Risk prediction method, device, electronic device and storage medium for terminal equipment
By determining the threat level of threat events in the terminal device and using the hidden Markov model to predict the risk status, the problem of potential risk prediction of terminal devices before network payment is solved, and the accuracy of risk prediction and user interests are achieved.
Patent Information
- Application Number
- CN202311136321.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-04
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2043-09-04
AI Technical Summary
Before users make online payments, how to accurately predict the potential risks of the terminal equipment used by users to reduce user losses and protect user interests.
By determining whether a threat event occurs in the terminal device during the operation cycle, determining the threat level of each threat event, and inputting it as an observation into the hidden Markov model, predicting the target risk status of the terminal device at the future moment, and thus taking timely stopping Loss strategy.
It improves the accuracy of risk prediction and can take timely measures when there are security risks in terminal equipment to reduce user losses and safeguard user interests.
Smart Images

Figure CN117217525B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data security analysis and risk prediction, and in particular to a risk prediction method, device, electronic device and storage medium for a terminal device. Background Art
[0002] With the continuous development of the Internet and the continuous progress of the economy, users can enjoy daily services such as online shopping, taxi-hailing, and food ordering through application software. When conducting these online activities, users need to submit online orders and make online payments before or after completing the corresponding services.
[0003] Before users make online payments, how to accurately predict the potential risks of the terminal devices used by users in order to reduce user losses and protect user interests is an urgent problem to be solved. Summary of the invention
[0004] The present application provides a risk prediction method, device, electronic device and storage medium for a terminal device, which can accurately predict the potential risks of the terminal device used by the user to reduce user losses and safeguard user interests.
[0005] In a first aspect, the present application provides a risk prediction method for a terminal device, the method comprising: determining whether a threat event occurs during an operation cycle of the terminal device; in the event of at least one threat event, determining the threat level of each threat event, wherein the threat level represents the degree of threat posed by the threat event to the security of the terminal device; taking the threat level of each threat event as an observation value, inputting it into a hidden Markov model, and obtaining a predicted risk state output by the hidden Markov model; and predicting a target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state.
[0006] Optionally, the parameters of the hidden Markov model include a triplet (π, A, B); wherein: π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment; A is the state transition probability matrix, including the probability of transition between each preset risk state; B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time.
[0007] Optionally, predicting a target risk state of the terminal device at a future moment after the operating cycle based on the predicted risk state includes: when the predicted risk state includes at least one of the first risk states, based on a relationship between the number of the predicted risk states and a first quantity threshold, determining one of the first risk states as the target risk state, wherein the first risk state is a risk state in the preset risk states and the corresponding risk level is higher than the first risk threshold; when the predicted risk state does not include the first risk state, based on a relationship between the number of the predicted risk states and a second quantity threshold, determining one of the second risk states as the target risk state, wherein the second risk state is a risk state in the preset risk states other than the first risk state.
[0008] Optionally, the first risk state includes a medium-risk state and a high-risk state, and the risk level corresponding to the medium-risk state is lower than the risk level corresponding to the high-risk state; and according to the relationship between the number of the predicted risk states and a first quantity threshold, determining one of the first risk states as the target risk state includes: when the number of the predicted risk states is higher than the first quantity threshold, determining the high-risk state as the target risk state; when the number of the predicted risk states is not higher than the first quantity threshold, determining the medium-risk state as the target risk state.
[0009] Optionally, the second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state; and according to the relationship between the number of the predicted risk states and the second quantity threshold, determining one of the second risk states as the target risk state includes: when the number of the predicted risk states is higher than the second quantity threshold, determining the low risk state as the target risk state; when the number of the predicted risk states is not higher than the second quantity threshold, determining the good state as the target risk state.
[0010] Optionally, the risk level corresponding to the target risk state is higher than a second risk threshold; after predicting the target risk state of the terminal device at a future moment after the operating cycle based on the predicted risk state, it also includes: in response to receiving a payment request initiated by the terminal device, sending product information and payment information to the terminal device through the user identity module SIM server, and the product information and payment information are used to be displayed on the terminal device; receiving the verification result of the payment key sent by the SIM server and the confirmation information of the payment information by the user to which the terminal device belongs; verifying the confirmation information to obtain the verification result of the confirmation information; generating a payment result based on the verification result of the payment key and the verification result of the confirmation information, and sending the payment result to the terminal device.
[0011] Optionally, determining the threat level of each threat event includes: determining the priority, severity and credibility of the threat event for each threat event; and determining the threat level of the threat event based on the priority, severity and credibility of the threat event.
[0012] Optionally, determining the priority, severity and credibility of the threat event for each threat event includes: determining, for each threat event, a target event type to which the threat event belongs; determining the priority, severity and credibility corresponding to the target event type; and determining the priority, severity and credibility of the threat event based on the priority, severity and credibility corresponding to the target event type.
[0013] Optionally, the priority is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score; the determining the threat level of the threat event by combining the priority, severity and credibility of the threat event includes: fusing the first score, the second score and the third score according to the weights corresponding to the priority, the severity and the credibility to obtain a total score; determining the threat level of the threat event according to the score range of the total score, wherein each threat level has a corresponding score range.
[0014] In a second aspect, the present application provides a risk prediction device for a terminal device, the device comprising: an event determination module, used to determine whether a threat event occurs in the terminal device during an operation cycle; a level determination module, used to determine the threat level of each threat event when at least one threat event occurs, wherein the threat level indicates the degree of threat posed by the threat event to the security of the terminal device; a state determination module, used to input the threat level of each threat event as an observation value into a hidden Markov model to obtain a predicted risk state output by the hidden Markov model; and a prediction module, used to predict, based on the predicted risk state, a target risk state of the terminal device at a future moment after the operation cycle.
[0015] Optionally, the parameters of the hidden Markov model include a triplet (π, A, B); wherein: π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment; A is the state transition probability matrix, including the probability of transition between each preset risk state; B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time.
[0016] Optionally, the prediction module includes: a first determination unit for determining, when the predicted risk state includes at least one of the first risk states, one of the first risk states as the target risk state based on a relationship between the number of the predicted risk states and a first quantity threshold, wherein the first risk state is a risk state in the preset risk states and the corresponding risk level is higher than the first risk threshold; and a second determination unit for determining, when the predicted risk state does not include the first risk state, one of the second risk states as the target risk state based on a relationship between the number of the predicted risk states and a second quantity threshold, wherein the second risk state is a risk state other than the first risk state in the preset risk states.
[0017] Optionally, the first risk state includes a medium-risk state and a high-risk state, and the risk level corresponding to the medium-risk state is lower than the risk level corresponding to the high-risk state; the first determination unit is specifically used to: when the number of the predicted risk states is higher than the first quantity threshold, determine the high-risk state as the target risk state; when the number of the predicted risk states is not higher than the first quantity threshold, determine the medium-risk state as the target risk state.
[0018] Optionally, the second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state; the second determination unit is specifically used to: when the number of the predicted risk states is higher than the second quantity threshold, determine the low risk state as the target risk state; when the number of the predicted risk states is not higher than the second quantity threshold, determine the good state as the target risk state.
[0019] Optionally, the risk level corresponding to the target risk state is higher than a second risk threshold; the device also includes: a sending module, used to send product information and payment information to the terminal device through the user identity module SIM server in response to receiving a payment request initiated by the terminal device, and the product information and payment information are used to be displayed on the terminal device; a receiving module, used to receive the verification result of the payment key sent by the SIM server and the confirmation information of the payment information by the user to which the terminal device belongs; a verification module, used to verify the confirmation information and obtain the verification result of the confirmation information; a generation module, used to generate a payment result based on the verification result of the payment key and the verification result of the confirmation information; the sending module is also used to send the payment result to the terminal device.
[0020] Optionally, the level determination module includes: a third determination unit, used to determine the priority, severity and credibility of the threat event for each threat event; and a fourth determination unit, used to determine the threat level of the threat event in combination with the priority, severity and credibility of the threat event.
[0021] Optionally, the third determination unit is specifically used to: determine, for each threat event, the target event type to which the threat event belongs; determine the priority, severity and credibility corresponding to the target event type; and determine the priority, severity and credibility of the threat event based on the priority, severity and credibility corresponding to the target event type.
[0022] Optionally, the priority is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score; the fourth determination unit is specifically used to: merge the first score, the second score and the third score according to the weights corresponding to the priority, the severity and the credibility to obtain a total score; determine the threat level of the threat event according to the score range of the total score, wherein each threat level has a corresponding score range.
[0023] In a third aspect, the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the first aspect.
[0024] In a fourth aspect, the present application provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the method described in the first aspect of the embodiment of the present application.
[0025] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.
[0026] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:
[0027] By determining whether a threat event occurs in the terminal device during the operation cycle, when at least one threat event occurs, the threat level of each threat event is determined, wherein the threat level represents the degree of threat to the security of the terminal device caused by the threat event, and the threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain the predicted risk state output by the hidden Markov model, and according to the predicted risk state, the target risk state of the terminal device at a future moment after the operation cycle is predicted, thereby realizing the prediction of the target risk state of the terminal device at a future moment after the operation cycle according to the threat events occurring in the terminal device during the operation cycle, so that when there is a security risk in the terminal device, the corresponding strategy can be adopted in time to stop the loss, so as to reduce the user's loss and safeguard the user's interests, and by using the big data model such as the hidden Markov model to realize risk prediction, the accuracy of risk prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0029] Figure 1 A schematic diagram of a process flow of a risk prediction method for a terminal device provided in an embodiment of the present application;
[0030] Figure 2 A schematic diagram of a flow chart of another method for predicting risk of a terminal device provided in an embodiment of the present application;
[0031] Figure 3 A schematic diagram of a flow chart of another method for predicting risk of a terminal device provided in an embodiment of the present application;
[0032] Figure 4 An example diagram of a method for determining a target risk state according to a predicted risk state provided in an embodiment of the present application;
[0033] Figure 5 A schematic diagram of a flow chart of another method for predicting risk of a terminal device provided in an embodiment of the present application;
[0034] Figure 6 A flowchart of a method for implementing a risk control management strategy provided in an embodiment of the present application;
[0035] Figure 7 A schematic diagram of a pop-up window including product information and payment information provided in an embodiment of the present application;
[0036] Figure 8 A schematic diagram of the structure of a risk prediction device for a terminal device provided in an embodiment of the present application;
[0037] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0038] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0039] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0040] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.
[0041] Before users make online payments, how to predict the potential risks of the terminal devices used by users in order to reduce user losses and protect user interests is an urgent problem to be solved.
[0042] In response to the above problems, the present application proposes the following technical concepts: determining whether a threat event occurs in a terminal device during an operation cycle; in the event of at least one threat event, determining the threat level of each threat event, wherein the threat level indicates the degree of threat posed by the threat event to the security of the terminal device; taking the threat level of each threat event as an observation value, inputting the hidden Markov model, and obtaining a predicted risk state output by the hidden Markov model; predicting the target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state, thereby realizing the prediction of the target risk state of the terminal device at a future moment after the operation cycle based on the threat events that occurred in the terminal device during the operation cycle, so that when there is a security risk in the terminal device, the corresponding strategy can be adopted in time to stop the loss, so as to reduce user losses and safeguard user interests, and by using the hidden Markov model, a big data model, to realize risk prediction, the accuracy of risk prediction is improved.
[0043] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0044] First combine Figure 1 , the risk prediction method for the terminal device provided in the embodiment of the present application is described. Figure 1 A flowchart of a risk prediction method for a terminal device provided in an embodiment of the present application.
[0045] It should be noted that the risk prediction method for a terminal device provided in the embodiment of the present application can be executed by a risk prediction device of the terminal device, wherein the risk prediction device of the terminal device can be an application software in the terminal device that can realize online payment, or the server of the application software, and the present application does not limit this. The various embodiments of the present application take the risk prediction device of the terminal device as the server of the application software as an example for explanation. Among them, the various embodiments of the present application refer to the application software as payment software, and the server as payment server. Among them, the payment software can be shopping application software, communication application software, telephone bill payment application software, etc., and the present application does not limit this.
[0046] like Figure 1 As shown, the risk prediction method of the terminal device includes the following steps 101-104.
[0047] Step 101, determining whether a threat event occurs in a terminal device during an operation cycle.
[0048] Among them, the terminal device can be a device used by users to make online payments, such as mobile phones, computers, wearable devices, etc., and this application does not impose any restrictions on this.
[0049] Among them, the operating cycle is the operating cycle of the terminal equipment, which can be two months, one month, half a month, 5 days, 10 days, etc., and can be set as needed, and this application does not impose any restrictions on this.
[0050] Among them, the operating cycle in the embodiment of the present application may refer to one operating cycle or multiple operating cycles, and the present application does not impose any restrictions on this.
[0051] Among them, a threat event is an event that threatens the security of the terminal device.
[0052] In one embodiment, step 101 may be implemented in the following manner: acquiring historical operation data of the terminal device in one or more operation cycles, and determining whether a threat event occurs to the terminal device in the one or more operation cycles based on the historical operation data.
[0053] The historical operation data may include operation data of the terminal device in one or more operation cycles before the current time, and the operation data includes data of each event processed by the terminal device during the operation process.
[0054] In one embodiment, the risk of the terminal device may be predicted each time the payment software is started. Accordingly, the historical operation data may include the operation data of the terminal device in one or more operation cycles before the payment software is started.
[0055] In one embodiment, the payment software is installed in the terminal device, and a data probe can be pre-embedded in the payment software to collect the operation data of the terminal device at a certain preset frequency and upload the collected operation data to the payment service end. The data probe can start collecting the operation data when the payment software is started, or when the payment software is ready to make an online payment during operation, or at other set times.
[0056] In one embodiment, determining whether a threat event occurs in a terminal device during an operation cycle based on historical operation data includes: judging whether an event of a set event type occurs in the terminal device based on historical operation data, and determining an event of the set event type that occurs in the terminal device during the operation cycle as a threat event.
[0057] Among them, the set event type can be set as needed, for example, it can include: e_inject (injection), e_devicesreuse (device reuse), e_location (location fraud), e_debug (debugging behavior), e_emulator (emulator), e_illegalapp (illegal application), e_speed (system acceleration), e_gameplugin (game plug-in), e_hostfraud (domain name fraud), root (obtaining root directory permissions), risk_frame (risk framework), risk_app (risk application), risk_process (risk process), sys_conf (system configuration), IP address change, BS (base station change), call (call abnormality), noun (SMS abnormality), etc.
[0058] Step 102: when at least one threat event occurs, determine the threat level of each threat event, wherein the threat level indicates the degree of threat of the threat event to the security of the terminal device.
[0059] It is understandable that a terminal device may not experience a threat event during its operation cycle. In this case, it can be determined that there is no security risk to the terminal device. In the event that a threat event occurs during its operation cycle, the number of threat events may be one or more. In this case, risk prediction for the terminal device can be performed through steps 102-104.
[0060] In one embodiment, the threat level of each event type of threat event can be set in advance according to the degree of threat posed by each event type of threat event to the security of the terminal device. Therefore, when it is determined that at least one threat event has occurred in the terminal device during its operation cycle, for each threat event, the threat level of each event type of threat event can be queried according to the event type to which the threat event belongs to determine the threat level of the threat event.
[0061] Step 103: The threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain a predicted risk state output by the hidden Markov model.
[0062] Among them, the predicted risk state output by the hidden Markov model is the risk state of the terminal device predicted by the hidden Markov model, which may include the risk state of the terminal device during the operation cycle, or may include the risk state of the terminal device during the operation cycle and a time period after the operation cycle.
[0063] In the embodiments of the present application, the Viterbi algorithm (Viterbi algorithm, a dynamic programming algorithm) of the hidden Markov model can be used to estimate the risk state of the terminal device. Among them, the hidden Markov model is a statistical learning model that can be used for labeling problems. The model generates an observable observation random sequence through a hidden state random sequence and has a wide range of applications in speech recognition, natural language processing, bioinformatics, pattern recognition, network security and other fields.
[0064] It can be understood that the change of the risk state of the terminal device, which is composed of several risk states and transition probabilities, is a Markov chain. The threat events occurring in the terminal device are a random process. Each threat event will have a certain impact on the transfer of the risk state of the terminal device. Threat events of different threat levels have different impacts. In this way, a hidden Markov model is formed between the sequence of threat levels of each threat event and the risk state of the terminal device.
[0065] Among them, the hidden Markov model can be composed of a hidden state, an observable state, and a triple (π, A, B).
[0066] Among them, the implicit state can include multiple preset risk states, and different risk states correspond to different risk levels, such as good state, low risk state, medium risk state, and high risk state with gradually increasing risk levels. That is, S = {G, L, M, H}, where S represents the set of implicit states, G represents good state, L represents low risk state, M represents medium risk state, and H represents high risk state. Assume that the risk state of the terminal device at a certain time t is q t , then q t ∈S, the risk state of the terminal device at multiple times constitutes a risk state sequence.
[0067] The observable state may include multiple observation values, each of which is a preset threat level, wherein the preset threat level may be a threat level pre-set for a threat event belonging to each set event type, that is, V = {v1, v2, ..., v N}, where V represents the set of observable states, that is, the set of observed values, and v N represents the Nth observation value, where N is an integer greater than 1. Assume that the threat level of the threat event occurring at a certain time t is o t , then t ∈V, the threat levels of threat events occurring at multiple moments in the terminal device constitute an observation sequence.
[0068] Among them, π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment; A is the state transition probability matrix, including the probability of conversion between each preset risk state; B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time. Among them, taking the element of the jth column in the initial state probability matrix as an example, it represents the probability of being in the jth preset risk state at the initial moment. Taking the element of the i-th row and j-th column in the state transition probability matrix as an example, it represents the probability of transferring to the j-th preset risk state at the next moment under the condition of being in the i-th preset risk state at the current moment. Taking the element of the i-th row and j-th column in the observation probability matrix as an example, it represents the probability of generating the j-th preset threat level under the condition of being in the i-th preset risk state at any moment.
[0069] π and A determine the risk state sequence, and B determines the observation sequence, so the hidden Markov model can be represented using a ternary symbol, and π, A, and B are called the three elements of the hidden Markov model.
[0070] In the embodiment of the present application, the forward-backward (Baum-Welch) algorithm in the related art can be used to perform parameter estimation, obtain the values of the three-element symbols π, A, and B in the triplet, and implement the learning of the hidden Markov model. Then, the risk state of the terminal device can be predicted through the learned hidden Markov model.
[0071] By taking the threat level of at least one threat event occurring in the operation cycle of the terminal device as an observation value and inputting it into the hidden Markov model, the hidden Markov model can output at least one predicted risk state, thereby predicting the risk state of the terminal device through the hidden Markov model. Among them, the number of risk states in which the terminal device is located can be the same as the number of threat events occurring in the operation cycle. In the case where there is only one threat event occurring in the operation cycle, the threat level of one threat event can be used as an observation value and input into the hidden Markov model, and the hidden Markov model can output a predicted risk state; in the case where there are multiple threat events sent in the operation cycle, the threat levels of multiple threat events can be used as multiple observation values, and multiple observation values can form an observation sequence and be input into the hidden Markov model, so that the hidden Markov model can output a risk state sequence, and the risk state sequence includes multiple predicted risk states.
[0072] Step 104, predicting the target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state.
[0073] The future moment may be the current moment after the operation cycle, or any moment within a time period after the current moment, and this application does not impose any restrictions on this.
[0074] In one embodiment, the target risk state of the terminal device at a future moment after the operation cycle can be predicted based on the predicted risk state output by the hidden Markov model and the number of predicted risk states, that is, the number of threat events occurring in the terminal device during the operation cycle.
[0075] For example, when multiple threat events occur in the terminal device during its operation cycle, the number of predicted risk states output by the hidden Markov model is also multiple, and the predicted risk state with the largest number of occurrences can be determined as the target risk state.
[0076] In summary, the risk prediction method for terminal devices provided in the embodiment of the present application determines whether a threat event occurs during the operation cycle of the terminal device. When at least one threat event occurs, the threat level of each threat event is determined, and the threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain the predicted risk state output by the hidden Markov model. According to the predicted risk state, the target risk state of the terminal device at a future time after the operation cycle is predicted, thereby realizing the prediction of the target risk state of the terminal device at a future time after the operation cycle according to the threat events that occurred during the operation cycle of the terminal device, so that when there is a security risk in the terminal device, the corresponding strategy can be adopted in time to stop the loss, so as to reduce user losses and safeguard user interests. Risk prediction is realized by utilizing a big data model such as a hidden Markov model, thereby improving the accuracy of risk prediction.
[0077] Through the above analysis, it can be known that the threat level of each threat event can be determined in the embodiment of the present application. Figure 2 , the process of determining the threat level of each threat event in the risk prediction method for the terminal device provided in the embodiment of the present application is described.
[0078] Figure 2 A flowchart of another risk prediction method for a terminal device provided in an embodiment of the present application.
[0079] like Figure 2 As shown, the risk prediction method of the terminal device includes the following steps 201-205.
[0080] Step 201, determining whether a threat event occurs in a terminal device during an operation cycle.
[0081] The specific implementation process and principle of step 201 may refer to the description of other embodiments and will not be repeated here.
[0082] Step 202: When at least one threat event occurs, determine the priority, severity, and credibility of each threat event.
[0083] Among them, priority indicates the priority level of threat event processing; severity indicates the severity and importance of threat event; credibility indicates the credibility of whether the threat event actually occurred.
[0084] In one embodiment, step 202 can be implemented in the following manner: for each threat event, determine the target event type to which the threat event belongs; determine the priority, severity and credibility corresponding to the target event type; and determine the priority, severity and credibility of the threat event based on the priority, severity and credibility corresponding to the target event type.
[0085] The following describes the methods for determining the priority, severity, and credibility of threat events based on the target event type.
[0086] In one embodiment, the priority corresponding to each set event type can be preset, so that after determining the target event type to which the threat event belongs, the priority corresponding to the target event type can be queried, and then the priority corresponding to the target event type can be determined as the priority of the threat event. The priority corresponding to each set event type can be set according to the principle that the greater the threat level of the threat event, the higher the priority corresponding to the event type.
[0087] For example, the priorities corresponding to the set event types may be shown in the following Table 1. In Table 1, a score between 0 and 1 indicates the priority level, and the higher the score, the higher the priority.
[0088] Table 1 Priorities corresponding to each set event type
[0089]
[0090] Referring to Table 1, it can be seen that each set event type can be divided into three categories: threat class, environment class, and behavior class. Among them, for threat events belonging to the threat class, since the threat level is relatively high, the event type under the threat class can be set to a higher priority, while most threat events belonging to the environment class can be set to a lower priority because the threat level is relatively low. Among the event types under the threat class, the priority corresponding to the "e_inject (injection)" and "e_location (location fraud)" types is relatively high, because the threat level of the threat events belonging to the "injection" type is greater. Among the event types under the environment class, since the threat level of the "root" type threat event is greater, the priority corresponding to the "root" type is higher, and the priority corresponding to other event types is lower. For example, the "game plug-in" type belongs to the environment class, but the threat event of this event type basically does not pose a threat to online payment, so it does not represent an attack on the terminal device, so its priority can be set to be lower.
[0091] In one embodiment, each event type can be divided into one or more different subdivision types according to the content of threat events of different event types, and the severity of the threat event can be determined according to the subdivision type to which the threat event belongs. In Table 2, the severity is represented by a score between 0 and 1, and the higher the score, the higher the severity. Taking the subdivision type "dlopen" in Table 2 as an example, the more times the threat events of this subdivision type have occurred, the higher the severity corresponding to this subdivision type. Taking the subdivision type "chook" in Table 2 as an example, the priority corresponding to this subdivision type can be set based on experience.
[0092] Table 2 Severity of each subdivision type
[0093]
[0094] In one embodiment, the credibility corresponding to each set event type can be pre-set, so that after determining the target event type to which the threat event belongs, the credibility corresponding to the target event type can be queried, and then the credibility corresponding to the target event type can be determined as the credibility of the threat event. The credibility corresponding to each set event type can be set according to the principle that the greater the false alarm rate of the threat event, the lower the credibility corresponding to the event type.
[0095] For example, the credibility corresponding to each set event type may be shown in the following Table 3. In Table 3, a score between 0 and 1 indicates the credibility, and the higher the score, the higher the credibility.
[0096] Table 3 Credibility of each set event type
[0097]
[0098] Referring to Table 3, it can be seen that for threat events with a relatively high false alarm rate, such as threat events of the "e_illegalapp (illegal application)" type, since the false alarm rate is relatively high, the credibility corresponding to the event type can be set to be lower.
[0099] Step 203, determining the threat level of the threat event in combination with the priority, severity and credibility of the threat event, wherein the threat level indicates the degree of threat posed by the threat event to the security of the terminal device.
[0100] In one embodiment, the priority of the threat event is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score. Step 203 can be implemented in the following manner: the first score, the second score, and the third score are merged by weights corresponding to the priority, severity, and credibility to obtain a total score; the threat level of the threat event is determined according to the score range of the total score, wherein each threat level has a corresponding score range.
[0101] In one embodiment, the first score, the second score and the third score can be combined according to the formula V1=α1*p+α2*s+α3*r to obtain a total score, wherein V1 is the total score; α1, α2, α3 are the weights corresponding to the priority, severity and credibility respectively; p is the first score indicating the priority; s is the second score indicating the severity; and r is the third score indicating the credibility.
[0102] In order to determine the weights corresponding to the priority, severity, and credibility, multiple experiments can be conducted to make the total score more distinguishable and the score distribution of the total score closer to the actual business. For example, multiple experiments can be conducted to determine that α1, α2, and α3 are 6, 3, and 1, respectively.
[0103] In one embodiment, the total score may be rounded down to obtain the threat level of the threat event.
[0104] By combining the priority, severity and credibility of each threat event to determine the threat level of the threat event, it is possible to comprehensively consider multiple aspects and more accurately determine the threat level of the threat event.
[0105] Step 204: The threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain a predicted risk state output by the hidden Markov model.
[0106] Step 205: predicting the target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state.
[0107] The specific implementation process and principle of steps 204-205 may refer to the description of other embodiments and will not be repeated here.
[0108] Therefore, the risk prediction method for a terminal device provided in an embodiment of the present application determines at least one threat event occurring during an operation cycle of the terminal device, determines the priority, severity and credibility of the threat event for each threat event, and determines the threat level of the threat event in combination with the priority, severity and credibility of the threat event, wherein the threat level indicates the degree of threat posed by the threat event to the security of the terminal device, and uses the threat level of each threat event as an observation value, which is input into a hidden Markov model to obtain a predicted risk state output by the hidden Markov model, and predicts the target risk state of the terminal device at a future time after the operation cycle based on the predicted risk state, thereby predicting the target risk state of the terminal device at a future time after the operation cycle based on the threat events occurring during the operation cycle of the terminal device, so that when there is a security risk in the terminal device, a corresponding strategy can be promptly adopted to stop the loss, thereby reducing user losses and safeguarding user interests, and by using a big data model such as a hidden Markov model to achieve risk prediction, the accuracy of risk prediction is improved. In addition, by combining the priority, severity and credibility of each threat event to determine the threat level of the threat event, we can take multiple aspects into consideration and more accurately determine the threat level of the threat event, thereby further improving the accuracy of risk prediction.
[0109] Through the above analysis, it can be known that in the embodiment of the present application, the target risk state of the terminal device at a future moment after the operation cycle can be predicted based on the predicted risk state output by the hidden Markov model. Figure 3 , in the risk prediction method for a terminal device provided in an embodiment of the present application, the process of predicting the target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state is further explained.
[0110] Figure 3 A flowchart of another risk prediction method for a terminal device provided in an embodiment of the present application.
[0111] like Figure 3 As shown, the risk prediction method of the terminal device includes the following steps 301-305.
[0112] Step 301, determining whether a threat event occurs in a terminal device during an operation cycle.
[0113] Step 302: when at least one threat event occurs, determine the threat level of each threat event, wherein the threat level indicates the degree of threat of the threat event to the security of the terminal device.
[0114] Step 303: The threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain a predicted risk state output by the hidden Markov model.
[0115] The specific implementation process and principle of steps 301-303 may refer to the description of other embodiments and will not be repeated here.
[0116] Among them, the risk state determined in step 303 may include one or more. During the operation cycle, if the number of threat events that occur is multiple, then using the hidden Markov model, according to the observation sequence composed of the threat level of the threat event, the number of risk states of the terminal device obtained is also multiple. In actual situations, if the terminal device is attacked, multiple threat events are required to form an attack tree. In the embodiment of the present application, when the risk state of the terminal device obtained in step 304 includes one or more, the target risk state of the terminal device can be determined by the following steps 305-306.
[0117] Step 304: when the predicted risk state includes at least one of the first risk states, determine one of the first risk states as a target risk state according to a relationship between the number of the predicted risk states and a first number threshold.
[0118] The first risk state is a risk state in which the corresponding risk level in the preset risk state is higher than the first risk threshold.
[0119] The preset risk state is a risk state included in the implicit state set of the hidden Markov model.
[0120] The number of predicted risk states is the number of predicted risk states output by the hidden Markov model, that is, the number of threat events that occurred during the operation cycle.
[0121] The first risk threshold can be set as needed, and this application does not impose any restrictions on this.
[0122] The first quantity threshold can be set as needed, and this application does not limit this. For example, it can be set to 3 or 5.
[0123] For example, assuming that the preset risk state includes a good state, a low risk state, a medium risk state, and a high risk state with gradually increasing risk levels. Then the first risk state may include a medium risk state and a high risk state. In the case where the predicted risk state output by the hidden Markov model includes at least one of a risk state and a high risk state, one of the medium risk state and the high risk state may be determined as the target risk state of the terminal device based on the relationship between the number of predicted risk states and the first quantity threshold.
[0124] In one embodiment, when the first risk state includes a medium-risk state and a high-risk state, and the risk level corresponding to the medium-risk state is lower than the risk level corresponding to the high-risk state, one of the first risk states is determined as the target risk state based on the relationship between the number of predicted risk states and a first quantity threshold. This may include: when the number of predicted risk states is higher than the first quantity threshold, determining the high-risk state as the target risk state; and when the number of predicted risk states is not higher than the first quantity threshold, determining the medium-risk state as the target risk state.
[0125] Step 305: when the predicted risk state does not include the first risk state, one of the second risk states is determined as a target risk state according to the relationship between the number of predicted risk states and the second quantity threshold.
[0126] The second risk state is other risk states among the preset risk states except the first risk state.
[0127] The second quantity threshold can be set as needed, and this application does not limit this. For example, it can be set to 3 or 5, etc. Among them, the first quantity threshold and the second quantity threshold can be the same or different, and this application does not limit this.
[0128] For example, assuming that the preset risk states include a good state, a low risk state, a medium risk state, and a high risk state with gradually increasing risk levels, the first risk state may include a medium risk state and a high risk state, and the second risk state may include a good state and a low risk state. In the case where the predicted risk state output by the hidden Markov model does not include a medium risk state or a high risk state, one of the good state and the low risk state may be determined as the target risk state of the terminal device based on the relationship between the number of predicted risk states and the second quantity threshold.
[0129] In one embodiment, when the second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state, one of the second risk states is determined as the target risk state based on the relationship between the number of predicted risk states and the second quantity threshold. This may include: when the number of predicted risk states is higher than the second quantity threshold, determining the low risk state as the target risk state; when the number of predicted risk states is not higher than the second quantity threshold, determining the good state as the target risk state.
[0130] Combine the following Figure 4 Taking the first quantity threshold and the second quantity threshold as an example, the process of predicting the target risk state of the terminal device at a future moment after the operation cycle according to each predicted risk state and the number of predicted risk states is described by way of example. Figure 4In the figure, F0 represents the first risk threshold, and M0 represents the first quantity threshold and the second quantity threshold.
[0131] refer to Figure 4 , assuming that the preset risk status includes a good status, a low risk status, a medium risk status and a high risk status. Among them, the risk levels corresponding to the good risk status and the low risk status are lower than the first risk threshold F0, and the risk levels corresponding to the medium risk status and the high risk status are higher than the first risk threshold F0. Then, the first risk status may include the medium risk status and the high risk status, and the second risk status may include the good status and the high risk status.
[0132] After the predicted risk state is obtained through the hidden Markov model, when the predicted risk state includes at least one of the medium risk state and the high risk state, one of the medium risk state and the high risk state can be determined as the target risk state according to the relationship between the number of predicted risk states and M0. Wherein, when the number of predicted risk states is higher than M0, the high risk state can be determined as the target risk state; when the number of predicted risk states is not higher than M0, the medium risk state can be determined as the target risk state.
[0133] In the case where the predicted risk state does not include the medium risk state and does not include the high risk state, one of the good state and the low risk state can be determined as the target risk state according to the relationship between the number of predicted risk states and M0. In particular, in the case where the number of predicted risk states is higher than M0, the low risk state can be determined as the target risk state; in the case where the number of predicted risk states is not higher than M0, the good state can be determined as the target risk state.
[0134] Take M0 as 3 as an example. Assume that 5 threat events occur in the terminal device within one operation cycle, and the threat level is represented by a score. The threat levels of the 5 threat events arranged in chronological order are [9, 5, 7, 3, 3]. The optimal risk state path of the terminal device predicted by the Viterbi algorithm of the hidden Markov model is [M, M, L, G, G], that is, the predicted risk state includes M, M, L, G, G. Among them, G represents a good state, L represents a low risk state, M represents a medium risk state, and H represents a high risk state. Since the predicted risk state includes M and H, and the number of predicted risk states is 5, which is greater than M0, it can be determined that the target risk state is H.
[0135] Therefore, the predicted risk state and the number of predicted risk states obtained according to the hidden Markov model prediction are achieved, and the target risk state of the terminal device at a future moment after the operation cycle is accurately predicted.
[0136] It is understandable that on a terminal device in a high-risk state, the user's online payment page may be covered or simulated clicked due to a Trojan or other reasons, so that the user is completely unaware of the payment process of the terminal device, resulting in uninformed deductions. After the user knows that the fee has been deducted, he may file a complaint through the customer service of the payment software. In the embodiment of the present application, the prediction accuracy of the risk prediction method can be verified according to the complaint situation of terminal devices in different risk states.
[0137] Referring to Table 4, the device information of the terminal devices that generated online payment orders within an operating cycle can be collected, and deduplication can be performed based on the device information to obtain the number of terminal devices that performed online payment within an operating cycle. Based on the historical operating data of these deduplicated terminal devices within an operating cycle, the risk prediction method for terminal devices provided in the embodiment of the present application is used to predict the target risk status of each terminal device, and the number of terminal devices corresponding to each target risk status and the number of online payment orders generated are obtained.
[0138] In addition, considering that complaints may cause time delays, the uninformed complaint data of online payment orders within the operating cycle and a period of time thereafter can be collected to obtain the number of uninformed complaints and the uninformed complaint rate of terminal devices corresponding to different target risk states.
[0139] Referring to Table 4, the risk levels corresponding to good state, low risk state, medium risk state, and high risk state gradually increase, and the higher the risk level, the higher the corresponding uninformed complaint rate. Therefore, the risk prediction method for terminal devices provided in the embodiment of the present application can accurately predict the security risk of terminal devices.
[0140] Table 4 Uninformed complaints of terminal devices with different target risk status
[0141]
[0142] It is understandable that by predicting the security risks of terminal devices, the next time the terminal device generates a payment behavior, the corresponding strategy can be used to manage the risk of the terminal device during the payment process to reduce user losses, safeguard user interests, and ensure the safety of user funds. Figure 5 , in the risk prediction method for the terminal device provided in the embodiment of the present application, the risk control management strategy when the terminal device initiates a payment request is explained.
[0143] Figure 5 A flowchart of another risk prediction method for a terminal device provided in an embodiment of the present application.
[0144] like Figure 5As shown, the risk prediction method of the terminal device includes the following steps 501-508.
[0145] Step 501, determining whether a threat event occurs in a terminal device during an operation cycle.
[0146] Step 502: when at least one threat event occurs, determine the threat level of each threat event, wherein the threat level indicates the degree of threat of the threat event to the security of the terminal device.
[0147] Step 503: The threat level of each threat event is used as an observation value and input into the hidden Markov model to obtain a predicted risk state output by the hidden Markov model.
[0148] Step 504: predict the target risk state of the terminal device at a future moment after the operation cycle based on the predicted risk state.
[0149] The specific implementation process and principle of steps 501-504 may refer to the description of other embodiments and will not be repeated here.
[0150] In an embodiment of the present application, when the terminal device is in different target risk states, different risk control management strategies can be used for risk control management. The following describes the risk control management strategy used when the risk level corresponding to the target risk state of the terminal device is higher than the second risk threshold. The second risk threshold can be set as needed, and the present application does not limit this.
[0151] Step 505, in response to receiving the payment request initiated by the terminal device, the commodity information and payment information are sent to the terminal device through the subscriber identity module SIM server, and the commodity information and payment information are used to be displayed on the terminal device.
[0152] Among them, product information is information related to the product that the user needs to purchase, such as product name, contact information, etc.
[0153] Payment information may include any information related to payment, such as payment amount and payment object.
[0154] SIM server is the background server of SIM card.
[0155] refer to Figure 6 , a represents the terminal device, b represents the payment server, and c represents the SIM server. In the embodiment of the present application, after the user selects the purchased product in the payment software and triggers the payment request, the payment software can send the payment request to the payment server (refer to Figure 6After receiving the payment request initiated by the terminal device, the payment service end may send the terminal device's phone number, product information, and payment information to the SIM service end (refer to Figure 6 Step 602 in the example above) is where the SIM server sends the product information and payment information to the terminal device via the phone number (see Figure 6 Then, the terminal device can display the product information and payment information (refer to step 603 in FIG. Figure 6 In addition, a reminder message for reminding the user to enter the payment key may be displayed on the terminal device (see step 604). Figure 6 By displaying the commodity information and payment information on the terminal device, the user can be reminded of payment to prevent uninformed deductions, reduce user losses, and safeguard user interests.
[0156] Among them, the product information and payment information can be displayed on the terminal device through a pop-up window. Thus, a strong reminder of the payment behavior of the terminal device can be given, so that the user knows in time that the terminal device is preparing to make an online payment.
[0157] Among them, the payment information may include multiple information available for users to select, as well as prompt information for users to confirm the payment information. Each information is displayed in the form of a pop-up window on the terminal device.
[0158] refer to Figure 7 For example, the display content of the pop-up window including product information and payment information can be as follows Figure 7 As shown. Among them, Figure 7 The information in the box in the upper middle part is the product information, and the information in the dotted box is the payment information.
[0159] Step 506: Receive the verification result of the payment key sent by the SIM server and the confirmation information of the payment information from the user of the terminal device.
[0160] In an embodiment of the present application, the user can enter the payment key on the terminal device and confirm the payment information to generate confirmation information of the payment information, so that the terminal device can send the payment key entered by the user and the confirmation information of the payment information to the SIM server (refer to Figure 6 Step 605 in the example above) verifies whether the payment key is correct by the SIM server (refer to Figure 6 The payment key verification result is sent to the payment server, and the payment information confirmation information is transparently transmitted to the payment server (refer to step 606 in FIG. Figure 6 607 in step 607).
[0161] Step 507: verify the confirmation information to obtain a verification result of the confirmation information.
[0162] refer to Figure 6 In step 608, the payment server may verify the confirmation information and obtain a verification result of the confirmation information. For example, if the payment information includes the payment amount, the confirmation information of the payment information may include the payment amount selected by the user. The payment server may compare the payment amount selected by the user with the actual amount to be paid by the user, and obtain a verification result of verification passed or verification failed according to whether the payment amount selected by the user is consistent with the actual amount to be paid by the user or not.
[0163] Step 508: Generate a payment result based on the verification result of the payment key and the verification result of the confirmation information, and send the payment result to the terminal device.
[0164] refer to Figure 6 In steps 609 and 610, the payment service end may generate a payment result based on the verification result of the payment key and the verification result of the confirmation information, and then send the payment result to the terminal device.
[0165] Among them, if the verification result of the payment key and the payment result of the confirmation information are both verified, a successful payment result can be obtained; if at least one of the verification result of the payment key and the payment result of the confirmation information is verified unsuccessful, a failed payment result can be obtained.
[0166] It should be noted that the risk control management strategy of the embodiment of the present application can be applied to the scenario where a terminal device in a high-risk state performs network payment confirmation through a super SIM server. In order to prevent the false triggering and phishing attacks of the super SIM (for example, by sending phishing information to the terminal device used by the user, inducing the user to mistakenly enter the super SIM password without knowing or paying attention, resulting in successful payment and financial loss, or the user mistakenly clicks on the order link on the payment page, triggering the SIM payment of the terminal device, and the user mistakenly enters the password to cause unnecessary ordering, etc.), the embodiment of the present application can optimize the process of calling the super SIM server for network payment confirmation, and use the SIM shield password (i.e., the payment key in the embodiment of the present application) and the payment information double authentication method to perform payment authentication.
[0167] Therefore, after receiving the payment request from the terminal device, the product information and payment information are sent to the terminal device through the SIM server to display the product information and payment information on the terminal device. This can remind the user to pay and prevent unknowing deductions. By double-verifying the payment key and payment information and generating the payment result based on the double verification result, it is possible to prevent social engineering attacks and false triggering to achieve online payment, reduce user losses and safeguard user interests.
[0168] Figure 8This is a schematic diagram of the structure of the risk prediction device of the terminal device provided in the embodiment of the present application. Figure 8 As shown, the risk prediction device 800 of the terminal device includes: an event determination module 810, a level determination module 820, a state determination module 830 and a prediction module 840.
[0169] The event determination module 810 is used to determine whether a threat event occurs in the terminal device during the operation cycle;
[0170] A level determination module 820 is used to determine the threat level of each threat event when at least one threat event occurs, wherein the threat level indicates the degree of threat of the threat event to the security of the terminal device;
[0171] The state determination module 830 is used to input the threat level of each threat event as an observation value into the hidden Markov model to obtain the predicted risk state output by the hidden Markov model;
[0172] The prediction module 840 predicts the target risk state of the terminal device at a future moment after the operation cycle according to the predicted risk state.
[0173] It should be noted that the risk prediction device 800 of the terminal device provided in the embodiment of the present application can execute the risk prediction method of the terminal device in the aforementioned embodiment. Among them, the risk prediction device of the terminal device can be an application software in the terminal device that can realize online payment, or the server of the application software, and the present application does not limit this. The various embodiments of the present application take the risk prediction device of the terminal device as the server of the application software as an example for explanation. Among them, the various embodiments of the present application refer to the application software as payment software, and the server as payment server. Among them, the payment software can be shopping application software, communication application software, telephone bill payment application software, etc., and the present application does not limit this.
[0174] In one embodiment, the parameters of the hidden Markov model include a triple (π, A, B); where:
[0175] π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment;
[0176] A is the state transition probability matrix, including the probability of transition between each preset risk state;
[0177] B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time.
[0178] In one embodiment, the prediction module 840 includes:
[0179] A first determining unit is used to determine, when the predicted risk state includes at least one of the first risk states, one of the first risk states as a target risk state according to a relationship between the number of the predicted risk states and a first number threshold, wherein the first risk state is a risk state in which the corresponding risk level among the preset risk states is higher than the first risk threshold;
[0180] The second determination unit is used to determine one of the second risk states as the target risk state based on the relationship between the number of predicted risk states and a second quantity threshold when the predicted risk state does not include the first risk state, wherein the second risk state is other risk state in the preset risk state except the first risk state.
[0181] In one embodiment, the first risk state includes a medium risk state and a high risk state, and the risk level corresponding to the medium risk state is lower than the risk level corresponding to the high risk state; the first determining unit is specifically configured to:
[0182] In the case where the number of predicted risk states is higher than a first number threshold, determining the high risk state as a target risk state;
[0183] When the number of predicted risk states is not higher than the first number threshold, the medium risk state is determined as the target risk state.
[0184] In one embodiment, the second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state; the second determining unit is specifically configured to:
[0185] In a case where the number of predicted risk states is higher than a second number threshold, determining the low risk state as the target risk state;
[0186] In a case where the number of predicted risk states is not higher than a second number threshold, a good state is determined as the target risk state.
[0187] In one embodiment, the risk level corresponding to the target risk state is higher than the second risk threshold, and the risk prediction device 800 of the terminal device further includes:
[0188] A sending module, configured to send commodity information and payment information to the terminal device through a user identity module SIM server in response to receiving a payment request initiated by the terminal device, wherein the commodity information and payment information are used to be displayed on the terminal device;
[0189] A receiving module, used to receive the verification result of the payment key sent by the SIM server and the confirmation information of the user of the terminal device on the payment information;
[0190] A verification module, used to verify the confirmation information and obtain a verification result of the confirmation information;
[0191] A generation module, used to generate a payment result according to the verification result of the payment key and the verification result of the confirmation information;
[0192] The sending module is also used to send the payment result to the terminal device.
[0193] In one embodiment, the level determination module 820 includes:
[0194] A third determination unit, for determining the priority, severity and credibility of each threat event;
[0195] The fourth determining unit is used to determine the threat level of the threat event based on the priority, severity and credibility of the threat event.
[0196] In one embodiment, the third determining unit is specifically configured to:
[0197] For each threat event, determine the event type to which the threat event belongs;
[0198] Determine the priority, severity, and credibility of the incident type;
[0199] Determine the priority, severity and credibility of the threat event based on the priority, severity and credibility of the event type.
[0200] In one embodiment, the priority is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score; the fourth determination unit is specifically configured to:
[0201] The first score, the second score and the third score are combined by weights corresponding to the priority, severity and credibility to obtain a total score;
[0202] The threat level of the threat event is determined according to the score interval of the total score, wherein each threat level has a corresponding score interval.
[0203] The risk prediction device for a terminal device provided in an embodiment of the present application may be used to execute the technical solution of the risk prediction method for a terminal device in the above-mentioned embodiment. Its implementation principle and technical effects are similar and will not be described in detail here.
[0204] The risk prediction device for a terminal device provided in an embodiment of the present application determines whether a threat event occurs in an operation cycle of the terminal device. When at least one threat event occurs, the device determines the threat level of each threat event, wherein the threat level indicates the degree of threat to the security of the terminal device posed by the threat event. The threat level of each threat event is used as an observation value and input into a hidden Markov model to obtain a predicted risk state output by the hidden Markov model. Based on the predicted risk state, the target risk state of the terminal device at a future moment after the operation cycle is predicted. This achieves prediction of the target risk state of the terminal device at a future moment after the operation cycle based on the threat events that occurred in the operation cycle of the terminal device. Therefore, when there is a security risk in the terminal device, a corresponding strategy can be adopted in time to stop the loss, thereby reducing user losses and safeguarding user interests. Risk prediction is achieved by utilizing a big data model such as a hidden Markov model, thereby improving the accuracy of risk prediction.
[0205] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the event determination module 810 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above event determination module 810. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.
[0206] In order to implement the above-mentioned embodiments, the present application also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the risk prediction method for a terminal device proposed in the aforementioned embodiments of the present application.
[0207] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the risk prediction method of the terminal device as described in the first aspect embodiment.
[0208] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the method described in the first aspect of the embodiment when executed by a processor.
[0209] Fig. 9 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Fig. 9 The electronic device 12 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0210] like Fig. 9 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that connects various system components (including the memory 28 and the processing unit 16).
[0211] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.
[0212] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.
[0213] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig. 9 Not shown, often called a "hard drive").
[0214] although Fig. 9 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.
[0215] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0216] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. Fig. 9 As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0217] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing the risk prediction method of the terminal device mentioned in the above embodiment.
[0218] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0219] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A risk prediction method for a terminal device, characterized in that: The method comprises: Determine whether a threat event occurs during the operation cycle of the terminal device; In the event of at least one threat event, determining a threat level of each threat event, wherein the threat level indicates the degree of threat of the threat event to the security of the terminal device; The threat level of each threat event is used as an observation value and input into a hidden Markov model to obtain a predicted risk state output by the hidden Markov model; According to the predicted risk state, predict the target risk state of the terminal device at a future moment after the operation cycle; when the risk level corresponding to the target risk state is higher than a second risk threshold, after receiving the payment request of the terminal device, send the commodity information and the payment information to the terminal device through the SIM server, perform double verification on the payment key and the payment information, and generate the payment result according to the double verification result, After receiving the payment request from the terminal device, sending the commodity information and the payment information to the terminal device through the SIM server, performing double verification on the payment key and the payment information, and generating the payment result according to the double verification result, including: In response to receiving a payment request initiated by the terminal device, sending commodity information and payment information to the terminal device through a subscriber identity module SIM server, wherein the commodity information and payment information are used to be displayed on the terminal device; Receiving the verification result of the payment key sent by the SIM server and the confirmation information of the payment information by the user of the terminal device; Verifying the confirmation information to obtain a verification result of the confirmation information; A payment result is generated according to the verification result of the payment key and the verification result of the confirmation information, and the payment result is sent to the terminal device.
2. The method according to claim 1, characterized in that The parameters of the hidden Markov model include a triple (π, A, B); wherein: π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment; A is the state transition probability matrix, including the probability of transition between each preset risk state; B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time.
3. The method according to claim 1, characterized in that: The step of predicting a target risk state of the terminal device at a future time after the operation cycle according to the predicted risk state includes: In a case where the predicted risk state includes at least one of the first risk states, one of the first risk states is determined as the target risk state according to a relationship between the number of the predicted risk states and a first number threshold, wherein the first risk state is a risk state in the preset risk states, the corresponding risk level of which is higher than the first risk threshold; In the case that the predicted risk state does not include the first risk state, one of the second risk states is determined as the target risk state based on the relationship between the number of the predicted risk states and a second quantity threshold, wherein the second risk state is a risk state other than the first risk state in the preset risk state.
4. The method according to claim 3, characterized in that The first risk state includes a medium risk state and a high risk state, and the risk level corresponding to the medium risk state is lower than the risk level corresponding to the high risk state; The determining, according to the relationship between the number of the predicted risk states and the first number threshold, one of the first risk states as the target risk state includes: In a case where the number of the predicted risk states is higher than the first number threshold, determining the high risk state as the target risk state; In a case where the number of the predicted risk states is not higher than the first number threshold, the medium risk state is determined as the target risk state.
5. The method according to claim 3, characterized in that: The second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state; The step of determining one of the second risk states as the target risk state according to the relationship between the number of the predicted risk states and the second number threshold comprises: In a case where the number of the predicted risk states is higher than the second number threshold, determining the low risk state as the target risk state; In a case where the number of the predicted risk states is not higher than the second number threshold, the good state is determined as the target risk state.
6. The method according to any one of claims 1 to 5, characterized in that Determining the threat level of each threat event includes: For each of the threat events, determine the priority, severity and credibility of the threat event; The threat level of the threat event is determined based on the priority, severity and credibility of the threat event.
7. The method according to claim 6, characterized in that The step of determining the priority, severity and credibility of each threat event includes: For each of the threat events, determining the target event type to which the threat event belongs; Determine the priority, severity and credibility of the target event type; The priority, severity and credibility of the threat event are determined according to the priority, severity and credibility corresponding to the target event type.
8. The method according to claim 6, characterized in that The priority is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score; and determining the threat level of the threat event by combining the priority, severity, and credibility of the threat event includes: The first score, the second score and the third score are combined according to the weights corresponding to the priority, the severity and the credibility to obtain a total score; The threat level of the threat event is determined according to the score interval of the total score, wherein each threat level has a corresponding score interval.
9. A risk prediction device for a terminal device, characterized in that: The device comprises: An event determination module is used to determine whether a threat event occurs in the terminal device during the operation cycle; A level determination module, configured to determine the threat level of each threat event when at least one threat event occurs, wherein the threat level indicates the degree of threat posed by the threat event to the security of the terminal device; A state determination module, used to take the threat level of each threat event as an observation value, input it into a hidden Markov model, and obtain a predicted risk state output by the hidden Markov model; A prediction module, configured to predict a target risk state of the terminal device at a future moment after the operation cycle according to the predicted risk state; When the risk level corresponding to the target risk state is higher than the second risk threshold, after receiving the payment request of the terminal device, the commodity information and the payment information are sent to the terminal device through the SIM server, and the payment key and the payment information are double-verified, and a payment result is generated according to the double-verification result. After receiving the payment request from the terminal device, sending the commodity information and the payment information to the terminal device through the SIM server, performing double verification on the payment key and the payment information, and generating the payment result according to the double verification result, including: a sending module, configured to send commodity information and payment information to the terminal device through a user identity module SIM server in response to receiving a payment request initiated by the terminal device, wherein the commodity information and payment information are used to be displayed on the terminal device; A receiving module, used to receive the verification result of the payment key sent by the SIM server and the confirmation information of the user of the terminal device on the payment information; A verification module, used to verify the confirmation information and obtain a verification result of the confirmation information; A generation module, used to generate a payment result according to the verification result of the payment key and the verification result of the confirmation information; The sending module is also used to send the payment result to the terminal device.
10. The device according to claim 9, characterized in that The parameters of the hidden Markov model include a triple (π, A, B); wherein: π is the initial state probability matrix, including the distribution probability of each preset risk state at the initial moment; A is the state transition probability matrix, including the probability of transition between each preset risk state; B is the observation probability matrix, including the probability of generating each preset threat level under the condition of being in each preset risk state at any time.
11. The device according to claim 9, characterized in that The prediction module comprises: a first determining unit, configured to, when the predicted risk state includes at least one of the first risk states, determine one of the first risk states as the target risk state according to a relationship between the number of the predicted risk states and a first quantity threshold, wherein the first risk state is a risk state in the preset risk states, the corresponding risk degree of which is higher than the first risk threshold; A second determination unit is used to determine one of the second risk states as the target risk state based on a relationship between the number of the predicted risk states and a second quantity threshold when the predicted risk state does not include the first risk state, wherein the second risk state is a risk state other than the first risk state in the preset risk state.
12. The device according to claim 11, characterized in that The first risk state includes a medium risk state and a high risk state, and the risk level corresponding to the medium risk state is lower than the risk level corresponding to the high risk state; the first determining unit is specifically used to: In a case where the number of the predicted risk states is higher than the first number threshold, determining the high risk state as the target risk state; In a case where the number of the predicted risk states is not higher than the first number threshold, the medium risk state is determined as the target risk state.
13. The device according to claim 11, characterized in that The second risk state includes a good state and a low risk state, and the risk level corresponding to the good state is lower than the risk level corresponding to the low risk state; the second determining unit is specifically used to: In a case where the number of the predicted risk states is higher than the second number threshold, determining the low risk state as the target risk state; In a case where the number of the predicted risk states is not higher than the second number threshold, the good state is determined as the target risk state.
14. The device according to any one of claims 9 to 13, characterized in that The level determination module comprises: A third determining unit, configured to determine, for each of the threat events, the priority, severity and credibility of the threat event; The fourth determining unit is used to determine the threat level of the threat event based on the priority, severity and credibility of the threat event.
15. The device according to claim 14, characterized in that The third determining unit is specifically configured to: For each of the threat events, determining the target event type to which the threat event belongs; Determine the priority, severity and credibility of the target event type; The priority, severity and credibility of the threat event are determined according to the priority, severity and credibility corresponding to the target event type.
16. The device according to claim 14, characterized in that The priority is represented by a first score, the severity is represented by a second score, and the credibility is represented by a third score; the fourth determination unit is specifically configured to: The first score, the second score and the third score are combined according to the weights corresponding to the priority, the severity and the credibility to obtain a total score; The threat level of the threat event is determined according to the score interval of the total score, wherein each threat level has a corresponding score interval.
17. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.
18. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method as claimed in any one of claims 1 to 8.
