Subway crew attendance and attendance data transmission method and system

Abstract

The invention relates to the technical field of attendance data processing, in particular to a subway crew attendance and attendance data transmission method and system. The method comprises the following steps: firstly, based on the difference between different out-of-service data of metro crew members, clustering the out-of-service data by using an iterative self-organizing clustering algorithm, and calculating the outlier degree of each out-of-service data in any round of iteration process; according to the change condition of the outlier degree in each iteration process, calculating the isolation degree of the out-of-service and out-of-service data of the subway crew members; based on the isolation degrees of different out-of-service data, utilizing an iterative self-organizing clustering algorithm to obtain a final exception category; according to the final exception category, determining the exception degree of each piece of out-of-service data, and screening out exceptional out-of-service data; and transmitting the abnormal attendance and attendance data. According to the invention, the detection of abnormal data in the attendance data is improved, so that management personnel can more accurately obtain the attendance state of subway crew members.

Description

Technical Field

[0001] The present invention relates to the technical field of attendance data processing, and in particular to a method and system for transmitting data of attendance and check-out of subway crew members. Background Art

[0002] With the acceleration of urbanization, subway, as an efficient public transportation tool, is becoming more and more popular. Subway crew members are crucial to the safety and efficiency of subway operations. Similarly, the attendance management of subway crew members is also crucial to the safety and efficiency of subway operations. The attendance data of subway crew members usually includes attendance time, departure time, absence records and working hours. By transmitting the attendance data of subway crew members to the database, the real-time update of the attendance data of subway crew members can be realized, ensuring that managers can obtain the latest attendance status of subway crew members at any time. Therefore, it is particularly important to transmit the attendance data of subway crew members.

[0003] The existing transmission of subway crew attendance data usually directly uses an iterative self-organizing clustering algorithm to detect anomalies in the attendance data, and then transmits the abnormal part of the attendance data. The iterative self-organizing clustering algorithm is an algorithm for anomaly detection of multidimensional data. During the clustering process, the cluster center and each cluster are continuously iteratively updated, thereby realizing the adaptive update of the collected attendance data. However, due to human errors of subway crew members or other reasons, the attendance data of subway crew members may be abnormal. These abnormal data will cause the misclassification of clusters during the clustering process, resulting in low accuracy in obtaining abnormal data, thereby affecting the accuracy of subsequent iterative updates. Summary of the invention

[0004] In order to solve the technical problem of low accuracy of abnormal data in obtaining attendance and exit data of subway crew members, the purpose of the present invention is to provide a method and system for transmitting attendance and exit data of subway crew members. The technical solution adopted is as follows: In a first aspect, an embodiment of the present invention provides a method for transmitting data of a subway crew member's departure and arrival, the method comprising: Obtain the attendance and departure data of subway crew members; Based on the differences between different attendance data, the attendance data are clustered using an iterative self-organizing clustering algorithm, and in any round of iteration, the degree of outlier of each attendance data is calculated; According to the change of outlier degree in each round of iteration, the isolation degree of the attendance data of the subway crew is calculated; based on the isolation degree of different attendance data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal category; According to the final abnormality category, the abnormality degree of each attendance data is determined, and according to the abnormality degree, the abnormal attendance data is screened out from the attendance data; and the abnormal attendance data is transmitted.

[0005] Furthermore, based on the differences between different attendance data, the attendance data are clustered using an iterative self-organizing clustering algorithm, and in any round of iteration, the degree of outlier of each attendance data is calculated, including: Calculating the distances between different multi-dimensional attendance data, and using the distances to represent the differences between different attendance data; Analyze the distance between each attendance data and the attendance data in the cluster to which it belongs in the current round of iteration, and determine the initial outlier degree of each attendance data; According to the initial outlier degree, the attendance data of the subway crew are screened to obtain the initial screening attendance data after the first screening; any initial screening attendance data is used as the target attendance data, the difference between the target attendance data and other initial screening attendance data is analyzed, and the outlier degree of the target attendance data is determined; wherein the outlier degree of each non-initial screening attendance data is set to 0.

[0006] Furthermore, the analyzing the distance between each attendance data and the attendance data in the corresponding cluster in the current round of iteration to determine the initial outlier degree of each attendance data includes: Taking any attendance data as the attendance data to be analyzed, obtaining the distance between the attendance data to be analyzed and the cluster center of the cluster to which it belongs as the centrifugal distance; Analyze the overall difference between the centrifugal distance of the attendance data to be analyzed and the centrifugal distance of the attendance data in the cluster to which it belongs as the overall dispersion; An initial outlier degree of each attendance data is determined according to the centrifugal distance and the overall dispersion of each attendance data.

[0007] Furthermore, determining the initial outlier degree of each attendance data according to the centrifugal distance and the overall dispersion of each attendance data includes: The normalized value of the ratio of the centrifugal distance to the overall dispersion of each attendance data is used as the initial outlier degree of each attendance data.

[0008] Furthermore, analyzing the difference between the target attendance data and other pre-screened attendance data to determine the degree of outlier of the target attendance data includes: Taking the distance between the target attendance data and other initially screened attendance data as the numerator and the similarity between the data vectors of the target attendance data and other initially screened attendance data as the denominator, determine the difference between the target attendance data and other initially screened attendance data; The sum of the differences between the target attendance data and all other initially screened attendance data is calculated as the first dispersion; the first dispersion is weighted with the initial outlier degree of the target attendance data as the weight to obtain the outlier degree of the target attendance data.

[0009] Furthermore, the calculation of the isolation degree of the subway crew's attendance and departure data according to the change of the outlier degree in each round of iteration includes: Take any initially screened attendance data as the attendance data to be analyzed, calculate the mean of the outlier degree of the attendance data to be analyzed in each iteration process before the current iteration process, and record it as the first mean; For any round of iteration, the difference between the outlier degree of the to-be-analyzed attendance data and the mean of the outlier degree of other initially screened attendance data is calculated, and recorded as the first difference; The first mean is used as the numerator, the sum of the first differences of all the initially screened attendance data is used as the denominator, and the ratio formed by the numerator and the denominator is normalized to obtain the degree of isolation of the attendance data.

[0010] Furthermore, the isolation degree of different attendance data is based on the iterative self-organizing clustering algorithm to obtain the final abnormality category, including: Before the first iterative self-organizing clustering, the initially screened out attendance data with a degree of isolation greater than a preset isolation threshold are eliminated to obtain the first data points to be clustered, and the first data points to be clustered are clustered to obtain the first category; before the second iterative self-organizing clustering, the degree of isolation of all the first data points to be clustered is obtained, and the first data points to be clustered with a degree of isolation greater than the preset isolation threshold are eliminated to obtain the second data points to be clustered, and the second data points to be clustered are clustered to obtain the second category; and so on; until the position of the cluster center no longer changes or the preset number of iterations is reached, no iteration is performed, and the category obtained in the last iteration is used as the final abnormal category.

[0011] Furthermore, the determining of the abnormality level of each attendance data according to the final abnormality category includes: Based on the abnormal category, the ratio of the mean of the outlier degree of each initially screened attendance data in the abnormal category to the number of iterations is calculated as the abnormal degree of each initially screened attendance data, where the abnormal degree of non-initial screened attendance data is 0.

[0012] Furthermore, the step of screening out abnormal attendance data from attendance data according to the abnormality degree includes: The attendance data with an abnormality greater than or equal to a preset abnormality threshold is regarded as abnormal attendance data.

[0013] In a second aspect, a subway crew departure and arrival data transmission system is provided, the system comprising the following modules: The attendance and exit data collection module is used to obtain the attendance and exit data of subway crew members; A first data analysis module is used to cluster the attendance data using an iterative self-organizing clustering algorithm based on the differences between different attendance data, and calculate the degree of outlier of each attendance data in any round of iteration; The second data analysis module is used to calculate the isolation degree of the attendance and exit data of the subway crew according to the change of the outlier degree in each round of iteration; based on the isolation degree of different attendance and exit data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal category; The data transmission module is used to determine the abnormality degree of each attendance data according to the final abnormality category, and filter out abnormal attendance data from the attendance data according to the abnormality degree; and transmit the abnormal attendance data.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, various possible embodiments of the first aspect are implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0016] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute various possible implementations of the first aspect.

[0017] The embodiments of the present invention have at least the following beneficial effects: The present invention first determines the degree of outlier of each attendance data by analyzing the differences between different attendance data, because there is usually a large difference between abnormal attendance data and normal attendance data. The degree of isolation of the attendance data of any subway crew member in the iterative clustering process is calculated. The degree of isolation of the attendance data is further calculated because there may be human errors or other reasons of the subway crew members that cause the subway crew attendance data to be abnormal. These abnormal data will cause the misclassification of clusters in the clustering process. Therefore, further, by considering the degree of outliers in each round of iteration, the degree of isolation of the attendance data is determined. And according to the degree of isolation, the data samples participating in the clustering in the iterative process are screened, so that the clustering results are more accurate, and the abnormal data in the attendance data of the subway crew members is further accurately obtained, so that the management personnel can accurately obtain the attendance status of the crew members at any time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A method flow chart of a method for transmitting subway crew attendance and departure data provided by an embodiment of the present invention; Figure 2 A flow chart of a method for obtaining the outlier degree of each attendance data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, a subway crew attendance and departure data transmission method and system proposed in accordance with the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows.

[0021] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0022] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0023] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0024] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0025] The embodiments of the present invention are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0026] The embodiment of the present invention provides a specific implementation method of a subway crew attendance data transmission method and system, which is applicable to attendance scenarios. In this scenario, the problem of low accuracy of abnormal data in the attendance data of subway crew members is solved. The present invention calculates the degree of isolation of the multi-dimensional attendance data of any subway crew member in the iterative clustering process, and screens the attendance data participating in the clustering in the iterative process according to the degree of isolation, so as to make the clustering result more accurate, and further accurately obtain the abnormal data in the attendance data of subway crew members, so that the management personnel can accurately obtain the attendance status of the crew members at any time.

[0027] The following describes in detail a specific scheme of a subway crew attendance and departure data transmission method and system provided by the present invention in conjunction with the accompanying drawings.

[0028] See also Figure 1 , which shows a flowchart of a method for transmitting subway crew attendance and departure data provided by an embodiment of the present invention, the method comprising the following steps: Step S100, obtaining the attendance and departure data of subway crew members.

[0029] Every other day is a sampling time point. The subway electronic attendance system collects the attendance and exit data of subway crew members. The attendance time, exit time, absence record and working hours of the attendance and exit data are collected for a total of one month. The attendance time, exit time, absence record and working hours corresponding to each sampling time point are taken as the attendance and exit data sequence of subway crew members.

[0030] A multidimensional space is constructed according to the attendance time, leave time, absence record and working hours corresponding to each sampling time point, and the attendance and leave data sequence of the subway crew is input into the multidimensional space to obtain the multidimensional attendance and leave data of several subway crew members, that is, each attendance and leave data contains four types of data values: attendance time, leave time, absence record and working hours.

[0031] Step S200: clustering the attendance data using an iterative self-organizing clustering algorithm based on the differences between different attendance data, and calculating the degree of outlier of each attendance data in any round of iteration.

[0032] The iterative self-organizing clustering algorithm is a clustering algorithm based on adaptive characteristics. It optimizes the clustering results by randomly selecting the initial cluster center and iterating repeatedly. In each iteration, the algorithm assigns the data point to the nearest cluster center and updates the position of the cluster center according to the assignment result until the cluster center no longer changes or reaches the preset number of iterations, thereby realizing the clustering of high-dimensional data and clustering multi-dimensional attendance data with similar characteristics in the same cluster cluster; in the process of iterative clustering, all attendance data are involved in the clustering. Considering that these abnormal data affect the accuracy of the iteration of the cluster center, thereby affecting the accuracy of the clustering results, the present invention needs to calculate the abnormality of each multi-dimensional attendance data, so as to facilitate the subsequent processing of the multi-dimensional attendance data according to the abnormality of the data.

[0033] For the attendance data of subway crew members, if the attendance data is more isolated or more discrete than other attendance data, the corresponding attendance data is more likely to be abnormal. Therefore, based on the differences between different attendance data, the attendance data can be clustered using an iterative self-organizing clustering algorithm, and the degree of outlier of each attendance data can be calculated in any round of iteration.

[0034] In some embodiments, the outlier degree of each attendance and leave data is obtained, that is, the above step S200 can be performed by Figure 2 The steps shown achieve: Step S210 , calculating the distances between different multi-dimensional attendance data, and using the distances to represent the differences between different attendance data.

[0035] The greater the distance between the attendance data, the greater the probability that the corresponding attendance data is abnormal, and the distance between different attendance data is used to characterize the difference between different attendance data. In the embodiment of the present invention, the distance between different multi-dimensional attendance data is the Euclidean distance.

[0036] Step S220 , analyzing the distance between each attendance data and the attendance data in the corresponding cluster in the current round of iteration, and determining the initial outlier degree of each attendance data.

[0037] Taking the i-th round as the current round of iteration process and the j-th cluster of the i-th round as an example, the initial outlier degree of each attendance data is determined. That is, for each round of iteration process, the initial outlier degree of each attendance data in each round is calculated. The initial outlier degree represents the discrete degree of the current attendance data. The greater the discrete degree, the greater the probability of abnormality in the corresponding attendance data.

[0038] Take any attendance data as the attendance data to be analyzed, obtain the distance between the attendance data to be analyzed and the cluster center of the cluster to which it belongs as the centrifugal distance; analyze the overall difference between the centrifugal distance of the attendance data to be analyzed and the centrifugal distance of the attendance data in the cluster to which it belongs as the overall dispersion; determine the initial outlier degree of each attendance data according to the centrifugal distance and the overall dispersion. Among them, the centrifugal distance is positively correlated with the initial outlier degree of the attendance data; the overall dispersion is negatively correlated with the initial outlier degree of the attendance data.

[0039] More specifically: a normalized value of the ratio of the centrifugal distance to the overall dispersion of each attendance data is used as the initial outlier degree of each attendance data.

[0040] In some embodiments, the attendance data of the kth subway crew member in the jth cluster in the i-th round is used as the attendance data to be analyzed, and the calculation formula of the initial outlier degree is: ; in, is the initial outlier degree of the k-th subway crew member’s attendance and departure data in the j-th cluster in the i-th round; is the distance between the attendance data of the kth subway crew member in the jth cluster in the i-th round and the cluster center of the cluster to which it belongs, that is, the eccentric distance corresponding to the attendance data of the kth subway crew member in the jth cluster in the i-th round; is the mean of the centrifugal distances of the attendance and withdrawal data in the jth cluster in the i-th round; is the overall dispersion of the attendance and departure data of the kth subway crew in the jth cluster in the i-th round; is the number of subway crew members’ attendance and departure data in the jth cluster in the i-th round; norm is the normalization function.

[0041] Indicates the distance between the multi-dimensional attendance data of the subway crew and the cluster to which it belongs. The larger the value, the greater the initial outlier degree of the multi-dimensional attendance data of the subway crew; Characterize the confidence level of the initial outlier degree of the multi-dimensional attendance and departure data of the subway crew, The smaller the value is, the closer the Euclidean distance between the multidimensional attendance data of all subway crew members in the cluster to which the attendance data of the kth subway crew member in the jth cluster in the i-th round belongs and the cluster center of the cluster to which it belongs is, and the greater the confidence level of the initial outlier degree of the multidimensional attendance data of the subway crew member is.

[0042] Step S230, screening the attendance data of the subway crew according to the initial outlier degree to obtain the initial screening attendance data after the first screening; taking any initial screening attendance data as the target attendance data, analyzing the difference between the target attendance data and other initial screening attendance data, and determining the outlier degree of the target attendance data.

[0043] The outlier degree of each non-preliminary screened attendance data is set to 0.

[0044] In the subway crew's attendance data sequence, due to the subway crew's leave behavior, the distance between the attendance time of the subway crew's attendance data and its cluster center will become larger, resulting in some outlier data points that are not abnormal data. Therefore, the initial outlier degree obtained by the above method is inaccurate. If the outlier data point is abnormal data, the position distribution between the outlier data point and other outlier data points is farther; and there is no regularity between its multi-dimensional attendance data; for example, if the crew's attendance time changes due to leave, his working hours and absence records will change; but if the abnormal data is caused by the system, only the attendance time will be changed, and the data of other dimensions will not change, so the regularity of the multi-dimensional data of the data point will be destroyed; therefore, it is necessary to correct the initial outlier degree by analyzing the position distribution between the data points with a large degree of outliers and the regularity of their multi-dimensional data, so as to obtain the final outlier degree of the subway crew's multi-dimensional data points.

[0045] First, according to the initial outlier degree, the attendance data of the subway crew are screened to obtain the initial screening attendance data after the first screening. Specifically: the attendance data with an initial outlier degree greater than or equal to the preset outlier threshold T is recorded as the initial screening attendance data, and the initial screening attendance data is the data showing an outlier state, and the subway crew multi-dimensional data points with an initial outlier degree less than the preset outlier threshold T are recorded as normal data points, that is, non-initial screening attendance data, and the outlier degree of each non-initial screening attendance data is set to 0.

[0046] After the first screening of the attendance data of subway crew members, any one of the initially screened attendance data is used as the target attendance data, and the difference between the target attendance data and other initially screened attendance data is analyzed to determine the degree of outlier of the target attendance data. Specifically, the distance between the target attendance data and other initially screened attendance data is used as a numerator, and the similarity between the data vectors of the target attendance data and other initially screened attendance data is used as a denominator to determine the degree of difference between the target attendance data and other initially screened attendance data; the sum of the degrees of difference between the target attendance data and all other initially screened attendance data is calculated as a first discrete degree; the initial degree of outlier of the target attendance data is used as a weight to weight the first discrete degree to obtain the degree of outlier of the target attendance data.

[0047] In some embodiments, the calculation formula of the outlier degree of the target attendance data is: ; in, To determine the degree of outliers in attendance data; The initial outlier level of attendance data is given as the target; Indicates the number of initially screened attendance data other than the target attendance data; Attendance data and its first The Euclidean distance between the initially screened attendance data; Output attendance data and its first The cosine similarity of the data vectors between the initially screened out attendance data. Among them, the data vector is composed of multi-dimensional target attendance data.

[0048] In the calculation formula of the outlier degree of target attendance data, It represents the correction factor for correcting the initial outlier degree. The greater the distance between the target attendance data and the initial screening attendance data, the more discrete the distribution of the target attendance data is, and the greater the possibility that it is abnormal data. The greater the cosine similarity of the data vectors between the target attendance data and the initial screening attendance data, the more likely it is that the target attendance data is an outlier caused by normal leave behavior, not abnormal data, and the smaller its outlier degree is.

[0049] Step S300, according to the change of the degree of outliers in each round of iteration, the isolation degree of the attendance data of the subway crew is calculated; based on the isolation degree of different attendance data, an iterative self-organizing clustering algorithm is used to obtain the final abnormal category.

[0050] For the multidimensional attendance data of any subway crew member, if its outlier degree has been maintained at a high level during the iteration process, it means that the difference between the multidimensional attendance data of the subway crew member and the multidimensional attendance data of other subway crew members is relatively large, that is, the multidimensional attendance data of the subway crew member has a high degree of isolation; in the process of iteratively clustering the multidimensional attendance data of all subway crew members using the iterative self-organizing clustering algorithm, the multidimensional attendance data of these subway crew members will be allocated to different clustering clusters in different clustering rounds, so the final outlier degree of the multidimensional attendance data of any subway crew member in any clustering cluster in any round in the above step corresponds one to one to its final outlier degree in different rounds.

[0051] According to the change of the outlier degree in each round of iteration, the isolation degree of the attendance data of the subway crew is calculated. Specifically: any initially screened attendance data is used as the attendance data to be analyzed, and the mean of the outlier degree of the attendance data to be analyzed in each round of iteration before the current round of iteration is calculated, which is recorded as the first mean; for any round of iteration, the difference between the outlier degree of the attendance data to be analyzed and the mean of the outlier degree of other initially screened attendance data is calculated, which is recorded as the first difference; the first mean is used as the numerator and the sum of the first differences is used as the denominator, and the ratio formed by the numerator and the denominator is normalized to obtain the isolation degree of the attendance data.

[0052] The calculation formula for the degree of isolation is: ; in, is the degree of isolation of the mth initially screened attendance data; norm is the normalization function; is the total number of iterations for the mth initial screening of attendance withdrawal data; is the degree of outlier of the mth initially screened attendance data in the i-th round of iteration; is the average outlier degree of the mth initially screened attendance data in all rounds of iterations; is the first mean; is the difference between the mean of the degree of outliers of the mth initially screened out attendance data and other initially screened out attendance data, that is, the first difference; It is the sum of the first difference values ​​of all the initially screened attendance data.

[0053] Among them, the calculation formula of isolation degree is It indicates the average level of the final outlier degree of the multi-dimensional initial screening and retirement data of the subway crew in the iteration process. The higher the value, the higher the isolation degree of the multi-dimensional initial screening and retirement data of the subway crew; It represents the difference between the outlier degree of the multi-dimensional initial screening out attendance data of subway crew members in each round of iteration and the average level of the outlier degree. The smaller the value is, the smaller the difference is, which means that the fluctuation of the final outlier degree of the multi-dimensional initial screening out attendance data of the subway crew members in the iteration process is smaller, and the isolation degree of the multi-dimensional initial screening out attendance data of the subway crew members is higher.

[0054] Since the higher the isolation degree of the multi-dimensional initial screening out attendance data of subway crew members, the greater the impact on the clustering results, it is necessary to timely remove the initial screening out attendance data with a large degree of isolation to improve the accuracy of the clustering results; therefore, for any multi-dimensional initial screening out attendance data of subway crew members, if the isolation degree of the multi-dimensional initial screening out attendance data of the subway crew members is greater than the preset isolation threshold, the multi-dimensional initial screening out attendance data of the subway crew members will be removed, so that the multi-dimensional initial screening out attendance data of the subway crew members will not participate in the subsequent clustering until the clustering is completed; that is, before the first iteration of self-organizing clustering, the isolation degree of all subway crew multi-dimensional data points is obtained by the above method. In the embodiment of the present invention, the preset isolation threshold value is 0.7, and in other embodiments, the implementer adjusts the value according to the actual situation.

[0055] More specifically: before the first iterative self-organizing clustering, the initially screened out attendance data with a degree of isolation greater than a preset isolation threshold are eliminated to obtain the first data points to be clustered, and the first data points to be clustered are clustered to obtain the first category; before the second iterative self-organizing clustering, the degree of isolation of all the first data points to be clustered is obtained, and the first data points to be clustered with a degree of isolation greater than the preset isolation threshold are eliminated to obtain the second data points to be clustered, and the second data points to be clustered are clustered to obtain the second category; and so on; until the position of the cluster center no longer changes or the preset number of iterations is reached, no iteration is performed, and the category obtained from the last iteration is used as the final abnormal category.

[0056] Step S400, determining the abnormality degree of each attendance data according to the final abnormality category, screening out abnormal attendance data from the attendance data according to the abnormality degree; and transmitting the abnormal attendance data.

[0057] Based on the abnormal category obtained by the final clustering, the abnormal degree of each attendance data is calculated. Specifically: based on the abnormal category, the ratio of the mean of the outlier degree of each initially screened attendance data in the abnormal category to the number of iterations is calculated as the abnormal degree of each initially screened attendance data, where the abnormal degree of non-initial screened attendance data is 0.

[0058] The calculation formula for the abnormality degree is: ; in, is the abnormality degree of the mth attendance data; is the total number of iterations for the mth initial screening of attendance withdrawal data; is the outlier degree of the mth initially screened attendance data in the i-th round of iteration.

[0059] Among them, in the calculation formula of abnormality degree, It represents the average level of the final outlier degree of the multi-dimensional attendance and exit data of the subway crew in the clustering process. The larger the average level of the final outlier degree, the higher the abnormality of the subway crew multi-dimensional data point. Conversely, the lower the abnormality of the subway crew multi-dimensional data point. The total number of iteration rounds The larger the value is, the more rounds of clustering the multidimensional attendance data of the subway crew participate in, that is, there are more other multidimensional attendance data of the subway crew that are similar to the multidimensional attendance data of the subway crew, that is, the lower the abnormality of the multidimensional attendance data of the subway crew.

[0060] According to the abnormality level, the abnormal attendance data are screened out from the attendance data. Specifically, the attendance data with an abnormality level greater than or equal to the preset abnormality threshold is regarded as abnormal attendance data. In the embodiment of the present invention, the preset abnormality threshold is 0.8. In other embodiments, the implementer can adjust the value according to the actual situation. That is, when the abnormality level of the multi-dimensional attendance data of the subway crew is greater than or equal to the preset abnormality threshold , the multi-dimensional attendance data of the subway crew corresponding to the multi-dimensional data point of the subway crew is marked as abnormal, that is, as abnormal attendance data, so that the management personnel can obtain the attendance status of the crew at any time; the processed attendance data sequence of the subway crew containing the abnormal attendance data is transmitted and stored in the database.

[0061] An embodiment of the present invention provides a subway crew departure and arrival data transmission system, the system comprising: The attendance and exit data collection module is used to obtain the attendance and exit data of subway crew members; A first data analysis module is used to cluster the attendance data using an iterative self-organizing clustering algorithm based on the differences between different attendance data, and calculate the degree of outlier of each attendance data in any round of iteration; The second data analysis module is used to calculate the isolation degree of the attendance and exit data of the subway crew according to the change of the outlier degree in each round of iteration; based on the isolation degree of different attendance and exit data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal category; The data transmission module is used to determine the abnormality degree of each attendance data according to the final abnormality category, and filter out abnormal attendance data from the attendance data according to the abnormality degree; and transmit the abnormal attendance data.

[0062] Optionally, the transmission medium may be a wired link, such as but not limited to coaxial cable, optical fiber, and digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth, and mobile device network.

[0063] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0064] A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the aforementioned subway crew departure and arrival data transmission methods.

[0065] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute the subway crew attendance data transmission method provided in an embodiment of the present invention.

[0066] The embodiment of the present invention can divide the functional modules of the device according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0067] In the case of dividing each module according to each function, the device may also include a signal uploading module, a determining module, an adjusting module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0068] It should be understood that the device provided in the embodiment of the present invention is used to execute the above-mentioned subway crew attendance and departure data transmission method, and thus can achieve the same effect as the above-mentioned implementation method.

[0069] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the actions of the device. The storage module may be used to support the device to execute mutual program codes, etc. The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor may also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0070] In addition, the device provided in the embodiment of the present invention may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the subway crew attendance data transmission method provided in the above embodiment.

[0071] An embodiment of the present invention also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the subway crew attendance and departure data transmission method provided in the above embodiment.

[0072] The embodiment of the present invention also provides a computer program product. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement the subway crew attendance and departure data transmission method provided in the above embodiment.

[0073] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Through the description of the above implementation methods, technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways.

[0074] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other divisions in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0075] It should also be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0076] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0078] The above contents are only specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A method for transmitting subway crew departure and arrival data, characterized in that: The method comprises the following steps: Obtain the attendance and exit data of subway crew members; Based on the differences between different attendance data, the attendance data are clustered using an iterative self-organizing clustering algorithm, and in any round of iteration, the degree of outlier of each attendance data is calculated; According to the change of outlier degree in each round of iteration, the isolation degree of the attendance data of the subway crew is calculated; based on the isolation degree of different attendance data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal category; According to the final abnormality category, the abnormality degree of each attendance data is determined, and according to the abnormality degree, the abnormal attendance data is screened out from the attendance data; and the abnormal attendance data is transmitted.

2. A method for transmitting subway crew departure and arrival data according to claim 1, characterized in that: Based on the differences between different attendance data, the attendance data are clustered using an iterative self-organizing clustering algorithm, and in any round of iteration, the degree of outlier of each attendance data is calculated, including: Calculating the distances between different multi-dimensional attendance data, and using the distances to represent the differences between different attendance data; Analyze the distance between each attendance data and the attendance data in the cluster to which it belongs in the current round of iteration, and determine the initial outlier degree of each attendance data; According to the initial outlier degree, the attendance data of the subway crew are screened to obtain the initial screening attendance data after the first screening; any initial screening attendance data is used as the target attendance data, the difference between the target attendance data and other initial screening attendance data is analyzed, and the outlier degree of the target attendance data is determined; wherein the outlier degree of each non-initial screening attendance data is set to 0.

3. A method for transmitting subway crew departure and arrival data according to claim 2, characterized in that: The step of analyzing the distance between each attendance data and the attendance data in the corresponding cluster in the current round of iteration to determine the initial outlier degree of each attendance data includes: Taking any attendance data as the attendance data to be analyzed, obtaining the distance between the attendance data to be analyzed and the cluster center of the cluster to which it belongs as the centrifugal distance; Analyze the overall difference between the centrifugal distance of the attendance data to be analyzed and the centrifugal distance of the attendance data in the cluster to which it belongs as the overall dispersion; An initial outlier degree of each attendance data is determined according to the centrifugal distance and the overall dispersion of each attendance data.

4. A method for transmitting subway crew departure and arrival data according to claim 3, characterized in that: The step of determining the initial outlier degree of each attendance data according to the centrifugal distance and the overall dispersion of each attendance data comprises: The normalized value of the ratio of the centrifugal distance to the overall dispersion of each attendance data is used as the initial outlier degree of each attendance data.

5. A method for transmitting subway crew departure and arrival data according to claim 2, characterized in that: Analyzing the difference between the target attendance data and other pre-screened attendance data to determine the degree of outlier of the target attendance data includes: Taking the distance between the target attendance data and other initially screened attendance data as the numerator and the similarity between the data vectors of the target attendance data and other initially screened attendance data as the denominator, determine the difference between the target attendance data and other initially screened attendance data; The sum of the differences between the target attendance data and all other initially screened attendance data is calculated as the first dispersion; the first dispersion is weighted with the initial outlier degree of the target attendance data as the weight to obtain the outlier degree of the target attendance data.

6. A method for transmitting subway crew departure and arrival data according to claim 2, characterized in that: The calculation of the isolation degree of the subway crew's attendance and departure data according to the change of the outlier degree in each round of iteration includes: Take any initially screened attendance data as the attendance data to be analyzed, calculate the mean of the outlier degree of the attendance data to be analyzed in each iteration process before the current iteration process, and record it as the first mean; For any round of iteration, the difference between the outlier degree of the to-be-analyzed attendance data and the mean of the outlier degree of other initially screened attendance data is calculated, and recorded as the first difference; The first mean is used as the numerator, the sum of the first differences of all the initially screened attendance data is used as the denominator, and the ratio formed by the numerator and the denominator is normalized to obtain the degree of isolation of the attendance data.

7. A method for transmitting subway crew departure and arrival data according to claim 2, characterized in that: Based on the isolation degree of different attendance data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal categories, including: Before the first iterative self-organizing clustering, the initially screened out attendance data with a degree of isolation greater than a preset isolation threshold are eliminated to obtain the first data points to be clustered, and the first data points to be clustered are clustered to obtain the first category; before the second iterative self-organizing clustering, the degree of isolation of all the first data points to be clustered is obtained, and the first data points to be clustered with a degree of isolation greater than the preset isolation threshold are eliminated to obtain the second data points to be clustered, and the second data points to be clustered are clustered to obtain the second category; and so on; until the position of the cluster center no longer changes or the preset number of iterations is reached, no iteration is performed, and the category obtained from the last iteration is used as the final abnormal category.

8. A method for transmitting subway crew departure and arrival data according to claim 1, characterized in that: According to the final abnormality category, the abnormality degree of each attendance data is determined, including: Based on the abnormal category, the ratio of the mean of the outlier degree of each initially screened attendance data in the abnormal category to the number of iterations is calculated as the abnormal degree of each initially screened attendance data, where the abnormal degree of non-initial screened attendance data is 0.

9. A method for transmitting subway crew departure and arrival data according to claim 1, characterized in that: The step of screening out abnormal attendance data from the attendance data according to the abnormality degree includes: The attendance data with an abnormality greater than or equal to a preset abnormality threshold is regarded as abnormal attendance data.

10. A subway crew departure and arrival data transmission system, characterized in that: The system includes the following modules: The attendance and exit data collection module is used to obtain the attendance and exit data of subway crew members; A first data analysis module is used to cluster the attendance data using an iterative self-organizing clustering algorithm based on the differences between different attendance data, and calculate the degree of outlier of each attendance data in any round of iteration; The second data analysis module is used to calculate the isolation degree of the subway crew's attendance and exit data according to the change of the outlier degree in each round of iteration; Based on the isolation degree of different attendance data, the iterative self-organizing clustering algorithm is used to obtain the final abnormal category; The data transmission module is used to determine the abnormality degree of each attendance data according to the final abnormality category, and filter out abnormal attendance data from the attendance data according to the abnormality degree; and transmit the abnormal attendance data.

Images