Student dormitory allocation method based on big data

Abstract

The present invention discloses a student dormitory allocation method based on big data, including data collection, data preprocessing, building dormitory allocation clusters, optimizing clusters and student dormitory allocation. The present invention relates to the field of dormitory management technology, and specifically refers to a student dormitory allocation method based on big data. The scheme improves the accuracy, robustness and overall performance of clustering by designing a refined neighboring point reference distance function, calculating enhanced point cluster inter-cluster connectivity, designing a clustering effect evaluation mechanism, creating noise clusters, and designing a dynamic update strategy for cluster centers; by introducing an adaptive search strategy, a mode switching mechanism, and a method combining multi-directional and adaptive search, the parameter search efficiency, flexibility and global optimization capability are improved, ensuring the reliability of the optimization result.

Description

Technical Field

[0001] The present invention relates to the technical field of dormitory management, and in particular to a student dormitory allocation method based on big data. Background Art

[0002] The student dormitory allocation method based on big data combines big data technology and artificial intelligence algorithms to deeply mine and process student data, obtain student groups with similar characteristics, and achieve efficient, accurate and humanized dormitory allocation, ensuring that every student can get a comfortable living and learning environment in the dormitory, providing better protection and support for students' campus life. However, the traditional dormitory allocation clustering method has problems with low accuracy, robustness and overall performance; the traditional cluster construction parameter optimization method has problems with low search efficiency, flexibility and global optimization ability. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a student dormitory allocation method based on big data. In view of the problems of low accuracy, robustness and overall performance of traditional dormitory allocation clustering methods, this scheme improves the accuracy, robustness and overall performance of clustering by designing a sophisticated reference distance function of neighboring points, calculating enhanced connectivity between point clusters, designing a clustering effect evaluation mechanism, creating noise clusters, and designing a dynamic update strategy for cluster centers; in view of the problems of low search efficiency, flexibility and global optimization capability of traditional cluster construction parameter optimization methods, this scheme improves the parameter search efficiency, flexibility and global optimization capability by introducing an adaptive search strategy, a mode switching mechanism, and a method combining multi-directional and adaptive search, thereby ensuring the reliability of the optimization results.

[0004] The technical solution adopted by the present invention is as follows: a student dormitory allocation method based on big data, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: data preprocessing;

[0007] Step S3: construct dormitory allocation clusters;

[0008] Step S4: Optimizing clusters;

[0009] Step S5: Student dormitory allocation.

[0010] Furthermore, in step S1, the data collection is to collect students' basic information, living habit data, learning characteristics data and social preference data; the basic information includes student number, gender, college, grade, major, and class; the living habit data includes work and rest time, hygiene habits, consumption habits, exercise habits, whether they are from other provinces and whether they have lived in school; the learning characteristics data includes learning style, interests and hobbies, and academic performance; the social preference data includes social skills and willingness to participate in group activities.

[0011] Furthermore, in step S2, the data preprocessing specifically includes the following steps:

[0012] Step S21: Data cleaning, checking the data, removing duplicate data, filling in missing data, verifying and modifying erroneous data;

[0013] Step S22: data encoding, label encoding of multiple categories of text data;

[0014] Step S23: data normalization, unifying the format, range and unit of data;

[0015] Step S24: construct a feature vector, add each feature of each data sample to the vector, and form a feature vector of the data.

[0016] Furthermore, in step S3, the construction of dormitory allocation clusters specifically includes the following steps:

[0017] Step S31: Design a neighboring point reference distance function, which is expressed as follows:

[0018] ;

[0019] Among them, i and j represent the index of the data point, and Respectively represent the locations of the i-th data point and the j-th data point, represents the reference distance of the neighboring points between the i-th data point and the j-th data point, ed(·) represents the Euclidean distance, represents the data point closest to the i-th data point, represents the Euclidean distance between the ith data point and the nearest data point, represents the Euclidean distance between the data point closest to the i-th data point and the j-th data point, represents the data point closest to the jth data point, represents the Euclidean distance between the data point closest to the jth data point and the i-th data point, represents the Euclidean distance between the jth data point and the nearest data point, Represents the square of the Euclidean distance between the i-th data point and the j-th data point;

[0020] Step S32: Calculate the connection degree between point clusters, expressed as follows:

[0021] ;

[0022] Among them, o and k represent the index of the cluster center, represents the position of the oth cluster center, represents the degree of connection between the ith data point and the oth cluster center, represents the total number of cluster centers, represents the reference distance of the neighboring points between the ith data point and the oth cluster center, represents the location of the kth cluster center, represents the reference distance of the neighboring points between the i-th data point and the k-th cluster center, represents the connection factor between clusters;

[0023] Step S33: Design a clustering effect evaluation function, which is expressed as follows:

[0024] ;

[0025] in, represents the clustering effect evaluation value, represents the total number of data points, represents the Euclidean distance between the kth cluster center and the i-th data point, represents the index of the cluster center, represents the kth cluster center and the The Euclidean distance between cluster centers;

[0026] Step S34: cluster data allocation, calculating the connection degree between each data point and each cluster center, and allocating the data point to the cluster with the highest connection degree;

[0027] Step S35: define the noise index, which is defined by measuring the relative distance of the data points within the cluster and the dispersion degree of the cluster and the nearest neighbor cluster, as shown below:

[0028] ;

[0029] in, represents the noise index of the ith data point, represents the noise weight, represents the standard deviation of the distance from all data points in the kth cluster to the cluster center, represents the total number of data points in the kth cluster, Indicates that the jth data point belongs to the kth cluster, represents the Euclidean distance between the i-th data point and the j-th data point, represents the average distance from all data points in the kth cluster to the center of the nearest neighbor cluster, Represents the average distance from all data points in the kth cluster to the cluster center;

[0030] Step S36: creating a noise cluster, setting a noise index threshold, calculating the noise index corresponding to each data point, and classifying the data points whose noise index is greater than the noise index threshold into the noise cluster;

[0031] Step S37: Update the cluster center, as shown below:

[0032] ;

[0033] in, represents the updated cluster center, Indicates that the i-th data point belongs to the k-th cluster;

[0034] Step S38: Cluster formation, repeating steps S34-S37 until the cluster structure remains stable.

[0035] Furthermore, in step S4, the cluster optimization is to optimize the cluster construction parameters, which specifically includes the following steps:

[0036] Step S41: search initialization, determine search parameters, including inter-cluster connection factors and noise weights, create parameter search space, set clustering effect evaluation values ​​as parameter performance values, and generate initial parameter search point clusters;

[0037] Step S42: Design a search directional factor, which is expressed as follows:

[0038] ;

[0039] Where t represents the number of parameter searches, represents the search orientation factor during the t-th parameter search, represents the maximum number of parameter searches, and e represents a natural constant;

[0040] Step S43: Design an adaptive search step length, which is expressed as follows:

[0041] ;

[0042] in, represents the adaptive search step size during the t-th parameter search, hb represents the upper boundary of the search space, db represents the lower boundary of the search space, Indicates taking the absolute value, represents the length of the search space, represents the number of parameter search points, represents the average position of the initial parameter search points;

[0043] Step S44: Design a mode switching factor to adjust the search mode according to the distance between the parameter point with high fitness and the parameter point with low fitness, as shown below:

[0044] ;

[0045] in, represents the mode switching factor during the tth parameter search, Indicates the location of the parameter point with the highest initial fitness value, Indicates the location of the parameter point with the highest current performance value. Indicates the parameter point position with the lowest current performance value. represents the zero removal factor;

[0046] Step S45: Design a multi-directional search function, the formula used is as follows:

[0047] ;

[0048] in, Indicates the parameter position searched by the multi-directional search function during the t+1th parameter search. It represents the parameter position searched by the multi-directional search function during the t-th parameter search, and r1 represents a random number ranging from 0 to 1;

[0049] Step S46: Design an adaptive search function, the formula used is as follows:

[0050] ;

[0051] in, Indicates the parameter position searched by the adaptive search function during the t+1th parameter search. Indicates the parameter position searched by the adaptive search function during the tth parameter search, Indicates the parameter position searched by the adaptive search function during the t-1th parameter search;

[0052] Step S47: Design a mode switching exploration function, the formula used is as follows:

[0053] ;

[0054] in, Indicates the parameter position searched by the mode switching exploration function during the t+1th parameter search. Indicates the parameter position searched by the mode switching exploration function during the tth parameter search;

[0055] Step S48: parameter search, set the performance threshold of the parameter and the maximum number of parameter searches, calculate the performance value of the initial parameter search point cluster parameter, perform parameter searches of the multi-directional search function and the adaptive search function in turn, calculate the performance value of the parameter point obtained by the two parameter searches, compare the parameter performance values ​​before and after the search, if the performance values ​​of more than 60% of the parameter points are improved, then perform the next round of search; otherwise, perform a parameter search of the mode switching exploration function first, and then perform the next round of search; if during the search process there is a parameter point whose performance value is greater than the parameter performance threshold, the search ends, and the point parameter is output as the optimized cluster construction parameter; if the maximum number of parameter searches is reached, perform search initialization, and search again; otherwise, continue to search.

[0056] Furthermore, in step S5, the student dormitory allocation is to combine the student data of the dormitory to be allocated and the constructed cluster structure data, match the student data to be allocated to the constructed cluster structure, design a student dormitory allocation plan based on the data of other students in the cluster to which the students are allocated, allocate students in the same cluster to the same dormitory, and collect dormitory allocation result data and students' feedback data to continuously improve and update the cluster structure.

[0057] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0058] (1) In view of the problems of low accuracy, robustness and overall performance of traditional dormitory allocation clustering methods, this scheme improves the accuracy, robustness and overall performance of clustering by designing a refined reference distance function of neighboring points, calculating the enhanced connectivity between point clusters, designing a clustering effect evaluation mechanism, creating noise clusters, and designing a dynamic update strategy for cluster centers.

[0059] (2) The traditional cluster construction parameter optimization method has problems with low search efficiency, flexibility and global optimization ability. This scheme improves the parameter search efficiency, flexibility and global optimization ability by introducing adaptive search strategies, mode switching mechanisms, and a combination of multi-directional and adaptive search methods, thereby ensuring the reliability of the optimization results. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of the flow of the student dormitory allocation method based on big data provided by the present invention;

[0061] Figure 2 is a schematic flow chart of step S2;

[0062] Figure 3 is a schematic flow chart of step S3;

[0063] Figure 4is a schematic flow chart of step S4;

[0064] Figure 5 Schematic diagram of search rules;

[0065] Figure 6 Schematic diagram of parameter performance threshold detection.

[0066] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0068] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0069] Example 1, see Figure 1 The present invention provides a student dormitory allocation method based on big data, which comprises the following steps:

[0070] Step S1: Data collection, collecting students’ basic information, living habits data, learning characteristics data and social preference data;

[0071] Step S2: Data preprocessing, data cleaning, data encoding, data normalization and feature vector construction are used to preprocess the data;

[0072] Step S3: Construct dormitory allocation clusters by designing neighboring point reference distance function, calculating the connection degree between point clusters, designing clustering effect evaluation function, cluster data allocation, defining noise index, creating noise clusters, and updating cluster centers;

[0073] Step S4: Optimizing clusters by performing parameter search through designing search directional factors, designing mode switching factors, designing multi-directional search functions, designing adaptive search functions, and designing mode switching exploration functions to optimize clusters;

[0074] Step S5: Student dormitory allocation, matching the student data to be allocated to the constructed cluster structure, and allocating students in the same cluster to the same dormitory.

[0075] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the data collection is to collect students' basic information, living habit data, learning characteristics data and social preference data; the basic information includes student number, gender, college, grade, major, and class; the living habit data includes work and rest time, hygiene habits, consumption habits, exercise habits, whether from other provinces and whether there is living experience; the learning characteristics data includes learning style, interests and hobbies, and academic performance; the social preference data includes social skills and willingness to participate in group activities.

[0076] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the data preprocessing specifically includes the following steps:

[0077] Step S21: Data cleaning, checking the data, removing duplicate data, filling in missing data, verifying and modifying erroneous data;

[0078] Step S22: data encoding, label encoding of multiple categories of text data;

[0079] Step S23: data normalization, unifying the format, range and unit of data;

[0080] Step S24: construct a feature vector, add each feature of each data sample to the vector, and form a feature vector of the data.

[0081] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, the construction of dormitory allocation clusters specifically includes the following steps:

[0082] Step S31: Design a neighboring point reference distance function, which is expressed as follows:

[0083] ;

[0084] Among them, i and j represent the index of the data point, and Respectively represent the locations of the i-th data point and the j-th data point, represents the reference distance of the neighboring points between the i-th data point and the j-th data point, ed(·) represents the Euclidean distance, represents the data point closest to the i-th data point, represents the Euclidean distance between the ith data point and the nearest data point, represents the Euclidean distance between the data point closest to the i-th data point and the j-th data point, represents the data point closest to the jth data point, represents the Euclidean distance between the data point closest to the jth data point and the i-th data point, represents the Euclidean distance between the jth data point and the nearest data point, Represents the square of the Euclidean distance between the i-th data point and the j-th data point;

[0085] Step S32: Calculate the connection degree between point clusters, expressed as follows:

[0086] ;

[0087] Among them, o and k represent the index of the cluster center, represents the position of the oth cluster center, represents the degree of connection between the ith data point and the oth cluster center, represents the total number of cluster centers, represents the reference distance of the neighboring points between the ith data point and the oth cluster center, represents the reference distance of the neighboring points between the i-th data point and the k-th cluster center, represents the connection factor between clusters;

[0088] Step S33: Design a clustering effect evaluation function, which is expressed as follows:

[0089] ;

[0090] in, represents the clustering effect evaluation value, represents the total number of data points, represents the Euclidean distance between the kth cluster center and the i-th data point, represents the index of the cluster center, represents the kth cluster center and the The Euclidean distance between cluster centers;

[0091] Step S34: cluster data allocation, calculating the connection degree between each data point and each cluster center, and allocating the data point to the cluster with the highest connection degree;

[0092] Step S35: define the noise index, which is defined by measuring the relative distance of the data points within the cluster and the dispersion degree of the cluster and the nearest neighbor cluster, as shown below:

[0093] ;

[0094] in, represents the noise index of the ith data point, represents the noise weight, represents the standard deviation of the distance from all data points in the kth cluster to the cluster center, represents the total number of data points in the kth cluster, Indicates that the jth data point belongs to the kth cluster, represents the Euclidean distance between the i-th data point and the j-th data point, represents the average distance from all data points in the kth cluster to the center of the nearest neighbor cluster, Represents the average distance from all data points in the kth cluster to the cluster center;

[0095] Step S36: creating a noise cluster, setting a noise index threshold, calculating the noise index corresponding to each data point, and classifying the data points whose noise index is greater than the noise index threshold into the noise cluster;

[0096] Step S37: Update the cluster center, as shown below:

[0097] ;

[0098] in, represents the updated cluster center, Indicates that the i-th data point belongs to the k-th cluster;

[0099] Step S38: Cluster formation, repeating steps S34-S37 until the cluster structure remains stable.

[0100] By performing the above operations, the traditional dormitory allocation clustering method has problems of low accuracy, robustness and overall performance. This scheme improves the accuracy, robustness and overall performance of clustering by designing a sophisticated neighboring point reference distance function, calculating enhanced inter-cluster connectivity, designing a clustering effect evaluation mechanism, creating noise clusters, and designing a dynamic update strategy for cluster centers.

[0101] Example 5, see Figure 1 , Figure 4 , Figure 5 and Figure 6 This embodiment is based on the above embodiment. In step S4, the cluster optimization is to optimize the cluster construction parameters, which specifically includes the following steps:

[0102] Step S41: search initialization, determine search parameters, including inter-cluster connection factors and noise weights, create parameter search space, set clustering effect evaluation values ​​as parameter performance values, and generate initial parameter search point clusters;

[0103] Step S42: Design a search directional factor, which is expressed as follows:

[0104] ;

[0105] Where t represents the number of parameter searches, represents the search orientation factor during the t-th parameter search, represents the maximum number of parameter searches, and e represents a natural constant;

[0106] Step S43: Design an adaptive search step length, which is expressed as follows:

[0107] ;

[0108] in, represents the adaptive search step size during the t-th parameter search, hb represents the upper boundary of the search space, db represents the lower boundary of the search space, Indicates taking the absolute value, represents the length of the search space, represents the number of parameter search points, represents the average position of the initial parameter search points;

[0109] Step S44: Design a mode switching factor to adjust the search mode according to the distance between the parameter point with high fitness and the parameter point with low fitness, as shown below:

[0110] ;

[0111] in, represents the mode switching factor during the tth parameter search, Indicates the location of the parameter point with the highest initial fitness value, Indicates the location of the parameter point with the highest current performance value. Indicates the parameter point position with the lowest current performance value. represents the zero removal factor;

[0112] Step S45: Design a multi-directional search function, the formula used is as follows:

[0113] ;

[0114] in, Indicates the parameter position searched by the multi-directional search function during the t+1th parameter search. It represents the parameter position searched by the multi-directional search function during the t-th parameter search, and r1 represents a random number ranging from 0 to 1;

[0115] Step S46: Design an adaptive search function, the formula used is as follows:

[0116] ;

[0117] in, Indicates the parameter position searched by the adaptive search function during the t+1th parameter search. Indicates the parameter position searched by the adaptive search function during the tth parameter search, Indicates the parameter position searched by the adaptive search function during the t-1th parameter search;

[0118] Step S47: Design a mode switching exploration function, the formula used is as follows:

[0119] ;

[0120] in, Indicates the parameter position searched by the mode switching exploration function during the t+1th parameter search. Indicates the parameter position searched by the mode switching exploration function during the tth parameter search;

[0121] Step S48: parameter search, set the performance threshold of the parameter and the maximum number of parameter searches, calculate the performance value of the initial parameter search point cluster parameter, perform parameter searches of the multi-directional search function and the adaptive search function in turn, calculate the performance value of the parameter point obtained by the two parameter searches, compare the parameter performance values ​​before and after the search, if the performance values ​​of more than 60% of the parameter points are improved, then perform the next round of search; otherwise, perform a parameter search of the mode switching exploration function first, and then perform the next round of search; if during the search process there is a parameter point whose performance value is greater than the parameter performance threshold, the search ends, and the point parameter is output as the optimized cluster construction parameter; if the maximum number of parameter searches is reached, perform search initialization, and search again; otherwise, continue to search.

[0122] By performing the above operations, the traditional cluster construction parameter optimization method has the problems of low search efficiency, flexibility and global optimization ability. This scheme improves the parameter search efficiency, flexibility and global optimization ability by introducing adaptive search strategies, mode switching mechanisms, and a combination of multi-directional and adaptive search methods, thereby ensuring the reliability of the optimization results.

[0123] Example 6, see Figure 1This embodiment is based on the above embodiment. In step S5, the student dormitory allocation is to combine the student data of the dormitory to be allocated and the constructed cluster structure data, match the student data to be allocated to the constructed cluster structure, design the student dormitory allocation plan according to the data of other students in the cluster to which the students are allocated, allocate students in the same cluster to the same dormitory, and collect dormitory allocation result data and students' feedback data to continuously improve and update the cluster structure.

[0124] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0125] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0126] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A student dormitory allocation method based on big data, characterized in that: The method comprises the following steps: Step S1: Data collection, collecting students’ basic information, living habits data, learning characteristics data and social preference data; Step S2: Data preprocessing, data cleaning, data encoding, data normalization and feature vector construction are used to preprocess the data; Step S3: construct dormitory allocation clusters, by designing neighboring point reference distance function, calculating the connection degree between point clusters, designing clustering effect evaluation function, cluster data allocation, defining noise index, creating noise clusters and updating cluster centers; Step S4: Optimizing clusters by performing parameter search through designing search directional factors, designing mode switching factors, designing multi-directional search functions, designing adaptive search functions, and designing mode switching exploration functions to optimize clusters; Step S5: Student dormitory allocation, matching the student data to be allocated to the constructed cluster structure, and allocating students in the same cluster to the same dormitory; In step S3, the construction of dormitory allocation clusters specifically includes the following steps: Step S31: Design a neighboring point reference distance function, which is expressed as follows: ； Among them, i and j represent the index of the data point, and Respectively represent the locations of the i-th data point and the j-th data point, represents the reference distance of the neighboring points between the i-th data point and the j-th data point, ed(·) represents the Euclidean distance, represents the data point closest to the i-th data point, represents the Euclidean distance between the ith data point and the nearest data point, represents the Euclidean distance between the data point closest to the i-th data point and the j-th data point, represents the data point closest to the jth data point, represents the Euclidean distance between the data point closest to the jth data point and the i-th data point, represents the Euclidean distance between the jth data point and the nearest data point, Represents the square of the Euclidean distance between the i-th data point and the j-th data point; Step S32: Calculate the connection degree between point clusters, expressed as follows: ； Among them, o and k represent the index of the cluster center, represents the position of the oth cluster center, represents the degree of connection between the ith data point and the oth cluster center, represents the total number of cluster centers, represents the reference distance of the neighboring points between the ith data point and the oth cluster center, represents the reference distance of the neighboring points between the i-th data point and the k-th cluster center, represents the connection factor between point clusters; Step S33: Design a clustering effect evaluation function, which is expressed as follows: ； in, represents the clustering effect evaluation value, represents the total number of data points, represents the Euclidean distance between the kth cluster center and the i-th data point, represents the index of the cluster center, represents the kth cluster center and the The Euclidean distance between cluster centers; Step S34: cluster data allocation, calculating the connection degree between each data point and each cluster center, and allocating the data point to the cluster with the highest connection degree; Step S35: define the noise index, which is defined by measuring the relative distance of the data points within the cluster and the dispersion degree of the cluster and the nearest neighbor cluster, as shown below: ； in, represents the noise index of the ith data point, represents the noise weight, represents the standard deviation of the distance from all data points in the kth cluster to the cluster center, represents the total number of data points in the kth cluster, Indicates that the jth data point belongs to the kth cluster, represents the Euclidean distance between the i-th data point and the j-th data point, represents the average distance from all data points in the kth cluster to the center of the nearest neighbor cluster, Represents the average distance from all data points in the kth cluster to the cluster center; Step S36: creating a noise cluster, setting a noise index threshold, calculating the noise index corresponding to each data point, and classifying the data points whose noise index is greater than the noise index threshold into the noise cluster; Step S37: Update the cluster center, as shown below: ； in, represents the updated cluster center, Indicates that the i-th data point belongs to the k-th cluster; Step S38: Cluster formation, repeating steps S34-S37 until the cluster structure remains stable; In step S4, the cluster optimization is to optimize the cluster construction parameters, which specifically includes the following steps: Step S41: search initialization, determine search parameters, including inter-cluster connection factors and noise weights, create parameter search space, set clustering effect evaluation values ​​as parameter performance values, and generate initial parameter search point clusters; Step S42: Design a search directional factor, which is expressed as follows: ； Where t represents the number of parameter searches, represents the search orientation factor during the t-th parameter search, represents the maximum number of parameter searches, and e represents a natural constant; Step S43: Design an adaptive search step length, which is expressed as follows: ； in, represents the adaptive search step size during the t-th parameter search, hb represents the upper boundary of the search space, db represents the lower boundary of the search space, Indicates taking the absolute value, represents the length of the search space, represents the number of parameter search points, represents the average position of the initial parameter search points; Step S44: Design a mode switching factor to adjust the search mode according to the distance between the parameter point with high fitness and the parameter point with low fitness, as shown below: ； in, represents the mode switching factor during the tth parameter search, Indicates the location of the parameter point with the highest initial fitness value, Indicates the location of the parameter point with the highest current performance value. Indicates the parameter point position with the lowest current performance value. represents the zero removal factor; Step S45: Design a multi-directional search function, the formula used is as follows: ； in, Indicates the parameter position searched by the multi-directional search function during the t+1th parameter search. It represents the parameter position searched by the multi-directional search function during the t-th parameter search, and r1 represents a random number ranging from 0 to 1; Step S46: Design an adaptive search function, the formula used is as follows: ； in, Indicates the parameter position searched by the adaptive search function during the t+1th parameter search. Indicates the parameter position searched by the adaptive search function during the tth parameter search, Indicates the parameter position searched by the adaptive search function during the t-1th parameter search; Step S47: Design a mode switching exploration function, the formula used is as follows: ； in, Indicates the parameter position searched by the mode switching exploration function during the t+1th parameter search. Indicates the parameter position searched by the mode switching exploration function during the tth parameter search; Step S48: parameter search, set the performance threshold of the parameter and the maximum number of parameter searches, calculate the performance value of the initial parameter search point cluster parameter, perform parameter searches of the multi-directional search function and the adaptive search function in turn, calculate the performance value of the parameter point obtained by the two parameter searches, compare the parameter performance values ​​before and after the search, if the performance values ​​of more than 60% of the parameter points are improved, then perform the next round of search; otherwise, perform a parameter search of the mode switching exploration function first, and then perform the next round of search; if during the search process there is a parameter point whose performance value is greater than the parameter performance threshold, the search ends, and the point parameter is output as the optimized cluster construction parameter; if the maximum number of parameter searches is reached, perform search initialization, and search again; otherwise, continue to search.

2. The student dormitory allocation method based on big data according to claim 1 is characterized by: In step S2, the data preprocessing specifically includes the following steps: Step S21: Data cleaning, checking the data, removing duplicate data, filling in missing data, verifying and modifying erroneous data; Step S22: data encoding, label encoding of multiple categories of text data; Step S23: data normalization, unifying the format, range and unit of data; Step S24: construct a feature vector, add each feature of each data sample to the vector, and form a feature vector of the data.

3. The student dormitory allocation method based on big data according to claim 1 is characterized by: In step S1, the data collection is to collect students' basic information, living habits data, learning characteristics data and social preference data; the basic information includes student number, gender, college, grade, major, and class; the living habits data includes work and rest time, hygiene habits, consumption habits, exercise habits, whether they are from other provinces and whether they have lived in school; the learning characteristics data includes learning style, interests and hobbies, and academic performance; the social preference data includes social skills and willingness to participate in group activities; In step S5, the student dormitory allocation is to combine the student data of the dormitory to be allocated and the constructed cluster structure data, match the student data to be allocated to the constructed cluster structure, design a student dormitory allocation plan based on the data of other students in the cluster to which the students are allocated, allocate students in the same cluster to the same dormitory, and collect dormitory allocation result data and students' feedback data to continuously improve and update the cluster structure.

Images