WO2021184211A1

WO2021184211A1 - Risk evaluation method and apparatus, electronic device, and storage medium

Info

Publication number: WO2021184211A1
Application number: PCT/CN2020/079761
Authority: WO
Inventors: 程肯
Original assignee: 深圳市欢太科技有限公司; Oppo广东移动通信有限公司
Priority date: 2020-03-17
Filing date: 2020-03-17
Publication date: 2021-09-23
Also published as: CN115088007A

Abstract

Disclosed are a risk evaluation method and apparatus, an electronic device, and a storage medium. The method comprises: extracting a first feature vector from acquired data to be evaluated; determining, according to the first feature vector and a first risk evaluation model, a first evaluation score of the data to be evaluated; determining, according to the first feature vector and a second risk evaluation model, a second evaluation score of the data to be evaluated; and determining, according to the first evaluation score and the second evaluation score, a target risk type of the data to be evaluated.

Description

Risk assessment method, device, electronic equipment and storage medium

Technical field

The embodiments of the present application relate to computer technology, and in particular to a risk assessment method, device, electronic equipment, and storage medium.

Background technique

With the continuous development of electronic devices, the functions of electronic devices have become more diversified. While this is convenient for users to use, it will also greatly increase the difficulty of security management of electronic equipment. For example, with the use of electronic device payment functions, users can make payments through the payment code of the electronic device. Although the payment function brings convenience to users' lives, there are certain risks when users perform payment tasks, such as the disclosure of payment codes.

In related technologies, electronic devices perform risk assessment on tasks to be performed to solve safety problems caused by the diversified functions of electronic devices. Currently, the risk assessment of tasks to be performed requires manual manual operations, such as manual manual assessment of task data and warnings to users who perform high-risk services. The subjectiveness of the assessment criteria leads to low risk assessment accuracy.

Summary of the invention

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

In the 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;

Score the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score;

Score the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score;

According to the first evaluation score and the second evaluation score, the target risk type of the data to be evaluated is determined.

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

The first acquisition module is configured to acquire the data to be evaluated, and extract the first feature vector from the data to be evaluated through a feature extraction algorithm;

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

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

The determining module is configured to determine 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 also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and running on the processor, and the processor implements the risk when the computer program is executed. assessment method:

In a fourth aspect, an embodiment of the present application also provides a storage medium containing executable instructions of an electronic device. The executable instructions of the electronic device are used to perform the risk assessment described in the embodiments of the present application when executed by the processor of the electronic device. method.

Description of the drawings

By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes, and advantages of the present application will become more apparent.

Fig. 1 is a schematic diagram of a first scenario of a risk assessment method provided by an embodiment of the present application.

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

FIG. 3 is a schematic diagram of the first process of a risk assessment method provided by an embodiment of the present application.

FIG. 4 is a schematic diagram of a third scenario of a risk assessment method provided by an embodiment of the present application.

Fig. 5 is a schematic structural diagram of a self-encoder provided by an embodiment of the present application.

FIG. 6 is a schematic diagram of the second process of the risk assessment method provided by the embodiment of the present application.

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

FIG. 8 is a first structural schematic diagram of an electronic device provided by an embodiment of the present application.

FIG. 9 is a schematic diagram of a second structure of an electronic device provided by an embodiment of the present application.

Detailed ways

The application will be further described in detail below with reference to the drawings and embodiments. It is understandable that the specific embodiments described here are used to explain the application, but not to limit the application. In addition, it should be noted that, for ease of description, the drawings only show a part of the structure related to the present application instead of all of the structure.

The embodiment of the present application provides a risk assessment method, which is applied to an electronic device. Wherein, the execution subject of the risk assessment method may be the risk assessment device provided in the embodiment of the present application, or an electronic device integrated with the risk assessment device. The risk assessment device may be implemented in hardware or software, and the electronic device may be a smart device. Mobile phones, tablet computers, handheld computers, notebook computers, or desktop computers are equipped with processors and have processing capabilities.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a first scenario of a risk assessment method provided by an embodiment of the application. When the client detects a payment request based on payment task A triggered by the user, the client sends a payment request for payment task A to the server. After receiving the payment request sent by the client, the server combines the first risk assessment model and the second risk assessment model to perform risk assessment on payment task A. If the risk of payment task A is not high, the server responds to the payment request of payment task A, processes payment task A, and sends a "payment successful" notification to the client. If the risk of payment task A is high, in order to improve security, the server prohibits responding to the payment request of payment task A and sends an identity verification request to the client.

Please refer to FIG. 2, which is a schematic diagram of a second scenario of the risk assessment method provided by an embodiment of the application. When the client terminal detects a payment request based on the payment task B triggered by the user, the client terminal performs risk assessment on the payment task B in combination with the first risk assessment model and the second risk assessment model. If the risk of payment task B is not high, the client sends the payment request of payment task B to the server, so that the server can process payment task B according to the payment request. If the risk of payment task B is high, the client requires the user to reconfirm whether payment task B is executed, and requires the user to provide identity verification. After the user reconfirms and the identity verification is qualified, the client sends the payment request of payment task B to the server, so that the server can process payment task B according to the payment request.

Please refer to FIG. 3, which is a schematic diagram of the first process of the risk assessment method provided by an embodiment of the application. The process of this risk assessment method is as follows:

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

In this embodiment of the application, when a task to be executed is detected, the electronic device obtains the data to be evaluated corresponding to the task to be executed, and extracts the first feature vector from the data to be evaluated through a feature extraction algorithm for the risk assessment model to perform risk scoring .

Among them, the task to be performed is different, and the corresponding data to be evaluated is also different. For example, the to-be-evaluated data corresponding to the to-be-executed task "application A's membership recharge" is different from the to-be-evaluated data corresponding to the to-be-executed task "download application A". In addition, the data to be evaluated may be multi-dimensional data, and the data to be evaluated includes at least task data, account data, and device data.

For example, suppose that the electronic device has a task to be performed: downloading application B in the application store. The data to be evaluated corresponding to the task to be performed includes at least task data (e.g., downloaded application name, download time, download location, etc.), account data (e.g., total number of account logins to the app store, account login to the app store) The collection of time, the collection of login locations for the account to log in to the application store, the total number of times the account has downloaded applications, the type of applications downloaded by the account, etc.), device data (such as the total number of device logins to the application store, the collection of time devices log in to the application store) , The set of login locations where the device logs in to the application store, the total number of times the device has downloaded applications, the type of applications downloaded by the device, etc.).

It is understandable that multiple accounts can be logged in to the same device, and one account can also be logged in to multiple devices. Therefore, when the electronic device obtains the data to be evaluated, it obtains both the account data and the device data, which can make the data to be evaluated more comprehensive, thereby improving the accuracy of the risk assessment.

Among them, the feature extraction algorithm is used to extract features from the data and generate feature vectors based on the features. For example, suppose that an electronic device extracts 1,000 features from the data to be evaluated through a feature extraction algorithm, and then generates a 1,000-dimensional first feature vector based on the 1,000 features for risk assessment by the risk assessment model.

In some embodiments, after the electronic device obtains the data to be evaluated, the electronic device cleans and completes the data to be evaluated, and then uses a feature extraction algorithm to extract the first feature vector from the processed data to be evaluated.

102. According to the first feature vector and the first risk evaluation model, score the data to be evaluated to obtain a first evaluation score.

In the embodiment of the present application, after obtaining the first feature vector, 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 the first assessment score.

Among them, the first risk assessment model uses an unsupervised algorithm, which can be used to score the risk of the data to be assessed. For example, the first risk assessment model can be obtained by training 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 that can perform risk scoring on the data to be assessed through an unsupervised algorithm, which is not specifically limited in the embodiment of the present application.

103. According to the first feature vector and the second risk evaluation model, score the data to be evaluated to obtain a second evaluation score.

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

Among them, the second risk assessment model uses a supervised algorithm, which can be used to score the risk of the data to be assessed. For example, the second risk assessment model can be obtained by training a pre-built classification model. For example, the second risk assessment model can be obtained by training a neural network model built in advance. Alternatively, the second risk assessment model may also be another model that can perform risk scoring on the data to be assessed through a supervised algorithm, which is not specifically limited in the embodiment of the present application.

104. Determine 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, after obtaining the first evaluation score and the second evaluation score, the electronic device may determine the target evaluation score of the data to be evaluated according to the first evaluation score and the second evaluation score, and then set the target evaluation score corresponding to a preset The risk type is determined 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 based on 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 the first weight coefficient corresponding to the first evaluation score and the corresponding value corresponding to the second evaluation score according to the type of the data to be evaluated. The second weight coefficient. Based on the first weight coefficient, the second weight coefficient, the first evaluation score, and the second evaluation score, the target evaluation score of the data to be evaluated is calculated.

Wherein, compared with the second risk assessment model, when this type of data to be assessed uses the first risk assessment model with higher accuracy, the first weight coefficient corresponding to the first assessment score is greater than the second assessment score corresponding to the second Weight coefficient. Compared with the first risk assessment model, when this type of data to be assessed 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 .

In another implementation manner, after obtaining the first evaluation score, the electronic device may directly determine the target risk type of the data to be evaluated according to the first evaluation score. For example, when the first risk assessment model is trained by 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, the lower the risk degree of the target risk type of the data to be evaluated, and the larger the first evaluation score, the higher the risk degree of the target risk type of the data to be evaluated.

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

As can be seen from the above, in the embodiment of the application, the electronic device scores the evaluation data in two ways: the first risk evaluation model is used to score the evaluation data, the second risk evaluation model is used to score the evaluation data, and finally the two methods are combined. Method of scoring results to comprehensively determine the target risk type of the data to be assessed, which can improve the accuracy of risk assessment.

Please refer to FIG. 4, which is a schematic diagram of a third scenario of a risk assessment method provided by an embodiment of the application. In some embodiments, according to the first feature vector and the first risk evaluation model, the data to be evaluated is scored, and when the first evaluation score is obtained, the electronic device may perform the following:

Encoding the first feature vector by an encoding algorithm to obtain a second feature vector, where the first feature vector is a discrete feature and the second feature vector is a continuous feature;

Based on the second feature vector and the first risk evaluation model, score the data to be evaluated to obtain the first evaluation score.

Among them, the encoding algorithm is used to encode the feature vector, so that the vector elements of the feature vector are changed from discrete features to continuous features. The encoding algorithm in this solution is based on pre-built autoencoder (AE) training.

For example, the electronic device obtains multiple sample vectors to form the first training set. Then use the first training set to train the autoencoder to update the model parameters of the autoencoder. Finally, based on the encoder in the autoencoder after updating the model parameters, an encoding algorithm is constructed. Among them, the self-encoder includes an encoder (encoder) and a decoder (decoder).

Please refer to FIG. 5, which is a schematic structural diagram of a self-encoder according to an embodiment of the application. During training, the autoencoder will perform encoding and decoding operations on each sample vector X. The encoding operation refers to mapping the sample vector X to the feature space through the encoder to obtain the abstract feature vector Z. Decoding operation refers to mapping the abstract feature vector Z back to the original space through the decoder to obtain the reconstructed vector

It is understandable that when the sample vector X and the reconstruction vector

When the error of is the smallest, the autoencoder training is completed.

It should be noted that because the eigenvectors whose vector elements are discrete features are not suitable for risk scoring using the first risk assessment model, an encoding algorithm is used to convert the eigenvectors whose vector elements are discrete features into eigenvectors whose vector elements are continuous features. Make it suitable for risk scoring using the first risk assessment model, thereby improving the accuracy of risk assessment.

Please refer to FIG. 6. FIG. 6 is a schematic diagram of the second process of the risk assessment method provided by the embodiment of the application. The process of this risk assessment method is as follows:

201. Obtain data to be evaluated, and perform feature extraction on the data to be evaluated through a feature extraction algorithm to obtain first numerical features and text features.

Among them, the first numerical feature refers to a feature represented by a numerical value. For example, the electronic device uses a feature extraction algorithm to extract the feature of "the number of times the device downloads the application C: 5" to obtain the first numerical feature: "5". The text feature refers to the feature represented by the text. For example, the electronic device uses the feature extraction algorithm to extract the feature of "the location where the device downloads the application C: Beijing" to obtain the text feature: "Beijing".

202. Perform normalization processing on the first numerical feature, and perform conversion processing on the text feature, so as to convert the text feature into a second numerical feature.

Among them, the purpose of the normalization processing is to normalize the value representing the first numerical feature, so that the value representing the first numerical feature is within a specified numerical range (for example, within a numerical range of 0 to 1).

The purpose of the conversion process in this solution is to convert text features into second numerical features. Among them, the second numerical characteristic also refers to a characteristic expressed by a numerical value.

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

203. Generate a first feature vector based on the first numerical feature and the second numerical feature.

In the embodiment of the present application, after obtaining the first numerical feature and the second numerical feature, the electronic device generates the first feature vector according to the preset order of each feature according to the first numerical feature and the second numerical feature.

For example, suppose that the electronic device obtains 2 first numerical characteristics and 1 second numerical characteristic. The two first numerical features are respectively: 0.05 (obtained from the number of times the account has downloaded application D "5"), 0.1 (obtained from the number of account logins "100"), and one second numerical characteristic is: 1 (by downloading Get the location "Beijing"). If the number of account logins is the first-dimensional vector element, the account download application D is the second-dimensional vector element, and the download location is the third-dimensional vector element, then the preset order of the first numerical feature "0.05" is 2. The preset order of the first numerical feature "0.1" is 1, and the preset order of the second numerical feature "1" is 3. The first feature vector generated by the electronic device is (0.1, 0.05, 1).

204. Determine the weight value corresponding to each vector element in the second risk assessment model according to the arrangement order of the vector elements in the first feature vector, where the vector element includes the first numerical feature and the second numerical feature.

In the embodiment of the present application, after the first feature vector is generated, the electronic device determines the weight value corresponding to each vector element in the second risk assessment model according to the arrangement order of the vector elements in the first feature vector. 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.

Among them, the weight value can 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. The smaller the weight value, the less important the feature represented by the vector element.

It should be noted that because the fourth feature vector used to train the second risk assessment model and the first feature vector have the same content in the same dimension vector element, such as the fourth feature vector and the second dimension vector element of the first feature vector Both indicate the number of account logins. Therefore, the weight value corresponding to each vector element in the second risk assessment model can represent the importance of the feature represented by the vector element.

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

In the embodiment of the present 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. Among them, if the corresponding weight value is large, it indicates that the vector element corresponding to the weight value is more important, and the electronic device can increase the value of the vector element so that the vector element can be distinguished from other vector elements.

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

206. According to the third feature vector and the first risk assessment model, score the data to be assessed, and obtain the first assessment score.

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

For example, suppose that the first risk assessment model is trained by a pre-built isolated forest model. After obtaining the third feature vector, the electronic device inputs the third feature vector into the first risk assessment model to determine the average path length corresponding to each vector element in the second risk assessment model, according to the average path length of each vector element , Get and output the first evaluation score. Among them, the first risk assessment model includes at least two isolated trees. The number of nodes traversed by a vector element in each isolated tree is used as the path length of the vector element in the isolated tree. The average path length corresponding to the vector elements in the second risk assessment model is the average of the path lengths of the vector elements in each isolated tree.

It should be noted that because the third feature vector adjusts the value of the vector element corresponding to the large weight value to distinguish the vector element from other vector elements, when scoring the evaluation data through the first risk assessment 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. According to the first feature vector and the second risk evaluation model, score the data to be evaluated to obtain a second evaluation score.

For example, suppose that the second risk assessment model is obtained from a pre-built classification model. After obtaining the first feature vector, the electronic device inputs the first feature vector into the second risk assessment model, and then, according to the arrangement order of the vector elements in the first feature vector, determines the corresponding value of each vector element in the second risk assessment model. The weight value is weighted and summed based on the weight value and the vector elements to obtain and output the second evaluation score.

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

In this embodiment of the application, after obtaining the first evaluation score and the second evaluation score, the electronic device may determine the target evaluation score of the data to be evaluated according to the first evaluation score and the second evaluation score, and then set the target evaluation score to a preset The risk type is determined as the target risk type of the data to be evaluated.

209. When the risk level of the target risk type is lower than or equal to the preset level, execute the to-be-executed task corresponding to the to-be-assessed data.

In the embodiment of the present application, after determining the target risk type of 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 execute the task to be performed 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 performed corresponding to the data to be evaluated, and output prompt information to the user, such as a prompt message of "the task to be performed has a high risk level".

It can be seen from the above that, in the embodiment of the present application, before processing the task to be performed, the electronic device first performs risk assessment through the to-be-evaluated data corresponding to the task to be performed, and executes the task to be performed when the risk level is lower than or equal to the preset level When the risk level is higher than the preset level, the execution of the task to be performed is prohibited and the prompt information is output to the user, which can improve the safety of the electronic device.

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

Obtain multiple sample evaluation data;

Extract the fourth feature vector from the sample evaluation data through a feature extraction algorithm;

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

Use the training set to train the classification model to update the model parameters of the classification model.

Among them, the specific implementation manner of extracting the fourth feature vector from the sample evaluation data through the feature extraction algorithm can refer to the above specific implementation manner 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 can be extracted from one sample evaluation data. A fourth feature vector corresponds to a sample risk type.

In addition, the method for obtaining the sample risk type in this solution is not specifically limited in the embodiment of the present application. For example, the electronic device can obtain 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 the sample risk type of the sample evaluation data, etc.

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

According to the first risk assessment model and the corresponding fourth feature vector, the sample assessment data is scored to obtain the third assessment score, and the sample risk type of the sample assessment data is determined according to the third assessment score.

In this solution, the electronic device automatically determines the sample risk type of the sample evaluation data through the first risk assessment model, which can reduce manual operations and save the time for determining the sample risk type, thereby shortening the training time of the second risk assessment model and increasing the second risk Evaluate the training efficiency of the model.

It should be noted that based on this solution, the first risk assessment model automatically determines the sample risk type of the sample assessment data, which improves the training efficiency of the second risk assessment model. The electronic device can train the second risk assessment model in a short time. For example, the electronic device trains the second risk assessment model every preset time interval (for example, 30 minutes), thereby improving the real-time performance of the second risk assessment model.

In some embodiments, when determining the sample risk type of the sample evaluation data according to the third evaluation score, the electronic device may perform the following:

When the third evaluation score is within the preset interval, use the preset risk type corresponding to the third evaluation score as the sample risk type of the sample evaluation data;

When the third evaluation score is not within the preset interval, the sample risk type set by the user for the sample evaluation data is acquired.

Wherein, the electronic device presets at least two preset intervals. Different preset intervals correspond to different sample risk types. The sample risk type corresponding to the preset interval of the third evaluation score is the sample risk type of the sample evaluation data.

It should be noted that when the preset interval is set in advance, some sample risk types corresponding to the third evaluation score are considered to be unstable. In order to improve the accuracy of the sample risk types and the training effect of the second risk evaluation model, the electronic device is setting the preset When setting the interval, only the third evaluation score of the corresponding sample risk type is considered stable. For the third evaluation score that corresponds to the unstable risk type of the sample, the user manually determines the risk type of the sample. 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, suppose that the sample risk types include non-risk types and risky types. The first risk assessment model is trained by the pre-built isolated forest model, and the value range of the third assessment score is 0 to 1. Because the sample evaluation data with the third evaluation score near 0.5 is difficult to distinguish between the risk-free type and the risky type, the preset interval preset by the electronic device includes the risk-free interval (such as [0, 0.2]) and the risky interval (such as [0.8, 1]).

FIG. 7 is a schematic structural diagram of a risk assessment device provided by an embodiment of the present application. The device is used to implement the risk assessment method provided in the above-mentioned embodiment, and has functional modules and beneficial effects corresponding to the execution method. The risk assessment device 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 acquisition module 301 is configured to acquire data to be evaluated, and extract a first feature vector from the data to be evaluated by a feature extraction algorithm;

The first scoring module 302 is configured to score the data to be evaluated according to the first feature vector and the first risk evaluation model 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 the second risk evaluation model to obtain a second evaluation score;

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

In some embodiments, the data to be evaluated is scored according to the first feature vector and the first risk assessment model, and when the first evaluation score is obtained, the first scoring module 302 may be used to:

Performing encoding processing on the first feature vector by an encoding algorithm to obtain a second feature vector, where the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

Score the data to be assessed based on the second feature vector and the first risk assessment model to obtain a first assessment score.

In some embodiments, when the first feature vector is extracted from the data to be evaluated by a feature extraction algorithm, the first acquisition module 301 may be used to:

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

Performing normalization processing on the first numerical feature, and performing conversion processing on the text feature, so as to convert the text feature into a second numerical feature;

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

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;

According to the first feature vector and the first risk evaluation model, the data to be evaluated is scored, and when the first evaluation score is obtained, the first scoring module 302 can be used to:

According to the sequence of the vector elements in the first feature vector, the weight value corresponding to each vector element in the second risk assessment model is determined, wherein the vector element includes the first numerical feature and the second Numerical characteristics;

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

According to the third feature vector and the first risk assessment model, score the data to be assessed to obtain a first assessment score.

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

Increase the value of the preset number of vector elements corresponding to the largest weight value.

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 evaluation device 300 further includes:

The execution module is configured to 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.

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

The second acquisition module is used to acquire multiple sample evaluation data;

An extraction module, configured to extract a fourth feature vector from the sample evaluation data through the feature extraction algorithm;

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

The training module is configured to use the training set to train the classification model to update the model parameters of the classification model.

In some embodiments, when obtaining the sample risk type of each sample evaluation data, the third obtaining module may be used to:

According to the first risk assessment model and the corresponding fourth feature vector, the sample assessment data is scored to obtain a third assessment score, and the sample risk type of the sample assessment data is determined according to the third assessment score.

In some embodiments, when determining the sample risk type of the sample evaluation data according to the third evaluation score, the third acquisition module may be used to:

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

When the third evaluation score is not within the preset interval, acquiring the sample risk type set by the user for the sample evaluation data.

As can be seen from the above, in the risk assessment device 300 provided by the embodiment of the present application, the first acquisition module 301 acquires the data to be evaluated, and extracts the first feature vector from the data to be evaluated through the feature extraction algorithm, and then the first scoring module 302 uses the first feature The vector and the first risk evaluation model are used to score the data to be evaluated to obtain the first evaluation score, and the second scoring module 303 scores the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain the second evaluation score, The final determination module 304 determines the target risk type of the data to be evaluated according to the first evaluation score and the second evaluation score. Combining the scoring results of the first risk assessment model and the second risk assessment model to comprehensively determine the target risk type of the data to be assessed can improve the accuracy of risk assessment.

It should be noted that the risk assessment device provided in the embodiment of this application belongs to the same concept as the risk assessment method in the above embodiment. Any method provided in the risk assessment method embodiment can be run on the risk assessment device, and its specific implementation For details of the process, refer to the embodiment of the risk assessment method, which will not be repeated here.

An embodiment of the present application also provides an electronic device. Please refer to FIG. 8, which is a first schematic structural diagram of the electronic device provided by the embodiment of the present application. The electronic device 400 includes a processor 401 and a memory 402. Wherein, the processor 401 and the memory 402 are electrically connected.

The processor 401 is the control center of the electronic device 400. It uses various interfaces and lines to connect various parts of the entire electronic device. Various functions of the device 400 and processing data.

The memory 402 may be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running 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. The program storage area may store an operating system, a computer program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of electronic equipment, etc.

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

In the embodiment of the present application, the processor 401 in the electronic device 400 will load the instructions corresponding to the process of one or more computer programs into the memory 402 according to the following steps, and run the instructions by the processor 401 and store them in the memory 402. In order to realize various functions in the computer program, as follows:

Please refer to FIG. 9. FIG. 9 is a schematic diagram of a second structure of an electronic device provided by an embodiment of the application. The difference from the electronic device shown in FIG. 8 is that the electronic device further includes: a radio frequency circuit 403, a display screen 404, a control circuit 405, Input unit 406, audio circuit 407, sensor 408, and power supply 409. The processor 401 is electrically connected to the radio frequency circuit 403, the display screen 404, the control circuit 405, the input unit 406, the audio circuit 407, the sensor 408, and the power supply 409, respectively.

The radio frequency circuit 403 is used to transmit and receive radio frequency signals to communicate with network equipment or other electronic equipment through wireless communication.

The display screen 404 may be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device. These graphical user interfaces may be composed of images, text, icons, videos, and any combination thereof.

The control circuit 405 is electrically connected to the display screen 404 for controlling the display screen 404 to display information.

The input unit 406 can be used to receive inputted numbers, character information, or user characteristic information (such as fingerprints), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Wherein, the input unit 406 may include a fingerprint recognition module.

The audio circuit 407 can provide an audio interface between the user and the electronic device through a speaker and a microphone. Among them, the audio circuit 407 includes a microphone. The microphone is electrically connected to the processor 401. The microphone is used to receive voice information input by the user.

The sensor 408 is used to collect external environmental information. The sensor 408 may include one or more of sensors such as an environmental brightness sensor, an acceleration sensor, and a gyroscope.

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

Although not shown in FIG. 9, the electronic device 400 may also include a camera, a Bluetooth module, etc., which will not be repeated here.

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

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

According to the first feature vector and the first risk assessment model, the data to be assessed is scored, and when the first assessment score is obtained, the processor 401 is configured to execute:

Adjusting the size of each of the vector elements according to the size of the corresponding weight value to obtain the third feature vector;

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

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 execute:

When the risk level of the target risk type is lower than or equal to the preset level, the task to be performed corresponding to the data to be evaluated is executed.

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

Obtain multiple sample evaluation data;

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

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;

The training set is used to train the classification model to update the model parameters of the classification model.

In some embodiments, when obtaining the sample risk type of each sample evaluation data, the processor 401 is configured to execute:

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

It can be seen from the foregoing that, after acquiring the data to be evaluated, the electronic device uses a feature extraction algorithm to extract a first feature vector from the data to be evaluated, and then, according to the first feature vector and the first risk assessment model, the electronic device extracts the first feature vector from the data to be evaluated. The data is scored to obtain the first evaluation score, and the evaluation data is scored according to the first feature vector and the second risk evaluation model, and the second evaluation score is obtained. Finally, according to the first evaluation score and the second evaluation score, the evaluation is determined The target risk type of the data. Combining the scoring results of the first risk assessment model and the second risk assessment model to comprehensively determine the target risk type of the data to be assessed can improve the accuracy of risk assessment.

An embodiment of the present application also provides a storage medium that 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 of the above embodiments, such as: obtaining data to be assessed , And extract a first feature vector from the data to be evaluated by a feature extraction algorithm; score the data to be evaluated according to the first feature vector and the first risk assessment model to obtain a first evaluation score; The first feature vector and the second risk evaluation model are used to score the data to be evaluated to obtain a second evaluation score; according to the first evaluation score and the second evaluation score, the target risk of the data to be evaluated is determined type.

In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a read only memory (Read Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

It should be noted that for the risk assessment method of the embodiment of the present application, ordinary testers in the field can understand that all or part of the process of implementing the risk assessment method of the embodiment of the present application can be completed by controlling the relevant hardware through a computer program. The computer program can be stored in a computer readable storage medium, such as stored in the memory of an electronic device, and executed by at least one processor in the electronic device. The execution process can include, for example, the implementation of a risk assessment method Example process. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, and the like.

Claims

A risk assessment method, which includes

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

Score the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score;

Score the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score;

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

Performing encoding processing on the first feature vector by an encoding algorithm to obtain a second feature vector, where the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

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

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

Performing normalization processing on the first numerical feature, and performing conversion processing on the text feature, so as to convert the text feature into a second numerical feature;

Based on the first numerical feature and the second numerical feature, a first feature vector is generated.
The method according to claim 1, wherein 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;

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

According to the sequence of the vector elements in the first feature vector, the weight value corresponding to each vector element in the second risk assessment model is determined, wherein the vector element includes the first numerical feature and the second Numerical characteristics;

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

According to the third feature vector and the first risk assessment model, score the data to be assessed to obtain a first assessment score.
The method according to claim 4, wherein the adjusting the size of each of the vector elements according to the size of the corresponding weight value comprises:

Increase the value of the preset number of vector elements corresponding to the largest weight value.
The method according to claim 1, 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 method further comprises:

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

Obtain multiple sample evaluation data;

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

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;

The training set is used to train the classification model to update the model parameters of the classification model.
The method according to claim 7, wherein said obtaining the sample risk type of each sample evaluation data comprises:

According to the first risk assessment model and the corresponding fourth feature vector, the sample assessment data is scored to obtain a third assessment score, and the sample risk type of the sample assessment data is determined according to the third assessment score.
The method according to claim 8, wherein the determining the sample risk type of the sample evaluation data according to the third evaluation score comprises:

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

When the third evaluation score is not within the preset interval, acquiring the sample risk type set by the user for the sample evaluation data.
A risk assessment device, which includes:

The first acquisition module is configured to acquire the data to be evaluated, and extract the first feature vector from the data to be evaluated through a feature extraction algorithm;

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

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

The determining module is configured to determine 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 running on the processor, wherein the processor implements a risk assessment method when the computer program is executed:

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

Score the data to be evaluated according to the first feature vector and the first risk evaluation model to obtain a first evaluation score;

Score the data to be evaluated according to the first feature vector and the second risk evaluation model to obtain a second evaluation score;

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

Performing encoding processing on the first feature vector by an encoding algorithm to obtain a second feature vector, where the first feature vector is a discrete feature, and the second feature vector is a continuous feature;

Score the data to be assessed based on the second feature vector and the first risk assessment model to obtain a first assessment score.
The electronic device according to claim 11, wherein the first feature vector is extracted from the data to be evaluated by a feature extraction algorithm, and the processor is configured to execute:

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

Performing normalization processing on the first numerical feature, and performing conversion processing on the text feature, so as to convert the text feature into a second numerical feature;

Based on the first numerical feature and the second numerical feature, a first feature vector is generated.
The electronic device according to claim 11, wherein 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;

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

According to the sequence of the vector elements in the first feature vector, the weight value corresponding to each vector element in the second risk assessment model is determined, wherein the vector element includes the first numerical feature and the second Numerical characteristics;

Adjusting the size of each of the vector elements according to the size of the corresponding weight value to obtain the third feature vector;

Score the data to be assessed according to the third feature vector and the first risk assessment model to obtain a first assessment score.
The electronic device according to claim 14, wherein the size of each of the vector elements is adjusted according to the size of the corresponding weight value, and the processor is configured to execute:

Increase the value of the preset number of vector elements corresponding to the largest weight value.
11. The electronic device according to claim 11, wherein, after the target risk type of the data to be evaluated is determined according to the first evaluation score and the second evaluation score, the processor is further configured to execute:

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

Obtain multiple sample evaluation data;

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

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;

The training set is used to train the classification model to update the model parameters of the classification model.
The electronic device according to claim 17, wherein said acquiring the sample risk type of each sample evaluation data, said processor is configured to execute:

According to the first risk assessment model and the corresponding fourth feature vector, the sample assessment data is scored to obtain a third assessment score, and the sample risk type of the sample assessment data is determined according to the third assessment score.
The electronic device according to claim 18, wherein the determining the sample risk type of the sample evaluation data according to the third evaluation score, and the processor is configured to execute:

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

When the third evaluation score is not within the preset interval, acquiring the sample risk type set by the user for the sample evaluation data.
A storage medium containing executable instructions of an electronic device, wherein the executable instructions of the electronic device are used to execute the risk assessment method according to any one of claims 1 to 9 when executed by an electronic device processor.