CN115088007A

CN115088007A - Risk assessment method and device, electronic equipment and storage medium

Info

Publication number: CN115088007A
Application number: CN202080096711.7A
Authority: CN
Inventors: 程肯
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2020-03-17
Filing date: 2020-03-17
Publication date: 2022-09-20
Also published as: WO2021184211A1

Abstract

The embodiment of the application discloses a risk assessment method, a risk assessment device, electronic equipment and a storage medium, wherein the method comprises the steps of extracting a first feature vector from obtained data to be assessed; determining a first evaluation score of the data to be evaluated according to the first feature vector and the first risk evaluation model; determining a second evaluation score of the data to be evaluated according to the first feature vector and a second risk evaluation model; and determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

Description

Risk assessment method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to computer technologies, and in particular, to a risk assessment method and apparatus, an electronic device, and a storage medium.

Background

With the continuous development of electronic devices, the functions of the electronic devices are more diversified. This also can greatly increase the safety control degree of difficulty of electronic equipment when facilitating the use of user. For example, with the use of the electronic device payment function, the user may make a payment via the payment code of the electronic device. Although the payment function brings convenience to the life of the user, the user has certain risks such as leakage of a payment code when the user executes a payment task.

In the related art, the electronic device performs risk assessment on a task to be executed so as to solve the safety problem caused by the function diversification of the electronic device. At present, the risk assessment of a task to be executed needs to depend on manual operation, for example, the task data is manually assessed, a user executing a high-risk service is warned, and the risk assessment accuracy is low due to the strong subjectivity of the assessment standard.

Disclosure of Invention

The application provides a risk assessment method, a risk assessment device, electronic equipment and a storage medium, which can improve the accuracy of risk assessment.

In a first aspect, an embodiment of the present application provides a risk assessment method, including:

acquiring data to be evaluated, and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm;

according to the first feature vector and a first risk assessment model, scoring the data to be assessed to obtain a first assessment score;

according to the first feature vector and a second risk assessment model, scoring the data to be assessed to obtain a second assessment score;

and determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In a second aspect, an embodiment of the present application further provides a risk assessment apparatus, including:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring data to be evaluated and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm;

the first scoring module is used for scoring the data to be evaluated according to the first feature vector and a first risk evaluation model to obtain a first evaluation score;

the second scoring module is used for scoring the data to be evaluated according to the first feature vector and a second risk evaluation model to obtain a second evaluation score;

and the determining module is used for determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing a risk assessment method when executing the computer program:

In a fourth aspect, the present application further provides a storage medium containing electronic device executable instructions, which are used for executing the risk assessment method according to the present application when executed by an electronic device processor.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings.

Fig. 1 is a schematic view of a first scenario of a risk assessment method according to an embodiment of the present application.

Fig. 2 is a schematic diagram of a second scenario of a risk assessment method according to an embodiment of the present application.

Fig. 3 is a first flowchart of a risk assessment method according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a third scenario of a risk assessment method according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of an auto-encoder according to an embodiment of the present application.

Fig. 6 is a second flowchart of the risk assessment method according to the embodiment of the present application.

Fig. 7 is a schematic structural diagram of a risk assessment device according to an embodiment of the present application.

Fig. 8 is a schematic view of a first structure of an electronic device according to an embodiment of the present application.

Fig. 9 is a second structural schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are for purposes of illustration and not limitation. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.

The embodiment of the application provides a risk assessment method, which is applied to electronic equipment. The main body of the risk assessment method may be the risk assessment apparatus provided in the embodiment of the present application, or an electronic device integrated with the risk assessment apparatus, where the risk assessment apparatus may be implemented in a hardware or software manner, and the electronic device may be a device with processing capability and configured with a processor, such as a smart phone, a tablet computer, a palmtop computer, a notebook computer, or a desktop computer.

Referring to fig. 1, fig. 1 is a schematic view of a first scenario of a risk assessment method according to an embodiment of the present application. When the client detects a payment request based on a payment task A triggered by a user, the client sends the payment request of the payment task A to the server. After receiving a payment request sent by a client, the server performs risk assessment on the payment task A by combining the first risk assessment model and the second risk assessment model. And if the risk of the payment task A is not high, the server side responds to the payment request of the payment task A, processes the payment task A and sends a payment success notification to the client side. And if the risk of the payment task A is high, in order to improve the safety, the server prohibits responding to the payment request of the payment task A and sends an authentication request to the client.

Referring to fig. 2, fig. 2 is a schematic diagram of a second scenario of the risk assessment method according to the embodiment of the present application. And when the client detects a payment request based on a payment task B triggered by a user, the client carries out risk assessment on the payment task B by combining the first risk assessment model and the second risk assessment model. And if the risk of the payment task B is not high, the client sends the payment request of the payment task B to the server so that the server can process the payment task B according to the payment request. If the risk of the payment task B is high, the client needs the user to confirm whether the payment task B is executed again and requires the user to provide authentication. And after the user reconfirms and the identity is qualified, the client sends the payment request of the payment task B to the server so that the server processes the payment task B according to the payment request.

Referring to fig. 3, fig. 3 is a first flowchart of a risk assessment method according to an embodiment of the present disclosure. The process of the risk assessment method is as follows:

101. and acquiring data to be evaluated, and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm.

In the embodiment of the application, when the task to be executed is detected, the electronic equipment acquires data to be evaluated corresponding to the task to be executed, and extracts a first feature vector from the data to be evaluated through a feature extraction algorithm so as to enable a risk evaluation model to carry out risk scoring.

The tasks to be executed are different, and the corresponding data to be evaluated are also different. For example, the data to be evaluated corresponding to the task to be performed "membership recharge for application a" is different from the data to be evaluated corresponding to the task to be performed "download application a". In addition, the data to be evaluated may be multidimensional data, and the data to be evaluated at least includes task data, account data, and device data.

For example, suppose that the electronic device has a task to be performed: application B is downloaded at the application store. The data to be evaluated corresponding to the task to be executed at least comprises the following data: task data (such as name of downloaded application, download time, download place, etc.), account data (such as total number of times an account logs in an application store, time set of the account logging in the application store, login place set of the account logging in the application store, total number of times an account downloads an application, type of application downloaded by the account, etc.), device data (such as total number of times a device logs in an application store, time set of the device logging in an application store, login place set of the device logging in an application store, total number of times a device downloads an application, type of application downloaded by the device, etc.).

It can be understood that the same device can log in a plurality of accounts, and one account can also log in a plurality of devices. Therefore, when the electronic equipment acquires the data to be evaluated, the account data and the equipment data are acquired, so that the data to be evaluated can be more comprehensive, and the accuracy of risk evaluation is improved.

Wherein the feature extraction algorithm is used for extracting features from the data and generating feature vectors according to the features. For example, suppose that the electronic device extracts 1000 features from the data to be evaluated by a feature extraction algorithm, and then generates a 1000-dimensional first feature vector according to the 1000 features, so as to provide the risk evaluation model for risk evaluation.

In some embodiments, after the electronic device obtains the data to be evaluated, the electronic device performs cleaning processing and completion processing on the data to be evaluated, and then extracts a first feature vector from the processed data to be evaluated through a feature extraction algorithm.

102. And scoring the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score.

In the embodiment of the application, after the first feature vector is obtained, the electronic device inputs the first feature vector into the first risk assessment model, and scores the data to be assessed through the first risk assessment model to obtain a first assessment score.

The first risk assessment model adopts an unsupervised algorithm and can be used for carrying out risk scoring on data to be assessed. For example, the first risk assessment model may be trained by a pre-built cluster analysis model. For example, the first risk assessment model can be obtained by training a pre-built isolated forest model. Alternatively, the first risk assessment model may also be another model capable of performing risk scoring on data to be assessed through an unsupervised algorithm, and the embodiment of the present application is not particularly limited.

103. And scoring the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score.

In the embodiment of the application, after the first feature vector is obtained, the electronic device inputs the first feature vector into the second risk assessment model, and the data to be assessed is scored through the second risk assessment model to obtain a second assessment score.

The second risk assessment model adopts a supervised algorithm and can be used for carrying out risk scoring on data to be assessed. For example, the second risk assessment model may be trained by a pre-built classification model. For example, the second risk assessment model may be trained by a pre-constructed neural network model. Alternatively, the second risk assessment model may also be another model capable of performing risk scoring on data to be assessed through a supervised algorithm, and the embodiment of the present application is not particularly limited.

104. And determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In the embodiment of the application, after the first evaluation score and the second evaluation score are obtained, the electronic device may determine a target evaluation score of the data to be evaluated according to the first evaluation score and the second evaluation score, and then determine a preset risk type corresponding to the target evaluation score as the target risk type of the data to be evaluated.

For example, when determining the target evaluation score of the data to be evaluated from the first evaluation score and the second evaluation score, the electronic device may use the sum of the first evaluation score and the second evaluation score as the target evaluation score of the data to be evaluated.

For example, when determining the target evaluation score of the data to be evaluated according to the first evaluation score and the second evaluation score, the electronic device may determine a first weight coefficient corresponding to the first evaluation score and a second weight coefficient corresponding to the second evaluation score according to the type of the data to be evaluated. And calculating a target evaluation score of the data to be evaluated based on the first weight coefficient, the second weight coefficient, the first evaluation score and the second evaluation score.

When the type of data to be evaluated uses the first risk evaluation model more accurately than the second risk evaluation model, a first weight coefficient corresponding to the first evaluation score is greater than a second weight coefficient corresponding to the second evaluation score. When the type of data to be evaluated uses the second risk assessment model with higher accuracy, the first weight coefficient corresponding to the first assessment score is smaller than the second weight coefficient corresponding to the second assessment score, compared with the first risk assessment model.

In another embodiment, after obtaining the first evaluation score, the electronic device may determine the target risk type of the data to be evaluated directly according to the first evaluation score. For example, when the first risk assessment model is obtained by training a pre-built isolated forest model, the value range of the first assessment score is between 0 and 1. The smaller the first evaluation score is, the lower the risk degree of the target risk type of the data to be evaluated is, and the larger the first evaluation score is, the higher the risk degree of the target risk type of the data to be evaluated is.

In another embodiment, after obtaining the second evaluation score, the electronic device may determine the target risk type of the data to be evaluated directly according to the second evaluation score. For example, when the second risk assessment model is trained by a pre-built classification model, the magnitude of the second assessment score is positively or negatively correlated with the risk degree of the target risk type of the data to be assessed.

As can be seen from the above, in the embodiment of the present application, the electronic device scores the data to be evaluated in two ways: the data to be evaluated is scored through the first risk evaluation model, the data to be evaluated is scored through the second risk evaluation model, and finally the target risk type of the data to be evaluated is comprehensively determined by combining the scoring results of the two modes, so that the accuracy of risk evaluation can be improved.

Referring to fig. 4, fig. 4 is a schematic diagram of a third scenario of the risk assessment method according to the embodiment of the present application. In some embodiments, when scoring the data to be assessed according to the first feature vector and the first risk assessment model to obtain a first assessment score, the electronic device may perform the following:

coding the first feature vector through a coding algorithm to obtain a second feature vector, wherein the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

and scoring the data to be evaluated based on the second feature vector and the first risk evaluation model to obtain a first evaluation score.

The encoding algorithm is used for encoding the feature vector, so that vector elements of the feature vector are changed from discrete features to continuous features. The encoding algorithm in the scheme is obtained based on pre-built self-encoder (AE) training.

For example, the electronic device obtains a plurality of sample vectors, constituting a first training set. The self-encoder is then trained using the first training set to update model parameters of the self-encoder. And finally, constructing an encoding algorithm based on the encoder in the self-encoder after the model parameters are updated. The self-encoder includes an encoder (encoder) and a decoder (decoder), among others.

Referring to fig. 5, fig. 5 is a schematic structural diagram of a self-encoder according to an embodiment of the present disclosure. The self-encoder performs an encoding operation and a decoding operation on each sample vector X during training. The encoding operation is to map the sample vector X to a feature space through an encoder to obtain an abstract feature vector Z. The decoding operation refers to the abstraction of the feature vector by the decoderZ is mapped back to the original space to obtain a reconstructed vector

It will be appreciated that when the sample vector X is compared to the reconstructed vector

When the error of (2) is minimum, the self-encoder training is completed.

It should be noted that, because the feature vector whose vector elements are discrete features is not suitable for risk scoring using the first risk assessment model, the feature vector whose vector elements are discrete features is converted into the feature vector whose vector elements are continuous features by the encoding algorithm, so that the feature vector is suitable for risk scoring using the first risk assessment model, thereby improving the accuracy of risk assessment.

Referring to fig. 6, fig. 6 is a second flow chart of the risk assessment method according to the embodiment of the present application. The process of the risk assessment method is as follows:

201. and acquiring data to be evaluated, and performing feature extraction on the data to be evaluated through a feature extraction algorithm to obtain a first numerical feature and a text feature.

Wherein, the first numerical characteristic refers to the characteristic expressed by numerical value, such as: the electronic equipment uses a feature extraction algorithm to determine the frequency of downloading the application program C by the equipment: 5' carrying out feature extraction to obtain a first numerical feature: "5". Text features refer to features represented in text, such as: the electronic equipment uses a feature extraction algorithm to' the location of the equipment downloading the application program C: beijing' performs feature extraction to obtain text features: "Beijing".

202. And normalizing the first numerical characteristic and converting the text characteristic to convert the text characteristic into a second numerical characteristic.

The normalization process is to normalize the value representing the first numerical characteristic to a value within a predetermined range (e.g., a range of 0 to 1).

The purpose of the conversion process in this scheme is to convert the text feature into a second numerical feature. The second numerical characteristic is also a characteristic expressed by a numerical value.

For example, when the electronic device converts the text feature "beijing" into the second numerical feature, it determines whether the electronic device is currently located in beijing, and if the electronic device is currently located in beijing, the text feature "beijing" is converted into the second numerical feature: "1", if the electronic device is not located in Beijing, converting the text feature "Beijing" into a second numerical feature: "0".

203. Based on the first numerical feature and the second numerical feature, a first feature vector is generated.

In the embodiment of the application, after the first numerical feature and the second numerical feature are obtained, the electronic device generates a first feature vector according to the first numerical feature and the second numerical feature according to a preset sequence of each feature.

For example, assume that the electronic device obtains 2 first numerical features and 1 second numerical feature. The 2 first numerical characteristics are respectively: 0.05 (obtained from the number of times of account downloading application D "5"), 0.1 (obtained from the number of times of account login "100"), and 1 second numerical features are: 1 (obtained from the download location "beijing"). If the account login times are vector elements serving as a first dimension, the account download application program D is vector elements serving as a second dimension, and the download location is vector elements serving as a third dimension, the preset sequence of the first numerical feature "0.05" is 2, the preset sequence of the first numerical feature "0.1" is 1, and the preset sequence of the second numerical feature "1" is 3. The first feature vector generated by the electronic device is (0.1, 0.05, 1).

204. And determining a weight value corresponding to each vector element in the second risk assessment model according to the arrangement sequence of the vector elements in the first feature vector, wherein the vector elements comprise a first numerical feature and a second numerical feature.

In the embodiment of the application, after the first feature vector is generated, the electronic device determines, according to the arrangement order of the vector elements in the first feature vector, a weight value corresponding to each vector element in the second risk assessment model. For example, for vector elements arranged in the second dimension in the first feature vector, their corresponding weight values in the second risk assessment model are also arranged in the second dimension.

The weight value may represent the importance of the feature represented by the vector element. The larger the weight value, the more important the feature represented by the vector element is. The smaller the weight value, the less important the feature represented by the vector element.

It should be noted that, because the content of the fourth feature vector used for training the second risk assessment model and the content of the first feature vector in the same vector element are the same, if the second vector element of the fourth feature vector and the second vector element of the first feature vector both represent the account login times. The weight value of each vector element in the second risk assessment model can represent the importance of the feature represented by the vector element.

205. And adjusting the size of each vector element according to the size of the corresponding weight value to obtain a third feature vector.

In the embodiment of the application, after determining the weight value of each vector element corresponding to the second risk assessment model, the size of each vector element is adjusted according to the size of the corresponding weight value. If the corresponding weight value is large, it indicates that the vector element corresponding to the weight value is important, and the electronic device may increase the value of the vector element, so that the vector element can be distinguished from other vector elements.

In some embodiments, when adjusting the size of each vector element according to the size of the corresponding weight value, the electronic device may increase the value of a preset number of vector elements for which the corresponding weight value is the largest. For example, assume that the weight values corresponding to 7 vector elements are noted as: 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, the preset number is 3, and the electronic device increases the values of the vector element corresponding to the weight value of 0.5, the vector element corresponding to 0.6, and the vector element corresponding to 0.7. The preset number is preset in the electronic device, and the preset number can be determined autonomously by the electronic device or manually by a user.

206. And scoring the data to be evaluated according to the third feature vector and the first risk evaluation model to obtain a first evaluation score.

In the embodiment of the application, after the third feature vector is obtained, the electronic device inputs the third feature vector into the first risk assessment model, and the data to be assessed is scored through the first risk assessment model to obtain a first assessment score.

For example, assume that a first risk assessment model is trained from a pre-built isolated forest model. After the third feature vector is obtained, the electronic device inputs the third feature vector into the first risk assessment model, determines the average path length of each vector element in the second risk assessment model, and obtains and outputs a first assessment score according to the average path length of each vector element. Wherein the first risk assessment model comprises at least two isolated trees. The number of nodes traversed by a vector element in each isolated tree is taken as the path length of the vector element in the isolated tree. The mean path length of the vector elements in the second risk assessment model is the mean of the path lengths of the vector elements in each of the orphan trees.

It should be noted that, because the third feature vector adjusts the value of the vector element corresponding to the large weight value, so that the vector element is distinguished from other vector elements, when the data to be evaluated is evaluated by the first risk evaluation model, the electronic device may use the sub-score obtained based on the vector element as an important component of the first evaluation score.

207. And scoring the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score.

For example, assume that the second risk assessment model is derived from a pre-built classification model. After the first feature vector is obtained, the electronic device inputs the first feature vector into the second risk assessment model, then determines a weight value corresponding to each vector element in the second risk assessment model according to the arrangement sequence of the vector elements in the first feature vector, and performs weighted summation processing based on the weight values and the vector elements to obtain and output a second assessment score.

208. And determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In the embodiment of the application, after the first evaluation score and the second evaluation score are obtained, the electronic device may determine a target evaluation score of the data to be evaluated according to the first evaluation score and the second evaluation score, and then determine a preset risk type corresponding to the target evaluation score as a target risk type of the data to be evaluated.

209. And when the risk level of the target risk type is lower than or equal to the preset level, executing a task to be executed corresponding to the data to be evaluated.

In the embodiment of the application, after the target risk type of the data to be evaluated is determined, when the risk level of the target risk type is lower than or equal to the preset level, the electronic device may execute the task to be executed corresponding to the data to be evaluated. When the risk level of the target risk type is lower than or equal to the preset level, the electronic device may prohibit the task to be executed corresponding to the data to be evaluated, and output a prompt message to the user, such as a prompt message of "the task to be executed is high in risk level".

As can be seen from the above, in the embodiment of the application, before the electronic device processes the task to be executed, risk assessment is performed through the data to be assessed corresponding to the task to be executed, the task to be executed is executed when the risk level is lower than or equal to the preset level, and the task to be executed is prohibited to be executed and prompt information is output to a user when the risk level is higher than the preset level, so that the safety of the electronic device can be improved.

In some embodiments, the second risk assessment model is a classification model, and the electronic device may further perform the following:

acquiring a plurality of sample evaluation data;

extracting a fourth feature vector from the sample evaluation data by a feature extraction algorithm;

acquiring a sample risk type of each sample evaluation data, and forming a training set according to the fourth feature vector and the sample risk type;

the classification model is trained using a training set to update model parameters of the classification model.

The specific implementation of extracting the fourth feature vector from the sample evaluation data through the feature extraction algorithm may refer to the specific implementation of extracting the first feature vector from the data to be evaluated through the feature extraction algorithm. It should be noted that a fourth feature vector may be extracted from a sample evaluation data. A fourth feature vector corresponds to a sample risk type.

In addition, the embodiment of the present application is not particularly limited to the method for acquiring the sample risk type in this scheme. For example, the electronic device may enable the obtaining of the sample risk type by receiving the sample risk type set by the user for the sample evaluation data. For example, the electronic device can automatically determine a sample risk type for the sample evaluation data, and so forth.

In some embodiments, the electronic device may perform the following when obtaining the sample risk type for each sample evaluation data:

and grading the sample evaluation data through the first risk evaluation model and the corresponding fourth feature vector to obtain a third evaluation score, and determining the sample risk type of the sample evaluation data according to the third evaluation score.

In the scheme, the electronic equipment automatically determines the sample risk type of the sample evaluation data through the first risk evaluation model, so that manual operation can be reduced, and the time for determining the sample risk type is saved, thereby shortening the training time of the second risk evaluation model and improving the training efficiency of the second risk evaluation model.

It should be noted that, based on the scheme, the sample risk type of the sample evaluation data is automatically determined through the first risk evaluation model, so that the training efficiency of the second risk evaluation model is improved, and the electronic device can train the second risk evaluation model in a short time, for example, the electronic device trains the second risk evaluation model at preset time intervals (for example, 30 minutes), so that the real-time performance of the second risk evaluation model is improved.

In some embodiments, in determining the sample risk type for the sample evaluation data based on the third evaluation score, the electronic device may perform the following:

when the third evaluation score is located in the preset interval, taking a preset risk type corresponding to the third evaluation score as a sample risk type of the sample evaluation data;

and when the third evaluation score is not in the preset interval, acquiring a sample risk type set for the sample evaluation data by the user.

The electronic equipment is preset with at least two preset intervals. Different preset intervals correspond to different sample risk types. The sample risk type corresponding to the preset interval where the third evaluation score is located is the sample risk type of the sample evaluation data.

It should be noted that, when the preset interval is preset, some unstable sample risk types corresponding to the third evaluation scores are considered, and in order to improve the accuracy of the sample risk types and the training effect of the second risk evaluation model, the electronic device only considers the stable third evaluation scores of the corresponding sample risk types when the preset interval is set. And for the third evaluation score with unstable corresponding sample risk types, adopting a mode that a user manually determines the sample risk types. The training effect of the second risk assessment model can be improved, and the training efficiency of the second risk assessment model can be improved to a certain extent.

For example, assume that the sample risk types include a no risk type and a at risk type. The first risk assessment model is obtained by training a pre-built isolated forest model, and the value range of the third assessment score is 0-1. Since it is difficult for the sample evaluation data having the third evaluation score around 0.5 to distinguish between the no-risk type and the at-risk type, the preset intervals set in advance by the electronic device include a no-risk interval (e.g., [0, 0.2]) and a at-risk interval (e.g., [0.8, 1 ]).

Fig. 7 is a schematic structural diagram of a risk assessment apparatus provided in an embodiment of the present application, where the apparatus is used to execute the risk assessment method provided in the foregoing embodiment, and has corresponding functional modules and beneficial effects of the execution method. The risk assessment apparatus 300 specifically includes: a first obtaining module 301, a first scoring module 302, a second scoring module 303, and a determining module 304, wherein:

the first obtaining module 301 is configured to obtain data to be evaluated, and extract a first feature vector from the data to be evaluated through a feature extraction algorithm;

a first scoring module 302, configured to score the data to be evaluated according to the first feature vector and a first risk evaluation model, so as to obtain a first evaluation score;

the second scoring module 303 is configured to score the data to be evaluated according to the first feature vector and a second risk evaluation model to obtain a second evaluation score;

a determining module 304, configured to determine a target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In some embodiments, when scoring the data to be evaluated according to the first feature vector and the first risk assessment model to obtain a first assessment score, the first scoring module 302 may be configured to:

In some embodiments, when extracting the first feature vector from the data to be evaluated through the feature extraction algorithm, the first obtaining module 301 may be configured to:

performing feature extraction on the data to be evaluated through a feature extraction algorithm to obtain a first numerical feature and a text feature;

normalizing the first numerical feature, and converting the text feature to convert the text feature into a second numerical feature;

generating a first feature vector based on the first numerical feature and the second numerical feature.

In some embodiments, the first risk assessment model is obtained by training a pre-built isolated forest model, and the second risk assessment model is obtained by a pre-built classification model;

when scoring the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score, the first scoring module 302 may be configured to:

determining a weight value corresponding to each vector element in the second risk assessment model according to an arrangement order of the vector elements in the first feature vector, wherein the vector elements comprise the first numerical feature and the second numerical feature;

adjusting the size of each vector element according to the size of the corresponding weight value to obtain a third feature vector;

and scoring the data to be evaluated according to the third feature vector and the first risk evaluation model to obtain a first evaluation score.

In some embodiments, when the size of each vector element is adjusted according to the size of the corresponding weight value, the first scoring module 302 may be configured to:

and increasing the value of the vector elements with the maximum weight value in the preset number.

In some embodiments, after determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score, the risk assessment apparatus 300 further comprises:

and the execution module is used for executing the task to be executed corresponding to the data to be evaluated when the risk grade of the target risk type is lower than or equal to a preset grade.

In some embodiments, the second risk assessment model is a classification model, and the risk assessment apparatus 300 further includes:

the second acquisition module is used for acquiring a plurality of sample evaluation data;

an extraction module for extracting a fourth feature vector from the sample evaluation data by the feature extraction algorithm;

the third acquisition module is used for acquiring the sample risk type of each sample evaluation data, and forming a training set according to the fourth feature vector and the sample risk type;

and the training module is used for training the classification model by using the training set so as to update the model parameters of the classification model.

In some embodiments, the third obtaining module, in obtaining the sample risk type for each sample evaluation data, may be configured to:

and scoring the sample evaluation data through the first risk evaluation model and the corresponding fourth feature vector to obtain a third evaluation score, and determining the sample risk type of the sample evaluation data according to the third evaluation score.

In some embodiments, in determining the sample risk type for the sample evaluation data from the third evaluation score, the third obtaining module may be configured to:

when the third evaluation score is within a preset interval, taking a preset risk type corresponding to the third evaluation score as a sample risk type of the sample evaluation data;

and when the third evaluation score is not located in the preset interval, acquiring a sample risk type set by the user for the sample evaluation data.

As can be seen from the above, in the risk assessment apparatus 300 provided in this embodiment of the application, the first obtaining module 301 obtains data to be assessed, and extracts a first feature vector from the data to be assessed through a feature extraction algorithm, then the first scoring module 302 scores the data to be assessed according to the first feature vector and the first risk assessment model to obtain a first assessment score, the second scoring module 303 scores the data to be assessed according to the first feature vector and the second risk assessment model to obtain a second assessment score, and finally the determining module 304 determines the target risk type of the data to be assessed according to the first assessment score and the second assessment score. And comprehensively determining the target risk type of the data to be evaluated by combining the grading results of the first risk evaluation model and the second risk evaluation model, so that the accuracy of risk evaluation can be improved.

It should be noted that the risk assessment device provided in the embodiment of the present application and the risk assessment method in the above embodiments belong to the same concept, any method provided in the embodiment of the risk assessment method may be run on the risk assessment device, and the specific implementation process thereof is described in detail in the embodiment of the risk assessment method, and is not described herein again.

An electronic device is further provided in the embodiment of the present application, please refer to fig. 8, which is a first structural schematic diagram of the electronic device provided in the embodiment of the present application. The electronic device 400 comprises a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.

The processor 401 is a control center of the electronic device 400, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device 400 and processes data by running or loading a computer program stored in the memory 402 and calling data stored in the memory 402.

The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the computer programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like.

Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.

In this embodiment, the processor 401 in the electronic device 400 loads instructions corresponding to processes of one or more computer programs into the memory 402 according to the following steps, and the processor 401 runs the computer programs stored in the memory 402, thereby implementing various functions, as follows:

Referring to fig. 9, fig. 9 is a second schematic structural diagram of an electronic device according to an embodiment of the present application, and the difference from the electronic device shown in fig. 8 is that the electronic device further includes: radio frequency circuit 403, display 404, control circuit 405, input unit 406, audio circuit 407, sensor 408, and power supply 409. The processor 401 is electrically connected to the rf circuit 403, the display 404, the control circuit 405, the input unit 406, the audio circuit 407, the sensor 408, and the power source 409.

The radio frequency circuit 403 is used for transceiving radio frequency signals to communicate with a network device or other electronic devices through wireless communication.

The display screen 404 may be used to display information entered by or provided to the user as well as various graphical user interfaces of the electronic device, which may be comprised of images, text, icons, video, and any combination thereof.

The control circuit 405 is electrically connected to the display screen 404, and is configured to control the display screen 404 to display information.

The input unit 406 may be used to receive input numbers, character information, or user characteristic information (e.g., fingerprint), and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. The input unit 406 may include a fingerprint recognition module.

The audio circuit 407 may provide an audio interface between the user and the electronic device through a speaker, microphone. Wherein the audio circuit 407 comprises a microphone. The microphone is electrically connected to the processor 401. The microphone is used for receiving voice information input by a user.

The sensor 408 is used to collect external environmental information. The sensor 408 may include one or more of an ambient light sensor, an acceleration sensor, a gyroscope, and the like.

The power supply 409 is used to power the various components of the electronic device 400. In some embodiments, the power source 409 may be logically connected to the processor 401 through a power management system, so that functions of managing charging, discharging, and power consumption are implemented through the power management system.

Although not shown in fig. 9, the electronic device 400 may further include a camera, a bluetooth module, and the like, which are not described in detail herein.

In this embodiment, the processor 401 in the electronic device 400 loads instructions corresponding to one or more processes of the computer program into the memory 402 according to the following steps, and the processor 401 runs the computer program stored in the memory 402, so as to implement various functions, as follows:

In some embodiments, when the data to be evaluated is scored according to the first feature vector and the first risk evaluation model to obtain a first evaluation score, the processor 401 is configured to:

In some embodiments, when extracting the first feature vector from the data to be evaluated by the feature extraction algorithm, the processor 401 is configured to perform:

when the data to be evaluated is scored according to the first feature vector and the first risk evaluation model to obtain a first evaluation score, the processor 401 is configured to execute:

In some embodiments, when the size of each of the vector elements is adjusted according to the size of the corresponding weight value, the processor 401 is configured to perform:

In some embodiments, after determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score, the processor 401 is further configured to:

and when the risk level of the target risk type is lower than or equal to a preset level, executing a task to be executed corresponding to the data to be evaluated.

In some embodiments, the second risk assessment model is a classification model, and the processor 401 is further configured to perform:

obtaining a plurality of sample evaluation data;

extracting a fourth feature vector from the sample evaluation data by the feature extraction algorithm;

training the classification model using the training set to update model parameters of the classification model.

In some embodiments, in obtaining the sample risk type for each sample evaluation data, processor 401 is configured to:

In some embodiments, in determining the sample risk type of the sample evaluation data according to the third evaluation score, the processor 401 is configured to perform:

when the third evaluation score is located in a preset interval, taking a preset risk type corresponding to the third evaluation score as a sample risk type of the sample evaluation data;

As can be seen from the above, after the electronic device obtains the data to be evaluated, the electronic device extracts the first feature vector from the data to be evaluated through the feature extraction algorithm, scores the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score, scores the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score, and finally determines the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score. And comprehensively determining the target risk type of the data to be evaluated by combining the grading results of the first risk evaluation model and the second risk evaluation model, so that the accuracy of risk evaluation can be improved.

An embodiment of the present application further provides a storage medium, where the storage medium stores a computer program, and when the computer program runs on a computer, the computer is caused to execute the risk assessment method in any one of the above embodiments, for example: acquiring data to be evaluated, and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm; according to the first feature vector and a first risk assessment model, scoring the data to be assessed to obtain a first assessment score; according to the first feature vector and a second risk assessment model, scoring the data to be assessed to obtain a second assessment score; and determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.

In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

It should be noted that, for the risk assessment method in the embodiment of the present application, it may be understood by a person skilled in the art that all or part of the process of implementing the risk assessment method in the embodiment of the present application may be implemented by controlling related hardware through a computer program, where the computer program may be stored in a computer-readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and the process of executing the process may include the process of the embodiment of the risk assessment method. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

Claims

A method of risk assessment, comprising

Acquiring data to be evaluated, and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm;

according to the first feature vector and a first risk assessment model, scoring the data to be assessed to obtain a first assessment score;

according to the first feature vector and a second risk assessment model, scoring the data to be assessed to obtain a second assessment score;

and determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.
The method of claim 1, wherein the scoring the data to be evaluated according to the first feature vector and a first risk assessment model to obtain a first assessment score comprises:

coding the first feature vector through a coding algorithm to obtain a second feature vector, wherein the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

and scoring the data to be evaluated based on the second feature vector and the first risk evaluation model to obtain a first evaluation score.
The method of claim 1, wherein said extracting a first feature vector from the data to be evaluated by a feature extraction algorithm comprises:

performing feature extraction on the data to be evaluated through a feature extraction algorithm to obtain a first numerical feature and a text feature;

normalizing the first numerical characteristic, and converting the text characteristic to convert the text characteristic into a second numerical characteristic;

generating a first feature vector based on the first numerical feature and the second numerical feature.
The method according to claim 1, wherein the first risk assessment model is trained from a pre-built isolated forest model and the second risk assessment model is derived from a pre-built classification model;

the scoring the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score includes:

determining a weight value corresponding to each vector element in the second risk assessment model according to an arrangement order of the vector elements in the first feature vector, wherein the vector elements comprise the first numerical feature and the second numerical feature;

adjusting the size of each vector element according to the size of the corresponding weight value to obtain a third feature vector;

and scoring the data to be evaluated according to the third feature vector and the first risk evaluation model to obtain a first evaluation score.
The method of claim 4, wherein said resizing each of said vector elements according to a magnitude of a corresponding weight value comprises:

and increasing the value of the vector elements with the maximum weight value in the preset number.
The method of claim 1, wherein the determining a target risk type for the data to be evaluated according to the first evaluation score and the second evaluation score further comprises:

and when the risk level of the target risk type is lower than or equal to a preset level, executing a task to be executed corresponding to the data to be evaluated.
The method of claim 1, wherein the second risk assessment model is a classification model, the method further comprising:

obtaining a plurality of sample evaluation data;

extracting a fourth feature vector from the sample evaluation data by the feature extraction algorithm;

obtaining a sample risk type of each sample evaluation data, and forming a training set according to the fourth feature vector and the sample risk type;

training the classification model using the training set to update model parameters of the classification model.
The method of claim 7, wherein the obtaining of the sample risk type for each sample evaluation data comprises:

and scoring the sample evaluation data through the first risk evaluation model and the corresponding fourth feature vector to obtain a third evaluation score, and determining the sample risk type of the sample evaluation data according to the third evaluation score.
The method of claim 8, wherein said determining a sample risk type for the sample evaluation data from the third evaluation score comprises:

when the third evaluation score is within a preset interval, taking a preset risk type corresponding to the third evaluation score as a sample risk type of the sample evaluation data;

and when the third evaluation score is not located in the preset interval, acquiring a sample risk type set for the sample evaluation data by a user.
A risk assessment device, comprising:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring data to be evaluated and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm;

the first scoring module is used for scoring the data to be evaluated according to the first feature vector and a first risk evaluation model to obtain a first evaluation score;

the second scoring module is used for scoring the data to be evaluated according to the first feature vector and a second risk evaluation model to obtain a second evaluation score;

and the determining module is used for determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.
An electronic device, comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements a risk assessment method:

acquiring data to be evaluated, and extracting a first feature vector from the data to be evaluated through a feature extraction algorithm;

according to the first feature vector and a first risk assessment model, scoring the data to be assessed to obtain a first assessment score;

according to the first feature vector and a second risk assessment model, scoring the data to be assessed to obtain a second assessment score;

and determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score.
The electronic device of claim 11, wherein the scoring the data to be evaluated according to the first feature vector and a first risk assessment model to obtain a first assessment score, and the processor is configured to:

coding the first feature vector through a coding algorithm to obtain a second feature vector, wherein the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

and scoring the data to be evaluated based on the second feature vector and the first risk evaluation model to obtain a first evaluation score.
The electronic device of claim 11, wherein the extracting a first feature vector from the data to be evaluated by a feature extraction algorithm, the processor to perform:

performing feature extraction on the data to be evaluated through a feature extraction algorithm to obtain a first numerical feature and a text feature;

normalizing the first numerical feature, and converting the text feature to convert the text feature into a second numerical feature;

generating a first feature vector based on the first numerical feature and the second numerical feature.
The electronic device of claim 11, wherein the first risk assessment model is trained from a pre-built isolated forest model and the second risk assessment model is derived from a pre-built classification model;

the data to be evaluated is scored according to the first feature vector and a first risk evaluation model to obtain a first evaluation score, and the processor is configured to execute:

determining a weight value corresponding to each vector element in the second risk assessment model according to an arrangement order of the vector elements in the first feature vector, wherein the vector elements comprise the first numerical feature and the second numerical feature;

adjusting the size of each vector element according to the size of the corresponding weight value to obtain a third feature vector;

and scoring the data to be evaluated according to the third feature vector and the first risk evaluation model to obtain a first evaluation score.
The electronic device of claim 14, wherein the resizing each of the vector elements according to a magnitude of a corresponding weight value, the processor to perform:

and increasing the value of the vector elements with the maximum weight value in the preset number.
The electronic device of claim 11, wherein after determining the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score, the processor is further configured to:

and when the risk level of the target risk type is lower than or equal to a preset level, executing a task to be executed corresponding to the data to be evaluated.
The electronic device of claim 11, wherein the second risk assessment model is a classification model, the processor further configured to perform:

obtaining a plurality of sample evaluation data;

extracting a fourth feature vector from the sample evaluation data by the feature extraction algorithm;

obtaining a sample risk type of each sample evaluation data, and forming a training set according to the fourth feature vector and the sample risk type;

training the classification model using the training set to update model parameters of the classification model.
The electronic device of claim 17, wherein the obtaining of the sample risk type for each sample evaluation data, the processor is configured to perform:

and scoring the sample evaluation data through the first risk evaluation model and the corresponding fourth feature vector to obtain a third evaluation score, and determining the sample risk type of the sample evaluation data according to the third evaluation score.
The electronic device of claim 18, wherein the determining a sample risk type for the sample evaluation data from the third evaluation score, the processor to perform:

when the third evaluation score is within a preset interval, taking a preset risk type corresponding to the third evaluation score as a sample risk type of the sample evaluation data;

and when the third evaluation score is not located in the preset interval, acquiring a sample risk type set for the sample evaluation data by a user.
A storage medium containing electronic device-executable instructions, which when executed by an electronic device processor, are for performing the risk assessment method of any one of claims 1 to 9.