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

Abstract

The invention discloses a bathing facility energy-saving control method and system based on big data analysis, and relates to the technical field of energy-saving control, and the method comprises the steps: firstly collecting and storing bathing multi-dimensional data and temperature adjustment influence factors; constructing and iterating a bathing decision tree algorithm, traversing to obtain a water temperature regulation and control method, and automatically regulating and controlling the water temperature; and finally, judging whether an iterative algorithm is adopted or not according to the temperature regulation influence factors, and determining whether to update the water temperature regulation method or not. According to the method, multi-dimensional bathing data are collected, a decision tree algorithm is utilized to calculate the impurity degree in combination with temperature adjustment influence factors, features with high certainty are selected as father nodes to divide data, a preferred water temperature interval is accurately recognized, algorithm iteration is dynamically triggered according to the user temperature adjustment frequency, stability is maintained for zero times, refinement is reset for multiple times, and a strategy is corrected in time. Manual temperature adjustment and energy consumption are reduced, and the energy-saving effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving control technology, and specifically to a bathing facility energy-saving control method and system based on big data analysis. Background Art

[0002] With the world's increasing emphasis on carbon emission control and green development, reducing the energy consumption of bathing facilities is a necessary measure to implement energy-saving and emission reduction policies and fulfill social responsibilities. This is especially true in high-frequency usage scenarios such as hotels, schools, and public bathrooms. Long-term high energy consumption not only increases operating costs but also runs counter to sustainable development goals. However, traditional bathing facilities rely on manual temperature adjustment based on human experience. They lack real-time collection and intelligent analysis of multi-dimensional data such as traffic flow, time periods, and water temperature requirements, making it impossible to accurately match the appropriate water temperature. As a result, users have to frequently manually adjust the temperature and heat the water, increasing the energy consumption of bathing facilities. Summary of the Invention

[0003] Technical problems solved

[0004] In response to the shortcomings of the existing technology, the present invention provides an energy-saving control method and system for bathing facilities based on big data analysis, which solves the problem that traditional bathing facilities rely on manual experience 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 the water temperature being unable to accurately match the requirements. Users need to frequently adjust the temperature manually, thereby increasing the energy consumption of the facilities.

[0005] Technical Solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a bathing facility energy-saving control method and system based on big data analysis, including the following specific steps and modules: Step 1: Collect and store multi-dimensional bathing data and temperature control influencing factors; Step 2: Construct and iterate a bathing decision tree algorithm, and after traversal, obtain a water temperature control method, and automatically control the water temperature according to the water temperature control method; Step 3: Judge whether the bathing decision tree algorithm is iterated based on the temperature control influencing factor. If it is judged to be iterative, the algorithm is iterated and the water temperature control method is updated. If it is judged not to be iterative, the water temperature control method is not updated.

[0007] Furthermore, the specific steps of constructing and iterating the bathing decision tree algorithm are as follows: S1: performing comprehensive calculations based on the Gini coefficient division criterion and the temperature adjustment influencing factor, and determining a certain feature data as the parent node, and automatically dividing the child nodes belonging to the parent node ; S2: According to Before further dividing to obtain child nodes, first determine Can the division continue? S3: If the division can continue, the other feature data are further divided according to the parent node to obtain child nodes. If the division cannot continue, a leaf node is obtained. S4: Repeat S1 to S3 until no further division is possible, so that the algorithm is constructed, and the updated bathing multidimensional data and temperature control influencing factors are iterated according to S1 to S3.

[0008] Furthermore, the specific method of obtaining the parent node is as follows: the multidimensional bathing data includes feature data, the feature data includes sub-features, one of which is the hot water temperature of each bath. According to the Gini coefficient division criterion and the temperature adjustment influencing factor, various sub-features of the feature data are comprehensively calculated to obtain the sub-impurity of each sub-feature. The sub-impurity of each sub-feature is weighted and summed according to the number of each sub-feature to obtain the impurity. The impurity of each feature data is compared by bubble sort to obtain the feature data with the lowest impurity, and the feature data with the lowest impurity is used as the parent node.

[0009] Furthermore, the specific method for obtaining the sub-impurity of each sub-feature is as follows: ;in, Represents the sub-impurity of each sub-feature, represents the total probability, Indicates the sub-feature type in the feature data, Indicates the first random draw to The probability of the class sub-feature, Indicates the first random draw to After the sub-features are replaced, the second random sampling is The probability of the class sub-feature, It represents the sum of the probabilities of randomly extracting the same category twice from all category sub-features, so It represents the probability of getting different categories by randomly drawing twice, Indicates the temperature control influencing factor.

[0010] Furthermore, the specific method of obtaining the impurity degree is as follows: ;in, Indicates the impurity level, Indicates the sub-feature type in the feature data, represents the number of sub-features of each category, Indicates the sub-impurity of each sub-feature.

[0011] Furthermore, the basis Before further dividing to obtain child nodes, first determine The specific steps for whether to continue dividing are: S1: calculate the impurity of each feature data; S2: compare the impurity of each feature data through bubble sorting to obtain the feature data with the lowest impurity ; S3: If The impurity level is less than The impurity level can be further divided. The impurity level is greater than or equal to If the impurity level is higher than , the classification cannot be continued.

[0012] Furthermore, the specific steps of judging whether the bathing decision tree algorithm should be iterated based on the temperature adjustment influencing factor are as follows: S1: detecting and counting the number of times the user adjusts the water temperature during each bath, and recording it as the number of satisfactory temperatures; S2: if the number of satisfactory temperatures is equal to zero, the algorithm is not iterated locally; if the number of satisfactory temperatures is greater than zero, the algorithm is iterated all over again until the child nodes are no longer divided.

[0013] Furthermore, the specific steps of re-iterating the algorithm are as follows: S1: sorting the impurity of each feature data by quick sorting to obtain the feature data with the smallest impurity, and using this feature data as the root node; S2: continuing to divide the root node as the parent node until it cannot be divided anymore, thus completing the algorithm iteration.

[0014] Furthermore, the specific steps of sorting the impurity of each feature data by quick sorting are: S1: randomly selecting the impurity of a certain feature data as the baseline feature data; S2: arranging the feature data whose impurity is less than or equal to the basic feature data to the left of the baseline feature data, and arranging the feature data whose impurity is greater than the basic feature data to the right of the baseline feature data; S3: repeating S1 to S2 until the arrangement is completed.

[0015] Furthermore, a multidimensional data acquisition and storage module, a bathing strategy analysis and control module, and a user operation feedback correction module; the multidimensional data acquisition and storage module is used to acquire and store multidimensional bathing data and temperature control influencing factors; the bathing strategy analysis and control module is used to construct and iterate a bathing decision tree algorithm, obtain a water temperature control method after traversal, and automatically control the water temperature according to the water temperature control method; the user operation feedback correction module is used to judge whether the bathing decision tree algorithm is iterated according to the temperature control influencing factors. If it is judged to be iterative, the algorithm is iterated and the water temperature control method is updated. If it is judged not to be iterative, 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 comprehensively calculated using the decision tree algorithm and the temperature adjustment influencing factors. The feature data with the strongest certainty is preferentially selected as the parent node and the data is divided. The user's preferred water temperature range is accurately identified, the energy waste caused by frequent manual temperature adjustment is reduced, and the energy consumption of the facility is reduced from the source.

[0019] 2. Dynamically trigger algorithm iteration based on the number of temperature adjustments by the user. If the number of temperature adjustments is zero, the algorithm remains stable. If the number is greater than zero, the root node is reset through quick sorting and the division is refined, and the water temperature control strategy is corrected in real time. This mechanism not only avoids the time-consuming re-iteration based on historical data, but also updates the rules in a timely manner according to user needs, continuously improving energy saving effects.

[0020] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This invention: a flow chart of a bathing facility energy-saving control method based on big data analysis.

[0022] Figure 2 This is the present invention: a structural diagram of an energy-saving control system for bathing facilities based on big data analysis. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts 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 only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0025] like Figure 1 As shown, the embodiment of the present invention provides a bathing facility energy-saving control method based on big data analysis, which includes the following specific steps:

[0026] Step 1: Collect bathing multidimensional data and the number of times the user adjusts the water temperature during each bath. Bathing multidimensional data includes the time period of each bath, the amount of hot water used for each bath, and the hot water temperature of each bath. The time period of each bath, the amount of hot water used for each bath, and the hot water temperature of each bath are all feature data of bathing multidimensional data. Feature data includes various sub-features. Data cleaning is performed on the bathing multidimensional data to remove missing values and redundant values, improve the data quality of the bathing multidimensional data, store the bathing multidimensional data, and obtain historical data, so as to facilitate the construction of the algorithm through historical data and iterate the algorithm after each update of the historical data. The reason for iterating the algorithm through historical data instead of real-time data is because it takes time to collect a large amount of bathing multidimensional data to ensure the accuracy of the data, thereby avoiding a decrease in the accuracy of the algorithm.

[0027] Step 2: Construct and iterate a bathing decision tree algorithm based on historical data and the number of times the user adjusts the water temperature during each bath. The number of times the user adjusts the water temperature during each bath is recorded as the temperature adjustment influence factor. The temperature adjustment influence factor only affects the hot water temperature of each bath. Traverse the bathing decision tree algorithm to obtain a water temperature control method, and automatically adjust the water temperature according to the water temperature control method.

[0028] The specific steps to construct and iterate the bathing decision tree algorithm are:

[0029] S1: Perform comprehensive calculation based on the Gini coefficient division criteria and the temperature control influencing factor, determine a certain feature data as the parent node, and automatically divide the child nodes belonging to the parent node , the Gini coefficient is suitable for the rapid division of large amounts of data;

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

[0031] S3: If further division is possible, it means that there is little impurity in the feature data. Based on the parent node, the other feature data are further divided to obtain child nodes. If further division is not possible, leaf nodes are obtained, and the child nodes that cannot be divided further are recorded as leaf nodes.

[0032] S4: Repeat S1 to S3 until no further division is possible, so that the algorithm is constructed, and the updated historical data and temperature control influence factors are iterated according to S1 to S3.

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

[0034] According to the Gini coefficient division criterion and the temperature adjustment influencing factor, various sub-features of the feature data are standardized and comprehensively calculated to obtain the sub-impurity of each sub-feature. The sub-impurity of each sub-feature is weighted and summed according to the number of sub-features in each category to obtain the impurity. Since the number of identical sub-features in feature data with low impurity is high, and the number of identical sub-features in feature data with high impurity is low, the impurity of each feature data is compared through bubble sorting to obtain the feature data with the lowest impurity. The feature data with the lowest impurity is used as the parent node, which means that continuing to divide the child nodes through this parent node can reduce invalid divisions of the child nodes or divisions with small sub-node division effects. 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 has the strongest certainty.

[0035] The specific method for obtaining the sub-impurity of each sub-feature is as follows:

[0036] ;

[0037] in, Represents the sub-impurity of each sub-feature, represents the total probability, Indicates the sub-feature type in the feature data, Indicates the first random draw to The probability of the class sub-feature, Indicates the first random draw to After the sub-features are replaced, the second random sampling is The probability of each sub-feature is mutually exclusive. It represents the sum of the probabilities of randomly extracting the same category twice from all category sub-features, so It represents the probability of getting different categories by randomly drawing twice, The number of times the user adjusts the water temperature each time he takes a bath, that is, the number of times the user adjusts the water temperature until he is satisfied with the existing water temperature each time he takes a bath, is recorded as the number of times the user adjusts the water temperature until he is satisfied with the temperature. When it is zero, it means the number of times the user did not adjust the water temperature during each bath. When it is greater than zero, the number of satisfactory temperatures increases. Since the ultimate goal of increasing the number of satisfactory temperatures is to adjust the appropriate water temperature, the temperature adjustment influencing factor only improves and optimizes the characteristic data of the hot water temperature of each bath, which is recorded as the satisfactory temperature, that is, Regardless of whether it is zero or not, it only affects the hot water temperature of each bath. In addition, the proportion of satisfactory temperature in the hot water temperature of each bath is uncertain, so the algorithm needs to be completely iterated. The complete re-iteration of the algorithm is not real-time, and a large amount of historical data is required to ensure the accuracy of the algorithm. Before this, the algorithm cannot be completely iterated again, and can only forcibly reduce the impurity of the characteristic data of the hot water temperature of each bath through the temperature adjustment influencing factor, and then assume that the proportion of satisfactory temperature increases, and force the algorithm to be completely iterated again, thereby improving the algorithm's calculation accuracy of the satisfactory temperature and reducing the number of times users frequently adjust the water temperature.

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

[0039] ;

[0040] in, Indicates the impurity level, Indicates the sub-feature type in the feature data, represents the number of sub-features of each category, Indicates the sub-impurity of each sub-feature.

[0041] according to Before further dividing to obtain child nodes, first determine The specific steps to continue the division are:

[0042] S1: Calculate the impurity of each feature data, based on Each sub-feature in the feature data inherits 's features, so they need to be recalculated;

[0043] S2: Compare the impurity of each feature data through bubble sorting to obtain the feature data with the lowest impurity ;

[0044] S3: If The impurity level is less than The impurity level can be further divided. The impurity level is greater than or equal to If the impurity level is too low, the division cannot be continued because the purpose of division is to reduce the impurity level. The impurity level is greater than or equal to If the impurity level is less than 0, the classification is ineffective.

[0045] Step 3: Determine whether the bathing decision tree algorithm is iterative based on the temperature control influencing factor. If it is iterative, iterate the algorithm and update the water temperature control method. If it is not iterative, the water temperature control method is not updated.

[0046] The specific steps for judging whether the bathing decision tree algorithm should be iterated based on the temperature adjustment influencing factor are as follows:

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

[0048] S2: If the number of satisfactory temperatures is equal to zero, the algorithm will not be iterated. If the number of satisfactory temperatures is greater than zero, it means that the impurity of the hot water temperature for each bath 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 all again based on historical data and improves the flexibility of the algorithm, but also allows users or subsequent users to avoid frequent manual temperature adjustment during bathing before the algorithm is iterated based on historical data, thereby preventing frequent temperature adjustment from causing additional energy consumption and increasing facility energy consumption.

[0049] The specific steps to iterate the algorithm again are:

[0050] S1: Sort the impurity of each feature data by quick sorting, and obtain the feature data with the smallest impurity, and use this feature data as the root node;

[0051] S2: Continue to divide the root node as the parent node until it cannot be divided anymore, completing the algorithm iteration.

[0052] like Figure 2 As shown, the embodiment of the present invention provides a bathing facility energy-saving control system based on big data analysis, which includes the following specific modules:

[0053] Multi-dimensional data acquisition and storage module: used to collect and store multi-dimensional bathing data and temperature control influencing factors;

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

[0055] User operation feedback correction module: used to judge whether the bathing decision tree algorithm is iterative based on the temperature control influencing factor. If it is iterative, the algorithm is iterated and the water temperature control method is updated. If it is not iterative, the water temperature control method is not updated.

[0056] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A bathing facility energy-saving control method based on big data analysis, characterized by: The specific steps include: Step 1: Collect and store multi-dimensional bathing data and temperature control influencing factors; Step 2: Construct and iterate a bathing decision tree algorithm, obtain a water temperature control method after traversal, and automatically control the water temperature according to the water temperature control method; Step 3: Determine whether the bathing decision tree algorithm is iterative based on the temperature control influencing factor. If it is iterative, iterate the algorithm and update the water temperature control method. If it is not iterative, the water temperature control method is not updated.

2. The method for energy-saving control of bathing facilities based on big data analysis according to claim 1, characterized in that: The specific steps of constructing and iterating the bathing decision tree algorithm are: S1: Perform comprehensive calculation based on the Gini coefficient division criteria and the temperature control 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 the division continue? S3: If further division is possible, the other feature data is further divided according to the parent node to obtain child nodes. If further division is not possible, a leaf node is obtained. S4: Repeat S1 to S3 until no further division is possible, so that the algorithm is constructed, and the updated bathing multi-dimensional data and temperature control influencing factors are iterated according to S1 to S3.

3. The method for energy-saving control of bathing facilities based on big data analysis according to claim 2, characterized in that: The specific method of obtaining the parent node is as follows: Bathing multidimensional data includes feature data, which includes sub-features. One of the feature data is the hot water temperature of each bath. Based on the Gini coefficient division criterion and the temperature adjustment influencing factor, various sub-features of the feature data are comprehensively calculated to obtain the sub-impurity of each sub-feature. The sub-impurity of each sub-feature is weighted and summed according to the number of each sub-feature to obtain the impurity. The impurity of each feature data is compared through bubble sort to obtain the feature data with the lowest impurity. The feature data with the lowest impurity is used as the parent node.

4. The method for energy-saving control of bathing facilities based on big data analysis according to claim 3, characterized in that: The specific method for obtaining the sub-impurity of each sub-feature is as follows: ； in, Represents the sub-impurity of each sub-feature, represents the total probability, Indicates the sub-feature type in the feature data, Indicates the first random draw to The probability of the class sub-feature, Indicates the first random draw to After the sub-features are replaced, the second random sampling is The probability of the class sub-feature, It represents the sum of the probabilities of randomly extracting the same category twice from all category sub-features, so It represents the probability of getting different categories by randomly drawing twice, Indicates the temperature control influencing factor.

5. The method for energy-saving control of bathing facilities based on big data analysis according to claim 3 is characterized in that: The specific method for obtaining the impurity degree is as follows: ; in, Indicates the impurity level, Indicates the sub-feature type in the feature data, represents the number of sub-features of each category, Indicates the sub-impurity of each sub-feature.

6. The method for energy-saving control of bathing facilities based on big data analysis according to claim 2, characterized in that: The basis Before further dividing to obtain child nodes, first determine The specific steps to continue the division are: S1: Calculate the impurity of each feature data; S2: Compare the impurity of each feature data through bubble sorting to obtain the feature data with the lowest impurity ; S3: If The impurity level is less than The impurity level can be further divided. The impurity level is greater than or equal to If the impurity level is higher than , the classification cannot be continued.

7. The method for energy-saving control of 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 should be iterated according to the temperature adjustment influencing factor are: S1: Detect and count the number of times the user adjusts the water temperature during each bath, and record it as the number of times the user adjusts the water temperature; S2: If the number of satisfied temperature is equal to zero, the algorithm will not be iterated locally. If the number of satisfied temperature is greater than zero, the algorithm will be iterated again until the child node is no longer divided.

8. The method for energy-saving control of bathing facilities based on big data analysis according to claim 7, characterized in that: The specific steps of re-iterating the algorithm are: S1: Sort the impurity of each feature data by quick sorting, and obtain the feature data with the smallest impurity, and use this feature data as the root node; S2: Continue to divide the root node as the parent node until it cannot be divided anymore, completing the algorithm iteration.

9. The method for energy-saving control of bathing facilities based on big data analysis according to claim 8, characterized in that: The specific steps of sorting the impurity of each feature data by quick sorting are: S1: Randomly select the impurity of a certain feature data as the benchmark feature data; S2: Arrange the feature data whose impurity is less than or equal to the basic feature data to the left of the reference feature data, and arrange the feature data whose impurity is greater than the basic feature data to the right of the reference feature data; S3: Repeat S1 to S2 until the arrangement is completed.

10. 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 according to any one of claims 1 to 9, characterized in that: 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 is used to acquire and store multi-dimensional bathing data and temperature control influencing factors; The bathing strategy analysis and control module is used to construct and iterate a bathing decision tree algorithm, obtain a water temperature control method after traversal, and automatically control the water temperature according to the water temperature control method; The user operation feedback correction module is used to judge whether the bathing decision tree algorithm is iterative according to the temperature control influencing factor. If it is iterative, the algorithm is iterated and the water temperature control method is updated. If it is not iterative, the water temperature control method is not updated.

Images