User risk assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a user risk assessment method and device, electronic equipment and a storage medium, and relates to the field of financial science and technology, and the method comprises the steps: obtaining user state data, business behavior data and personal basic data of a target user; wherein the user state data comprises a state detection text; according to the user state data of the target user, obtaining state evaluation data of the target user; and obtaining a risk assessment result of the target user through a risk prediction model according to the state assessment data, the business behavior data and the personal basic data of the target user. According to the technical scheme provided by the embodiment of the invention, various potential risks of the user are comprehensively reflected based on the multi-dimensional user information, the accuracy of the risk assessment result is improved, the risk assessment efficiency is improved, and the evaluation result deviation caused by subjective evaluation is avoided.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a user risk assessment method, device, electronic device and storage medium. Background Art

[0002] With the diversification of financial services, financial institutions are facing more and more customers, and it becomes particularly important to assess the business qualifications of different customers by assessing their risks.

[0003] In the prior art, the assessment of customer risk is usually based on the customer's current economic situation to predict the possible business risks. The prediction method is that after the user submits relevant qualification certificates, the staff will manually review them to assess their specific risk level and possible business risks.

[0004] However, the customer's current economic situation can only reflect his or her personal information in a single dimension over a period of time in the past, and cannot fully reflect the customer's potential risks. The risk assessment results have large errors. In addition, the manual assessment method has low efficiency, and the subjectivity of manual assessment will also lead to further deviations in the assessment results. Summary of the invention

[0005] The present invention provides a user risk assessment method, device, electronic device and storage medium to solve the problem of large errors in user risk assessment results.

[0006] According to one aspect of the present invention, a user risk assessment method is provided, comprising:

[0007] Acquire user status data, business behavior data and basic personal data of the target user; wherein the user status data includes status detection text;

[0008] Acquiring status evaluation data of the target user according to the user status data of the target user;

[0009] According to the status assessment data, business behavior data and personal basic data of the target user, a risk assessment result of the target user is obtained through a risk prediction model.

[0010] The user status data includes a status detection image; and obtaining the status evaluation data of the target user based on the user status data of the target user includes: recognizing the status detection image of the target user through an image recognition model to obtain the action characteristics and expression characteristics of the target user; and obtaining the status category of the target user through an image classification model based on the action characteristics and expression characteristics of the target user.

[0011] The method of obtaining the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user includes: inputting the status assessment data into a recurrent neural network model to obtain a first risk prediction result of the target user; inputting the business behavior data into a long short-term memory neural network model to obtain a second risk prediction result of the target user; inputting the personal basic data into a Transformer neural network model to obtain a third risk prediction result of the target user; and obtaining the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result and the third risk prediction result.

[0012] The method of obtaining the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result and the third risk prediction result includes: inputting the status assessment data, the business behavior data and the personal basic data into a convolutional neural network model to obtain a fourth risk prediction result of the target user; and obtaining the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result, the third risk prediction result and the fourth risk prediction result.

[0013] The method of obtaining the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user includes: inputting the status assessment data, the business behavior data and the personal basic data into multiple risk prediction models, and obtaining the risk assessment result of the target user based on the risk prediction results of each risk prediction model; wherein the model structures of the risk prediction models are different.

[0014] After obtaining the risk assessment result of the target user, the method further includes: obtaining a target business matching the target user according to the risk assessment result of the target user, and recommending the target business to the target user.

[0015] According to another aspect of the present invention, there is provided a user risk assessment device, comprising:

[0016] A data acquisition module, used to acquire user status data, business behavior data and personal basic data of the target user; wherein the user status data includes status detection text;

[0017] An evaluation execution module, used to obtain status evaluation data of the target user according to the user status data of the target user;

[0018] The risk assessment module is used to obtain the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user risk assessment method described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user risk assessment method described in any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the user risk assessment method according to any embodiment of the present invention is implemented.

[0025] The technical solution of the embodiment of the present invention obtains the business behavior data and personal basic data of the target user, as well as the user status data including the status detection text, and obtains the status evaluation data of the target user according to the user status data of the target user; and obtains the risk evaluation result of the target user through the risk prediction model according to the status evaluation data, business behavior data and personal basic data of the target user. Based on this, the user information based on multiple dimensions comprehensively reflects the potential risks of the user, improves the accuracy of the risk evaluation result, improves the efficiency of the risk evaluation, and avoids the evaluation result deviation caused by subjective evaluation.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 is a flow chart of a user risk assessment method provided according to Embodiment 1 of the present invention;

[0029] Figure 2 is a flow chart of another user risk assessment method provided according to Embodiment 2 of the present invention;

[0030] Figure 3 is a flowchart of another user risk assessment method provided according to Embodiment 3 of the present invention;

[0031] Figure 4 is a schematic diagram of the structure of a user risk assessment device provided according to a fourth embodiment of the present invention;

[0032] Figure 5 It is a structural schematic diagram of an electronic device for implementing the user risk assessment method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 This is a flowchart of a user risk assessment method provided in the first embodiment of the present invention. This embodiment can be applied to obtain risk assessment results based on multi-dimensional user information. This method can be executed by a user risk assessment device in any embodiment of the present invention. The user risk assessment device can be implemented in the form of hardware and / or software. The user risk assessment device can be configured in an electronic device such as a server. Figure 1 As shown, the method includes:

[0037] S101. Acquire user status data, business behavior data, and basic personal data of a target user; wherein the user status data includes status detection text.

[0038] User status refers to the user's mental state, and its ideal state includes maintaining correct cognition, reasonable will, positive attitude and appropriate behavior. User status data reflects the user's mental health status, including multiple dimensions such as status, cognition and social adaptability. Among them, the status detection text is a test report presented in text form after the user has been tested by a professional organization.

[0039] Status detection refers to the scientific analysis of the subject's memory, intelligence, personality and other status information made by the relevant institutions with detection qualifications, under the guidance of professionals, in accordance with certain operating procedures, with the help of scales and interviews. The status detection text is obtained only after the user's authorization, and the acquisition method is reasonable and legal. It can be submitted by the target user actively, or after obtaining the user's authorization, it can be obtained through docking with relevant testing institutions. At the same time, the user's status evaluation information can also be obtained by providing the user with a status detection questionnaire; in addition, the user status data can also include other forms of multi-dimensional data information submitted by the user.

[0040] Business behavior data refers to the various behaviors and reactions exhibited by users when using products or services in the business system of the current business organization, such as transfers, browsing, purchases, transactions, and comments. Business behaviors can be classified according to different dimensions, such as behavior purpose, behavior frequency, and behavior path. Among them, behavior purpose can include navigation behavior, information acquisition behavior, interactive behavior, and transaction behavior. Different behavior purposes reflect different needs of users. Behavior frequency can include low-frequency behavior and high-frequency behavior. Behavior path shows the behavioral habits of user behavior in the business system.

[0041] Basic personal data includes basic identity information, education and occupation information, economic status information, equipment usage information, etc. Obviously, user status data, business behavior data and basic personal data describe the personal status information of the target user from different dimensions. In particular, in order to ensure data security, the Transport Layer Security Protocol (TLS) can be used to protect the security of the above data during transmission, and corresponding encryption methods are used during data storage to prevent unauthorized access.

[0042] In addition, the identity of the accessing user is verified through authentication methods to ensure that only compliant users authorized by the system can access the above data, and each user only has specific access rights and can only view relevant data within the authority; at the same time, the above access behavior strictly complies with applicable regulations and legal requirements. Users who provide data have the right to access, correct or delete their own data, and can withdraw access authorization to their own data at any time.

[0043] S102: Acquire status evaluation data of the target user according to the user status data of the target user.

[0044] After obtaining the user status data, the data can be filtered to obtain only the data items with abnormal problems; for example, for the status detection text, only the abnormal status information is filtered and obtained, which is used as the evaluation data of the abnormal problem; for the above-mentioned status detection questionnaire, only the questions with lower scores are obtained to simplify the data structure of the user status data; at this time, the status evaluation data used to evaluate the user status is actually part of the component data in the user status data.

[0045] The user status data can also be input into a pre-trained status data analysis model, such as a biomedical model, a psychodynamic model, a social cognitive model, and an integrated self-model, and algorithmically analyzed by the status data analysis model to obtain a status evaluation result; for example, the status evaluation result can be labeled as to whether there are potential status problems and what specific possible status problems exist; at this time, the status evaluation data actually includes not only the user status data, but also the conclusive or predictive label information drawn by the status data analysis model based on the user status data.

[0046] Optionally, in an embodiment of the present invention, the user status data includes a status detection image; and obtaining the status evaluation data of the target user based on the user status data of the target user includes: identifying the status detection image of the target user through an image recognition model to obtain the motion characteristics and expression characteristics of the target user; and obtaining the status category of the target user through an image classification model based on the motion characteristics and expression characteristics of the target user.

[0047] Specifically, the state detection image refers to the user image obtained by the image acquisition device during the state detection process, which records the user's actions and expressions during the state detection process; the state detection image matches the state detection text, and the acquisition method is also consistent with the state detection text; after the state detection image is obtained, the state detection image is first recognized by the image recognition model to extract the action features and expression features therein.

[0048] Then, the image classification model is used to determine the state category of the target user based on the above action features and expression features; for example, joy, sadness, fatigue, and anxiety. Compared with the state detection text, which reflects the subjective feelings of the tester, the state detection image objectively reflects the real state of the current user, thereby obtaining more accurate user state data and avoiding the influence of subjective evaluation results on the data results. In particular, the state detection image is also obtained after the user's authorization, and the acquisition method is reasonable and legal.

[0049] S103: Obtain a risk assessment result of the target user through a risk prediction model according to the status assessment data, business behavior data and personal basic data of the target user.

[0050] To obtain the risk prediction model, first, after obtaining the authorization of each user, the user status data, business behavior data and personal basic data of the above-mentioned multiple users are obtained as sample data; secondly, the above-mentioned sample data are preprocessed, including processing missing values, outliers, normalization and standardization, etc., to ensure the consistency and availability of the sample data; then the labeled sample data are obtained; wherein each sample data is assigned a corresponding category label, for example, whether it is high risk or whether there is a potential risk problem.

[0051] Then, based on neural network structures such as deep neural network (DNN), convolutional neural network (CNN) and recurrent neural network (RNN), and combined with pre-configured structural parameters such as the number of layers, number of nodes and activation function, the initial model is constructed; then, the sample data is divided into training set, validation set and test set; among them, the training set is used for model training, the validation set is used to adjust model parameters, and the test set is used to evaluate model performance.

[0052] Specifically, the initial model is first trained using the training set. The weights and biases of the model can be adjusted through the back-propagation algorithm to minimize the gap between the predicted results and the actual labels. The hyperparameters of the model are then adjusted according to the performance of the validation set, such as the learning rate and batch size, to obtain better generalization performance. Finally, the performance of the trained model is evaluated using the test set. Evaluation indicators may include accuracy, recall rate, and precision, thereby completing the pre-training process of the risk prediction model.

[0053] Therefore, based on the target user's status assessment data, business behavior data and personal basic data, the risk assessment result of the target user can be obtained through the pre-trained risk prediction model; wherein the risk assessment result may include the assessed user risk level, for example, dividing the user risk level into low risk, medium risk and high risk; it may also be a specific risk tolerance level, for example, tolerable low risk, tolerable medium risk and tolerable high risk; it may also be a specific risk coefficient, for example, the risk coefficient includes 0 to 10.

[0054] Optionally, in an embodiment of the present invention, after obtaining the risk assessment result of the target user, it further includes: obtaining a target business matching the target user according to the risk assessment result of the target user, and recommending the target business to the target user. The risk assessment result of the target user is compared with the business tags of each business to obtain a target business matching the current risk assessment result, and the target business is recommended to the target user, thereby achieving accurate recommendation of the target business, providing users with more accurate business suggestions, and improving user experience.

[0055] The technical solution of the embodiment of the present invention obtains the business behavior data and personal basic data of the target user, as well as the user status data including the status detection text, and obtains the status evaluation data of the target user according to the user status data of the target user; and obtains the risk evaluation result of the target user through the risk prediction model according to the status evaluation data, business behavior data and personal basic data of the target user. Based on this, the user information based on multiple dimensions comprehensively reflects the potential risks of the user, improves the accuracy of the risk evaluation result, improves the efficiency of the risk evaluation, and avoids the evaluation result deviation caused by subjective evaluation.

[0056] Embodiment 2

[0057] Figure 2 This is a flowchart of a user risk assessment method provided by Embodiment 2 of the present invention. The relationship between this embodiment and the above embodiments is that risk prediction models with different structures are selected according to the data characteristics of different types of user data. Figure 2 As shown, the method includes:

[0058] S201. Acquire user status data, business behavior data, and basic personal data of a target user; wherein the user status data includes status detection text.

[0059] S202: Acquire status evaluation data of the target user according to the user status data of the target user.

[0060] S203: Input the status assessment data into a recurrent neural network model to obtain a first risk prediction result for the target user.

[0061] For the status assessment data, there is a certain correlation between the various parameters. For example, the various detection parameters in the status detection text usually have a step-by-step guiding role. The recurrent neural network takes sequence data as input and performs recursion in the direction of sequence evolution. At the same time, all nodes are connected in a chain-like manner. The characteristic of the recursive neural network is that the continuous information input before and after is used as related information to ensure the content consistency of the status assessment data. Therefore, the status assessment data is input into the recurrent neural network model to obtain the first risk prediction result of the target user. Among them, the first risk prediction result reflects the user's risk tolerance and other user conditions.

[0062] S204: Input the business behavior data into a long short-term memory neural network model to obtain a second risk prediction result for the target user.

[0063] For business behavior data, not only are there correlations between various parameters, but the correlations are strong. For example, the generation of transaction A directly leads to the generation of subsequent transaction B. The long short-term memory neural network (LSTM) is different from the general recurrent neural network. It solves the long-term dependency problem in the recurrent neural network and pays more attention to the correlation between the previous and next data, and even the correlation between the previous and next data with a long interval, so as to ensure the strong correlation between the business behavior data. Therefore, the business behavior data is input into the long short-term memory neural network model to obtain the second risk prediction result of the target user. Among them, the second risk prediction result reflects the user's business type preference and business carrying capacity and other business conditions.

[0064] S205: Input the basic personal data into a Transformer neural network model to obtain a third risk prediction result of the target user.

[0065] For personal basic data, the various parameters are often not correlated and exist independently of each other. For example, age and education information exist independently of each other. The Transformer architecture is an Encoder-Decoder structure of an Attention mechanism, including multiple stacked Encoder layers and multiple stacked Decoder layers, and outputs the results through an output layer connected to the terminal Decoder layer, which ensures the independence of various personal basic data. Therefore, the personal basic data is input into the Transformer neural network model to obtain the third risk prediction result of the target user. Among them, the third risk prediction result reflects the personal conditions of this type of user, such as personal preferences and personal abilities.

[0066] S206. Obtain a risk assessment result of the target user according to the first risk prediction result, the second risk prediction result, and the third risk prediction result.

[0067] By summarizing the first risk prediction result, the second risk prediction result and the third risk prediction result, the risk assessment results of the target user in multiple dimensions can be obtained; the risk assessment model constructed based on different types of neural network structures ensures the diversity of the model structure, avoids the phenomenon that a single model causes large deviations in the assessment results, and improves the accuracy of the risk assessment results.

[0068] Optionally, in an embodiment of the present invention, obtaining the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result and the third risk prediction result includes: inputting the status assessment data, the business behavior data and the personal basic data into a convolutional neural network model to obtain a fourth risk prediction result of the target user; obtaining the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result, the third risk prediction result and the fourth risk prediction result.

[0069] Specifically, when status assessment data, business behavior data, and personal basic data are input into the same risk prediction model, due to the large amount of data and the large number of data types, the risk prediction model needs to have strong data processing efficiency and simplify the data processing complexity; the convolution calculation included in the convolutional neural network can improve the extraction accuracy of data features, and the application of the pooling layer reduces the calculation complexity of data features.

[0070] Therefore, the status assessment data, business behavior data and personal basic data are jointly input into the convolutional neural network model, which not only simplifies the complexity of data processing, but also has a higher data processing efficiency, ensuring the timely acquisition of the fourth risk prediction result; wherein, the fourth risk prediction result reflects the overall risk assessment under multi-dimensional data; thereby, the risk assessment result after summarizing the first risk prediction result, the second risk prediction result, the third risk prediction result and the fourth risk prediction result further improves the accuracy and comprehensiveness of the risk assessment result.

[0071] The technical solution of the embodiment of the present invention inputs the state assessment data into the recurrent neural network model to obtain the first risk prediction result of the target user; inputs the business behavior data into the long short-term memory neural network model to obtain the second risk prediction result of the target user; inputs the personal basic data into the Transformer neural network model to obtain the third risk prediction result of the target user; and obtains the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result and the third risk prediction result. The risk assessment model constructed based on different types of neural network structures ensures the diversity of the model structure, avoids the phenomenon that a single model causes a large deviation in the assessment result, and improves the accuracy of the risk assessment result.

[0072] Embodiment 3

[0073] Figure 3 This is a flowchart of a user risk assessment method provided by Embodiment 3 of the present invention. The relationship between this embodiment and the above embodiments is that the risk assessment results of the target user are obtained based on multiple risk prediction models with different model structures. Figure 3 As shown, the method includes:

[0074] S301. Acquire user status data, business behavior data, and basic personal data of a target user; wherein the user status data includes status detection text.

[0075] S302: Acquire status evaluation data of the target user according to the user status data of the target user.

[0076] S303, input the status assessment data, the business behavior data and the personal basic data into multiple risk prediction models, and obtain the risk assessment result of the target user according to the risk prediction results of each risk prediction model; wherein the model structures of each risk prediction model are different.

[0077] As described in the above technical solution, multiple risk prediction models with different model structures can be constructed through a variety of neural network technologies, such as the above-mentioned recurrent neural network model, long short-term memory neural network model, convolutional neural network model and Transformer neural network model, etc. Each risk prediction model obtains all data, namely status assessment data, business behavior data and personal basic data; the risk prediction results of the target users are obtained through each risk prediction model; among them, according to different prediction needs, the one that appears the most times among all risk prediction results can be used as the risk assessment result; or the one with the highest risk among all risk prediction results can be used as the risk assessment result.

[0078] Taking the risk prediction result as the user risk level as an example, the risk level that appears most times in the prediction results of multiple risk prediction models can be used as the risk level of the target user, so as to avoid the phenomenon that a single model structure causes a large deviation in the evaluation results, thereby improving the accuracy of the risk assessment results; in addition, the risk level with the highest risk level in the prediction results of multiple risk prediction models can be used as the risk level of the target user, so as to predict and obtain the maximum risk level of the target user, that is, to achieve the maximum possible risk assessment.

[0079] The technical solution of the embodiment of the present invention inputs status assessment data, business behavior data and personal basic data into multiple risk prediction models, and obtains the risk assessment results of the target users based on the risk prediction results of each risk prediction model; thereby avoiding the phenomenon that a single model structure causes a large deviation in the assessment results, improving the accuracy of the risk assessment results, and also achieving the maximum possible risk assessment acquisition.

[0080] Embodiment 4

[0081] Figure 4 : is a structural block diagram of a user risk assessment device provided by Embodiment 4 of the present invention, and the device specifically includes:

[0082] The data acquisition module 401 is used to acquire the user status data, business behavior data and personal basic data of the target user; wherein the user status data includes status detection text;

[0083] An evaluation execution module 402 is used to obtain status evaluation data of the target user according to the user status data of the target user;

[0084] The risk assessment module 403 is used to obtain the risk assessment result of the target user through a risk prediction model according to the status assessment data, business behavior data and personal basic data of the target user.

[0085] The technical solution of the embodiment of the present invention obtains the business behavior data and personal basic data of the target user, as well as the user status data including the status detection text, and obtains the status evaluation data of the target user according to the user status data of the target user; and obtains the risk evaluation result of the target user through the risk prediction model according to the status evaluation data, business behavior data and personal basic data of the target user. Based on this, the user information based on multiple dimensions comprehensively reflects the potential risks of the user, improves the accuracy of the risk evaluation result, improves the efficiency of the risk evaluation, and avoids the evaluation result deviation caused by subjective evaluation.

[0086] Optionally, the user status data includes a status detection image;

[0087] The evaluation execution module 402 is specifically used to identify the state detection image of the target user through an image recognition model to obtain the action characteristics and expression characteristics of the target user; according to the action characteristics and expression characteristics of the target user, the state category of the target user is obtained through an image classification model.

[0088] Optionally, the risk assessment module 403 is specifically used to input the status assessment data into a recurrent neural network model to obtain a first risk prediction result for the target user; input the business behavior data into a long short-term memory neural network model to obtain a second risk prediction result for the target user; input the personal basic data into a Transformer neural network model to obtain a third risk prediction result for the target user; and obtain a risk assessment result for the target user based on the first risk prediction result, the second risk prediction result and the third risk prediction result.

[0089] Optionally, the risk assessment module 403 is also used to input the status assessment data, the business behavior data and the personal basic data into a convolutional neural network model to obtain a fourth risk prediction result of the target user; and obtain the risk assessment result of the target user based on the first risk prediction result, the second risk prediction result, the third risk prediction result and the fourth risk prediction result.

[0090] Optionally, the risk assessment module 403 is also used to input the status assessment data, the business behavior data and the personal basic data into multiple risk prediction models, and obtain the risk assessment results of the target user based on the risk prediction results of each risk prediction model; wherein the model structures of each risk prediction model are different.

[0091] Optionally, the user risk assessment device is further used to obtain a target business matching the target user according to a risk assessment result of the target user, and recommend the target business to the target user.

[0092] The above device can execute the user risk assessment method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the user risk assessment method provided by any embodiment of the present invention.

[0093] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0094] Embodiment 5

[0095] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0096] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0097] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0098] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a user risk assessment method.

[0099] In some embodiments, the user risk assessment method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the user risk assessment method described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform the user risk assessment method in any other appropriate manner (e.g., by means of firmware).

[0100] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or electronic device.

[0102] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein may be implemented on a heterogeneous hardware accelerator having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the heterogeneous hardware accelerator. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0104] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data electronic device), or a computing system that includes middleware components (e.g., an application electronic device), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0105] The computing system may include a client and an electronic device. The client and the electronic device are generally remote from each other and usually interact through a communication network. The relationship between the client and the electronic device is generated by computer programs running on corresponding computers and having a client-electronic device relationship with each other. The electronic device may be a cloud electronic device, also known as a cloud computing electronic device or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0106] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0107] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A user risk assessment method, characterized in that: include: Acquire user status data, business behavior data and basic personal data of the target user; wherein the user status data includes status detection text; Acquiring status evaluation data of the target user according to the user status data of the target user; According to the status assessment data, business behavior data and personal basic data of the target user, a risk assessment result of the target user is obtained through a risk prediction model.

2. The method according to claim 1, characterized in that The user status data includes a status detection image; The acquiring the status evaluation data of the target user according to the user status data of the target user includes: Recognize the state detection image of the target user through an image recognition model to obtain the action features and expression features of the target user; According to the action features and expression features of the target user, the state category of the target user is obtained through an image classification model.

3. The method according to claim 1, characterized in that The step of obtaining the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user includes: Inputting the status assessment data into a recurrent neural network model to obtain a first risk prediction result of the target user; Inputting the business behavior data into a long short-term memory neural network model to obtain a second risk prediction result of the target user; Inputting the basic personal data into a Transformer neural network model to obtain a third risk prediction result of the target user; A risk assessment result of the target user is obtained according to the first risk prediction result, the second risk prediction result and the third risk prediction result.

4. The method according to claim 3, characterized in that The obtaining, according to the first risk prediction result, the second risk prediction result and the third risk prediction result, a risk assessment result of the target user includes: Inputting the status assessment data, the business behavior data and the personal basic data into a convolutional neural network model to obtain a fourth risk prediction result of the target user; A risk assessment result of the target user is obtained according to the first risk prediction result, the second risk prediction result, the third risk prediction result and the fourth risk prediction result.

5. The method according to claim 1, characterized in that The step of obtaining the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user includes: The status assessment data, the business behavior data and the basic personal data are input into multiple risk prediction models, and the risk assessment results of the target user are obtained according to the risk prediction results of each risk prediction model; wherein the model structures of the risk prediction models are different.

6. The method according to claim 1, characterized in that After obtaining the risk assessment result of the target user, the method further includes: According to the risk assessment result of the target user, a target business matching the target user is acquired, and the target business is recommended to the target user.

7. A user risk assessment device, characterized in that: include: A data acquisition module, used to acquire user status data, business behavior data and personal basic data of the target user; wherein the user status data includes status detection text; An evaluation execution module, used to obtain status evaluation data of the target user according to the user status data of the target user; The risk assessment module is used to obtain the risk assessment result of the target user through a risk prediction model based on the status assessment data, business behavior data and personal basic data of the target user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user risk assessment method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user risk assessment method according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the user risk assessment method according to any one of claims 1 to 6 is implemented.

Images