User risk information identification method and computer equipment

Abstract

The embodiment of the invention relates to the field of user risk information identification, in particular to a user risk information identification method and computer equipment. A specific embodiment of the method comprises the following steps: in response to determining that a target user account has logged in a user information processing end, performing key content extraction on page content corresponding to a user information verification page in the user information processing end to generate user information page key content; according to the user information page key content generated by the user information processing end and the user portrait information correspondingly set by the target user account, generating user risk identification information for the user information page key content by using a pre-trained user risk information identification model; and sending the user risk identification information to a user information processing end to execute risk early warning operation for the target user account. According to the embodiment, multi-dimensional risk identification can be carried out on the user, the risk user is discriminated and intercepted in real time in the insurance buying process, and the verification time is shortened.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of user risk information identification, and specifically to a user risk information identification method and computer device. Background Art

[0002] In the process of Internet insurance product insurance, the insurance product provider often has a shallow understanding of the customer and can only judge the customer's quality through the insurance information submitted by the customer to conclude the insurance contract. If there is no strict risk control system, it may lead to frequent occurrence of black and gray production, fraudulent insurance, malicious claims, etc., which will bring a lot of adverse consequences to the subsequent service of the insurance policy and affect the healthy development of the insurance business. At present, the method usually adopted for verifying the user's insurance information is: manual verification. However, manual verification usually has the following technical problems: manual verification takes a long time and easily causes a backlog of information; in addition, manual verification is subjective to a certain extent, and the verification accuracy is low. Summary of the invention

[0003] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0004] Some embodiments of the present application propose a user risk information identification method, a computer device, and a computer-readable storage medium to solve one or more of the technical problems mentioned in the above background technology section.

[0005] In the first aspect, some embodiments of the present application provide a method for identifying user risk information, the method comprising: in response to determining that a target user account has logged in at a user information processing terminal, extracting key content from a page content corresponding to a user information verification page at the user information processing terminal to generate key content of a user information page; generating user risk identification information for the key content of the user information page generated by the user information processing terminal and user portrait information corresponding to the target user account using a pre-trained user risk information identification model; and sending the user risk identification information to the user information processing terminal to perform a risk warning operation for the target user account. .

[0006] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0007] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0008] The above-mentioned embodiments of the present application have the following beneficial effects: the user risk information identification model can be used to identify the risk of users in multiple dimensions, and the risk users can be identified and intercepted in real time during the insurance process, thereby shortening the verification time, reducing the economic losses caused by malicious insurance, reducing the increase in the subsequent service costs caused by fraudulent insurance behavior, and ensuring the healthy and benign development of the business. First, in response to determining that the target user account has logged in to the user information processing end, the key content of the page content corresponding to the user information verification page is extracted in the above-mentioned user information processing end to generate the key content of the user information page. Thus, the user's historical insurance information (key content) can be extracted. Then, according to the key content of the above-mentioned user information page generated by the above-mentioned user information processing end and the user portrait information corresponding to the above-mentioned target user account, the pre-trained user risk information identification model is used to generate user risk identification information for the key content of the above-mentioned user information page. Thus, the user risk information identification model can be used to identify the risk of users in multiple dimensions. Finally, the above-mentioned user risk identification information is sent to the above-mentioned user information processing end to perform a risk warning operation for the above-mentioned target user account. Therefore, the user risk information identification model can be used to conduct multi-dimensional risk identification of users, and risky users can be screened and intercepted in real time during the insurance process, shortening the verification time, reducing the economic losses caused by malicious insurance, and reducing the increase in subsequent service costs caused by fraudulent insurance behavior, thereby ensuring the healthy and benign development of the business. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0010] Figure 1 is a flow chart of some embodiments of the method for identifying user risk information according to the present application; Figure 2 It is a schematic diagram of the structure of a computer device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0011] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0012] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0013] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0014] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0015] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0016] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0017] Figure 1 The process 100 of some embodiments of the method for identifying user risk information according to the present application is shown. The method for identifying user risk information comprises the following steps: Step 101, in response to determining that the target user account has logged in at the user information processing end, extract key content from the page content corresponding to the user information verification page at the user information processing end to generate key content of the user information page.

[0018] In some embodiments, the execution subject (e.g., computing device) of the user risk information identification method may extract key content from the page content corresponding to the user information verification page in the user information processing end in response to determining that the target user account has logged in to the user information processing end, so as to generate key content of the user information page. The target user account may be a user account to be insured (insurance). For example, the target user account may be an account for logging in to the insurance platform in the user information processing end. The insurance platform may be a platform that supports various processing operations such as user information risk determination, insurance content reading, and insurance purchase. The user information processing end may be a processing system that supports automated process processing. For example, the user information processing end may be Selenium. Selenium is an open source tool set for automated testing of Web applications, which supports multiple browsers and allows users to write test scripts in multiple programming languages ​​(such as Java, Python, etc.) to simulate the operations of real users in the browser. There is a corresponding operation device at the user information processing end. The operation device provides the necessary hardware and software environment for executing automated tasks. By correctly binding, logging in, and managing the operation device, the predetermined tasks can be executed efficiently and reliably. In practice, the operation device may be a physical device or a virtual device. Physical devices can be computers and servers, as well as mobile phones and tablets. Virtual devices can be cloud PCs or cloud phones. The corresponding operating environment needs to be configured in advance. The operating devices must meet the operating environment requirements of the RPA task, including the operating system, software dependencies, network connections, and security configurations. In the cloud environment, ensure that the resources of the virtual devices (such as CPU, memory, and storage) can meet the requirements of the insurance process processing tasks. The operating devices need to be continuously monitored to ensure the stable operation of the insurance process processing tasks. Any hardware or software failures need to be handled in a timely manner. The management operations of related devices include: regular updates, maintenance, and optimization to ensure an efficient and secure operating environment. It should be noted that for the platform login of the target account, you can log in by managing login information, starting a browser or application, navigating to the login page, and entering credentials. The user information verification page can be a page in the insurance platform where the user information verification is to be performed. For example, the user information verification page can be a page that displays the various insurance information of the current user. The page content can be the specific content in the user information verification page. For example, key content extraction can be the content corresponding to the key insurance field elements in the page.

[0019] As an example, the key content of the page content corresponding to the user information verification page can be extracted through the pre-set insurance key field extraction rule to generate the key content of the user information page. The insurance key field extraction rule can be an extraction rule set for extracting the insurance key field, which can include field type, field name, etc.

[0020] Step 102, based on the key content of the user information page generated by the user information processing terminal and the user portrait information corresponding to the target user account, a pre-trained user risk information identification model is used to generate user risk identification information for the key content of the user information page.

[0021] In some embodiments, the execution subject may generate user risk identification information for the key content of the user information page generated by the user information processing terminal and the user portrait information corresponding to the target user account, using a pre-trained user risk information identification model. The user risk identification information may indicate the insurance risk of the user corresponding to the target user account. For example, the user risk identification information may indicate the insurance risk of the user corresponding to the target user account. For example, the user risk identification information may indicate that the insurance risk of user A is relatively high, and the insurance amount needs to be increased / or user A is refused to be insured. Among them, the user risk information identification model may be a pre-trained neural network model with the key content of the user information page and the user portrait information as input and the user risk identification information as output. For example, the user risk information identification model may be a multi-layer forward neural network (MLFN), a recursive neural network (RNN), a self-organizing neural network, or a Hopfield neural network. The user portrait information may include: gender, age, region, annual income, various historical insurance behavior information, and various historical insurance behavior information. It should be noted that the user portrait information is the content that the target user account needs to fill in when registering, and it needs to be updated regularly. Multilayer feedforward neural network (MLFN): It adopts a multilayer local connection structure and no feedback. The neuron function is usually a Sigmoid function or RBF. It generally runs in discrete time and uses a supervised learning algorithm. This model is suitable for processing complex nonlinear relationships and has good adaptability for identifying user risk information. Recurrent neural network (RNN): It is mainly used for identification, modeling and control of nonlinear dynamic systems. Recurrent neural networks can process sequence data, which is very useful for processing time-dependent user behavior data, thereby helping to identify potential risk behaviors. Self-organizing neural network: The main function is to realize the clustering of input feature vectors, and on this basis, it is used to complete mapping such as function approximation, classification and pattern recognition. This model is suitable for processing complex and nonlinear user behavior data, and helps to discover potential risk patterns in user behavior. Hopfield neural network: This is a fully connected feedback network that can run in continuous time or discrete time. Hopfield neural network is suitable for processing complex optimization problems and has certain application value for identifying and predicting user risk information. It should be noted that user portrait information is real and verifiable portrait information. Historical insurance behavior information can represent the user's insurance behavior information. All historical insurance information and all historical policy issuance information can be queried on the insurance platform.

[0022] The user risk information identification model can be trained through the following steps: The first step is to determine the initial user risk information identification model. The initial user risk information identification model includes: the initial user information page key content risk identification network and the initial user portrait information risk identification network. The initial user portrait information risk identification network includes: the initial model input layer, the initial user risk information output layer and the loss function layer. The initial user information page key content risk identification network includes: the initial abnormal user page key feature information generation network and the initial page key content risk identification network.

[0023] The initial user information page key content risk identification network may be a user information page key content risk identification network that has not yet been trained. The user information page key content risk identification network may be a neural network model that generates user information page key content risk identification information. User information page key content risk identification information may be insurance risk level information obtained by risk identification of key content in the user information page. Insurance risk level information may represent the user's insurance risk level. For example, the user's insurance risk level may be {first level, second level, third level, fourth level}. The risk corresponding to the first level is greater than the risk corresponding to the second level. The risk corresponding to the second level is greater than the risk corresponding to the third level. The risk corresponding to the third level is greater than the risk corresponding to the fourth level.

[0024] The initial user risk information output layer may be a user risk information output layer that has not yet been trained. In practice, the user risk information output layer may include: a user risk characteristic information generation layer, an insurance risk level characteristic information generation layer, and an insurance risk value level characteristic information generation layer. The user risk characteristic information generation layer may be a network layer that generates user risk characteristic information. The insurance risk level characteristic information generation layer may be a network layer that generates insurance risk level characteristic information. The insurance risk value level characteristic information generation layer may be a network layer that generates insurance risk value level characteristic information. For example, the user risk characteristic information generation layer may be a multi-head attention mechanism model. The insurance risk level characteristic information generation layer may be a convolutional layer. The insurance risk value level characteristic information generation layer may be a convolutional layer. The loss function layer may include at least one loss function.

[0025] The initial model input layer may be a model input layer that has not been trained yet. The model input layer may be a data input layer. For example, the model input layer may be a feature information extraction layer. For example, the feature extraction layer may be a multi-layer series convolutional neural network.

[0026] The second step is to obtain a user risk information training sample set. The user risk information training sample includes: sample user information page key content, sample user portrait information, sample user value circulation information sequence, sample key content abnormality label and sample portrait value level label. The sample user value circulation information can represent the user's insurance value circulation behavior information at a certain time. For example, the sample user value circulation information can represent the insurance value information purchased by the user on the 10th. The sample key content abnormality label can represent the risk field content in the sample user information page key content. The sample portrait value level label can represent the value risk level corresponding to the sample user portrait information.

[0027] The third step is to train the initial user risk information identification model using the user risk information training sample set to obtain a trained user risk information identification model.

[0028] The third step may include the following sub-steps: The first sub-step is to select a target user risk information training sample from the user risk information training sample set. A user risk information training sample can be randomly selected from the user risk information training sample set as the target user risk information training sample.

[0029] In the second sub-step, based on the target user risk information training sample, the following training steps are performed: First, using the initial model input layer included in the initial user portrait information risk identification network, generate user portrait feature information corresponding to the sample user portrait information included in the above-mentioned target user risk information training sample and value circulation feature information corresponding to the sample user value circulation information sequence included.

[0030] The execution subject may use the initial model input layer to perform the following processing steps: The first processing step is to generate the first initial user portrait feature information for the above-mentioned sample user portrait information, and to generate the first initial user value circulation feature information corresponding to the above-mentioned sample user value circulation information sequence. Among them, the first initial user portrait feature information can be feature information fused together from each portrait feature in the sample user portrait information. The first initial user portrait feature information can represent the feature semantics corresponding to each portrait feature in the sample user portrait information. The first initial user value circulation feature information can be feature information fused together from each user value circulation feature in the sample user value circulation information sequence. The first initial user value circulation feature information can represent the feature semantics corresponding to each user value circulation feature in the sample user value circulation information sequence. Both the first initial user portrait feature information and the first initial user value circulation feature information can be feature information in the form of matrix vectors. For example, the above-mentioned execution subject can generate the first initial user portrait feature information and the first initial user value circulation feature information by onehot encoding.

[0031] The second processing step is to perform low-dimensional embedding processing on the above-mentioned first initial user portrait feature information and the above-mentioned first initial user value circulation feature information respectively to generate embedded user portrait feature information and embedded user value circulation feature information. Among them, the embedded user portrait feature information and the embedded user value circulation feature information can be feature information in the form of matrix vectors. The dimension of the matrix vector corresponding to the embedded user portrait feature information is smaller than the dimension of the matrix vector corresponding to the first initial user portrait feature information. The dimension of the matrix vector corresponding to the embedded user value circulation feature information is smaller than the dimension of the matrix vector corresponding to the first initial user value circulation feature information.

[0032] As an example, the execution entity may utilize a low-dimensional embedding layer to perform low-dimensional embedding processing on the first initial user portrait feature information and the first initial user value circulation feature information, respectively, to generate embedded user portrait feature information and embedded user value circulation feature information.

[0033] The third processing step is to input the above-mentioned embedded user portrait feature information into the initial compression excitation layer included in the above-mentioned initial model input layer to obtain the main feature information of the user portrait. Among them, the main feature information of the user portrait can be the feature information of the main portrait features in the sample user portrait information. As an example, first, the above-mentioned execution subject can perform average pooling processing on the embedded user portrait feature information to generate average pooling information. Secondly, multiply the above-mentioned average pooling information by the first parameter to obtain the first multiplication information. After that, add the first multiplication information to the second parameter to obtain the first addition information. Then, input the first addition information into the RELU activation function to generate the first output result. Then, multiply the first output result by the third parameter to obtain the second multiplication result. Secondly, add the second multiplication result to the fourth parameter to obtain the second addition information. Finally, input the second addition information into the Sigmoid activation function to output the main feature information of the user portrait.

[0034] The fourth processing step is to generate user portrait feature information and value circulation feature information based on the above-mentioned user portrait main feature information and the above-mentioned embedded user value circulation feature information.

[0035] The fourth processing step may include: 1. Generate initial embedded user value circulation feature information based on the embedded user value circulation feature information. As an example, the execution subject may average pool the embedded user value circulation feature information to generate pooled user value circulation feature information as the initial embedded user value circulation feature information.

[0036] 2. Generate the initial user portrait main feature information based on the above user portrait main feature information and the above embedded user portrait feature information. As an example, first, the above execution subject can perform the same or processing on the user portrait main feature information and the embedded user portrait feature information to generate the same or processing result. Then, the same or processing result is averaged pooled to generate the initial user portrait main feature information.

[0037] 3. Generate user portrait feature information and value circulation feature information based on the above-mentioned initial embedded user value circulation feature information and the above-mentioned initial user portrait main feature information. For example, the above-mentioned execution entity may input the initial embedded user value circulation feature information and the above-mentioned initial user portrait main feature information into the Bert model to generate user portrait feature information and value circulation feature information.

[0038] Second, using the above initial user risk information output layer, perform the following first processing steps: 1. Generate at least one user value feature information for at least one user value dimension based on the above-mentioned user portrait feature information and the above-mentioned value circulation feature information. Among them, the user value dimension may be a value dimension corresponding to the user. At least one user value dimension may be a description of the value of the user's insurance from multiple value dimensions. In practice, at least one user value dimension may include: a dimension of insurance categories that the user is interested in, and a dimension of insurance value categories that the user is interested in. For example, the dimension of insurance categories that the user is interested in may represent the type of insurance that the user is interested in. The dimension of insurance value categories that the user is interested in may represent the category dimension of the insurance value range that the user is interested in. For example, the above-mentioned execution entity may input the above-mentioned user portrait feature information and the above-mentioned value circulation feature information into the user risk feature information generation layer to generate at least one user value feature information for at least one user value dimension.

[0039] 2. Generate value dimension feature information and portrait value level feature information for the sample portrait value level label included in the target user risk information training sample based on the at least one user value feature information. As an example, the execution subject may generate value dimension feature information and portrait value level feature information for the sample portrait value level label included in the target user risk information training sample based on the at least one user value feature information using the insurance risk level feature information generation layer and the insurance risk value level feature information generation layer.

[0040] Third, through the loss function layer, the loss information between the above-mentioned value dimension feature information and the above-mentioned portrait value level feature information is determined. The loss function layer may include a preset loss function. For example, the loss function may be a cross entropy loss function or a hinge loss function.

[0041] Fourth, in response to determining that the training of the above-mentioned loss information characterization model is completed, the above-mentioned initial user portrait information risk identification network is determined as the trained user portrait information risk identification network.

[0042] Therefore, the trained user profile information risk identification network can be used to identify the insurance risks corresponding to the user profile information. Therefore, risky users can be identified and intercepted in real time during the insurance process, shortening the verification time, reducing the economic losses caused by malicious insurance, and reducing the increase in subsequent service costs caused by fraudulent insurance behavior, thus ensuring the healthy and benign development of the business.

[0043] Fifth, determine the initial abnormality identification configuration information and initial abnormal feature identification indication information of the corresponding user information page. The initial abnormality identification configuration information may be the abnormality identification configuration information before each training step is executed. The above-mentioned abnormality identification configuration information may be information for configuring the abnormal data identification method. The above-mentioned abnormality identification configuration information may include an identification feature type set, a data abnormality threshold set, and an abnormality type identification method identification set. The identification feature type in the above-mentioned identification feature type set may characterize the type of data corresponding to the feature required when performing abnormal data identification. The data abnormality threshold included in the above-mentioned data abnormality threshold set may be a threshold for characterizing the abnormality of value generation data of the corresponding data type. The abnormality type identification method identification in the abnormality type identification method identification set may be a unique identification of the abnormality type identification method. The above-mentioned abnormality type identification method may be a classification method for detecting the abnormal type of value generation data. The above-mentioned classification method may be: Lightgbm (Light Gradient Boosting Machine) machine learning model, LOF (Local Outlier Factor). The above-mentioned abnormality type may be, but is not limited to, one of the following: abnormality, no abnormality. The above-mentioned initial abnormality feature identification guidance information may be the abnormality feature identification guidance information before each training step is executed. The above-mentioned abnormal feature identification guidance information can be information used to guide the feature extraction model to extract the required features. The above-mentioned initial abnormal feature identification guidance information can include retrieving a value keyword text set, an abnormal numerical type set, a value verification type set, and numerical fluctuation information. In practice, the above-mentioned execution entity can determine the preset abnormal recognition configuration information and the preset abnormal feature recognition guidance information as the initial abnormal recognition configuration information and the initial abnormal feature recognition guidance information, respectively. Among them, the above-mentioned preset abnormal recognition configuration information can be a preset abnormal recognition configuration information. The above-mentioned preset abnormal feature recognition guidance information can be a preset abnormal feature recognition guidance information.

[0044] Sixth, the key content of the sample user information page included in the target user risk information training sample is input into the initial abnormal user page key feature information generation network corresponding to the initial abnormal feature identification indication information to obtain the abnormal feature information of the key content of the sample page. The key content of the sample user information page may include: user historical insurance information, user insurance information (insurance reporting), user income information, user insurance collection information (information on which insurances are collected), user insurance browsing information, etc. The initial abnormal user page key feature information generation network can be a feature extraction model for extracting features guided by the initial abnormal feature identification indication information in the key content of the sample user information page. The above-mentioned initial abnormal user page key feature information generation network can be a GPT model.

[0045] Seventh, according to the initial page key content risk identification network corresponding to the initial abnormal identification configuration information, the above-mentioned sample page key content abnormal feature information is subjected to content risk identification processing to obtain the sample page key content risk identification information. The initial abnormal user page key feature information generation network includes: a cause information generation subnetwork and an abnormal type generation subnetwork. Among them, the above-mentioned cause information generation subnetwork and can be a model for automatically generating abnormal cause information. The above-mentioned abnormal cause can be the cause of the abnormal key content of the page. The above-mentioned cause information generation subnetwork can be a GPT model. The abnormal type generation subnetwork can be: a model corresponding to at least one abnormal type identification method among the various abnormal type identification methods corresponding to the initial abnormal identification configuration information. The various abnormal type identification methods corresponding to the initial abnormal identification configuration information can be: various abnormal type identification methods corresponding to the abnormal type identification method identification set included in the initial abnormal identification configuration information.

[0046] Among them, the abnormal characteristic information of the key content of the above sample pages is processed for content risk identification, including: 1. Input the abnormal feature information of the key content of the sample page into the abnormal type generation subnetwork to obtain the abnormal type of the key content of the sample page. The abnormal type of the key content of the sample page can characterize whether there is an abnormality in the key content of the page. The abnormal type of the key content of the sample page can be: abnormal, no abnormality.

[0047] 2. In response to determining that the abnormal type of the key content of the sample page meets the preset abnormal type condition, the abnormal characteristic information of the key content of the sample page is input into the cause information generation subnetwork to obtain the abnormal cause information of the key content of the sample page. The preset abnormal type condition may be: the abnormal type of the key content of the sample page indicates that the key content of the page is abnormal.

[0048] 3. Combine the above-mentioned sample page key content abnormality type and the above-mentioned sample page key content abnormality reason information into the sample page key content risk identification information.

[0049] Eighth, determine the recognition loss value between the corresponding sample key content abnormal label and the above sample page key content risk identification information. For example, the recognition loss value between the corresponding sample key content abnormal label and the above sample page key content risk identification information can be determined by a preset loss function. The loss function can be a hinge loss function or a cross entropy loss function.

[0050] Ninth, in response to determining that the above-mentioned recognition loss value is less than or equal to the preset recognition loss value, the initial user information page key content risk recognition network is determined as the trained user information page key content risk recognition network.

[0051] Therefore, when the trained user information page key content risk identification network is used to identify abnormalities in the key content of the user information page, the accuracy of identifying abnormal value key content can be improved.

[0052] Step 103, sending the user risk identification information to the user information processing terminal to perform a risk warning operation on the target user account.

[0053] In some embodiments, the execution entity may send the user risk identification information to the user information processing terminal to perform risk warning operations on the target user account. For example, the target user account may be labeled with a risk level to avoid insuring the user.

[0054] For another example, risk warning operations may include: First: pass the current insurance data into the risk control model, score the user, and conduct verification according to the risk control strategy of the current product. If the risk label score is higher than the threshold, it will be rejected.

[0055] Second: Request risk control scores from third-party sources, and reject them if they are higher than the threshold.

[0056] Third: Feed back the scoring data from third-party sources into the risk control model system to provide decision-making indicators for subsequent scoring.

[0057] Fourth: For rejected users, if they meet the rules for joining the list and there are no rules for joining the list, then join the list rules. The present application also provides a computer device 200. Figure 2 As shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate with each other through the bus 201. The computer device 200 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 200.

[0058] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 201 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 201 may include a path for transmitting information between various components of the computer device 200 (for example, the memory 203, the processor 202, and the communication interface 204).

[0059] The processor 202 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0060] The memory 203 may include a volatile memory, such as a random access memory (RAM). The memory 203 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0061] The memory 203 stores executable program codes, and the processor 202 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby implementing the aforementioned method for identifying user risk information. That is, the memory 203 stores instructions for executing the aforementioned method for identifying user risk information.

[0062] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or a communication network.

[0063] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned method for identifying user risk information.

[0064] The embodiment of the present application also provides a computer-readable storage medium. The above-mentioned computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for identifying user risk information.

[0065] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0066] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying user risk information, comprising: In response to determining that the target user account has logged in at the user information processing end, extracting key content from page content corresponding to the user information verification page at the user information processing end to generate key content of the user information page; Generate user risk identification information for the key content of the user information page using a pre-trained user risk information identification model based on the key content of the user information page generated by the user information processing terminal and the user portrait information corresponding to the target user account; The user risk identification information is sent to the user information processing terminal to perform a risk warning operation on the target user account.

2. The user risk information identification method according to claim 1, wherein: Before generating user risk identification information for the key content of the user information page based on the key content of the user information page generated by the user information processing terminal and the user portrait information corresponding to the target user account by using a pre-trained user risk information identification model, the method further includes: Determine an initial user risk information identification model, wherein the initial user risk information identification model includes: an initial user information page key content risk identification network and an initial user portrait information risk identification network, the initial user portrait information risk identification network includes: an initial model input layer, an initial user risk information output layer and a loss function layer, and the initial user information page key content risk identification network includes: an initial abnormal user page key feature information generation network and an initial page key content risk identification network; Obtaining a user risk information training sample set, wherein the user risk information training sample includes: sample user information page key content, sample user portrait information, sample user value circulation information sequence, sample key content abnormality label and sample portrait value level label; The initial user risk information identification model is trained using the user risk information training sample set to obtain a trained user risk information identification model.

3. The method for identifying user risk information according to claim 2, wherein: The initial user risk information identification model is trained by using the user risk information training sample set to obtain a trained user risk information identification model, including: Selecting a target user risk information training sample from the user risk information training sample set; Based on the target user risk information training sample, perform the following training steps: Using the initial model input layer included in the initial user portrait information risk identification network, generating user portrait feature information corresponding to the sample user portrait information included in the target user risk information training sample and value circulation feature information corresponding to the sample user value circulation information sequence included; Using the initial user risk information output layer, the following first processing step is performed: Generating at least one user value feature information for at least one user value dimension according to the user portrait feature information and the value circulation feature information; Generate value dimension feature information and portrait value level feature information of a sample portrait value level label included in the target user risk information training sample according to the at least one user value feature information; Determine loss information between the value dimension feature information and the portrait value level feature information through a loss function layer; In response to determining that the loss information characterization model training is completed, the initial user profile information risk identification network is determined as a trained user profile information risk identification network.

4. The method for identifying user risk information according to claim 3, wherein: The training step also includes: Determine initial abnormality identification configuration information and initial abnormality feature identification indication information corresponding to the user information page; Inputting the key content of the sample user information page included in the target user risk information training sample into the initial abnormal user page key feature information generation network corresponding to the initial abnormal feature identification indication information to obtain the sample page key content abnormal feature information; According to the initial page key content risk identification network corresponding to the initial abnormal identification configuration information, content risk identification processing is performed on the abnormal characteristic information of the key content of the sample page to obtain the key content risk identification information of the sample page; Determine an identification loss value between a corresponding sample key content abnormal label and the sample page key content risk identification information; In response to determining that the recognition loss value is less than or equal to the preset recognition loss value, the initial user information page key content risk recognition network is determined as the trained user information page key content risk recognition network.

5. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images