A human-machine behavior detection method and system based on mobile terminal

Through collaborative work in mobile terminals and security gateways, real-time monitoring and analysis of device and click behavior information, the problems of easy cracking and high cost of traditional verification codes are solved, and comprehensive protection of automated attacks and business security are achieved.

CN118138330BActive Publication Date: 2024-11-19北京安胜华信科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410314229.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-19
Publication Date
2024-11-19
Estimated Expiration
2044-03-19

AI Technical Summary

Technical Problem

In the prior art, when identifying and protecting human-machine behavior, traditional verification codes are easily cracked. Third-party security verification codes increase costs and cannot fully protect against automated attacks, making them less secure.

Method used

By monitoring device ID, mobile status and click behavior information in real time on mobile terminals, combining threat analysis of security gateways, intercepting requests from risk devices, real-time risk protection is achieved, and data transmission is transmitted using encrypted encapsulation, improving data transmission security and business stability.

Benefits of technology

Effective identification and protection of automation tools improve business security and stability, reduce intrusion and cost, and achieve comprehensive protection of automated attacks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118138330B_ABST
    Figure CN118138330B_ABST
Patent Text Reader

Abstract

The present application relates to a method and system for detecting human-machine behavior based on a mobile terminal, which belongs to the field of information security technology. The detection method includes: the client detects the business request sent by the mobile terminal to the business system in real time; the client intercepts the business request and obtains the user equipment monitoring information of the mobile terminal; the client encapsulates and encrypts the user equipment monitoring information and stores it in the business request, generates encrypted business request information and sends it to the security gateway; the security gateway decrypts and analyzes the encrypted business request information to determine whether the mobile terminal has an automation device risk; if so, the security gateway marks the mobile terminal as a risky device and intercepts the business request of the risky device; if not, the security gateway sends the business request of the mobile terminal to the business system. The present application can comprehensively protect and identify automation tools, and can also protect business systems from intrusion, thereby improving business security.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a method and system for detecting human-computer behavior based on a mobile terminal. Background Art

[0002] In the digital age, business expansion of enterprises is accompanied by a surge in data traffic. However, not all data is beneficial to enterprises. Malicious data, such as attacks launched by hackers and crawlers from competitors, have become a major challenge facing enterprises. These invalid data not only consume resources, but may also have a serious impact on the normal operation of enterprises. Generally speaking, traditional enterprises tend to focus on business expansion in the early stages of development and ignore the importance of data security, which makes it easy for security issues to be missed during business development.

[0003] At present, in order to identify human and machine behavior, common solutions include using image recognition verification codes or requiring users to select specific items in the image. Although these solutions are effective to a certain extent, they have some obvious disadvantages. For example, simple verification codes are easily cracked by automated tools, and accessing third-party security verification codes may cause greater intrusion to the business and increase access costs. In addition, these solutions can often only protect specific APIs, but cannot fully protect and identify automated attacks, and have low security. Summary of the invention

[0004] In order to improve security, the present application provides a method and system for detecting human-computer behavior based on a mobile terminal.

[0005] In a first aspect, the present application provides a method for detecting human-machine behavior based on a mobile terminal, which adopts the following technical solution:

[0006] A method for detecting human-machine behavior based on a mobile terminal, the detection method comprising:

[0007] The client detects the business requests sent by the mobile terminal to the business system in real time;

[0008] The client intercepts the service request and obtains user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes device ID information, device movement status information and user click behavior information;

[0009] The client encapsulates and encrypts the user equipment monitoring information and stores it in the service request, generates encrypted service request information and sends it to the security gateway;

[0010] The security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk;

[0011] If yes, the security gateway marks the mobile terminal as a risky device and intercepts the service request of the risky device; if no, the security gateway sends the service request of the mobile terminal to the service system.

[0012] By adopting the above technical solution, the client monitors and intercepts the business requests of the mobile terminal to be detected in real time. By collecting multi-dimensional information such as device ID, mobile status, and click behavior, it can comprehensively analyze the risk of the requested automation equipment. By encrypting and encapsulating the monitoring data for transmission, the security of data transmission is guaranteed. Decryption and risk detection are performed at the gateway level. By intercepting the business requests of risky devices, a real-time risk protection mechanism is implemented to protect the data security and business stability of the enterprise. This application can not only comprehensively protect and identify automation tools through active monitoring of mobile terminals and combined with threat analysis of gateways, but also protect business systems from intrusion, thereby improving business security.

[0013] Optionally, the step of acquiring the device movement status information of the mobile terminal includes:

[0014] The client collects the (X, Y, Z) coordinate data of the mobile terminal in real time;

[0015] Based on a preset algorithm, a movement offset is calculated according to the (X, Y, Z) coordinate data;

[0016] It is determined whether the movement offset exceeds a preset offset threshold value. If so, it is determined that the movement state information of the device is a moving state; if not, it is determined that the movement state information of the device is a stationary state.

[0017] By adopting the above technical solution, the device movement status data is obtained based on the built-in gravity sensor of the mobile terminal, and the status is determined by comparing the movement offset threshold, which can quickly give real-time status feedback, thereby effectively identifying the movement of the device.

[0018] Optionally, the step of obtaining the user click behavior information of the mobile terminal includes:

[0019] The client collects page click events and corresponding timestamps of the mobile terminal in real time;

[0020] According to the page click events and corresponding timestamps, the user click behavior information is analyzed and obtained; wherein the user click behavior information includes click position distribution, click frequency, click interval and click trajectory.

[0021] By adopting the above technical solution and comprehensively analyzing the page click event data of the mobile terminal, and by analyzing the characteristics of multiple dimensions such as click position, frequency, interval, trajectory, etc., the user's real click behavior can be more comprehensively characterized, thereby providing a basis for abnormal detection of user click behavior.

[0022] Optionally, the security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk, including:

[0023] The security gateway decrypts and parses the encrypted service request information to obtain the device movement status information of the mobile terminal; determines whether the device movement status information of the mobile terminal is in a static state, and if so, determines that the mobile terminal has an automation device risk; if not, determines that the mobile terminal does not have an automation device risk.

[0024] By adopting the above technical solution, the security gateway only needs to judge the mobile status of a device to quickly obtain the risk assessment result of the automated equipment. The judgment efficiency is high and no complex calculation and reasoning are required.

[0025] Optionally, the security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk, including:

[0026] The security gateway decrypts and analyzes the encrypted service request information to obtain the user click behavior information of the mobile terminal; wherein the user click behavior information includes click position distribution, click frequency, click interval and click trajectory;

[0027] The user click behavior information is input into a pre-trained machine learning model to obtain a risk score for the mobile terminal; it is determined whether the risk score of the mobile terminal exceeds an abnormal threshold, and if so, it is determined that the mobile terminal has an automation device risk; if not, it is determined that the mobile terminal does not have an automation device risk.

[0028] By adopting the above technical solution, based on the behavioral characteristics analysis in multiple dimensions, we can describe the user's click behavior more comprehensively, automatically extract the behavioral patterns based on the machine learning algorithm, give a quantitative risk score, and measure the level of risk through the score. This can achieve a more granular risk level division, thereby improving the comprehensiveness and accuracy of the judgment.

[0029] Optionally, after the step of the security gateway marking the mobile terminal as a risky device, the method further includes:

[0030] The security gateway generates risky device prompt information according to the device ID information of the mobile terminal and sends the information to the business system.

[0031] By adopting the above technical solution, threat detection and risk device marking are performed at the gateway level, and risk device prompt information is sent to the business system at the same time, so that the business system can perceive risks in the first time and take corresponding risk prevention measures, further improving the security and stability of the business system.

[0032] In the second aspect, the present application provides a human-machine behavior detection system based on a mobile terminal, which adopts the following technical solution:

[0033] A human-machine behavior detection system based on a mobile terminal, the detection system comprising a client and a security gateway;

[0034] The client is used to detect the service request sent by the mobile terminal to the service system in real time, intercept the service request, and obtain the user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes device ID information, device movement status information and user click behavior information;

[0035] The client is further used to encapsulate and encrypt the user equipment monitoring information and store it in the service request, generate encrypted service request information and send it to the security gateway;

[0036] The security gateway is used to decrypt and analyze the encrypted business request information to determine whether the mobile terminal has an automation device risk; if so, the security gateway marks the mobile terminal as a risky device and intercepts the business request of the risky device; if not, the security gateway sends the business request of the mobile terminal to the business system.

[0037] By adopting the above technical solutions, based on active monitoring of mobile terminals and combined with threat analysis of gateways, it is not only possible to comprehensively protect and identify automation tools, but also to protect business systems from intrusion, thereby improving business security.

[0038] Optionally, the security gateway is further used to: generate risky device prompt information according to the device ID information of the mobile terminal and send the risky device prompt information to the business system.

[0039] By adopting the above technical solution, threat detection and risk device marking are performed at the gateway level, and risk device prompt information is sent to the business system at the same time, so that the business system can perceive risks in the first time and take corresponding risk prevention measures, further improving the security and stability of the business system.

[0040] In a third aspect, the present application provides a computer device, which adopts the following technical solution:

[0041] A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0043] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect.

[0044] To summarize, the present application includes at least one of the following beneficial technical effects: Through active monitoring of mobile terminals combined with threat analysis of gateways, the present application can not only comprehensively protect and identify automation tools, but also protect business systems from intrusion, thereby improving business security. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a first flow chart of a human-computer behavior detection method according to one of the embodiments of the present application.

[0046] Figure 2 It is a second flow chart of the human-computer behavior detection method of one of the embodiments of the present application.

[0047] Figure 3 It is a third flow chart of the human-computer behavior detection method of one of the embodiments of the present application.

[0048] Figure 4 It is a fourth flow chart of the human-computer behavior detection method according to one of the embodiments of the present application.

[0049] Figure 5 It is a fifth flow chart of the human-computer behavior detection method of one of the embodiments of the present application.

[0050] Figure 6 It is a structural diagram of a human-machine behavior detection system and a business system of one of the embodiments of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-6 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The embodiment of the present application discloses a method for detecting human-computer behavior based on a mobile terminal.

[0053] Reference Figure 1 , a method for detecting human-machine behavior based on a mobile terminal, the detection method comprising:

[0054] Step S101, the client detects in real time the service request sent by the mobile terminal to the service system;

[0055] Among them, mobile terminals include smart mobile terminals such as mobile phones and tablet computers, which can interact with the business system by sending business requests;

[0056] It is understandable that the purpose of deploying a monitoring program on a mobile terminal and performing real-time monitoring is to capture all service requests of the mobile terminal and provide a data basis for subsequent abnormal behavior analysis.

[0057] Step S102, the client intercepts the service request and obtains the user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes the device ID information, the device movement status information and the user click behavior information;

[0058] Among them, the device ID can be used to identify which specific device issued the request, the mobile state information is the current moving or stationary state of the device, and the user click behavior information can be used to determine whether it is an automatic machine click or a manual operation through features such as click location and frequency.

[0059] In one embodiment of the present application, a client for collecting user equipment monitoring information is deployed in the mobile terminal to be detected. The client may be an application installed on the mobile terminal. To achieve the above purpose, a traffic interceptor, a gravity sensor listener, and a page click event capturer may be deployed in the application respectively;

[0060] Specifically, the traffic interceptor will check all business requests issued by the device, and add additional information to the request header before the request is sent; the gravity sensor listener is used to obtain the status information of the mobile device in real time, especially to determine whether the device is in a stationary state, which can be achieved by monitoring the changes in the x, y, and z coordinates of the device; the page click event capturer is used to obtain the user's click coordinate position, and these click coordinates will be used for subsequent analysis of whether the user behavior meets the characteristics of the automation tool.

[0061] Step S103, the client encapsulates and encrypts the user equipment monitoring information and stores it in the service request, generates encrypted service request information and sends it to the security gateway;

[0062] It is understandable that for the sake of data security, the client will encapsulate and encrypt the device monitoring information, and then store it in the HTTP request header of the business request, forming an encrypted business request and sending it to the security gateway. Even if the request is intercepted during network transmission, it is difficult to decipher the content of the monitoring information.

[0063] Step S104, the security gateway decrypts and analyzes the encrypted service request information;

[0064] Step S105, the security gateway determines whether the mobile terminal has an automation device risk; if so, jump to step S106; if not, jump to step S107;

[0065] Step S106, the security gateway marks the mobile terminal as a risky device and intercepts the service request of the risky device;

[0066] Step S107: The security gateway sends the service request of the mobile terminal to the service system.

[0067] In some embodiments, after receiving an HTTP request containing encrypted information, the security gateway first performs a decryption operation to obtain the original device status and click coordinate information, and then analyzes the device's static state and the regularity of the click coordinates through big data, combined with the continuity and regularity of API access, to identify which devices may be automated devices.

[0068] In the above implementation mode, the client monitors and intercepts the business requests of the mobile terminal to be detected in real time. By collecting multi-dimensional information such as device ID, mobile status, and click behavior, it can comprehensively analyze the risk situation of the requested automation equipment. By encrypting and encapsulating the monitoring data for transmission, the security of data transmission is guaranteed. Decryption and risk detection are performed at the gateway level. By intercepting the business requests of risky devices, a real-time risk protection mechanism is implemented to protect the enterprise's data security and business stability.

[0069] Reference Figure 2 As an implementation of step S102, the step of obtaining the device movement status information of the mobile terminal includes:

[0070] Step S201, the client collects (X, Y, Z) coordinate data of the mobile terminal in real time;

[0071] Among them, through the gravity sensor listener deployed in the client application, the acceleration information of the mobile terminal in three-dimensional space detected by the built-in gravity sensor of the mobile terminal can be collected in real time. The data returned by the gravity sensor includes the acceleration components in the X, Y, and Z directions, and the unit is usually m / s 2 ,This raw data can reflect the changes in the posture and motion state of the device in space.

[0072] Step S202, based on a preset algorithm, calculate the movement offset according to the (X, Y, Z) coordinate data;

[0073] It is understandable that since pure acceleration data only reflects the instantaneous acceleration, it cannot directly characterize the displacement state change of the device. Therefore, by integrating the acceleration data within a preset time period, the displacement change of the device within this period, that is, the movement offset, can be obtained.

[0074] Specifically, commonly used integration algorithms include numerical integration methods such as rectangular integration, trapezoidal integration, and Simpson integration. By reasonably selecting the integration time window and integration step size, combined with the actual sampling frequency of the device, the mobile offset of the mobile terminal can be estimated more accurately. The above steps can all be completed in the client application.

[0075] Step S203, determining whether the movement offset exceeds a preset offset threshold, if so, jumping to step S204; if not, jumping to step S205;

[0076] Step S204, determining that the device movement state information is a moving state;

[0077] Step S205: determine that the device movement state information is a stationary state.

[0078] The selection of the motion offset threshold needs to be repeatedly tested and tuned according to the actual scenario and device characteristics to balance the sensitivity and false positive rate.

[0079] It is understandable that after the movement offset is calculated, it can be compared with a preset threshold to determine whether the device is currently stationary or moving. If the offset exceeds the threshold, it can be considered that the device is in a moving state, otherwise it is stationary.

[0080] In some embodiments, the calculation formula of the movement offset (diff) is:

[0081]

[0082] In addition, the movement offset threshold may be set to 2. When the movement offset (diff) is greater than 2, it can be determined that the mobile terminal is in a moving state, otherwise, it is in a stationary state.

[0083] In the above implementation, the device movement status data is obtained based on the built-in gravity sensor of the mobile terminal, and the status is determined based on the comparison of the movement offset threshold, which can quickly provide real-time status feedback, thereby effectively identifying the movement of the device.

[0084] Reference Figure 3 As an implementation of step S102, the step of obtaining the user click behavior information of the mobile terminal includes:

[0085] Step S301, the client collects page click events and corresponding timestamps of the mobile terminal in real time;

[0086] Among them, through the page click event capturer deployed in the client application, when the user clicks or slides the screen with a finger or a stylus, the page click event capturer can capture the coordinate position of the touch point in real time and record the timestamp of the page click event. In the embodiment of the present application, the touch screen of the mobile terminal can provide pixel-level page click positions and millisecond-level timestamps, which can provide high-quality raw data for detailed analysis of user click behavior.

[0087] It is understandable that these original page click event data are the basis for analyzing user click behavior. By deploying page click event capturers at the operating system level or application level, these click event data can be obtained in real time. In addition, the collection process is generally continuous. As long as the user is operating the mobile terminal, click event data will continue to be generated.

[0088] Step S302, analyzing and obtaining user click behavior information based on page click events and corresponding timestamps; wherein the user click behavior information includes click position distribution, click frequency, click interval and click trajectory.

[0089] Specifically, the click position distribution, that is, the coordinate distribution of the click event, is used to determine whether the user's click position conforms to normal operating habits and whether there is abnormal click position aggregation; the click frequency, that is, the number of click events within a certain time window, can be used to determine whether the user's click frequency is normal to determine whether there is an abnormally high-frequency click; the click interval, that is, the time interval between two adjacent click events, is used to determine whether there is an ultra-high-speed click that is not a human click; the click trajectory, that is, the position change trajectory of a series of click events, is used to determine whether there is a mechanical trajectory feature that is not a human click.

[0090] In the above implementation, the page click event data of the mobile terminal is comprehensively analyzed. By analyzing the characteristics of multiple dimensions such as click position, frequency, interval, trajectory, etc., the user's real click behavior can be more comprehensively characterized, thereby providing a basis for abnormal detection of user click behavior.

[0091] Reference Figure 4 As an implementation method of step S104 and step S105, the security gateway decrypts and analyzes the encrypted service request information, and the step of determining whether the mobile terminal has an automation device risk includes:

[0092] Step S401, the security gateway decrypts and parses the encrypted service request information to obtain the device movement status information of the mobile terminal;

[0093] Specifically, after the security gateway receives the encrypted service request from the client, it first needs to use the corresponding decryption algorithm and key to decrypt it, restore the original request information, and then extract the previously encapsulated device movement status information from the request information, that is, the status judgment result of whether the mobile terminal is stationary or moving.

[0094] Step S402, determining whether the mobile terminal's device movement state information is in a stationary state, if so, jumping to step S403; if not, jumping to step S404;

[0095] Step S403, determining that the mobile terminal has an automation device risk;

[0096] Step S404: Determine that there is no automation equipment risk in the mobile terminal.

[0097] It is understandable that when automated equipment is performing an operation task, it is usually stationary and does not show obvious displacement; based on this feature, the gateway can simply determine whether the device's movement state is stationary to preliminarily determine whether there is a risk of automated equipment. When the device movement state reported by the client is stationary, it can be considered that this business request has a high suspicion of automation and needs to be paid special attention and monitored.

[0098] In the above implementation, the security gateway only needs to determine the result of the movement status of a device to quickly obtain the risk determination result of the automation device, with high determination efficiency and without the need for complex calculations and reasoning.

[0099] Reference Figure 5 As another implementation of step S104 and step S105, the security gateway decrypts and analyzes the encrypted service request information, and the step of determining whether the mobile terminal has an automation device risk includes:

[0100] Step S501: The security gateway decrypts and parses the encrypted service request information to obtain the user click behavior information of the mobile terminal; wherein the user click behavior information includes click location distribution, click frequency, click interval and click trajectory;

[0101] Among them, these data in the user click behavior information reflect the user's actual click operation characteristics and contain rich behavior pattern information.

[0102] Step S502, inputting the user's click behavior information into a pre-trained machine learning model to obtain a risk score of the mobile terminal;

[0103] In some embodiments, the gateway may use a pre-trained machine learning model to perform a comprehensive feature analysis on these data to determine whether there are the following abnormal click behaviors from multiple dimensions:

[0104] Click location distribution: Normal users' click locations are usually scattered, while automated scripts' click locations are often very concentrated and have certain regularities;

[0105] Click frequency: The number of clicks per second of a normal user will fluctuate significantly, while the click frequency of an automated script is usually very constant;

[0106] Click interval: The click interval of normal users is random, while the click interval of automated scripts is usually regular;

[0107] Click trajectory: The click trajectory of a normal user is a continuously changing curve, while the click trajectory of an automated script is often a rigid broken line.

[0108] It should be noted that the establishment of this machine learning model requires the accumulation of a large amount of positive and negative sample data, and repeated training and optimization to improve the accuracy of risk assessment.

[0109] Step S503, determining whether the risk score of the mobile terminal exceeds the abnormal threshold, if so, jump to step S504; if not, jump to step S505;

[0110] Step S504, determining that the mobile terminal has an automation device risk;

[0111] Step S505: Determine that there is no automation equipment risk in the mobile terminal.

[0112] Among them, by comprehensively analyzing these behavioral characteristics and combining them with machine learning algorithms, the gateway can derive a risk score to quantify the level of risk of the automation equipment; when the score exceeds the preset abnormal threshold, it can be considered that the request comes from the automation equipment and needs to be processed and controlled accordingly.

[0113] In the above implementation, based on the behavioral feature analysis of multiple dimensions, the user's click behavior can be described more comprehensively, and the behavioral pattern can be automatically extracted based on the machine learning algorithm to give a quantitative risk score. By measuring the level of risk through the score, a more fine-grained risk level division can be achieved, thereby improving the comprehensiveness and accuracy of the judgment.

[0114] Combining the above two implementation methods, the second click behavior analysis method based on machine learning, although more complicated to implement, can judge the risks of automated equipment from multiple angles, and the judgment is more comprehensive and accurate, which is of great significance to improving the overall effect of human-machine behavior detection and controlling the risks of automated equipment; and the first method based on the movement status of the device can be used as a quick judgment method to complement the click behavior analysis and improve the adaptability of the present application scheme.

[0115] In addition, as a further implementation method of the human-machine behavior detection method, it is also possible to determine whether certain APIs have abnormal access behaviors or are subject to automated attacks by drawing a heat map of the API click location; the specific steps include:

[0116] Add log collection function on the API server to collect API call log data;

[0117] Store the collected API call log data in the data storage system;

[0118] Count the number of calls to each API from each client IP within a preset time range;

[0119] Use data visualization libraries to draw API call heat maps;

[0120] Based on the heat map, determine whether each API has an abnormally high frequency of calls; if so, send an alarm message based on the abnormal API.

[0121] Among them, under normal circumstances, the call distribution of each API should be relatively uniform, and the call frequency from the same client should be limited; if there are obvious "hot spots" on the heat map, that is, the call frequency of a certain API from certain IP addresses is much higher than that in other areas, it may be subject to automated attacks.

[0122] In the above implementation, by selecting a suitable visualization method, an intuitive and easy-to-understand heat map is generated, a judgment standard for abnormal calls is established, and the "hot spot" area on the heat map is automatically identified. By cooperating with timely alarms and handling processes, automated attack behaviors at the API level can be quickly discovered.

[0123] As a further implementation method of the human-machine behavior detection method, after the security gateway marks the mobile terminal as a risky device, the method further includes:

[0124] The security gateway generates risky device prompt information based on the device ID information of the mobile terminal and sends it to the business system.

[0125] The risky device prompt information includes the device ID information marked as a risky device and the risk prompt information.

[0126] In the above implementation, threat detection and risk device marking are performed at the gateway level, and risk device prompt information is sent to the business system, so that the business system can perceive the risk in the first time and take corresponding risk prevention measures, further improving the security and stability of the business system.

[0127] The embodiment of the present application also discloses a human-machine behavior detection system based on a mobile terminal.

[0128] Reference Figure 6 , a human-machine behavior detection system based on a mobile terminal, the detection system includes a client and a security gateway; the client is used to detect the service request sent by the mobile terminal to the service system in real time, intercept the service request, and obtain the user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes the device ID information, the device movement status information and the user click behavior information;

[0129] The client is also used to encapsulate and encrypt the user equipment monitoring information and store it in the service request, generate encrypted service request information and send it to the security gateway;

[0130] The security gateway is used to decrypt and analyze the encrypted business request information to determine whether the mobile terminal has an automation device risk; if so, the security gateway marks the mobile terminal as a risky device and intercepts the business request of the risky device; if not, the security gateway sends the business request of the mobile terminal to the business system.

[0131] In the above implementation, active monitoring based on mobile terminals combined with threat analysis of gateways can not only comprehensively protect and identify automation tools, but also protect business systems from intrusion, thereby improving business security.

[0132] As a further implementation method of the human-machine behavior detection system, the security gateway is also used to: generate risk device prompt information based on the device ID information of the mobile terminal and send it to the business system.

[0133] In the above implementation, threat detection and risk device marking are performed at the gateway level, and risk device prompt information is sent to the business system, so that the business system can perceive the risk in the first time and take corresponding risk prevention measures, further improving the security and stability of the business system.

[0134] The human-machine behavior detection system based on a mobile terminal in the embodiment of the present application can implement any of the above-mentioned human-machine behavior detection methods based on a mobile terminal, and the specific working process of each module in the human-machine behavior detection system can refer to the corresponding process in the above-mentioned method embodiment.

[0135] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0136] The embodiment of the present application also discloses a computer device.

[0137] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned human-computer behavior detection method based on a mobile terminal is implemented.

[0138] The embodiment of the present application also discloses a computer-readable storage medium.

[0139] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned methods for detecting human-computer behavior based on a mobile terminal.

[0140] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0141] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A method for detecting human-machine behavior based on a mobile terminal. It is characterized in that The detection method comprises: The client detects the business requests sent by the mobile terminal to the business system in real time; The client intercepts the service request and obtains user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes device ID information, device movement status information and user click behavior information; The client encapsulates and encrypts the user equipment monitoring information and stores it in the service request, generates encrypted service request information and sends it to the security gateway; The security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk; If yes, the security gateway marks the mobile terminal as a risky device and intercepts the service request of the risky device; if no, the security gateway sends the service request of the mobile terminal to the service system; The step of obtaining the device movement status information of the mobile terminal includes: The client collects the (X, Y, Z) coordinate data of the mobile terminal in real time; Based on a preset algorithm, a movement offset is calculated according to the (X, Y, Z) coordinate data; Determine whether the movement offset exceeds a preset offset threshold, and if so, determine that the device movement state information is a moving state; if not, determine that the device movement state information is a stationary state; The security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk, including: The security gateway decrypts and parses the encrypted service request information to obtain the device movement status information of the mobile terminal; After receiving the encrypted service request from the client, the security gateway uses the corresponding decryption algorithm and key to decrypt it, restore the original request information, and extract the previously encapsulated device movement status information from the request information, that is, the status judgment result of whether the mobile terminal is stationary or moving; Determine whether the device movement state information of the mobile terminal is in a stationary state, and if so, determine that the mobile terminal has an automation device risk; if not, determine that the mobile terminal does not have an automation device risk; The security gateway decrypts and analyzes the encrypted service request information to determine whether the mobile terminal has an automation device risk, including: The security gateway decrypts and analyzes the encrypted service request information to obtain the user click behavior information of the mobile terminal; wherein the user click behavior information includes click position distribution, click frequency, click interval and click trajectory; Inputting the user click behavior information into a pre-trained machine learning model to obtain a risk score of the mobile terminal; Determine whether the risk score of the mobile terminal exceeds an abnormal threshold, and if so, determine that the mobile terminal has an automation device risk; if not, determine that the mobile terminal does not have an automation device risk; The detection method further comprises: By drawing a heat map of the API click location, we can determine whether the API has abnormal access behavior or is subject to automated attacks. The specific steps include: Add log collection function on the API server to collect API call log data; Store the collected API call log data in the data storage system; Count the number of calls to each API from each client IP within a preset time range; Use data visualization libraries to draw API call heat maps; Based on the heat map, determine whether each API has an abnormally high frequency of calls; if so, send an alarm message based on the abnormal API.

2. According to the method for detecting human-machine behavior based on a mobile terminal according to claim 1, It is characterized in that The step of obtaining the user click behavior information of the mobile terminal includes: The client collects page click events and corresponding timestamps of the mobile terminal in real time; According to the page click events and corresponding timestamps, the user click behavior information is analyzed and obtained; wherein the user click behavior information includes click position distribution, click frequency, click interval and click trajectory.

3. According to the method for detecting human-machine behavior based on a mobile terminal according to claim 1, It is characterized in that After the step of the security gateway marking the mobile terminal as a risky device, the step further includes: The security gateway generates risky device prompt information according to the device ID information of the mobile terminal and sends the information to the business system.

4. A human-machine behavior detection system based on mobile terminal, It is characterized in that Used to execute a method for detecting human-machine behavior based on a mobile terminal as described in any one of claims 1 to 3, wherein the detection system includes a client and a security gateway; The client is used to detect the service request sent by the mobile terminal to the service system in real time, intercept the service request, and obtain the user equipment monitoring information of the mobile terminal; the user equipment monitoring information includes device ID information, device movement status information and user click behavior information; The client is further used to encapsulate and encrypt the user equipment monitoring information and store it in the service request, generate encrypted service request information and send it to the security gateway; The security gateway is used to decrypt and analyze the encrypted service request information to determine whether the mobile terminal has an automation device risk; If yes, the security gateway marks the mobile terminal as a risky device and intercepts the service request of the risky device; if no, the security gateway sends the service request of the mobile terminal to the service system.

5. A human-machine behavior detection system based on a mobile terminal according to claim 4, It is characterized in that The security gateway is also used to generate risky device prompt information according to the device ID information of the mobile terminal and send it to the business system.

6. A computer device, Features: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the method according to any one of claims 1 to 3 is implemented when the processor executes the program.

7. A computer-readable storage medium, Features: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 3.