Comprehensive security system based on RFID technology

Abstract

The invention discloses a comprehensive security system based on an RFID technology, and relates to the technical field of security systems, the comprehensive security system comprises an IoT platform end and a service cloud end which interact with each other, the IoT platform end comprises an acquisition module and a management module, and the service cloud end at least comprises a data analysis module; the acquisition module comprises an RFID tag signboard and an RFID reader which are matched with each other, the RFID tag signboard is used for presetting attendance authentication information, and the RFID reader is used for waking up the RFID tag signboard in a broadcast mode within a preset range of the RFID reader, obtaining the attendance authentication information of the RFID tag signboard and generating attendance data. According to the invention, managers are helped to better understand employee behaviors, future attendance trends are predicted, attendance data are analyzed, so that enterprises can predict manpower demands in peak periods, employee shifts are reasonably arranged, personnel scheduling is optimized, resource utilization efficiency is improved, manual calculation and management burdens are reduced, and transparency and efficiency of management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of security systems, and in particular to an integrated security system based on RFID technology. Background Art

[0002] At present, the most basic way of traditional security attendance management is to use a sign-in book. Security personnel write their names and times in the sign-in book at the specified working and leaving times. This method is simple and direct, but it has many disadvantages. For example, it is easy for someone to sign in on behalf of others. Some security personnel may ask their colleagues to help sign in because they have a good relationship with them, resulting in distorted attendance records. In addition, the sign-in book may be damaged or lost during the storage process, making it difficult to effectively store attendance data for a long time.

[0003] At the same time, with the development of mechanical technology, time clocks began to be used for security attendance. Security personnel use attendance cards to insert into the time clock, and the time clock will print the date and time on the card. This method improves accuracy to a certain extent compared to the sign-in book because a physical record is left on the card. However, attendance cards are easy to lose or damage, and the time of the time clock may be inaccurate. If the time clock fails, such as damage to the internal mechanical parts of the card clock, it will cause the clock time to be inaccurate, affecting the authenticity of the attendance data. In addition, the traditional attendance system lacks real-time data update and intelligent analysis capabilities, and it is difficult to meet the needs of modern enterprises for efficient and accurate attendance management.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a comprehensive security system based on RFID technology to overcome the above technical problems existing in the existing related technology.

[0006] The technical solution of the present invention is achieved in this way:

[0007] An integrated security system based on RFID technology, comprising: an IoT platform end and a service cloud end interacting with each other, the IoT platform end comprising: a collection module and a management module, the service cloud end at least comprising: a data analysis module, wherein;

[0008] The acquisition module includes: an RFID tag identification plate and an RFID reader adapted to each other, wherein the RFID tag identification plate is used to preset attendance authentication information, and the RFID reader is used to wake up the RFID tag identification plate in the form of broadcasting within the preset range of the RFID reader, obtain the attendance authentication information of the RFID tag identification plate and generate attendance data;

[0009] The management module is used to manage the acquired attendance data, including data processing, data monitoring, data storage and data uploading of the attendance data;

[0010] The data analysis module is used to construct a decision tree analysis model to analyze the attendance data and generate an analysis report, wherein the analysis report at least includes: predicting future attendance trends based on employees' attendance patterns, and optimizing personnel scheduling and resource allocation.

[0011] Furthermore, the data processing includes: data cleaning and data format unification, wherein;

[0012] The data cleaning is used to remove duplicate or erroneous attendance data;

[0013] The data format is unified, and the application organizes all the collected attendance data according to the unified format and converts the attendance location information into a standard location code.

[0014] Further, the data monitoring includes: real-time detection of abnormal conditions and data integrity checks, wherein;

[0015] The said real-time detection of abnormal situations, for unauthorized attendance or equipment failure, and immediate alarms and notifications;

[0016] The data integrity check is used to check whether there are missing values ​​in the attendance data. If the attendance data is missing within a preset range, it is inferred and filled based on the employee's historical attendance data or the attendance information of other employees in the same department. If the attendance data is missing outside the preset range, it is marked as abnormal data for early warning.

[0017] Furthermore, the data analysis module includes the following steps:

[0018] Calibrate the classification features of attendance data in advance and encode the data according to the classification features;

[0019] Constructing a decision tree analysis model based on the data encoding corresponding to the classification features includes the following steps:

[0020] Pre-calculate the information entropy. For a data set D containing n attendance anomaly classifications, its information entropy is expressed as:

[0021]

[0022] Among them, p i is the probability of category i appearing in data set D;

[0023] Calculate the information gain. For feature A, its information gain is expressed as:

[0024]

[0025] Among them, Values(A) is all possible values ​​of feature A, D v It is a subset of the dataset D where feature A takes the value v;

[0026] Select the best feature as the root node, including calculating the information gain of each feature and selecting the feature with the largest information gain as the root node of the decision tree;

[0027] Recursively construct the decision tree child nodes, including dividing a subset for each value of the root node, and repeating the above process of calculating information entropy, information gain and selecting the best feature for each subset to construct child nodes until the stopping condition is met.

[0028] Use the constructed decision tree analysis model to predict the attendance data, which includes: starting from the root node, according to the characteristic value of each sample in the attendance data, go down along the branch of the decision tree until reaching the leaf node. The category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal.

[0029] Furthermore, the stopping condition is satisfied, including: satisfying any one of the following: all samples in the subset belong to the same category, there are no more features to be selected, or the number of samples in the subset is less than a preset threshold, which is indicated as satisfying the stopping condition.

[0030] Furthermore, the category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal, including the following steps:

[0031] Based on whether the attendance is abnormal or not, the employee's future attendance trend is used to optimize personnel scheduling and resource allocation.

[0032] Beneficial effects of the present invention:

[0033] The present invention wakes up the RFID tag identification card in the form of broadcasting within a preset range, obtains the attendance authentication information of the RFID tag identification card and generates attendance data, which greatly reduces human errors in attendance, automatically identifies and records employee information, and avoids problems such as inaccurate card swiping and fingerprint recognition failure in traditional punch-in systems. At the same time, the management module can detect abnormal situations in real time, such as unauthorized attendance or equipment failure, and immediately issue alarms and notifications to ensure rapid response and problem solving, thereby enhancing the reliability of the security system; and it is convenient for managers to check employee attendance at any time, obtain detailed reports and statistical data, and improve data processing efficiency and decision-making accuracy.

[0034] In addition, the present invention can identify employees' attendance patterns by uploading attendance data to the service cloud in real time, helping managers to better understand employee behavior and predict future attendance trends. Analyzing attendance data enables enterprises to predict peak manpower needs, thereby rationally arranging employee shifts, optimizing personnel scheduling, and improving resource utilization efficiency; at the same time, it automatically generates attendance reports, calculates working hours and overtime, and reduces manual calculation and management burdens. At the same time, it automatically manages functions such as conference room use and employee access, improving management transparency and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be 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.

[0036] Figure 1 is a principle block diagram of a comprehensive security system based on RFID technology according to an embodiment of the present invention;

[0037] Figure 2 1 is a schematic diagram of a scenario of an integrated security system based on RFID technology according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0039] According to an embodiment of the present invention, a comprehensive security system based on RFID technology is provided.

[0040] like Figure 1-Figure 2 As shown, the integrated security system based on RFID technology according to an embodiment of the present invention includes: an IoT platform end 1 and a service cloud end 2 that interact with each other, the IoT platform end 1 includes: a collection module 11 and a management module 12, and the service cloud end 2 includes at least: a data analysis module 21, wherein;

[0041] The collection module 11 includes: an RFID tag identification plate 111 and an RFID reader 112 adapted to each other, wherein the RFID tag identification plate 111 is used to preset attendance authentication information, and the RFID reader 112 is used to wake up the RFID tag identification plate 111 in the form of broadcasting within the preset range of the RFID reader 112, obtain the attendance authentication information of the RFID tag identification plate 111 and generate attendance data;

[0042] In this technical solution, RFID tags are deployed on employee ID cards or personal devices. Each RFID tag has a unique identifier and preset attendance authentication information.

[0043] Management module 12, used for data management of the acquired attendance data, including data processing, data monitoring, data storage and data uploading of the attendance data;

[0044] Specifically, data processing includes: data cleaning, removing duplicate or erroneous data. For example, if the RFID reader 112 reads the data of the same RFID tag identification plate multiple times due to signal interference, it is necessary to identify and retain only valid data records.

[0045] It also includes: Data format unification: All collected attendance data will be organized in a unified format, such as converting the time into a specific time format (such as "YYYY-MM-DD HH:MM:SS"), and converting the attendance location information into a standard location code for subsequent data processing and analysis.

[0046] Among them, data monitoring includes: real-time detection of abnormal situations, such as unauthorized attendance or equipment failure, and immediate alarms and notifications to ensure rapid response and problem solving, enhancing the reliability of the security system.

[0047] Also includes: Data integrity check: Check whether there are missing values ​​in the data. For example, in some cases, the attendance location information of some employees may be missing due to network failure. For a small number of missing values, reasonable speculation can be made based on the employee's historical attendance data or the attendance information of other employees in the same department; for a large number of missing values, it is marked as abnormal data and the cause is further investigated.

[0048] The data storage includes: storing the acquired attendance authentication information in a relational database (such as MySQL), a non-relational database (such as MongoDB) or a data warehouse.

[0049] The data uploading includes: uploading the acquired attendance authentication information to the service cloud 2;

[0050] The data analysis module 21 is used to construct a decision tree analysis model to analyze the attendance data and generate an analysis report, wherein the analysis report at least includes: predicting future attendance trends based on the employee's attendance pattern, and optimizing personnel scheduling and resource allocation.

[0051] Specifically, the following steps are included:

[0052] Calibrate the classification features of attendance data and encode the data according to the classification features;

[0053] This technical solution specifically selects features for classification from attendance data, such as "day of the week", "whether to work overtime the day before", "number of late arrivals in the past week", etc. For classification features (such as day of the week), one-hot encoding can be performed. For example, the feature "day of the week" has 7 categories (Monday to Sunday), which can be converted into 7 binary features, with Monday represented as [1,0,0,0,0,0,0], Tuesday represented as [0,1,0,0,0,0,0], etc.

[0054] For continuous features (such as the number of late arrivals in the past week), you can keep their original numerical form or discretize them. For example, divide the number of late arrivals into several intervals: 0, 1-2, 3 and above, and encode them as 0, 1, and 2 respectively.

[0055] Constructing a decision tree analysis model based on the data encoding corresponding to the classification features includes the following steps:

[0056] Pre-calculate information entropy, which is used to measure the purity of a data set. For a data set D containing n categories (in attendance anomaly classification, the categories are usually: abnormal and normal), its information entropy is expressed as:

[0057]

[0058] Among them, p i is the probability that category i appears in data set D.

[0059] Calculate the information gain, which measures the degree to which a feature improves the purity of a data set. For feature A, its information gain is expressed as:

[0060]

[0061] Among them, Values(A) is all possible values ​​of feature A, D v It is a subset of the dataset D whose feature A has the value v.

[0062] Select the best feature as the root node: After calculating the information gain of each feature, select the feature with the largest information gain as the root node of the decision tree.

[0063] Specifically, in this technical solution, after calculation, it is found that the information gain of the feature "whether it is the day before overtime" is the largest, so it is used as the root node.

[0064] Recursively construct decision tree child nodes: For each value of the root node, divide a subset. For example, the root node "Whether to work overtime the day before" has two values ​​(yes and no), so two subsets are divided. Then repeat the above process of calculating information entropy, information gain and selecting the best features for each subset, and construct child nodes until the stopping condition is met.

[0065] The stopping condition includes: all samples in the subset belong to the same category (ie, the purity reaches 100%), there are no more features to choose from, or the number of samples in the subset is too small (eg, less than a preset threshold).

[0066] Use the constructed decision tree analysis model to predict the attendance data, which includes: starting from the root node, according to the characteristic value of each sample in the attendance data, go down along the branch of the decision tree until reaching the leaf node. The category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal.

[0067] The category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal, including the following steps:

[0068] Based on whether the attendance is abnormal or not, the employee's future attendance trend is used to optimize personnel scheduling and resource allocation.

[0069] Specifically, when applied, the features of a test sample are "day of the week = Monday", "whether to work overtime the day before = No", "number of lateness in the past week = 1". According to the branching rules of the decision tree, it eventually reaches a leaf node, and the category corresponding to the leaf node is "abnormal attendance", so it is predicted that this sample is abnormal attendance.

[0070] In summary, with the help of the above technical solution of the present invention, the following effects can be achieved:

[0071] The present invention wakes up the RFID tag identification card 111 in the form of broadcasting within a preset range, obtains the attendance authentication information of the RFID tag identification card 111 and generates attendance data, which greatly reduces human errors in attendance, automatically identifies and records employee information, and avoids problems such as inaccurate card swiping and fingerprint recognition failure in traditional punch-in systems. At the same time, the management module 12 can detect abnormal situations in real time, such as unauthorized attendance or equipment failure, and immediately issue alarms and notifications to ensure rapid response and problem solving, thereby enhancing the reliability of the security system; and it is convenient for managers to check employee attendance at any time, obtain detailed reports and statistical data, and improve data processing efficiency and decision-making accuracy.

[0072] In addition, the present invention can identify the attendance patterns of employees by uploading attendance data to the service cloud 2 in real time, helping managers to better understand employee behavior and predict future attendance trends. Analyzing attendance data enables enterprises to predict peak manpower needs, thereby reasonably arranging employee shifts, optimizing personnel scheduling, and improving resource utilization efficiency; at the same time, it automatically generates attendance reports, calculates working hours and overtime, and reduces manual calculation and management burdens. At the same time, it automatically manages functions such as conference room use and employee access, which improves the transparency and efficiency of management.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. After considering the disclosure of the specification and the examples, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and the examples are only regarded as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0074] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A comprehensive security system based on RFID technology, characterized in that: include: An IoT platform (1) and a service cloud (2) interacting with each other, wherein the IoT platform (1) comprises: a collection module (11) and a management module (12), and the service cloud (2) at least comprises: a data analysis module (21), wherein; The acquisition module (11) comprises: an RFID tag identification plate (111) and an RFID reader (112) adapted to each other, wherein the RFID tag identification plate (111) is used to preset attendance authentication information, and the RFID reader (112) is used to wake up the RFID tag identification plate (111) in the form of broadcasting within a preset range of the RFID reader (112), obtain the attendance authentication information of the RFID tag identification plate (111) and generate attendance data; The management module (12) is used to manage the acquired attendance data, including data processing, data monitoring, data storage and data uploading of the attendance data; The data analysis module (21) is used to construct a decision tree analysis model to analyze the attendance data and generate an analysis report, wherein the analysis report at least includes: predicting future attendance trends based on the employee's attendance pattern, and optimizing personnel scheduling and resource allocation.

2. The integrated security system based on RFID technology according to claim 1 is characterized in that: The data processing includes: data cleaning and data format unification, wherein; The data cleaning is used to remove duplicate or erroneous attendance data; The data format is unified, and the application organizes all the collected attendance data according to the unified format and converts the attendance location information into a standard location code.

3. The integrated security system based on RFID technology according to claim 2 is characterized in that: The data monitoring includes: real-time detection of abnormal conditions and data integrity checks, wherein; The said real-time detection of abnormal situations, for unauthorized attendance or equipment failure, and immediate alarms and notifications; The data integrity check is used to check whether there are missing values ​​in the attendance data. If the attendance data is missing within a preset range, it is inferred and filled based on the employee's historical attendance data or the attendance information of other employees in the same department. If the attendance data is missing outside the preset range, it is marked as abnormal data for early warning.

4. The integrated security system based on RFID technology according to claim 3 is characterized in that: The data analysis module (21) comprises the following steps: Calibrate the classification features of attendance data in advance and encode the data according to the classification features; Constructing a decision tree analysis model based on the data encoding corresponding to the classification features includes the following steps: Pre-calculate the information entropy. For a data set D containing n attendance anomaly classifications, its information entropy is expressed as: Among them, p i is the probability of category i appearing in data set D; Calculate the information gain. For feature A, its information gain is expressed as: Among them, Values(A) is all possible values ​​of feature A, D v It is a subset of the dataset D where feature A takes the value v; Select the best feature as the root node, including calculating the information gain of each feature and selecting the feature with the largest information gain as the root node of the decision tree; Recursively construct the decision tree child nodes, including dividing a subset for each value of the root node, and repeating the above process of calculating information entropy, information gain and selecting the best feature for each subset to construct child nodes until the stopping condition is met. Use the constructed decision tree analysis model to predict the attendance data, which includes: starting from the root node, according to the characteristic value of each sample in the attendance data, go down along the branch of the decision tree until reaching the leaf node. The category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal.

5. The integrated security system based on RFID technology according to claim 4 is characterized in that: The stopping condition is satisfied, including: satisfying any one of the following: all samples in the subset belong to the same category, there are no more features to be selected, or the number of samples in the subset is less than a preset threshold, which is indicated as satisfying the stopping condition.

6. The integrated security system based on RFID technology according to claim 4 is characterized in that: The category corresponding to the leaf node is the category of whether the attendance is predicted to be abnormal, including the following steps: Based on whether the attendance is abnormal or not, the employee's future attendance trend is used to optimize personnel scheduling and resource allocation.

Images