Office management method and system based on intelligent portal platform

Abstract

The invention discloses an office management method and system based on an intelligent portal platform, and particularly relates to the technical field of college platforms, and the method comprises the steps: collecting data, cleaning an error coefficient, updating a delay coefficient and an attack intensity coefficient, building an abnormal coefficient, and comparing the abnormal coefficient with a preset abnormal coefficient reference threshold value, so as to obtain an abnormal coefficient; if the abnormal coefficient is not smaller than a preset abnormal coefficient reference threshold value, the possibility that the running state of the teaching management system goes wrong is larger, and the possibility that records of students and teachers are disordered and inaccurate is larger, at the moment, an alarm signal is generated, early warning is given out, the teachers and workers are reminded in time, and the teaching management system is more convenient to use. When the operation state of the teaching management system has problems, the teaching management system needs to be maintained in time, so that the records of students and teachers are not disordered and inaccurate.

Description

Technical Field

[0001] The present invention relates to the technical field of university platforms, and more specifically, to an office management method and system based on an intelligent portal platform. Background Art

[0002] The teaching management system is a platform for managing courses, teaching resources, student grades and other teaching management tasks. It is not only used by teaching management personnel, but also provides teachers with functions such as course management, grade entry, and teaching resource sharing. Teachers can work on the teaching management system, including course management, teaching resource sharing, student management, grade entry and management, course evaluation, online communication and discussion, course scheduling and schedule management, etc. Teachers can use the teaching management system to achieve a series of teaching management tasks such as course management, teaching resource sharing, student grade management, thereby improving teaching efficiency and quality.

[0003] The prior art has the following deficiencies:

[0004] However, when the teaching management system is in operation, if a failure occurs but is not detected in time and continues to operate, it may have an adverse impact on teaching and management work; for example: in terms of grade entry and management, if a failure occurs, it may cause confusion and inaccuracy in the records of students and teachers, resulting in inaccurate or missing student grade records, which may affect students' academic development and evaluation.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an office management method and system based on an intelligent portal platform to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An office management method based on an intelligent portal platform comprises the following steps:

[0009] Acquire the teaching management system during operation, collect the operation status information of the teaching management system, including data cleaning error system information, real-time update change information and attack intensity information, and analyze and process the data cleaning error system information, real-time update change information and attack intensity information;

[0010] Clean the error information of the data analyzed and processed during the operation of the teaching management system, update the change information and attack intensity information in real time, establish a comprehensive analysis model, generate anomaly coefficients, and evaluate the operation status of the teaching management system through the anomaly coefficients;

[0011] Compare and analyze the generated abnormal coefficient with the preset abnormal coefficient reference threshold to judge the operation of the teaching management system and issue an early warning notification for abnormal situations;

[0012] The data cleaning error information includes the data cleaning error coefficient, the real-time update change information includes the update delay coefficient, and the attack intensity information includes the attack intensity coefficient. The data cleaning error coefficient, the update delay coefficient, and the attack intensity coefficient are denoted as Q x , W a and D z .

[0013] In a preferred embodiment, the logic for obtaining the data cleaning error coefficient is:

[0014] Get the student score data that needs to be uploaded and record it as score data set X, X = {C j}={C1, C2, ..., C n}, where n represents the total number of data in the score data set;

[0015] The mean and standard deviation of the data are calculated based on the following formulas: Standard Deviation Where X i is the i-th data point;

[0016] Calculate the Z-Score value: for each data point X i Calculate the corresponding Z-Score value, the calculation expression is:

[0017] Set anomaly threshold: According to the distribution of Z-Score values, you can select a suitable anomaly threshold to judge outliers;

[0018] Identify outliers: Identify outliers by comparing the calculated Z-Score value with the outlier threshold. i If the value is greater than the set abnormal threshold, the corresponding data point X i Considered as outliers;

[0019] Calculate the total number of outliers in the score data set X and mark it as K. Calculate the data cleaning error coefficient. The calculation expression is: Q x =K / n.

[0020] In a preferred embodiment, the acquisition logic of updating the delay coefficient is:

[0021] Record data update time: record the timestamp of each data update operation, i.e. t c Indicates the time of the cth data update;

[0022] Calculate update delay: For each data update, calculate the time difference between it and the latest data, that is, Δt c =t 最新 -t c ; where t 最新 is the current time;

[0023] Statistical delay time: Count the delay time of all update operations and get a delay time series {Δt1, Δt2, …, Δt d}, where d is the total number of updates;

[0024] Define update delay coefficient: Define update delay coefficient according to the statistical results of delay time; the definition method includes: Calculate the average value of all delay times:

[0025] Define a threshold τ, and obtain the difference between the average value A of the calculated delay time and the threshold τ to obtain the update delay coefficient, which is expressed as: W a =A-τ.

[0026] In a preferred embodiment, the acquisition logic of the attack intensity coefficient is:

[0027] Data preparation: Prepare data sets for training and testing, including network traffic data or user behavior data in the system;

[0028] Build an isolation tree: randomly select a feature from the data set, randomly select a cut value between the minimum and maximum values ​​of the selected feature, and split the data set into two parts; repeat the above process until the tree reaches a predetermined height or each branch has only one data point;

[0029] Constructing an isolation forest: constructing an isolation forest by constructing multiple isolated trees;

[0030] Outlier detection: For each data point, calculate its path length on each tree; use the path length to evaluate the degree of abnormality of the data point;

[0031] The expression of the path length of an isolated tree is: for a data point x, its path length h(x) in an isolated tree can be calculated by the following recursive method: h(x) = hu(x) + c(m), where ht(x) represents the path length of the data point x on the current tree u, and c(m) is the average path length estimated based on the data set size m;

[0032] The degree of anomaly is calculated by the anomaly score; the path lengths of all data points are normalized. For a data point x, its anomaly score s(x) is calculated as follows: Among them, E(h(x)) represents the average path length of data point z on all trees;

[0033] Set the threshold of the anomaly score and record it as we, and calculate the attack intensity coefficient. The expression is: D z =s(x)-we.

[0034] In a preferred embodiment, the logic for obtaining the abnormal coefficient is: clean the data of the error coefficient Q x , update delay coefficient W a and attack strength coefficient D z A comprehensive analysis model is established based on the formula:

[0035]

[0036] Where Pgh is the anomaly coefficient, α, β, and γ are the preset proportional coefficients of the data cleaning error coefficient, update delay coefficient, and attack intensity coefficient, respectively, and α, β, and γ are all greater than 0.

[0037] In a preferred embodiment, the abnormal coefficient is compared with a preset abnormal coefficient reference threshold. When the abnormal coefficient is less than the preset abnormal coefficient reference threshold, no warning is issued; when the abnormal coefficient is not less than the preset abnormal coefficient reference threshold, a warning is issued.

[0038] An office management system based on an intelligent portal platform includes a collection module, a processing module, a comparison and analysis module, and an early warning module, and the modules are connected by signals;

[0039] Collection module: used to collect data cleaning error information, update change information and attack intensity information in real time, and pass the collected information to the processing module;

[0040] Processing module: cleans the received data of error information, updates the change information and attack intensity information in real time to establish a comprehensive analysis model, generates anomaly coefficients, and passes the generated data to the comparative analysis module;

[0041] Comparative analysis module: compare and analyze the generated abnormal coefficient with the preset abnormal coefficient reference threshold to judge the operation of the teaching management system, and pass the judgment result to the comparison and early warning module;

[0042] Early warning module: When the abnormal coefficient is less than the preset abnormal coefficient reference threshold, no early warning is issued; when the abnormal coefficient is not less than the preset abnormal coefficient reference threshold, an early warning is issued.

[0043] Technical effects and advantages of the present invention:

[0044] The present invention collects data to clean error coefficients, update delay coefficients and attack intensity coefficients, and establishes an abnormal coefficient, and compares the abnormal coefficient with a preset abnormal coefficient reference threshold. If the abnormal coefficient is less than the preset abnormal coefficient reference threshold, it indicates that the possibility of a problem with the running state of the teaching management system is smaller, and the possibility of eventually causing confusion and inaccuracy in the records of students and teachers is smaller. At this time, no alarm signal is generated and no early warning is issued; if the abnormal coefficient is not less than the preset abnormal coefficient reference threshold, it indicates that the possibility of a problem with the running state of the teaching management system is greater, and the possibility of eventually causing confusion and inaccuracy in the records of students and teachers is greater. At this time, an alarm signal is generated and an early warning is issued to promptly remind teachers and staff that there is a problem with the running state of the teaching management system, and timely maintenance is required at this time, so that the records of students and teachers will not cause confusion and inaccuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0046] Figure 1 A flowchart of an office management method based on an intelligent portal platform provided by an embodiment of the present invention;

[0047] Figure 2 A framework diagram of an office management system based on an intelligent portal platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the 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 without creative work are within the scope of protection of the present invention.

[0049] Example

[0050] The first aspect of this embodiment discloses an office management method based on an intelligent portal platform, such as Figure 1 As shown, the following steps are included:

[0051] Acquire the teaching management system during operation, collect the operation status information of the teaching management system, including data cleaning error system information, real-time update change information and attack intensity information, and analyze and process the data cleaning error system information, real-time update change information and attack intensity information;

[0052] Clean the error information of the data analyzed and processed during the operation of the teaching management system, update the change information and attack intensity information in real time, establish a comprehensive analysis model, generate anomaly coefficients, and evaluate the operation status of the teaching management system through the anomaly coefficients;

[0053] The generated abnormal coefficient is compared and analyzed with the pre-set abnormal coefficient reference threshold to judge the operation of the teaching management system and issue an early warning notification for abnormal situations.

[0054] The data cleaning error information includes the data cleaning error coefficient, the real-time update change information includes the update delay coefficient, and the attack intensity information includes the attack intensity coefficient. The data cleaning error coefficient, the update delay coefficient, and the attack intensity coefficient are denoted as Q x , W a and D z .

[0055] Data cleaning error coefficient: refers to the degree of data cleaning errors caused by errors in data input or processing during the operation of the teaching management system. Data cleaning refers to cleaning, converting, repairing and other processing of data to ensure that the data quality meets the requirements. The data cleaning error coefficient can reflect the number of errors or the degree of errors that occur during the data cleaning process, such as duplicate data, format errors, missing data, etc. The size of this coefficient can be used to evaluate the data quality in the teaching management system, thereby helping to identify and solve data quality problems and ensure the normal operation of the system and data accuracy; in the present invention, for example, when a teacher works through the teaching management system and enters the student's grades into the teaching management system, before entering the student's grades into the system, the data needs to be cleaned to ensure the quality of the data. This includes checking the integrity, accuracy and consistency of the data, such as checking whether the grades meet the expected range, whether there are format errors, whether there are duplicate data, etc. Through data cleaning, possible errors can be discovered and corrected in a timely manner to ensure that the entered grade data is accurate. Once the degree of data cleaning error is greater, it will cause problems in the operation status of the teaching management system, and ultimately cause confusion and inaccuracy in the records of students and teachers, resulting in inaccurate or missing student grades, which may affect students' academic development and evaluation; the specific reasons are as follows:

[0056] Inaccurate or missing grades: If the data cleaning error coefficient is large, it means that the data quality is not high, which may lead to errors or omissions in the entered grades;

[0057] Chaotic student records: Data cleaning errors may cause student records to become confusing, including student personal information, academic records, etc. This will increase the difficulty for teachers to manage student information and affect teaching management efficiency;

[0058] Decreased teaching management efficiency: If the data in the teaching management system is inaccurate, it may cause teachers and administrators to spend more time checking and correcting the data;

[0059] Therefore, once the degree of data cleaning errors increases, it may have a serious impact on the operating status of the teaching management system;

[0060] The logic for obtaining the data cleaning error coefficient is:

[0061] Get the student score data that needs to be uploaded and record it as score data set X, X = {C j}={C1, C2, ..., C n}, where n represents the total number of data in the score data set;

[0062] The mean and standard deviation of the data are calculated based on the following formulas: Standard Deviation Where X i is the i-th data point;

[0063] Calculate the Z-Score value: for each data point X i Calculate the corresponding Z-Score value, the calculation expression is:

[0064] Set anomaly threshold: According to the distribution of Z-Score values, you can select a suitable anomaly threshold to judge outliers;

[0065] Identifying outliers:

[0066] By comparing the calculated Z-Score value with the abnormal threshold, the abnormal value is identified. i If the value is greater than the set abnormal threshold, the corresponding data point X i Considered as outliers;

[0067] Calculate the total number of outliers in the score data set X and mark it as K. Calculate the data cleaning error coefficient. The calculation expression is: Q k =K / n.

[0068] It should be noted that, usually, the selection of the anomaly threshold is determined according to the characteristics of the data and actual needs. In most cases, the anomaly threshold will indeed be set to a value greater than a certain threshold. This is because we are usually more concerned with identifying those data points that deviate from the normal range, that is, outliers. For example, in the method of the present invention, a threshold is usually selected, usually 2 or 3, to identify those data points that deviate from the mean by more than two to three standard deviations. Such a choice can ensure that we capture most of the data points that deviate from the normal range, thereby identifying potential outliers. Of course, for specific application scenarios, it may be necessary to adjust the anomaly threshold according to actual conditions. In some cases, a stricter threshold may be selected to ensure that only a very small number of outliers are identified, which can reduce false positives; in other cases, we may choose a relatively loose threshold to capture more outliers.

[0069] It can be seen from the calculation expression that the larger the performance value of the data cleaning error coefficient is, the greater the possibility that there is a problem with the operation status of the teaching management system, which will eventually lead to confusion and inaccuracy in the records of students and teachers, and the larger the abnormality coefficient is. Conversely, the smaller the possibility that there is a problem with the operation status of the teaching management system is, the smaller the abnormality coefficient is.

[0070] Update delay coefficient: refers to the degree of delay in data update in the teaching management system; in the teaching management system, data update may involve content such as student grades, course information, teacher information, etc. The calculation of the update delay coefficient can help evaluate the timeliness and effectiveness of data updates in the system; for example, in the present invention, teachers conduct office work through the teaching management system and enter students' grades into the teaching management system. Teachers may make changes to the grades, but if the actual information after the change is not updated in time or the degree of update delay increases, students and other teachers may see different grade information; once the degree of delay in data update in the teaching management system increases, it will cause problems in the operation status of the teaching management system, which will eventually cause confusion and inaccuracy in the records of students and teachers, resulting in inaccurate or missing student grade records, which may affect students' academic development and evaluation; the specific reasons are as follows:

[0071] Data without real-time data affects decision-making: In the teaching management system, teachers and administrators need to make decisions based on real-time data, such as adjusting teaching plans and allocating resources. If data updates are delayed, they may rely on outdated information to make decisions, which may lead to inaccurate decisions and resource allocation, thus affecting students' learning experience and the school's teaching quality.

[0072] Data consistency issues: Update delays may lead to data consistency issues, that is, data inconsistency in different systems or modules. For example, if a student's grade information is updated in one system but not synchronized in another system in time, it will lead to data inconsistency, thus affecting the overall operation of the teaching management system and data accuracy;

[0073] Increased processing costs and risks: Update delays will increase the cost and risk of data processing. The data in the teaching management system may be used for generating reports, statistical analysis, etc. If the data update is delayed, it will increase the workload and time of data processing, which may lead to delayed reporting and analysis results, thus affecting the decision-making and planning of school teaching management;

[0074] Therefore, it is very important to ensure that the speed of data update in the teaching management system is within the normal range;

[0075] The logic for obtaining the update delay coefficient is:

[0076] Record data update time: record the timestamp of each data update operation, i.e. t c Indicates the time of the cth data update;

[0077] Calculate update delay: For each data update, calculate the time difference between it and the latest data, that is, Δt c =t 最新 -t c ; where t 最新 is the current time;

[0078] Statistical delay time: Count the delay time of all update operations and get a delay time series {Δt1, Δt2, …, Δt d}, where d is the total number of updates;

[0079] Define update delay coefficient: Define update delay coefficient according to the statistical results of delay time; the definition method includes: Calculate the average value of all delay times:

[0080] Define a threshold τ, and obtain the difference between the average value A of the calculated delay time and the threshold τ to obtain the update delay coefficient, which is expressed as: W a =A-τ;

[0081] It should be noted that the time of each data update operation usually records the exact time point when the data is updated in the system; these timestamps can be automatically generated by the system, or they can be manually entered by the user when updating the data or automatically recorded by the system. The purpose of recording these timestamps is to track the update history of the data in order to monitor and evaluate the frequency, timeliness and accuracy of the data update; the specific timestamp is obtained according to the actual situation and is not limited to a specific value; in addition, the threshold τ is a data set comprehensively according to the actual situation and is not limited to a specific value;

[0082] It can be seen from the calculation expression that the larger the performance value of the update delay coefficient is, the greater the possibility that there is a problem with the operation status of the teaching management system, which will eventually lead to confusion and inaccuracy in the records of students and teachers, and the larger the abnormality coefficient is. Conversely, the smaller the possibility that there is a problem with the operation status of the teaching management system is, the smaller the abnormality coefficient is.

[0083] Attack intensity coefficient: refers to the intensity of external attacks during the operation of the teaching management system; for example, in the present invention, teachers use the teaching management system to work and enter students' grades into the teaching management system. In this process, if the intensity of external attacks is greater, the integrity and confidentiality of students' grades or other important data may be threatened; once the intensity of external attacks on the teaching management system is greater, problems will occur in the operation of the teaching management system, which will eventually cause confusion and inaccuracy in the records of students and teachers, resulting in inaccurate or missing student grades, which may affect students' academic development and evaluation; the specific reasons are as follows:

[0084] Data tampering and loss: External attacks may cause data in the system to be tampered with or lost. Attackers may modify students' grades or other important data through malicious means, or delete data in the system, thus threatening the accuracy of the data.

[0085] System service interruption: External attacks may cause service interruption or instability of the teaching management system. For example, a denial of service attack may overload the system's server, causing the system to be unable to operate normally or respond to user requests, resulting in the inability to record or update data in a timely manner.

[0086] Data confusion and disorder: Attacks may cause confusion and disorder of system data, making it difficult for students and teachers to identify the correct data information. For example, if the system is attacked by SQL injection, it may cause confusion or inconsistency of data in the database, making it impossible for students and teachers to accurately obtain the required information.

[0087] Therefore, external attacks on the teaching management system may cause problems in the system's operating status, which in turn affects the accuracy and completeness of students' and teachers' records.

[0088] The logic for obtaining the attack strength coefficient is:

[0089] Data preparation: Prepare data sets for training and testing, including network traffic data or user behavior data in the system;

[0090] Build an isolation tree: randomly select a feature from the data set, randomly select a cut value between the minimum and maximum values ​​of the selected feature, and split the data set into two parts; repeat the above process until the tree reaches a predetermined height or each branch has only one data point;

[0091] Constructing an isolation forest: constructing an isolation forest by constructing multiple isolated trees;

[0092] Outlier detection: For each data point, calculate its path length on each tree; use the path length to evaluate the degree of abnormality of the data point;

[0093] The expression of the path length of an isolated tree is: for a data point x, its path length h(x) in an isolated tree can be calculated by the following recursive method: h(x) = hu(x) + c(m), where ht(x) represents the path length of the data point x on the current tree u, and c(m) is the average path length estimated based on the data set size m;

[0094] The degree of anomaly is calculated by the anomaly score; the path lengths of all data points are normalized. For a data point x, its anomaly score s(x) is calculated as follows: Among them, E(h(x)) represents the average path length of data point x in all trees;

[0095] Set the threshold of the anomaly score and record it as we, and calculate the attack intensity coefficient. The expression is: D z =s(x)-we;

[0096] It should be noted that the network traffic data or user behavior data in the system can be various log data or event records collected from the teaching management system. Specifically, they can include but are not limited to the following: network traffic data: login and logout events, request and response data, data transmission volume, network connection status; user behavior data: operation log, behavior path, user interaction, user attributes. The specific selected data depends on the actual situation and is not specifically limited;

[0097] It can be seen from the calculation expression that the larger the value of the attack intensity coefficient is, the greater the possibility that there is a problem with the operation status of the teaching management system, which will eventually lead to confusion and inaccuracy in the records of students and teachers, and the larger the abnormality coefficient is. Conversely, the smaller the possibility that there is a problem with the operation status of the teaching management system is, the smaller the abnormality coefficient is.

[0098] Clean the error information of the data analyzed and processed during the operation of the teaching management system, update the change information and attack intensity information in real time, establish a comprehensive analysis model, generate anomaly coefficients, and evaluate the operation status of the teaching management system through the anomaly coefficients;

[0099] Clean the data with error coefficient Q x , update delay coefficient W a and attack strength coefficient D z A comprehensive analysis model is established based on the formula:

[0100]

[0101] Where Pgh is the anomaly coefficient, α, β, and γ are the preset proportional coefficients of the data cleaning error coefficient, update delay coefficient, and attack intensity coefficient, respectively, and α, β, and γ are all greater than 0.

[0102] The generated abnormal coefficient is compared and analyzed with the pre-set abnormal coefficient reference threshold to judge the operation of the teaching management system and issue an early warning notification for abnormal situations.

[0103] If the abnormality coefficient is less than the preset abnormality coefficient reference threshold, it indicates that the possibility of problems in the operation status of the teaching management system is smaller, and the possibility of confusion and inaccuracy in the records of students and teachers is smaller. At this time, no alarm signal is generated and no early warning is issued; if the abnormality coefficient is not less than the preset abnormality coefficient reference threshold, it indicates that the possibility of problems in the operation status of the teaching management system is greater, and the possibility of confusion and inaccuracy in the records of students and teachers is greater. At this time, an alarm signal is generated and an early warning is issued to promptly remind teachers and staff that there are problems in the operation status of the teaching management system, and timely maintenance is needed to prevent confusion and inaccuracy in the records of students and teachers.

[0104] The present invention provides Figure 2 An office management system based on an intelligent portal platform is shown, such as Figure 2 As shown, it includes a collection module, a processing module, a comparison and analysis module, and an early warning module, and the signals between the modules are connected;

[0105] Collection module: used to collect data cleaning error information, update change information and attack intensity information in real time, and pass the collected information to the processing module;

[0106] Processing module: cleans the received data of error information, updates the change information and attack intensity information in real time to establish a comprehensive analysis model, generates anomaly coefficients, and passes the generated data to the comparative analysis module;

[0107] Comparative analysis module: compare and analyze the generated abnormal coefficient with the preset abnormal coefficient reference threshold to judge the operation of the teaching management system, and pass the judgment result to the comparison and early warning module;

[0108] Early warning module: When the abnormal coefficient is less than the preset abnormal coefficient reference threshold, no early warning is issued; when the abnormal coefficient is not less than the preset abnormal coefficient reference threshold, an early warning is issued.

[0109] An office management system based on an intelligent portal platform provided in an embodiment of the present invention is implemented through the above-mentioned office management method based on an intelligent portal platform. The specific steps and processes of an office management system based on an intelligent portal platform are detailed in the embodiment of the above-mentioned office management method based on an intelligent portal platform, which will not be repeated here.

[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0111] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0112] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0113] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0119] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An office management method based on an intelligent portal platform, It is characterized in that The steps include: Acquire the teaching management system during operation, collect the operation status information of the teaching management system, including data cleaning error system information, real-time update change information and attack intensity information, and analyze and process the data cleaning error system information, real-time update change information and attack intensity information; Clean the error information of the data analyzed and processed during the operation of the teaching management system, update the change information and attack intensity information in real time, establish a comprehensive analysis model, generate anomaly coefficients, and evaluate the operation status of the teaching management system through the anomaly coefficients; Compare and analyze the generated abnormal coefficient with the preset abnormal coefficient reference threshold to judge the operation of the teaching management system and issue an early warning notification for abnormal situations; The data cleaning error information includes the data cleaning error coefficient, the real-time update change information includes the update delay coefficient, and the attack intensity information includes the attack intensity coefficient. The data cleaning error coefficient, the update delay coefficient, and the attack intensity coefficient are denoted as Q x , W a and D z .

2. According to claim 1, an office management method based on an intelligent portal platform, It is characterized in that The logic for obtaining the data cleaning error coefficient is: Get the student score data that needs to be uploaded and record it as score data set X, X = {C j }={C 1 , C 2 ,…,C n }, where n represents the total number of data in the score data set; The mean and standard deviation of the data are calculated based on the following formulas: Standard Deviation Where X i is the i-th data point; Calculate the Z-Score value: for each data point X i Calculate the corresponding Z-Score value, the calculation expression is: Set anomaly threshold: According to the distribution of Z-Score values, you can select a suitable anomaly threshold to judge outliers; Identify outliers: Identify outliers by comparing the calculated Z-Score value with the outlier threshold. i If the value is greater than the set abnormal threshold, the corresponding data point X i Considered as outliers; Calculate the total number of outliers in the score data set X and mark it as K. Calculate the data cleaning error coefficient. The calculation expression is: Q x =K / n.

3. According to the office management method based on the intelligent portal platform of claim 1, It is characterized in that The logic for obtaining the update delay coefficient is: Record data update time: record the timestamp of each data update operation, i.e. t c Indicates the time of the cth data update; Calculate update delay: For each data update, calculate the time difference between it and the latest data, that is, Δt c =t 最新 -t c ; where t 最新 is the current time; Statistical delay time: Count the delay time of all update operations to obtain a delay time series {Δt 1 , Δt 2 ,…,Δt d }, where d is the total number of updates; Define update delay coefficient: Define update delay coefficient according to the statistical results of delay time; the definition method includes: Calculate the average value of all delay times: Define a threshold τ, and obtain the difference between the average value A of the calculated delay time and the threshold τ to obtain the update delay coefficient, which is expressed as: W a =A-τ.

4. According to claim 1, an office management method based on an intelligent portal platform, It is characterized in that The logic for obtaining the attack strength coefficient is: Data preparation: Prepare data sets for training and testing, including network traffic data or user behavior data in the system; Build an isolation tree: randomly select a feature from the data set, randomly select a cut value between the minimum and maximum values ​​of the selected feature, and split the data set into two parts; repeat the above process until the tree reaches a predetermined height or each branch has only one data point; Constructing an isolation forest: constructing an isolation forest by constructing multiple isolated trees; Outlier detection: For each data point, calculate its path length on each tree; use the path length to evaluate the degree of abnormality of the data point; The expression of the path length of an isolated tree is: for a data point x, its path length h(x) in an isolated tree can be calculated by the following recursive method: h(x) = hu(x) + c(m), where ht(x) represents the path length of the data point x on the current tree u, and c(m) is the average path length estimated based on the data set size m; The degree of anomaly is calculated by the anomaly score; the path lengths of all data points are normalized. For a data point x, its anomaly score s(x) is calculated as follows: Among them, E(h(x)) represents the average path length of data point x in all trees; Set the threshold of the anomaly score and record it as we, and calculate the attack intensity coefficient. The expression is: D z =s(x)-we.

5. According to claim 1, an office management method based on an intelligent portal platform, It is characterized in that The logic for obtaining the abnormal coefficient is: clean the data to obtain the error coefficient Q x , update delay coefficient W a and attack strength coefficient D z A comprehensive analysis model is established based on the formula: Where Pgh is the anomaly coefficient, α, β, and γ are the preset proportional coefficients of the data cleaning error coefficient, update delay coefficient, and attack intensity coefficient, respectively, and α, β, and γ are all greater than 0.

6. According to claim 1, an office management method based on an intelligent portal platform, It is characterized in that The abnormal coefficient is compared with the preset abnormal coefficient reference threshold. When the abnormal coefficient is smaller than the preset abnormal coefficient reference threshold, no warning is issued; when the abnormal coefficient is not smaller than the preset abnormal coefficient reference threshold, a warning is issued.

7. An office management system based on an intelligent portal platform, used to implement an office management method based on an intelligent portal platform as claimed in any one of claims 1 to 6, It is characterized in that It includes acquisition module, processing module, comparison and analysis module, early warning module, and signal connection between each module; Collection module: used to collect data cleaning error information, update change information and attack intensity information in real time, and pass the collected information to the processing module; Processing module: cleans the received data of error information, updates the change information and attack intensity information in real time to establish a comprehensive analysis model, generates anomaly coefficients, and passes the generated data to the comparative analysis module; Comparative analysis module: compare and analyze the generated abnormal coefficient with the preset abnormal coefficient reference threshold to judge the operation of the teaching management system, and pass the judgment result to the comparison and early warning module; Early warning module: When the abnormal coefficient is less than the preset abnormal coefficient reference threshold, no early warning is issued; When the abnormal coefficient is not less than the preset abnormal coefficient reference threshold, an early warning is issued.

Images