Risk assessment method and device, equipment and storage medium

Abstract

The invention provides a risk assessment method and device, equipment and a storage medium, relates to the technical field of risk control, and aims to solve the problem that weight setting is limited when a customer risk level is determined by a general technology. The risk assessment method comprises the steps of obtaining risk assessment features of a to-be-assessed object; the risk assessment feature is used for representing the operation condition of the to-be-assessed object from multiple dimensions; determining a current risk assessment value of the to-be-assessed object according to the risk assessment features; updating a current assessment weight corresponding to the current risk assessment value according to a historical assessment weight corresponding to the historical risk assessment value; and determining a risk assessment result of the to-be-assessed object according to the current assessment weight and the current risk assessment value. The risk assessment result of the to-be-assessed object can be accurately determined.

Description

Technical Field

[0001] This application relates to the field of risk control technology, and in particular, to a risk assessment method, device, equipment and storage medium. Background Art

[0002] Telemarketing refers to using telephone operators to attract new customers and contact old customers to determine their satisfaction or whether they can accept orders. Whether the marketing scripts and marketing content of telephone operators meet the requirements need to be verified through quality inspection. During the process of quality inspection of telephone operators, if all telephone operators are inspected, it is time-consuming and laborious, and the efficiency is low. Therefore, usually, a certain quality inspection ratio is set to inspect telephone operators. When setting the quality inspection ratio, usually, the risk level of customers is determined and then a reasonable quality inspection ratio is set.

[0003] Currently, when determining the risk level of customers, usually, scoring indicators of customers are obtained, and a linear weighting method is used to set weights for the scoring indicators, and the weighted sum of the scoring indicators is obtained to get the risk level of customers.

[0004] However, setting weights by the linear weighting method has certain limitations. Summary of the Invention

[0005] This application provides a risk assessment method, device, equipment and storage medium, aiming to solve the problem that the weight setting has limitations when the general technology determines the customer risk level.

[0006] To achieve the above object, this application adopts the following technical solutions:

[0007] In the first aspect, a risk assessment method is provided, including: obtaining risk assessment features of an object to be evaluated; the risk assessment features are used to characterize the operation status of the object to be evaluated from multiple dimensions; determining the current risk assessment value of the object to be evaluated according to the risk assessment features; updating the current assessment weight corresponding to the current risk assessment value according to the historical assessment weight corresponding to the historical risk assessment value; determining the risk assessment result of the object to be evaluated according to the current assessment weight and the current risk assessment value.

[0008] Optionally, updating the current assessment weight corresponding to the current risk assessment value according to the historical assessment weight corresponding to the historical risk assessment value includes:

[0009] The current assessment weight corresponding to the current risk assessment value satisfies the following formula:

[0010]

[0011] where η is the learning rate; α is the Gini importance weight coefficient; is the historical evaluation weight corresponding to the historical risk assessment value; is the current evaluation weight corresponding to the current risk assessment value; N trees is the total number of decision trees in the preset random forest; k is the index for traversing all decision trees; nodes(k) are all split nodes in the k-th tree; the nodes are divided based on the data type of the risk assessment data corresponding to the risk assessment features; is the original prediction error of the k-th tree on the out-of-bag samples; is the updated prediction error of the k-th tree on the out-of-bag samples.

[0012] Optionally, obtain the risk assessment features of the object to be evaluated, including: obtaining the risk assessment data of the object to be evaluated; the risk assessment data includes at least one of the following: attribute data, operation data, and risk control event data; preprocess the risk assessment data to obtain risk assessment features; the preprocessing includes anomaly removal processing and / or normalization processing.

[0013] Optionally, determine the current risk assessment value of the object to be evaluated according to the risk assessment features, including: obtaining the data type of the risk assessment data corresponding to the risk assessment features; determining the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data.

[0014] Optionally, determine the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data, including: when the data type of the risk assessment data is the first type, perform weighted summation on the risk assessment features according to the feature weights corresponding to the risk assessment features to obtain the current risk assessment value of the object to be evaluated; the risk assessment data of the first type includes at least one of the following: attribute data, operation data, and risk control event data with an event level less than or equal to the preset level.

[0015] Optionally, determine the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data, including: when the data type of the risk assessment data is the second type, determine the risk assessment result corresponding to the risk assessment data of the second type as the current risk assessment value of the object to be evaluated; the risk assessment data of the second type includes: risk control event data with an event level greater than the preset level.

[0016] Optionally, the risk assessment method further includes: adjusting the quality inspection ratio of the object to be evaluated based on the risk assessment result; the quality inspection ratio of the object to be evaluated satisfies the following formula:

[0017] Sampling Rate=min(0.5,0.1·e 0.02·RiskScore );

[0018] The Sampling Rate is the quality inspection ratio, and the Risk Score is the result of risk assessment.

[0019] In a second aspect, a risk assessment device is provided. The risk assessment device includes a communication unit and a processing unit.

[0020] The communication unit is configured to obtain risk assessment features of an object to be evaluated; the risk assessment features are used to characterize the operation of the object to be evaluated from multiple dimensions;

[0021] The processing unit is configured to determine the current risk assessment value of the object to be evaluated according to the risk assessment features;

[0022] The processing unit is further configured to update the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value;

[0023] The processing unit is further configured to determine the risk assessment result of the object to be evaluated according to the current evaluation weight and the current risk assessment value.

[0024] In a third aspect, a risk assessment device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory through a bus; when the risk assessment device runs, the processor executes the computer execution instructions stored in the memory so that the risk assessment device executes the risk assessment method in the first aspect.

[0025] The risk assessment device can be an electronic device or a part of a device in an electronic device, such as a chip system in an electronic device. The chip system is used to support the electronic device to implement the functions involved in the first aspect and any possible implementation manner thereof. For example, to obtain and determine the data and / or information involved in the above risk assessment method. The chip system includes a chip and may also include other discrete devices or circuit structures.

[0026] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium includes computer execution instructions. When the computer execution instructions run on a computer, the computer is caused to execute the risk assessment method in the first aspect.

[0027] In a fifth aspect, a computer program product is further provided. The computer program product includes a computer program or instructions. When the computer instructions run on the risk assessment device, the risk assessment device is caused to execute the risk assessment method in the first aspect as described above.

[0028] It should be noted that the above computer instructions can be stored in whole or in part on a computer-readable storage medium. Among them, the computer-readable storage medium can be packaged together with the processor of the risk assessment device or separately packaged from the processor of the risk assessment device. This application embodiment does not make a limitation in this regard.

[0029] For the descriptions of the second, third, fourth, and fifth aspects in this application, reference may be made to the detailed description of the first aspect.

[0030] In the embodiments of this application, the name of the above risk assessment device does not constitute a limitation on the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. For example, the receiving unit may also be referred to as a receiving module, a receiver, etc. As long as the functions of each device or functional module are similar to those of this application and fall within the scope of the claims of this application and their equivalent technologies.

[0031] The technical solutions provided by this application at least bring the following beneficial effects:

[0032] Based on any of the above aspects, embodiments of this application provide a risk assessment method, including: First, risk assessment characteristics of an object to be evaluated (characterizing the operation of the object to be evaluated from multiple dimensions) can be obtained. Then, based on the risk assessment characteristics, the current risk assessment value of the object to be evaluated can be determined, and the current assessment weight corresponding to the current risk assessment value can be updated according to the historical assessment weight corresponding to the historical risk assessment value. Subsequently, based on the current assessment weight and the current risk assessment value, the risk assessment result of the object to be evaluated can be determined.

[0033] As can be seen from the above, when determining the risk assessment result of the object to be evaluated in this application, risk assessment characteristics that characterize the operation of the object to be evaluated from multiple dimensions are adopted. Therefore, this application can enrich the dimensions of risk assessment and solve the problem that the risk assessment dimensions of general technologies are relatively single.

[0034] Secondly, when determining the risk assessment result of the object to be evaluated in this application, the historical assessment weight corresponding to the historical risk assessment value can also be used to update the current assessment weight corresponding to the current risk assessment value, that is, the current assessment weight used to determine the risk assessment result of the object to be evaluated can be dynamically adjusted, solving the problem that the weights of general technologies are fixed and have certain limitations, and having stronger flexibility.

[0035] For the beneficial effects of the first, second, third, fourth, and fifth aspects in this application, reference may be made to the analysis of the above beneficial effects, and details are not elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic structural diagram of a risk assessment system provided by an embodiment of this application;

[0037] Figure 2 It is a schematic hardware structure diagram of a risk assessment device provided by an embodiment of this application;

[0038] Figure 3 Flow schematic diagram of a risk assessment method provided by an embodiment of the present application;

[0039] Figure 4 Flow schematic diagram of another risk assessment method provided by an embodiment of the present application;

[0040] Figure 5 Flow schematic diagram of another risk assessment method provided by an embodiment of the present application;

[0041] Figure 6 Structural schematic diagram of a risk assessment device provided by an embodiment of the present application. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0043] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner.

[0044] In order to facilitate a clear description of the technical solutions in the embodiments of the present application, in the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using words such as "first" and "second". Those skilled in the art can understand that the words such as "first" and "second" do not limit the quantity and execution order.

[0045] Before introducing the risk assessment method provided by the present application in detail, the application scenarios and implementation environments involved in the present application will be briefly introduced.

[0046] First, the application scenarios involved in the present application will be briefly introduced.

[0047] As described in the background art, in the existing risk assessment methods, when determining the risk level, usually by obtaining the scoring indicators of customers and setting weights for the scoring indicators in a linear weighting manner, resulting in fixed weights, which has certain limitations.

[0048] Secondly, when determining the risk level, the scoring indicators for customers are usually single scoring indicators, ignoring dynamic operation data (such as call frequency, response rate) and real-time risk control signals (such as fraud marks, complaint content), resulting in a lag in risk assessment.

[0049] In view of the above problems, the embodiment of the present application provides a risk assessment method, including: First, risk assessment characteristics of an object to be evaluated can be obtained (characterizing the operation of the object to be evaluated from multiple dimensions). Then, according to the risk assessment characteristics, the current risk assessment value of the object to be evaluated can be determined, and the current assessment weight corresponding to the current risk assessment value can be updated according to the historical assessment weight corresponding to the historical risk assessment value. Subsequently, according to the current assessment weight and the current risk assessment value, the risk assessment result of the object to be evaluated can be determined.

[0050] As can be seen from the above, when determining the risk assessment result of the object to be evaluated in the present application, risk assessment characteristics that characterize the operation of the object to be evaluated from multiple dimensions are adopted. Therefore, the present application can enrich the dimensions of risk assessment and solve the problem that the risk assessment dimensions of the general technology are relatively single.

[0051] Secondly, when determining the risk assessment result of the object to be evaluated in the present application, the historical assessment weight corresponding to the historical risk assessment value can also be used to update the current assessment weight corresponding to the current risk assessment value, that is, the current assessment weight used to determine the risk assessment result of the object to be evaluated can be dynamically adjusted, solving the problem that the weight of the general technology is fixed and has certain limitations, and the flexibility is stronger.

[0052] The implementation environment of the above risk assessment method can be the risk assessment system provided by the embodiment of the present application.

[0053] Figure 1 The structural schematic diagram of the risk assessment system provided by the embodiment of the present application is shown. As Figure 1 shown, the risk assessment system includes: a risk assessment device 101 and a data providing device 102.

[0054] Among them, the risk assessment device 101 is communicatively connected to the data providing device 102 respectively.

[0055] In practical applications, the risk assessment device 101 can be connected to any number of data providing devices 102. For the sake of easy understanding, Figure 1 take an example where a risk assessment device 101 is respectively connected to a data providing device 102 for illustration.

[0056] In the embodiment of the present application, the data providing device 102 is used to provide risk assessment data of the object to be evaluated to the risk assessment device, so that the risk assessment device 101 can perform risk assessment on the object to be evaluated according to the risk assessment data sent by the data providing device 102.

[0057] Optionally, the physical device of the risk assessment device 101 can be a server, a terminal, or other types of electronic devices. The embodiments of the present application do not make any limitations in this regard.

[0058] Optionally, the above-mentioned terminal can be a device that provides voice and / or data connectivity to the user, a handheld device with wireless connection capabilities, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a radio access network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal, or it can also be a portable, pocket-sized, handheld, computer-integrated, or vehicle-mounted mobile device that exchanges language and / or data with the wireless access network. For example, mobile phones, tablet computers, laptop computers, netbooks, and personal digital assistants (PDAs).

[0059] Optionally, the above-mentioned server can be a server in a server cluster (composed of multiple servers), a chip in the server, a system-on-chip in the server, or can also be implemented through a virtual machine (VM) deployed on a physical machine. The embodiments of the present application do not make any limitations in this regard.

[0060] Optionally, the physical device of the data providing device 102 can be a network management server for storing the risk assessment data of the object to be evaluated, or other types of storage devices for storing the risk assessment data of the object to be evaluated. No limitations are made here.

[0061] Optionally, the risk assessment device 101 and the data providing device 102 can be two independently set devices, or can be integrated in the same device. When the risk assessment device 101 and the data providing device 102 are integrated in the same device, the data providing device 102 can be a storage module (such as a database, etc.) of the risk assessment device 101.

[0062] It is easy to understand that when the risk assessment device 101 and the data providing device 102 are integrated in the same device, the communication method between the risk assessment device 101 and the data providing device 102 is the communication between internal modules of the device. In this case, the communication process between the two is the same as the communication process between the risk assessment device 101 and the data providing device 102 when they are independent of each other.

[0063] For the sake of easy understanding, the present application takes the risk assessment device 101 and the data providing device 102 being independent of each other as an example for illustration.

[0064] In some embodiments, the risk assessment device 101 may include: a data acquisition and preprocessing module, an index scoring engine, a dynamic weight optimization module, and a quality inspection strategy generator. Its main functions are as follows:

[0065] The data acquisition and preprocessing module is used to obtain the risk assessment data of the object to be evaluated and preprocess the obtained risk assessment data of the object to be evaluated to obtain risk assessment features.

[0066] The index scoring engine is used to determine the current risk assessment value of the object to be evaluated according to the risk assessment data (i.e., risk assessment features) of the object to be evaluated processed by the data acquisition and preprocessing module.

[0067] The dynamic weight optimization module is used to update the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value of the object to be evaluated.

[0068] The quality inspection strategy generator is used to adjust the quality inspection ratio of the object to be evaluated according to the risk assessment result of the object to be evaluated.

[0069] The risk assessment device 101 in the risk assessment system includes components as Figure 2 included. Taking the Figure 2 shown communication device as an example, the hardware structure of the risk assessment device 101 will be introduced.

[0070] Figure 2 As shown in , it is a schematic diagram of a hardware structure of a communication device provided by an embodiment of the present application. The communication device includes a processor 21, a memory 22, a communication interface 23, and a bus 24. The processor 21, the memory 22, and the communication interface 23 can be connected through the bus 24.

[0071] The processor 21 is the control center of the communication device, which can be a single processor or a collective term for multiple processing elements. For example, the processor 21 can be a general-purpose central processing unit (CPU), or other general-purpose processors, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0072] As an embodiment, the processor 21 may include one or more CPUs, such as Figure 2 the CPU0 and CPU1 shown in .

[0073] The memory 22 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0074] In a possible implementation, the memory 22 can exist independently of the processor 21. The memory 22 can be connected to the processor 21 through the bus 24 and is used to store instructions or program code. When the processor 21 calls and executes the instructions or program code stored in the memory 22, the risk assessment method provided in the following embodiments of the present application can be implemented.

[0075] In the embodiments of the present application, for the risk assessment device 101 and the data providing device 102, the software programs stored in the memory 22 are different, so the functions implemented by the risk assessment device 101 and the data providing device 102 are different. The functions performed by each device will be described in conjunction with the following flowcharts.

[0076] In another possible implementation, the memory 22 can also be integrated with the processor 21.

[0077] The communication interface 23 is used for the communication device to connect to other devices through a communication network. The communication network can be an Ethernet, a wireless access network, a wireless local area network (WLAN), etc. The communication interface 23 can include a receiving unit for receiving data and a sending unit for sending data.

[0078] The bus 24 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0079] It should be noted that Figure 2 the structure shown in does not constitute a limitation on the communication device. Except Figure 2 for the components shown, the communication device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0080] The risk assessment method provided by the embodiments of the present application will be introduced in detail below with reference to the accompanying drawings.

[0081] The risk assessment method provided by the embodiments of the present application is applied to Figure 1 the risk assessment device in the risk assessment system shown in, such as Figure 3 shown, the risk assessment method provided by the embodiments of the present application includes:

[0082] S301. The risk assessment device obtains the risk assessment characteristics of the object to be evaluated.

[0083] Specifically, in the scenario of risk assessment of the object to be evaluated, in order to accurately evaluate the risk assessment result of the object to be evaluated, therefore, the risk assessment device needs to obtain the risk assessment characteristics of the object to be evaluated.

[0084] Among them, the risk assessment characteristics are used to characterize the operation of the object to be evaluated from multiple dimensions.

[0085] Optionally, the object to be evaluated may be a marketing object under telemarketing, that is, a customer for the operator.

[0086] Optionally, the multiple dimensions in the above risk assessment characteristics may include: the attribute dimension of the object to be evaluated, the operation dimension, the risk control event dimension, etc.

[0087] S302. The risk assessment device determines the current risk assessment value of the object to be evaluated according to the risk assessment characteristics.

[0088] Specifically, after determining the risk assessment characteristics, since the risk assessment characteristics characterize the operation of the object to be evaluated from multiple dimensions, therefore, the risk assessment device can first determine the current risk assessment value of the object to be evaluated, so as to subsequently determine the risk assessment result of the object to be evaluated according to the current risk assessment value of the object to be evaluated.

[0089] Among them, the current risk assessment value is the assessment value corresponding to the risk assessment characteristics.

[0090] Optionally, when the risk assessment characteristics characterize the operation of the object to be evaluated from the attribute dimension of the object to be evaluated, the current risk assessment value may be the risk assessment value characterized from the attribute dimension of the object to be evaluated.

[0091] Optionally, when the risk assessment feature characterizes the operation of the object to be evaluated from the operation dimension of the object to be evaluated, the current risk assessment value may be the risk assessment value characterized from the operation dimension of the object to be evaluated.

[0092] Optionally, when the risk assessment feature characterizes the operation of the object to be evaluated from the risk control event dimension of the object to be evaluated, the current risk assessment value may be the risk assessment value characterized from the risk control event dimension of the object to be evaluated.

[0093] S303. The risk assessment device updates the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value.

[0094] Specifically, in order to obtain the risk assessment result of the evaluation object, it is necessary to first determine the current evaluation weight. If the current evaluation weight is directly set by the linear weighting method, the current evaluation weight will be solidified and have certain limitations. Therefore, in this application, the risk assessment device can update the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value, so as to subsequently determine the risk assessment result of the object to be evaluated according to the current evaluation weight and the current risk assessment value. In this way, the current evaluation weight used to determine the risk assessment result of the object to be evaluated can be dynamically adjusted, solving the problem that the weight in the general technology is solidified and has certain limitations, and having stronger flexibility.

[0095] Among them, the historical risk assessment value and the historical evaluation weight are the risk assessment value and the evaluation weight in the historical time period. The current risk assessment value and the current evaluation weight are the risk assessment value and the evaluation weight in the current time period.

[0096] Optionally, the evaluation weight refers to the weight value that needs to be used when determining the risk assessment result of the object to be evaluated.

[0097] S304. The risk assessment device determines the risk assessment result of the object to be evaluated according to the current evaluation weight and the current risk assessment value.

[0098] Specifically, in order to implement the risk assessment of the object to be evaluated, it is necessary to determine the risk assessment result of the object to be evaluated.

[0099] Optionally, the risk assessment device can perform weighted summation on the current evaluation weight and the current risk assessment value to obtain the risk assessment result of the object to be evaluated.

[0100] Combined with the above description, when the risk assessment features characterize the operation status of the object to be evaluated from the attribute dimension, operation dimension, and risk control event dimension of the object to be evaluated, the current risk assessment value includes the risk assessment value of the attribute dimension, the risk assessment value of the operation dimension, and the risk assessment value of the risk control event dimension. Correspondingly, the current evaluation weight also includes the evaluation weights of the above three dimensions. In this case, the risk assessment device can perform weighted summation based on the risk assessment values of the above three dimensions and their evaluation weights to obtain the risk assessment result of the object to be evaluated.

[0101] Exemplarily, assume that the evaluation weight corresponding to the attribute evaluation value is 0.2, and the evaluation weights corresponding to the operation evaluation value and the risk control event evaluation value are both 0.4. The risk assessment result of the object to be evaluated is obtained by performing weighted summation on the above three types of evaluation values according to the corresponding evaluation weights.

[0102] In some embodiments, in the above S303, the method for the risk assessment device to update the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value specifically includes:

[0103] The current evaluation weight corresponding to the current risk assessment value satisfies the following formula:

[0104]

[0105] where η is the learning rate; α is the Gini importance weight coefficient; is the historical evaluation weight corresponding to the historical risk assessment value; the current evaluation weight corresponding to the current risk assessment value; N trees is the total number of decision trees in the preset random forest; k is the index for traversing all decision trees; nodes(k) are all split nodes in the k-th tree; the nodes are divided based on the data type of the risk assessment data corresponding to the risk assessment features; is the original prediction error of the k-th tree on the out-of-bag samples; is the updated prediction error of the k-th tree on the out-of-bag samples.

[0106] where the updated prediction error is the prediction error corresponding to the risk assessment data corresponding to the risk assessment features after being shuffled; the original prediction error is the prediction error corresponding to the risk assessment data corresponding to the risk assessment features.

[0107] Optionally, the main calculation content of Gini importance is as follows: for each decision tree, calculate the reduction in Gini impurity when the risk assessment feature splits at each node, average the contributions of this risk assessment feature in all trees, and finally obtain the Gini importance. The main calculation content of out-of-bag error importance is as follows: predict the out-of-bag samples of each tree and record the original prediction error; randomly shuffle the values of the risk assessment and then re-predict to calculate the error increment; the average value of the error increments in all trees is the contribution of this risk assessment feature to the out-of-bag error. The detailed calculation processes of Gini importance and out-of-bag error can refer to the relevant descriptions of the general technology and will not be elaborated here.

[0108] Exemplarily, when calculating the current evaluation weight, in the above formula, the value of the learning rate η can be 0.1, and the value of the Gini importance weight coefficient α can be 0.6.

[0109] Exemplarily, Figure 4 shows a schematic flowchart of a risk assessment device for updating the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value. As Figure 4 shown, it includes:

[0110] S401. The risk assessment device obtains the risk assessment features of the object to be evaluated.

[0111] S402. The risk assessment device trains a random forest model through the risk assessment features of the object to be evaluated.

[0112] Optionally, when training the random forest model, it is necessary to calculate the feature importance. The features in the feature importance are the risk assessment features of the object to be evaluated. Calculating the feature importance includes setting the random forest parameters and initializing the feature importance.

[0113] Exemplarily, initializing the feature importance includes initializing the Gini importance matrix (recording the Gini contributions of each feature in each tree) and the out-of-bag error importance matrix (recording the changes in out-of-bag errors of each feature in each tree).

[0114] S403. The risk assessment device calculates the Gini importance corresponding to the risk assessment features through the random forest model.

[0115] Specifically, by statistically calculating the contribution degree of the risk assessment feature to the decrease in the Gini index when splitting the decision tree nodes, the average contribution degree of the risk assessment feature to the decrease in the Gini index when splitting the nodes can be obtained. This average contribution degree can represent the Gini importance corresponding to the risk assessment feature.

[0116] S404. The risk assessment device calculates the out-of-bag error importance corresponding to the risk assessment features through the random forest model.

[0117] Specifically, after randomly permuting the eigenvalues corresponding to the risk assessment features, observe the decrease in the accuracy of the random forest model on the out-of-bag samples to measure the impact of the risk assessment features on the prediction stability of the random forest model, and the out-of-bag error importance corresponding to the risk assessment features can be obtained.

[0118] S405. The risk assessment device obtains a comprehensive score by combining the Gini importance and the out-of-bag error importance.

[0119] Exemplarily, a comprehensive score (which can also be called comprehensive importance) is obtained by weighted calculation of the above Gini importance and out-of-bag error importance.

[0120] Exemplarily, the Gini importance weight can be 0.6. Correspondingly, the out-of-bag error importance weight can be 0.4.

[0121] S406. The risk assessment device adjusts the weight according to the comprehensive importance and determines whether the weight converges.

[0122] Exemplarily, assume that the convergence condition is whether the change in weight is less than the threshold 0.1. If the maximum change value of the weight in the second iteration and the weight in the first iteration is less than 0.1, it is determined that convergence is achieved, and S407 is executed; otherwise, S402 is continued to be executed repeatedly.

[0123] S407. The risk assessment device outputs the final weight.

[0124] Specifically, in the case where the weight converges, the current evaluation weight, that is, the final weight, can be determined according to the comprehensive score obtained in S405, the preset learning rate, and the historical evaluation weight.

[0125] In some embodiments, in the above S301, the method by which the risk assessment device obtains the risk assessment features of the object to be evaluated specifically includes:

[0126] S1. The risk assessment device obtains the risk assessment data of the object to be evaluated.

[0127] Among them, the risk assessment data includes at least one of the following: attribute data, operation data, and risk control event data.

[0128] Specifically, the risk assessment result of the object to be evaluated needs to be obtained through corresponding calculations of the risk assessment data of the object to be evaluated.

[0129] Optionally, if the risk assessment result is determined only by one type of data, there will be a problem of single risk assessment dimension, resulting in lagged risk assessment. Therefore, the risk assessment data of the object to be evaluated obtained by the risk assessment device needs to include at least one item of risk assessment data related to the object to be evaluated.

[0130] Optionally, the attribute data may include industry classification data and reporting scenario data; the operation data may include call growth data, call frequency data, and answer rate data; the risk control event data may include real-time fraud flag data, cumulative complaint data, recent complaint data, complaint content data, and flag data.

[0131] S2. The risk assessment device preprocesses the risk assessment data to obtain risk assessment features.

[0132] Among them, the preprocessing includes outlier removal processing and / or normalization processing.

[0133] Specifically, in order to determine the risk assessment value and assessment weight of the object to be evaluated subsequently, it is first necessary to preprocess the risk assessment data.

[0134] Exemplarily, the box plot method can be used to remove outliers for outlier removal processing, remove the outliers in the risk assessment data, achieve the removal of interference factors, and improve data consistency. The risk assessment data after removing outliers is normalized through the Z-score formula to eliminate the dimension difference and obtain risk assessment features.

[0135] Exemplarily, Figure 5 shows a schematic flowchart of a process for a risk assessment device to obtain risk assessment features of an object to be evaluated. As Figure 5 shown, it includes:

[0136] S501. The risk assessment device obtains the risk assessment data of the object to be evaluated.

[0137] Optionally, the input original data may include attribute data, operation data, and risk control event data.

[0138] Exemplarily, assuming that the input original data is operation data, this data may be 50 million call records per day on average. Assuming that the input original data is risk control event data, this data may be a complaint log containing NLP parsing.

[0139] S502. The risk assessment device determines the outlier range by calculating the quartiles of the data.

[0140] Exemplarily, the upper and lower boundaries of the data are determined according to the lower quartile Q1, the upper quartile Q3, and the interquartile range IQR = Q3 - Q1. The lower limit Q1 - 1.5×IQR and the upper limit Q3 + 1.5×IQR are the outlier ranges.

[0141] S503. The risk assessment device identifies the points exceeding the threshold through the outlier range.

[0142] Exemplarily, if a data point exceeds the outlier range in S502, it is regarded as an outlier. After processing the outlier, S504 is executed; otherwise, S504 is executed.

[0143] Optionally, the above S502 and S503 processes can be divided into an outlier detection module.

[0144] S504. The risk assessment device calculates the feature mean and standard deviation.

[0145] Optionally, calculate the feature mean and standard deviation of the risk assessment data after processing the outlier.

[0146] S505. The risk assessment device standardizes the risk assessment data using the Z-score formula.

[0147] Optionally, the standardization formula is:

[0148]

[0149] where x is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

[0150] S506. The risk assessment device outputs the standardized data set.

[0151] Specifically, the standardized risk assessment data obtained through S506 is the risk assessment feature of the object to be evaluated.

[0152] Optionally, the above S504, S505, and S506 processes can be divided into a standardization module.

[0153] In some embodiments, in the above S302, the risk assessment device determines the current risk assessment value of the object to be evaluated according to the risk assessment feature, which specifically includes:

[0154] S1. The risk assessment device obtains the data type of the risk assessment data corresponding to the risk assessment feature.

[0155] Specifically, because different data types of risk assessment data correspond to different risk assessment features, the risk assessment device needs to obtain the data type of the risk assessment data corresponding to the risk assessment feature.

[0156] Optionally, the data types of the risk assessment data may include attribute data, operation data, and risk control event data. The risk assessment features may include attribute features, operation features, and risk control event features. The attribute features may include industry classification features and reporting scenario features; the operation features may include call growth rate features, call frequency features, and answer rate features; the risk control event features may include real-time fraud marking features, cumulative complaint features, recent complaint features, complaint content features, and marking features.

[0157] S2. The risk assessment device determines the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data.

[0158] In some embodiments, the data type may include a first type and a second type.

[0159] Specifically, different data types of risk assessment data correspond to different risk assessment characteristics. When calculating the current risk assessment value of the object to be evaluated, it is necessary to calculate separately according to the data types corresponding to different risk assessment characteristics. Therefore, the risk assessment device needs to determine the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data. Optionally, the current risk assessment value may be obtained by weighted calculation based on three types of characteristic weights: the attribute characteristic, the operation characteristic, and the risk control event characteristic of the current time period.

[0160] Among them, the risk assessment data of the first type includes at least one of the following: attribute data, operation data, and risk control event data with an event level less than or equal to a preset level. The risk assessment data of the second type includes: risk control event data with an event level greater than the preset level.

[0161] Optionally, the risk assessment data of the first type may include attribute data, operation data, and risk control event data except for real-time fraud marks. The risk assessment data of the second type may be real-time fraud mark data of the risk control event data type.

[0162] Since the risk assessment data of the first type has a relatively weak risk level, the risk assessment device can perform weighted summation on the risk assessment characteristics according to the characteristic weights corresponding to the risk assessment characteristics to obtain the current risk assessment value of the object to be evaluated, specifically including:

[0163] Optionally, when the data type of the risk assessment data of the object to be evaluated is attribute data, the formula for calculating the attribute evaluation value of the object to be evaluated according to the attribute characteristics of the object to be evaluated is as follows:

[0164] Attribute evaluation value (S attr ):

[0165] S attr =(α·S industry +(1 - α)·S scene )·ω attr ;

[0166] Among them, α is the industry classification characteristic weight, ω attr is the attribute characteristic weight. The industry classification characteristic S industry is quantified based on the business attributes enjoyed and combined with expert scoring. S scene is the reported scenario characteristic.

[0167] Exemplarily, when calculating the evaluation value of an attribute, in the above formula, the industry classification feature weight α and the reporting scenario feature weight can both be 0.5, and the attribute feature weight ω attr can be 0.2.

[0168] Optionally, when the data type of the risk assessment data of the object to be evaluated is operation data, the calculation formula for the operation evaluation value of the object to be evaluated according to the operation characteristics of the object to be evaluated is as follows:

[0169] Operation evaluation value (S ops ):

[0170]

[0171] Parameter: β i is the weight corresponding to different features in the operation characteristics; ω ops is the operation feature weight.

[0172] Exemplarily, the growth rate feature weight can be 0.2, the call frequency feature weight and the answer rate feature weight can both be 0.4, and the operation feature weight ω ops can be 0.4.

[0173] Optionally, when the data type of the risk assessment data of the object to be evaluated is risk control event data, the calculation formula for the risk control event evaluation value of the object to be evaluated according to the risk control event characteristics of the object to be evaluated is as follows:

[0174] Risk control event evaluation value (S risk ):

[0175]

[0176] Parameter: γ is the real-time fraud flag weight; θ j is the weight of other features in the operation characteristics except the real-time fraud flag feature; ω risk is the risk control event weight.

[0177] Among them, it can be seen from the above formula that when the risk control event data is not real-time fraud flag data, the risk control event evaluation value of the object to be evaluated can be obtained by weighted summation according to the calculation method of the first type of risk assessment data.

[0178] Exemplarily, the real-time fraud flag weight can be 0.4, the cumulative complaint feature weight can be 0.2, the recent complaint feature weight can be 0.4, the complaint content feature weight can be 0.3, the flag feature weight can be 0.1, and the risk control event weight ω risk can be 0.4.

[0179] Since the risk assessment data of the second type has a relatively high risk level, the risk assessment device can determine the risk assessment result corresponding to the risk assessment data of the second type as the current risk assessment value of the object to be evaluated, specifically including:

[0180] Optionally, the risk assessment data of the second type may be real-time fraud flag data in the risk control event data.

[0181] Determine the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data.

[0182] Exemplarily, when the data type of the risk assessment data of the object to be evaluated is the second data type, the risk control event assessment value of the object to be evaluated can be obtained by directly assigning scores. Assume that the weight of the real-time fraud flag is 0.4, then the risk control event assessment value S risk = 100 × 0.4, and the obtained risk assessment value S risk is determined as the risk assessment value of the object to be evaluated.

[0183] In some embodiments, the risk assessment method provided by the embodiments of the present application further includes:

[0184] The risk assessment device adjusts the quality inspection ratio of the object to be evaluated based on the risk assessment result.

[0185] Among them, the quality inspection ratio of the object to be evaluated satisfies the following formula:

[0186] Sampling Rate = min(0.5, 0.1·e 0.02·RiskScore );

[0187] Sampling Rate is the quality inspection ratio, and Risk Score is the risk assessment result.

[0188] Optionally, according to the risk assessment result of the object to be evaluated, the quality inspection ratio of the object to be evaluated is calculated through the above formula, so as to realize dynamic adjustment of the quality inspection ratio.

[0189] Exemplarily, the upper limit of the quality inspection ratio for high-risk customers (Risk Score ≥ 80) is 50%, the upper limit of the quality inspection ratio for medium-risk (50 ≤ RiskScore < 80) is 30%, and the upper limit of the quality inspection ratio for low-risk (Risk Score < 50) is 10%.

[0190] Exemplarily, assume that the risk assessment data of the object to be evaluated is customer data with a value of 2000+. Through the above risk assessment method, the importance ranking of features after model training is obtained as follows: call frequency (0.35) > complaint content (0.28) > industry attribute (0.17). By adjusting the quality inspection ratio through the above risk assessment method, the quality inspection ratio of high-risk customers has been increased from 30% to 50%, and the number of intercepted illegal transactions has increased by 45%.

[0191] In some embodiments, the above risk assessment method is connected to the call system quality inspection system for real-time customer risk assessment. The verification effect obtained is that the measured AUC (Area Under the ROC Curve) value reaches 0.92 (baseline 0.79), the recall rate of high-risk customers is 95%, and the quality inspection labor cost is reduced by 32%.

[0192] The above mainly introduces the solution provided by the embodiments of the present application from the perspective of the method. To implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0193] The embodiments of the present application can divide the risk assessment device into functional modules according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. Optionally, the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. There may be other division methods in actual implementation.

[0194] Figure 6 Shows a schematic structural diagram of a risk assessment device provided by an embodiment of the present application. As Figure 6 shown, the risk assessment device includes: a communication unit 601 and a processing unit 602.

[0195] The communication unit 601 is used to obtain the risk assessment features of the object to be evaluated; the risk assessment features are used to characterize the operation status of the object to be evaluated from multiple dimensions. For example, in combination with Figure 3 , the communication unit 601 is used to execute S301.

[0196] The processing unit 602 is configured to determine the current risk assessment value of the object to be evaluated according to the risk assessment features. For example, in combination with Figure 3 , the processing unit 602 is configured to execute S302.

[0197] The processing unit 602 is further configured to update the current evaluation weight corresponding to the current risk assessment value according to the historical evaluation weight corresponding to the historical risk assessment value. For example, in combination with Figure 3 , the processing unit 602 is configured to execute S303.

[0198] The processing unit 602 is further configured to determine the risk assessment result of the object to be evaluated according to the current evaluation weight and the current risk assessment value. For example, in combination with Figure 3 , the processing unit 602 is configured to execute S304.

[0199] Optionally, the processing unit 602 is specifically configured to:

[0200] The current evaluation weight corresponding to the current risk assessment value satisfies the following formula:

[0201]

[0202] where η is the learning rate; α is the Gini importance weight coefficient; is the historical evaluation weight corresponding to the historical risk assessment value; is the current evaluation weight corresponding to the current risk assessment value; N trees is the total number of decision trees in the preset random forest; k is the index for traversing all decision trees; nodes(k) are all split nodes in the k-th tree; the nodes are divided based on the data type of the risk assessment data corresponding to the risk assessment features; is the original prediction error of the k-th tree on the out-of-bag samples; is the updated prediction error of the k-th tree on the out-of-bag samples. For example, the processing unit 602 is configured to execute S303.

[0203] Optionally, the communication unit ৬০১ is specifically configured to:

[0204] Obtain the risk assessment data of the object to be evaluated; the risk assessment data includes at least one of the following: attribute data, operation data, and risk control event data.

[0205] Preprocess the risk assessment data to obtain risk assessment features; the preprocessing includes anomaly handling and / or normalization processing. For example, in combination with Figure 3 , the communication unit 601 is configured to execute S301.

[0206] Optionally, the processing unit 602 is specifically configured to:

[0207] Obtain the data type of the risk assessment data corresponding to the risk assessment feature.

[0208] According to the data type of the risk assessment data, determine the current risk assessment value of the object to be evaluated. For example, in combination with Figure 3 , the processing unit 602 is used to execute S302.

[0209] Optionally, the processing unit 602 is specifically used for:

[0210] When the data type of the risk assessment data is the first type, perform weighted summation on the risk assessment features according to the feature weights corresponding to the risk assessment features to obtain the current risk assessment value of the object to be evaluated; the risk assessment data of the first type includes at least one of the following: attribute data, operation data, and risk control event data with an event level less than or equal to a preset level. For example, in combination with Figure 3 , the processing unit 602 is used to execute S302.

[0211] Optionally, the processing unit 602 is specifically used for:

[0212] When the data type of the risk assessment data is the second type, determine the risk assessment result corresponding to the risk assessment data of the second type as the current risk assessment value of the object to be evaluated; the risk assessment data of the second type includes: risk control event data with an event level greater than the preset level. For example, in combination with Figure 3 , the processing unit 602 is used to execute S302.

[0213] Optionally, the processing unit 602 is further used for:

[0214] Adjust the quality inspection ratio of the object to be evaluated based on the risk assessment result; the quality inspection ratio of the object to be evaluated satisfies the following formula:

[0215] Sampling Rate=min(0.5,0.1·e 0.02·RiskScore );

[0216] Sampling Rate is the quality inspection ratio, and Risk Score is the risk assessment result.

[0217] The embodiment of the present application further provides a computer-readable storage medium, and the computer-readable storage medium includes computer-executable instructions. When the computer-executable instructions run on a computer, the computer is enabled to execute the risk assessment method provided in the above embodiment.

[0218] The embodiment of the present application further provides a computer program, which can be directly loaded into a memory and contains software code. After the computer program is loaded and executed by a computer, it can implement the risk assessment method provided in the above embodiment.

[0219] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in this application can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. A computer-readable medium includes a computer-readable storage medium and a communication medium, where the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0220] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above function modules is used as an example. In actual applications, the above functions can be allocated to different function modules as needed, that is, the internal structure of the device can be divided into different function modules to complete all or part of the functions described above.

[0221] In several embodiments provided in this application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form. The units described as separate components may or may not be physically separated, and the components displayed as units can be one physical unit or multiple physical units, that is, they can be located in one place or distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0222] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the general technology, or all or part of the technical solution, may be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a device (which may be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0223] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A risk assessment method, characterized in that, Including: Obtain the risk assessment features of the object to be evaluated; The risk assessment features are used to characterize the operation status of the object to be evaluated from multiple dimensions; Determine the current risk assessment value of the object to be evaluated according to the risk assessment features; Update the current assessment weight corresponding to the current risk assessment value according to the historical assessment weight corresponding to the historical risk assessment value; Determine the risk assessment result of the object to be evaluated according to the current assessment weight and the current risk assessment value.

2. The method according to claim 1, characterized in that The step of updating the current assessment weight corresponding to the current risk assessment value according to the historical assessment weight corresponding to the historical risk assessment value includes: The current assessment weight corresponding to the current risk assessment value satisfies the following formula: Among them, η is the learning rate; α is the Gini importance weight coefficient; is the historical evaluation weight corresponding to the historical risk evaluation value; is the current evaluation weight corresponding to the current risk evaluation value; N trees is the total number of decision trees in the preset random forest; k is the index for traversing all decision trees; nodes(k) are all split nodes in the k-th tree; the nodes are divided based on the data type of the risk evaluation data corresponding to the risk evaluation features; is the original prediction error of the k-th tree on the out-of-bag samples; is the updated prediction error of the k-th tree on the out-of-bag samples.

3. The method according to claim 1, wherein The step of obtaining the risk assessment features of the object to be evaluated includes: Obtain the risk assessment data of the object to be evaluated; the risk assessment data includes at least one of the following: attribute data, operation data, and risk control event data; Preprocess the risk assessment data to obtain the risk assessment features; the preprocessing includes anomaly removal processing and / or normalization processing.

4. The method according to claim 3, characterized in that The step of determining the current risk assessment value of the object to be evaluated according to the risk assessment features includes: Obtain the data type of the risk assessment data corresponding to the risk assessment features; Determine the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data.

5. The method according to claim 4, characterized in that, The step of determining the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data includes: When the data type of the risk assessment data is the first type, perform weighted summation on the risk assessment features according to the feature weights corresponding to the risk assessment features to obtain the current risk assessment value of the object to be evaluated; the risk assessment data of the first type includes at least one of the following: the attribute data, the operation data, and the risk control event data with an event level less than or equal to the preset level.

6. The method according to claim 4, wherein The step of determining the current risk assessment value of the object to be evaluated according to the data type of the risk assessment data includes: When the data type of the risk assessment data is the second type, determine the risk assessment result corresponding to the risk assessment data of the second type as the current risk assessment value of the object to be evaluated; the risk assessment data of the second type includes: the risk control event data with an event level greater than the preset level.

7. The method according to claim 1, wherein It also includes: Adjust the quality inspection ratio of the object to be evaluated based on the risk assessment result; the quality inspection ratio of the object to be evaluated satisfies the following formula: Sampling Rate=min(0.5,0.1·e 0.02·Risk Score ); Sampling Rate is the quality inspection ratio, and Risk Score is the risk assessment result.

8. A risk assessment device, characterized in that, Including: A communication unit and a processing unit; The communication unit is used to obtain the risk assessment features of the object to be evaluated; The risk assessment features are used to characterize the operation status of the object to be evaluated from multiple dimensions; The processing unit is used to determine the current risk assessment value of the object to be evaluated according to the risk assessment features; The processing unit is also used to update the current assessment weight corresponding to the current risk assessment value according to the historical assessment weight corresponding to the historical risk assessment value; The processing unit is further configured to determine a risk assessment result of the object to be evaluated according to the current evaluation weight and the current risk assessment value.

9. A risk assessment device, characterized in that, including: a processor and a memory; wherein, the memory is configured to store one or more programs, and the one or more programs include computer execution instructions. When the risk assessment device runs, the processor executes the computer execution instructions stored in the memory, so that the risk assessment device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the computer execution instructions stored in the computer-readable storage medium are executed by the processor of the risk assessment device, the risk assessment device can execute the method according to any one of claims 1 to 7.

Images