CN115437901A - Computer user identification management system and method based on big data - Google Patents
Computer user identification management system and method based on big data Download PDFInfo
- Publication number
- CN115437901A CN115437901A CN202211257671.7A CN202211257671A CN115437901A CN 115437901 A CN115437901 A CN 115437901A CN 202211257671 A CN202211257671 A CN 202211257671A CN 115437901 A CN115437901 A CN 115437901A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- mouse
- computer
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a computer user identification management system and a method based on big data, comprising the following steps: the data processing module extracts corresponding characteristic data from the behavior data of the user, the data monitoring module monitors the computer when the user operates the computer, compares the behavior data of the current user with a behavior characteristic template of the user, transmits a data abnormal signal to the data deviation early warning module when detecting that the characteristic data of the current user is not matched with the characteristic template in the database, and the data deviation early warning module receives the abnormal signal and rejects the use operation of the current user on the computer.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a computer user identification management system and a computer user identification management method based on big data.
Background
With the rapid development of computer technology, computers become an indispensable important part in modern work, and meanwhile, because of insufficient protection measures, the privacy information of computer users has potential safety hazards, information leakage may cause personal reputation damage, and even huge economic loss. At present, the existing computer user identification system mainly comprises entity certificates, static passwords, biological characteristics and the like, but the technologies have respective defects when protection is provided for information security, the certificates need to be carried all the time and are easy to lose, the static passwords are easy to leak and break, the reliability is gradually lowered, the security of information stored in a computer is insufficient, the biological characteristic identification needs to provide additional hardware equipment, and the economic burden is increased.
Therefore, a computer user identification management system and method based on big data are needed to solve the above problems.
Disclosure of Invention
The present invention is directed to a system and method for identifying and managing a computer user based on big data, so as to solve the problems mentioned in the background art.
In order to solve the above problems, the present invention provides the following technical solutions: a big data-based computer user identification management system is characterized in that: the system comprises: the system comprises a data acquisition module, a database, a data processing module, a data monitoring module and a data deviation early warning module;
the data monitoring module is used for monitoring the relevant data of the computer user in the using process and matching the relevant data of the current user through the detection model, judging whether the data is normal or not, if so, continuing to monitor and normally operating the computer, otherwise, rejecting the using operation of the current user on the computer through the data deviation early warning module and storing the relevant information of the abnormal data.
Furthermore, the data acquisition module comprises a password input duration acquisition unit and a mouse behavior data acquisition unit, data of a user in the password input process is acquired through the password input duration acquisition unit, namely time data from key striking to leaving of fingers and interval time data from input completion of a previous digit to input of a next digit of adjacent two-digit password, and meanwhile mouse behavior data of the user when the computer is used are acquired through the mouse behavior data acquisition unit, namely static coordinate information of the mouse on a screen, the angle at which the mouse starts to move and the instantaneous acceleration at which the mouse starts to move, so that the detection model can be trained conveniently.
Furthermore, the data processing module comprises a feature extraction unit and a feature template generation unit, the acquired initial data is subjected to normalization processing by the feature extraction unit, and when the acquired data has large deviation and does not meet the acquisition condition and becomes a training sample of the detection model, adverse effects caused by singular sample data can be eliminated by the normalization processing, the accuracy of the detection model is improved, and the gradient reduction can accelerate the speed of obtaining an optimal solution; and selecting a Gaussian kernel function as a kernel function to establish an OCSVM detection model, wherein the kernel function is a conversion function of sample data, and the feature template generation unit trains the established OCSVM detection model by using the processed data to obtain a trained user feature detection model, so that whether a user has the right to operate the computer or not can be determined by the user feature detection model.
Furthermore, the data monitoring module comprises a user data monitoring unit and a user behavior matching unit, the user data monitoring unit monitors related data generated in the computer use process by the current user in real time, namely data in the password input process of the user and mouse behavior data generated in the computer use process of the user, and the user behavior matching unit matches the monitored related data with the trained user characteristic detection model to judge whether the user characteristics are met; the data deviation early warning module comprises a data abnormality early warning unit and an abnormal data recording unit, early warning is sent out when the user characteristics are matched and do not accord with each other through the data abnormality early warning unit, the using operation of a current user is refused, so that the safety of the computer is protected, the related information of the abnormal data is stored by the abnormal data recording unit, so that a normal user can check the abnormal record, the abnormal operation data is analyzed, the user can judge the generation object of the abnormal data, and the reliability of the information stored by the computer is improved.
A computer user identification management method based on big data is characterized in that: the method comprises the following steps:
s1: collecting relevant data of a user, wherein the relevant data comprises a time interval from key pressing to leaving of a finger during password input, interval duration during two adjacent password input, a static coordinate of a mouse, a moving angle of the mouse and instantaneous moving acceleration of the mouse;
s2: processing the acquired data, and obtaining a characteristic template of the user through training a detection model;
s3: and monitoring the password input behavior and the mouse input behavior of the user in real time, and judging whether the password input behavior and the mouse input behavior conform to the characteristic template: if yes, continuing monitoring; if not, executing step S4;
s4: analyzing and confirming that the current user is not the computer owner, refusing the use operation of the current user and recording related information of abnormal data.
According to the above technical solution, in step S1: the password input duration acquisition unit is used for acquiring data of a user when a password is input, and a time interval t from key striking to key leaving of a finger is obtained 1 、t 2 、...、t n A time interval delta t existing with the input time of the adjacent two-bit password 1 、Δt 2 、...、Δt n-1 Wherein n represents the number of digits of the password; the coordinate of the mouse in a computer screen when the mouse is static is acquired as (x, y) by using a mouse behavior data acquisition unit, the angle theta of the movement of the mouse and the instantaneous acceleration v 'are acquired, wherein theta = arctan (delta y/delta x), v' = dv/dt, and v = delta s/delta t, and the acquired data are transmitted to a data processing module.
According to the above technical solution, in step S2: the method comprises the following steps of utilizing a characteristic extraction unit to extract five characteristic subsets including password input key duration, adjacent password input interval duration, a mouse static coordinate, a mouse moving angle and mouse moving instantaneous acceleration from acquired password input data and mouse input data to form a user behavior characteristic sample set, obtaining a plurality of multidimensional matrixes from the extracted characteristic samples, and carrying out normalization processing on data in all the characteristic matrixes according to the following formula:
wherein x is data before normalization, a is specified data lower limit, b is specified data upper limit, and lambda min Is the minimum value, λ, of each column of data in the feature matrix max For the maximum value of each line of data in the characteristic matrix, the normalization processing can eliminate adverse effects caused by singular sample data, avoid the influence on the model accuracy caused by large deviation of the acquired data, and can accelerate the speed of obtaining an optimal solution so as to improve the accuracy of the model; and selecting a Gaussian kernel function as a kernel function to establish an OCSVM detection model, wherein the kernel function is a conversion function of sample data, and training the established OCSVM detection model of the single-class support vector machine by using the password input sample data and the mouse input sample data after the normalization processing by using a feature template generation unit to obtain the trained OCSVM detection model of the user feature single-class support vector machine.
According to the technical scheme, in the steps S3-S4: monitoring relevant data of a current user in real time by using a user data monitoring unit, matching the monitored relevant data with a trained user characteristic detection template, judging the result by a decision function f (x) = sgn (g (x)) of an OCSVM (online charging and maintenance) detection model, and judging the monitored data t i If f (t) i ) If the value is more than or equal to 0, the data is considered to belong to normal user data, monitoring is continuously kept, new data is stored into a database so as to be convenient for continuous model training, the accuracy of the detection model is continuously improved, and if f (t) is greater than or equal to 0 i ) If the data is less than 0, the data is considered to belong to abnormal user data, early warning is sent out through the data abnormality early warning unit, the data abnormality early warning unit is used for rejecting the use operation of the current user when the user behavior matches with the abnormal user data, the related information of the abnormal data is stored through the abnormal data recording unit, the user can check the abnormal use record of the computer in the database, and the safety of the computer information is improved.
Compared with the prior art, the invention has the following beneficial effects:
1. the behavior of the computer user is analyzed through a big data technology, a layer of guarantee is added to the original password identification identity, the reliability of information stored in the computer is more effectively guaranteed, meanwhile, when the behavior data of the user is monitored to be abnormal and not consistent with a characteristic template, early warning is timely carried out, the computer is locked, the using operation of the current user is refused, the related information of the abnormal operation is recorded in a database, the safety protection of the computer is improved, and the possibility of information leakage is reduced.
2. The invention realizes the identification of the identity of the computer user based on the big data, the identification method established on the basis of the big data is safer, the problems of easy loss and easy leakage of the traditional identification mode are solved, no additional hardware equipment is required to be installed, and certain cost is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of a big data based computer user identification management system of the present invention;
FIG. 2 is a flow chart of a method for managing computer user identification based on big data according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1-2, the present invention provides the following technical solutions: a big data-based computer user identification management system is characterized in that: the system comprises: the system comprises a data acquisition module, a database, a data processing module, a data monitoring module and a data deviation early warning module;
the data processing module is used for processing the relevant data acquired by the data acquisition module and establishing an identification detection model of the computer user according to the data in the database, the data monitoring module is used for monitoring the relevant data of the computer user in the using process and matching the relevant data of the current user through the detection model, judging whether the data is normal or not, if so, continuing to monitor, and the computer normally operates, otherwise, refusing the using operation of the current user on the computer through the data deviation early warning module and storing the relevant information of the abnormal data.
The data acquisition module comprises a password input duration acquisition unit and a mouse behavior data acquisition unit, data of a user in the password input process is acquired through the password input duration acquisition unit, namely time data from key striking to key leaving of a finger and interval time data from input completion of a previous digit to input of a next digit of adjacent two-digit password, and meanwhile mouse behavior data of the user in the computer use process, namely static coordinate information of the mouse on a screen, the angle at which the mouse starts to move and the instantaneous acceleration at which the mouse starts to move, are acquired through the mouse behavior data acquisition unit, so that the detection model can be trained conveniently.
The data processing module comprises a feature extraction unit and a feature template generation unit, the acquired initial data is normalized through the feature extraction unit, when the acquired data has large deviation and does not meet the acquisition condition to become a training sample of the detection model, adverse effects caused by singular sample data can be eliminated through normalization processing, and gradient descent can be accelerated to obtain the optimal solution; and selecting a Gaussian kernel function as a kernel function to establish an OCSVM detection model, and training the established OCSVM detection model by using the processed data through a feature template generation unit to obtain a trained user feature detection model, so that whether a user has the right to operate the computer or not can be determined through the user feature detection model.
The data monitoring module comprises a user data monitoring unit and a user behavior matching unit, the user data monitoring unit monitors related data generated by a current user in the computer using process in real time, namely data of the user in the password inputting process and mouse behavior data of the user in the computer using process, the user behavior matching unit matches the monitored related data with a trained user characteristic detection model, and whether the user characteristics are met or not is judged; the data deviation early warning module comprises a data abnormality early warning unit and an abnormal data recording unit, and sends out early warning when the user characteristics are matched and not matched through the data abnormality early warning unit, when a password is input, if the password is input in a wrong number mode or the input behavior characteristics are judged to be not matched through the detection model, the password input error is displayed to reject the login request of the current user, so that the computer safety is protected, and the possibility of computer information leakage is reduced; the abnormal data recording unit stores the related information of the abnormal data so that a normal user can check the abnormal record and analyze the abnormal operation data so that the user can judge the generation object of the abnormal data.
A computer user identification management method based on big data comprises the following steps:
s1: collecting relevant data of a user, wherein the relevant data comprises a time interval existing between key pressing and leaving of a finger when a password is input, interval duration when two adjacent passwords are input, a static coordinate of a mouse, a moving angle of the mouse and instantaneous moving acceleration of the mouse;
s2: processing the acquired data, and obtaining a characteristic template of the user through training a detection model;
s3: and monitoring the password input behavior and the mouse input behavior of the user in real time, and judging whether the password input behavior and the mouse input behavior conform to the characteristic template: if yes, continuing monitoring; if not, executing step S4;
s4: analyzing and confirming that the current user is not the computer owner, refusing the use operation of the current user and recording the related information of abnormal data.
In step S1: the password input duration acquisition unit is used for acquiring data of a user when a password is input, and a time interval t from key striking to key leaving of a finger is obtained 1 、t 2 、...、t n And the time interval delta t existing between the input time of the adjacent two-bit password 1 、Δt 2 、...、Δt n-1 Wherein n represents the number of digits of the password; the coordinate of the mouse in a computer screen when the mouse is static is acquired as (x, y) by using a mouse behavior data acquisition unit, the angle theta of the movement of the mouse and the instantaneous acceleration v 'are acquired, wherein theta = arctan (delta y/delta x), v' = dv/dt, and v = delta s/delta t, and the acquired data are transmitted to a data processing module.
In step S2: the method comprises the following steps of utilizing a characteristic extraction unit to extract five characteristic subsets including password input key duration, adjacent password input interval duration, a mouse static coordinate, a mouse moving angle and mouse moving instantaneous acceleration from acquired password input data and mouse input data to form a user behavior characteristic sample set, obtaining a plurality of multidimensional matrixes from the extracted characteristic samples, and carrying out normalization processing on data in all the characteristic matrixes according to the following formula:
wherein x is data before normalization, a is specified data lower limit, b is specified data upper limit, and lambda min Is the minimum value, λ, of each column of data in the feature matrix max For the maximum value of each line of data in the feature matrix, the adverse effect caused by singular sample data is eliminated through normalization, and the speed of solving the optimal solution through gradient descent is increased; and training the established single-class support vector machine OCSVM detection model by using the processed password input data and mouse input data by using the feature template generation unit to obtain the trained user feature single-class support vector machine detection model.
In steps S3-S4: monitoring relevant data of a current user by using a user data monitoring unit, matching the monitored data with a user characteristic detection template, judging the result by a decision function f (x) = sgn (g (x)) of an OCSVM (online charging management system) detection model, and judging the monitored data t i If f (t) i ) If the data is more than or equal to 0, the data is considered to belong to normal user data, the monitoring is continuously kept, and the data is newStoring the data in a database to facilitate continued training of the model, such that the accuracy of the test model is continuously improved if f (t) i ) If the data is less than 0, the data is considered to belong to abnormal user data, an early warning is sent out through the data abnormality early warning unit, the data abnormality early warning unit is used for rejecting the use operation of the current user when the user behaviors are not matched, the related information of the abnormal data is stored through the abnormal data recording unit, the user can check the abnormal use record of the computer in the database, and the safety of the computer information is improved.
The first embodiment is as follows: in the model training stage, a password input duration acquisition unit is used for acquiring user data of a computer user when a six-digit password is regularly input for 20 times, the acquired user data is transmitted to a data processing module, and a user characteristic single-class support vector machine detection model is trained according to a characteristic sample extracted by a characteristic extraction unit; monitoring the operation data of the current user by using a user data monitoring unit to obtain the key press time length t from key press to key off when the six-digit password is input 1 ＝120、t 2 ＝100、t 3 ＝170、t 4 ＝130、t 5 ＝110、t 6 =160 and time interval Δ t in which input times of adjacent two-bit passwords exist 1 ＝140、Δt 2 ＝180、Δt 3 ＝250、Δt 4 ＝130、Δt 5 =170, unit: lms, matching monitored user data with a feature detection template, making result judgment by a decision function f (x) = sgn (g (x)) of OCSVM, regarding the monitored data as negative class due to the decision function, regarding the data as abnormal user data, displaying a password input error, transmitting a data abnormal signal to a data deviation early warning module, sending an early warning by the data deviation early warning module, rejecting a login request of a current user to a computer, and storing related information of the abnormal data.
Example two: in the model training stage, a mouse behavior data acquisition unit is used for acquiring coordinates of a static mouse in each area of a screen, the angle at which the mouse starts to move and instantaneous acceleration for 10 times in the computer screen, the acquired user data is transmitted to a data processing module, and a user characteristic single-class support vector machine detection model is trained according to characteristic samples extracted by a characteristic extraction unit; the method comprises the steps of monitoring operation data of a current user by using a user data monitoring unit to obtain a static coordinate of a mouse (153,274), a moving angle of the mouse is 22.5 degrees and an instantaneous acceleration is 16, matching monitored user data with a feature detection template, judging a result by a decision function f (x) = sgn (g (x)) of an OCSVM (online analytical model), judging the monitored data to be positive because the decision function is judged to be positive, considering that the data belongs to normal user data, storing the data into a database continuous training model to improve the accuracy of the detection model, continuously monitoring and keeping normal use of a computer by the user.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A big data-based computer user identification management system is characterized in that: the system comprises: the system comprises a data acquisition module, a database, a data processing module, a data monitoring module and a data deviation early warning module;
the data monitoring module is used for monitoring the relevant data of the computer user in the using process and matching the relevant data of the current user through the detection model, judging whether the data is normal or not, if so, continuing to monitor and normally operating the computer, otherwise, refusing the using operation of the current user on the computer through the data deviation early warning module and storing the relevant information of the abnormal data.
2. A big data based computer user identification management system as claimed in claim 1, wherein: the data acquisition module comprises a password input duration acquisition unit and a mouse behavior data acquisition unit, the password input duration acquisition unit acquires time data from key striking to leaving of a finger of a user in a password input process and interval time data from the completion of the previous input of an adjacent two-digit password to the beginning of the next input of the finger of the user, and the mouse behavior data acquisition unit acquires mouse static position information, the direction of the mouse beginning to move and the acceleration of the mouse beginning to move of the user when the user uses a computer.
3. A big data based computer user identification management system as claimed in claim 1, wherein: the data processing module comprises a feature extraction unit and a feature template generation unit, the acquired initial data are normalized through the feature extraction unit, adverse effects caused by singular sample data are eliminated, the speed of solving an optimal solution through gradient descent is increased, a Gaussian kernel function is selected as a kernel function to establish an OCSVM detection model, and the feature template generation unit is used for training the established OCSVM detection model through the processed data to obtain a trained user feature detection model.
4. A big data based computer user identification management system as claimed in claim 1, wherein: the data monitoring module comprises a user data monitoring unit and a user behavior matching unit, the user data monitoring unit monitors related data generated in the computer using process of a current user in real time, and the user behavior matching unit matches the monitored data with the feature detection template and judges whether the data accords with the feature template; the data deviation early warning module comprises a data abnormity early warning unit and an abnormal data recording unit, and the data abnormity early warning unit gives out early warning when the user behaviors are matched and do not accord with each other, so that the use operation of the current user is refused, and the abnormal data recording unit stores the related information of the abnormal data.
5. A computer user identification management method based on big data is characterized in that: the method comprises the following steps:
s1: collecting relevant data of a user, wherein the relevant data comprises a time interval existing between key pressing and leaving of a finger when a password is input, interval duration when two adjacent passwords are input, a static coordinate of a mouse, a moving angle of the mouse and instantaneous moving acceleration of the mouse;
s2: processing the acquired data, and obtaining a characteristic template of the user through training a detection model;
s3: and monitoring the password input behavior and the mouse input behavior of the user in real time, and judging whether the password input behavior and the mouse input behavior conform to the characteristic template: if yes, continuing monitoring; if not, executing step S4;
s4: analyzing and confirming that the current user is not the computer owner, refusing the use operation of the current user and recording the related information of abnormal data.
6. The big data based computer user identification method of claim 5, wherein: in step S1: the password input duration acquisition unit is used for acquiring data of a user when a password is input, and a time interval t from key striking to key leaving of a finger is obtained 1 、t 2 、...、t n And the time interval delta t existing between the input time of the adjacent two-bit password 1 、Δt 2 、...、Δt n-1 Wherein n represents the number of digits of the password; the coordinate of the mouse in a computer screen when the mouse is static is acquired as (x, y) by using a mouse behavior data acquisition unit, the angle theta of the movement of the mouse and the instantaneous acceleration v 'are acquired, wherein theta = arctan (delta y/delta x), v' = dv/dt, and v = delta s/delta t, and the acquired data are transmitted to a data processing module.
7. A big data based computer user identification method according to claim 5, characterized in that: in step S2: the method comprises the following steps of utilizing a characteristic extraction unit to extract five characteristic subsets including password input key duration, adjacent password input interval duration, a mouse static coordinate, a mouse moving angle and mouse moving instantaneous acceleration from acquired password input data and mouse input data to form a user behavior characteristic sample set, obtaining a plurality of multidimensional matrixes from the extracted characteristic samples, and carrying out normalization processing on data in all the characteristic matrixes according to the following formula:
wherein x is data before normalization, a is specified data lower limit, b is specified data upper limit, and lambda min Is the minimum value, λ, of each column of data in the feature matrix max For the maximum value of each line of data in the feature matrix, the adverse effect caused by singular sample data is eliminated through normalization, and the speed of solving the optimal solution through gradient descent is increased; and training the established single-class support vector machine OCSVM detection model by using the processed password input data and mouse input data by using the feature template generation unit to obtain the trained user feature single-class support vector machine detection model.
8. The big data based computer user identification method of claim 5, wherein: in steps S3-S4: monitoring relevant data of a current user by using a user data monitoring unit, matching the monitored data with a user characteristic detection template, judging the result by a decision function f (x) = sgn (g (x)) of an OCSVM (online charging system VM) detection model, and carrying out data processing on the data t i If f (t) i ) And if not, the data is considered to belong to abnormal user data, an early warning is sent to a data abnormality early warning unit, the data abnormality early warning unit is used for rejecting the use operation of the current user when the user behavior matches the abnormal user data, and the abnormal data recording unit is used for storing the related information of the abnormal data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211257671.7A CN115437901A (en) | 2022-10-13 | 2022-10-13 | Computer user identification management system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211257671.7A CN115437901A (en) | 2022-10-13 | 2022-10-13 | Computer user identification management system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115437901A true CN115437901A (en) | 2022-12-06 |
Family
ID=84250224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211257671.7A Pending CN115437901A (en) | 2022-10-13 | 2022-10-13 | Computer user identification management system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115437901A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116467739A (en) * | 2023-03-30 | 2023-07-21 | 江苏途途网络技术有限公司 | Big data storage system and method for computer |
-
2022
- 2022-10-13 CN CN202211257671.7A patent/CN115437901A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116467739A (en) * | 2023-03-30 | 2023-07-21 | 江苏途途网络技术有限公司 | Big data storage system and method for computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Umphress et al. | Identity verification through keyboard characteristics | |
| US8443443B2 (en) | Security system and method for detecting intrusion in a computerized system | |
| Pusara et al. | User re-authentication via mouse movements | |
| CN109509093B (en) | Transaction security control method and system based on main body portrait | |
| JP5011987B2 (en) | Authentication system management method | |
| CN108965340B (en) | Industrial control system intrusion detection method and system | |
| CN108920921B (en) | Sustainable identity authentication method for smart phone sensitive APP | |
| CN107124395B (en) | Identification method of user identity identification system based on keystroke rhythm | |
| CN115437901A (en) | Computer user identification management system and method based on big data | |
| CN111625792A (en) | Identity recognition method based on abnormal behavior detection | |
| CN113658366A (en) | Safety management and control system for limited space operation of thermal power plant | |
| CN117992953A (en) | Abnormal user behavior identification method based on operation behavior tracking | |
| CN117609974B (en) | Service management system and method for technical transaction platform | |
| CN118154186A (en) | Method, device and server for determining abnormal operation of transaction service | |
| CN109446780B (en) | Identity authentication method, device and storage medium thereof | |
| CN114285596B (en) | Transformer substation terminal account abnormity detection method based on machine learning | |
| CN115690677A (en) | Abnormal behavior identification method based on local intuition fuzzy support vector machine | |
| Quraishi et al. | Secure system of continuous user authentication using mouse dynamics | |
| CN114297612A (en) | Authentication method, system and device based on improved cryptographic algorithm | |
| CN113496015A (en) | Identity authentication method and device and computer readable storage medium | |
| CN110795320A (en) | User behavior recording and tracing management method, device, electronic equipment and system | |
| CN118041707B (en) | Identity verification method based on computer network | |
| CN115967542B (en) | Intrusion detection method, device, equipment and medium based on human factor | |
| KR102470364B1 (en) | A method for generating security event traning data and an apparatus for generating security event traning data | |
| CN115695039B (en) | Network security vulnerability detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |