that two random samplings of all category sub-features will result in the same category. This represents the probability of getting different categories from two random draws. This indicates the number of times a user adjusts the water temperature during each shower; specifically, the number of times a user adjusts the water temperature until they are satisfied with it. This is recorded as the number of times the user is satisfied with the water temperature. When it is zero, that is, the number of times the user does not adjust the water temperature during each shower. When the value is greater than zero, the number of satisfactory temperature occurrences increases. Since the ultimate goal of increasing the number of satisfactory temperature occurrences is to adjust the water temperature to a suitable level, the temperature adjustment influencing factor only improves and optimizes the characteristic data of the hot water temperature for each bath, which is denoted as the satisfactory temperature. Regardless of whether the value is zero or not, it only affects the hot water temperature for each shower. Furthermore, the proportion of the satisfactory temperature in the hot water temperature of each shower is uncertain. Therefore, the algorithm needs to be completely re-iterated. However, the complete re-iteration of the algorithm is not real-time and requires a large amount of historical data to ensure the accuracy of the algorithm. Before that, the algorithm cannot be completely re-iterated. Instead, the impurity of the characteristic data of the hot water temperature for each shower can be forcibly reduced by adjusting the temperature influence factor. Then, assuming that the proportion of the satisfactory temperature increases, the algorithm is forcibly re-iterated to improve the accuracy of the algorithm in calculating the satisfactory temperature and reduce the number of times users frequently adjust the water temperature.

[0038] The specific method for obtaining impurity level is as follows:

[0039] ;

[0040] in, Indicates impurity level. Indicates the types of sub-features in the feature data. This indicates the number of features in each category. Sub-impurity degree representing various sub-characteristics.

[0041] according to Before further dividing to obtain child nodes, first determine The specific steps to determine whether further division is possible are as follows:

[0042] S1: Calculate the impurity level for each feature data, since it is based on... The sub-features in each feature data inherit from The characteristics of this necessitate recalculation.

[0043] S2: Use bubble sort to compare the impurity level of each feature data and obtain the feature data with the lowest impurity level. ;

[0044] S3: If Impurity level less than If the impurity level is low, further separation can be performed. Impurity degree greater than or equal to If the impurity level is too high, further sorting is not possible, because the purpose of sorting is to reduce the impurity level. Impurity degree greater than or equal to If the impurity level is too high, it means that the partitioning is ineffective.

[0045] Step 3: Determine whether the bathing decision tree algorithm should iterate based on the temperature control influencing factors. If it is determined to be iterative, then iterate the algorithm and update the water temperature control method. If it is determined not to iterate, then do not update the water temperature control method.

[0046] The specific steps for determining whether the bathing decision tree algorithm needs to iterate based on the temperature regulation influencing factor are as follows:

[0047] S1: Detect and count the number of times the user adjusts the water temperature during each shower, and record it as the number of times the user is satisfied with the temperature;

[0048] S2: If the number of satisfactory temperature readings is zero, the algorithm will not iterate. If the number of satisfactory temperature readings is greater than zero, it means that the impurity of the hot water temperature during each shower is reduced, and the algorithm will be iterated again until the child nodes are no longer divided. This not only saves the time of the algorithm to iterate again based on historical data and improves the flexibility of the algorithm, but also prevents users or subsequent users from frequently adjusting the temperature during showering before the algorithm iterates based on historical data, thus preventing frequent temperature adjustments from causing additional energy consumption and increasing the energy consumption of the facility.

[0049] The specific steps for iterating the algorithm again are as follows:

[0050] S1: Sort the impurity level of each feature data by quicksort, and obtain the feature data with the smallest impurity level. Use this feature data as the root node.

[0051] S2: Continue dividing the root node as the parent node until it can no longer be divided, thus completing the algorithm iteration.

[0052] like Figure 2 As shown, this embodiment of the invention provides an energy-saving control system for bathing facilities based on big data analysis, comprising the following specific modules:

[0053] Multidimensional data acquisition and storage module: used to collect and store multidimensional data on bathing and temperature control influencing factors;

[0054] Bathing strategy analysis and control module: used to construct and iterate the bathing decision tree algorithm, and after traversal, obtain the water temperature control method, and automatically control the water temperature according to the water temperature control method;

[0055] User operation feedback correction module: Used to determine whether the bathing decision tree algorithm should iterate based on the temperature control influencing factors. If it is determined to be iterating, the algorithm is iterated and the water temperature control method is updated. If it is determined not to iterate, the water temperature control method is not updated.

[0056] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A big data analysis based energy saving control method for bathing facilities, characterized in that: The method comprises the following specific steps: Step 1: collecting and storing bathing multi-dimensional data and temperature adjusting influencing factors; Step 2: constructing and iterating a bathing decision tree algorithm, and obtaining a water temperature regulation method after traversal, and automatically regulating the water temperature according to the water temperature regulation method; Step 3: judging whether the bathing decision tree algorithm is iterated according to the temperature adjusting influencing factors, if yes, iterating and updating the water temperature regulation method, and if no, not updating the water temperature regulation method; The specific steps of constructing and iterating the bathing decision tree algorithm are as follows: S1: According to the Gini coefficient division criterion and the temperature influence factor, a certain characteristic data is determined as a parent node, and the child nodes belonging to the parent node are automatically divided ; S2: According to Further division of the sub-nodes before the first judgment Can continue to divide; S3: if the division can continue, further dividing the parent node according to other feature data to obtain a child node, and if the division cannot continue, obtaining a leaf node; S4: repeatedly executing S1 to S3 until no further division is possible, so that the algorithm is constructed, and the updated bathing multi-dimensional data and temperature adjusting influencing factors are iterated according to S1 to S3; The specific acquisition method of the parent node is as follows: The bathing multi-dimensional data comprises feature data, the feature data comprises sub-features, and one of the feature data is hot water temperature of each bathing, the Gini coefficient division criterion and the temperature adjusting influencing factors are used for comprehensively calculating the sub-impurity degrees of various sub-features of the feature data, the sub-impurity degrees of various sub-features are weighted and summed according to the number of each type of sub-feature to obtain an impurity degree, and the impurity degrees of each feature data are compared through bubble sorting to obtain the feature data with the lowest impurity degree, and the feature data with the lowest impurity degree is taken as the parent node; The specific acquisition method of the sub-impurity degrees of various sub-features is as follows: ； wherein, denotes the sub-impurity degree of each type of sub-feature, denotes the total probability, denotes the type of sub-feature in the feature data, denotes the probability of randomly drawing the first time to the first type of sub-feature, denotes the probability of randomly drawing the second time to the first type of sub-feature after putting back after the first time, denotes the probability of randomly drawing the second time to the first type of sub-feature after putting back after the first time, denotes the probability of randomly drawing twice to different types of sub-features, denotes the temperature adjustment impact factor, denotes the number of times the user adjusts the water temperature each time.

2. The energy saving control method for bathing facilities based on big data analysis according to claim 1, characterized in that: The specific acquisition method of the impurity degree is as follows: ; wherein, represents the impurity degree, represents the sub-feature class in the feature data, represents the number of each class of sub-feature, represents the sub-impurity degree of each class of sub-feature.

3. The energy saving control method for bathing facilities based on big data analysis according to claim 1, characterized in that: The according to Before further dividing to obtain a child node, it is judged The specific steps of whether to continue dividing are: S1: calculating the impurity degree of each feature data; S2: comparing the impurity degrees of each feature data by bubble sorting to obtain the feature data with the lowest impurity degree ; S3: If the impurity degree is less than , the division can be continued, if the impurity degree is greater than or equal to , the division cannot be continued. the impurity degree is less than , the division can be continued, if the impurity degree is greater than or equal to , the division cannot be continued.

4. The energy saving control method for bathing facilities based on big data analysis according to claim 1, characterized in that: The specific steps of judging whether the bathing decision tree algorithm is iterated according to the temperature adjusting influencing factors are as follows: S1: detecting and counting the number of times of adjusting the water temperature of the user during each bathing, and recording as the number of satisfied temperature times; S2: if the number of satisfied temperature times is equal to zero, the algorithm is not iterated locally, and if the number of satisfied temperature times is greater than zero, the algorithm is iterated again in whole until the child node cannot be divided.

5. The big data analysis based energy saving control method for bathing facilities according to claim 4, characterized in that: The specific steps of iterating the algorithm again in whole are as follows: S1: sorting the impurity degrees of each feature data through quick sorting to obtain the feature data with the smallest impurity degree, and taking the feature data as a root node; S2: continuously dividing the root node as the parent node until no further division is possible, so that the iteration of the algorithm is completed.

6. The energy saving control method for bathing facilities based on big data analysis according to claim 5, characterized in that: The specific steps of sorting the impurity degrees of each feature data through quick sorting are as follows: S1: randomly selecting the impurity degree of a certain feature data as a reference feature data; S2: arranging the feature data with an impurity degree less than or equal to the reference feature data to the left of the reference feature data, and arranging the feature data with an impurity degree greater than the reference feature data to the right of the reference feature data; S3: repeatedly executing S1 to S2 until the arrangement is completed.

7. A bathing facility energy saving control system based on big data analysis, used to implement the bathing facility energy saving control method based on big data analysis in any one of claims 1-6, characterized in that, The system comprises a multi-dimensional data acquisition and storage module, a bathing strategy analysis and regulation module, and a user operation feedback correction module; The multi-dimensional data acquisition and storage module is used for collecting and storing bathing multi-dimensional data and temperature adjusting influencing factors; The bathing strategy analysis and regulation module is used for constructing and iterating a bathing decision tree algorithm, and obtaining a water temperature regulation method after traversal, and automatically regulating the water temperature according to the water temperature regulation method. The user operation feedback correction module is used for judging whether the bathing decision tree algorithm is iterated according to the temperature regulation influence factor, if the iteration is judged, the algorithm is iterated and the water temperature regulation method is updated, if the iteration is not judged, the water temperature regulation method is not updated.

Images