Anti-fraud risk identification method and system based on multi-modal interaction

Abstract

The invention relates to an anti-fraud risk identification method and system based on multi-modal interaction, and the method comprises the steps: configuring an interaction template which comprises a prompt type interaction template and a verification type interaction template; configuring an expert rule, wherein the expert rule comprises a transaction channel, a rule name, an interaction strategy, a prompt strategy, a disposal strategy, a post strategy and a notification strategy; and a transaction is initiated, a risk control center is called to carry out risk identification, differentiated early warning processing modes are configured according to the expert rules based on crowd differences, and an interaction mode is selected to carry out secondary risk identification. Multi-dimensional information is captured through multi-modal interaction, multi-dimensional risk features are extracted, risks are finely identified, risk education and persuasion of different modals are realized according to risk levels and risk types, and the payment stopping rate of risk transactions and the anti-fraud awareness of users are improved.

Description

Technical Field

[0001] The present invention relates to the field of risk prevention and control technology, and in particular to an anti-fraud risk identification method and system based on multimodal interaction. Background Art

[0002] Existing bank risk control platforms mainly focus on pre-, mid- and post-event monitoring of card theft scenarios where the card is stolen by someone other than the original owner. When the other party's account is detected as a risky account, the risk information in the transaction is obtained in real time, and the risk level and risk type are calculated using Drools expert rules. An automated risk management strategy is then used, which is a passive response mode.

[0003] Real-time risk prevention and control of bank anti-fraud currently mainly uses expert rules to monitor risk characteristics of accounts, customers, equipment, etc. in real time to achieve identity verification in scenarios where the card is stolen by someone other than the original owner. However, with the continuous evolution of telecommunications network fraud, new types of fraud are becoming more complex and diversified, making it more difficult for banks to prevent and control risks. Taking the "pig killing" as an example, the transaction relationship between the payee and the payee is stable (common counterparties, common equipment), and the number of transactions is frequent. Looking at the transaction elements alone, its fraud characteristics are not obvious, and traditional expert rules are difficult to identify risks in the process. In addition, after the bank identifies the risk and intercepts the payment, the deeply brainwashed customer may go to other channels to pay, making it more difficult to dissuade them. Summary of the invention

[0004] In order to address the deficiencies of the prior art, the present invention proposes an anti-fraud risk identification method based on multimodal interaction. Through the multimodal interaction method, a two-way communication mechanism with customers is established to guide customers to actively identify risks and further improve the bank's risk transaction stop rate.

[0005] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0006] An anti-fraud risk identification method based on multimodal interaction, characterized by comprising:

[0007] S1. Configure the interaction template, the interaction template includes a prompt interaction template and a verification interaction template;

[0008] S2. Configure expert rules, which include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies;

[0009] S3. After initiating the transaction, the risk control center is called to perform risk identification. Differentiated early warning processing methods are configured according to the expert rules based on differences among different groups of people, and an appropriate interactive mode is selected for secondary risk identification.

[0010] Furthermore, after the transaction is initiated, the risk control center is called to identify risks, differentiated early warning processing methods are configured according to the expert rules based on population differences, and a suitable interactive mode is selected for secondary risk identification, including:

[0011] After initiating a transaction, call the risk control center interface to conduct a preliminary risk assessment and obtain early warning results;

[0012] Based on the expert rules of the risk control center, the interaction strategy is matched according to the warning results to obtain the interaction mode and interaction results;

[0013] The risk control center is called a second time according to the interaction method, expert rules are matched to make a decision, and a decision result is obtained;

[0014] The risk is handled by matching the handling strategy according to the decision result.

[0015] Furthermore, based on the expert rules of the risk control center, the interaction strategy is matched according to the warning result to obtain the interaction mode and interaction result, including:

[0016] Actively initiate multiple interactions based on the early warning results based on the interaction templates. The prompt interaction templates include safety reminders and full-screen reminders. The verification interaction templates include question-and-answer reminders, smart questionnaires, AI text interactions, in-terminal voice, and smart customer service outbound calls.

[0017] The risk level of the transaction is determined based on the multiple interactions, and a risk label of the transaction is returned.

[0018] Furthermore, judging the risk level of the transaction based on multiple interactions and returning the risk label of the transaction includes:

[0019] Introducing an intention recognition model and a risk decision model, wherein the intention recognition model and the risk decision model include a multi-intention recognition module, an intention customization module, a multimodal emotion processing module, an evolutionary dialogue module, an interaction strategy module, and a risk level recognition module;

[0020] Obtaining a risk level of the transaction based on the intention recognition model and the risk decision model;

[0021] Based on the risk level, matching is performed according to the risk strategy library to obtain a risk label. The risk strategy library includes: an intention knowledge library, an interaction strategy library, a dialogue script library, and a security examination paper library.

[0022] Furthermore, the second calling of the risk control center according to the interactive mode, matching expert rules to make a decision, and obtaining a decision result further includes:

[0023] The decision result is pushed to the user.

[0024] Furthermore, after the risk treatment is performed by matching the treatment strategy according to the decision result, the method further includes:

[0025] Configure post-positioning and notification strategies based on expert rules based on population differences.

[0026] The present invention also relates to an anti-fraud risk identification system based on multimodal interaction, characterized in that it comprises:

[0027] An interaction configuration module, used to configure interaction templates, wherein the interaction templates include prompt interaction templates and verification interaction templates;

[0028] A rule configuration module is used to configure expert rules, wherein the expert rules include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies;

[0029] The risk identification module is used to call the risk control center for risk identification after initiating a transaction, configure differentiated early warning processing methods based on population differences according to the expert rules, and select appropriate interactive modes for secondary risk identification.

[0030] The present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0031] The present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0032] The memory is used to store program instructions;

[0033] The processor is used to execute the above method by calling program instructions.

[0034] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0035] The beneficial effects of the present invention are:

[0036] The anti-fraud risk identification method and system based on multimodal interaction described in the present invention solves the problem that the traditional risk control expert rule method of the bank cannot accurately identify the risk behavior of the individual (fraud characteristics are not obvious), and moves the post-event risk investigation to the in-event prevention and control, saving the manpower cost of post-event risk investigation, and effectively protecting the customer's funds. Through multimodal interaction, multi-dimensional information is captured, multi-dimensional risk characteristics are extracted, risks are identified in a refined manner, and risk education and persuasion of different modes are implemented according to risk levels and risk types, thereby improving the stop payment rate of risky transactions and the anti-fraud awareness of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0038] Figure 1 The figure is a flow chart of the anti-fraud risk identification method based on multimodal interaction of the present invention;

[0039] Figure 2 This is a schematic diagram of the structure of the anti-fraud risk identification system based on multimodal interaction of the present invention;

[0040] Figure 3 The figure is a schematic structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. It should be understood that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments, and these embodiments are only used to illustrate the present application and are not used to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0042] Based on the interaction between the risk control center and the transaction channel, the present invention introduces an intelligent customer service engine (big data center) as an interactive risk control product, and the newly added link conducts refined identification of risks through multiple interactions.

[0043] like Figure 1 As shown, the embodiment of the present invention discloses an anti-fraud risk identification method based on multimodal interaction, and the steps of the method include:

[0044] Step S1. Configure interaction templates, where the interaction templates include prompt interaction templates and verification interaction templates.

[0045] Among them, prompt-type interaction templates can include security reminders and full-screen templates; verification-type interaction templates can include question-and-answer reminders, intelligent questionnaires, AI text interactions, in-terminal voice, and intelligent customer service outbound calls.

[0046] Step S2. Configure expert rules, wherein the expert rules include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies.

[0047] The transaction channels in the embodiment of the present invention may include mobile banking and online banking.

[0048] Step S3. After initiating the transaction, the risk control center is called to perform risk identification, differentiated early warning processing methods are configured according to the expert rules based on population differences, and an appropriate interactive mode is selected for secondary risk identification.

[0049] Specifically, the step S3 also includes: step S31, step S32, step S33, and step S34.

[0050] Step S31: After initiating a transaction, call the risk control center interface to conduct a preliminary risk assessment and obtain warning results;

[0051] Step S32: matching the interaction strategy according to the warning result based on the expert rules of the risk control center to obtain the interaction mode and interaction result;

[0052] Step S33: calling the risk control center a second time according to the interaction mode, matching expert rules to make a decision, and obtaining a decision result;

[0053] Step S34: matching the disposal strategy with the decision result to perform risk disposal.

[0054] When initiating a transaction, the risk control center is first called to issue a risk warning for the transaction that the customer is executing. The risk warning result can be directly returned to the channel end to remind the customer that the transaction may be risky, thereby protecting the customer's funds.

[0055] In the present invention, an intelligent customer service engine (big data center) is introduced, so a new interactive link is added in the transaction process for refined risk identification. As the traditional bank risk control expert rules cannot accurately identify the individual's operational risk behavior (fraud characteristics are not obvious), the intelligent customer service engine (big data center) performs refined risk identification through multiple interactions, and moves the post-event risk investigation to the in-process stage, which can save the post-event manual investigation cost and effectively protect the customer's funds security.

[0056] Specifically, the step S32 also includes: step S321 and step S322.

[0057] Step S321: Actively initiate multiple interactions based on the interaction template according to the warning result. The prompt interaction template includes a safety reminder and a full-screen reminder. The verification interaction template includes a question-and-answer reminder, an intelligent questionnaire, an AI text interaction, an in-terminal voice, and an intelligent customer service outbound call.

[0058] Step S322: Determine the risk level of the transaction based on multiple interactions, and return a risk label for the transaction.

[0059] Furthermore, the step S322 also includes: step S3221, step S3222, and step S3223.

[0060] Step S3221, introducing an intention recognition model and a risk decision model, wherein the intention recognition model and the risk decision model include a multi-intention recognition module, an intention customization module, a multimodal emotion processing module, an evolutionary dialogue module, an interaction strategy module, and a risk level recognition module;

[0061] Step S3222: Obtaining a risk level of the transaction based on the intention recognition model and the risk decision model;

[0062] Step S3223: Matching is performed according to the risk strategy library based on the risk level to obtain a risk label. The risk strategy library includes: an intention knowledge library, an interaction strategy library, a dialogue script library, and a security test paper library.

[0063] In the embodiment of the present invention, the intelligent customer service engine (big data center) introduces a model and a strategy library. The model includes an intention recognition model and a risk decision model. The intention recognition model and the risk decision model can be used to conduct in-depth analysis and decision-making on multiple interaction results; according to the pre-defined risk strategy library, transactions can be accurately assessed and processed.

[0064] Among them, the application of intention recognition model and risk decision model includes the following aspects.

[0065] Multi-intent recognition: Use technologies such as natural language processing to identify and distinguish different user intentions in a single interaction, improve interaction capabilities and user experience, and more accurately understand users' diverse intentions;

[0066] Intent customization: Based on specific transaction scenarios, the intent recognition model is customized to more accurately capture and identify user intent in specific environments, thereby enhancing applicability and accuracy in specific scenarios.

[0067] Content Workshop: Provide a platform or tool that can flexibly adjust and optimize the model to continuously adapt to market changes, accelerate model iteration, ensure that the model can respond to new business scenarios in a timely manner, deal with new fraud scenarios, and improve the model's adaptability and predictive ability;

[0068] Risk decision-making: Generate the final risk decision results based on in-depth analysis of risk assessment, providing more reliable and accurate risk assessment;

[0069] Multimodal emotion processing: Processing user emotions and attitudes in multiple interaction modes (such as text, voice, and images), using sentiment analysis technology to identify and respond to user emotional changes, improving the quality of interaction with users, and enhancing user experience and satisfaction;

[0070] Evolutionary dialogue: Dynamically adjust and optimize dialogue strategies during the interaction process, and continuously improve user experience through real-time feedback and learning algorithms, ensuring a high level of interaction and service in long and complex dialogues;

[0071] Polygraph capabilities: Identify potential dishonesty or fraud by analyzing language and behavioral patterns during interactions, enhancing monitoring of risks and security issues;

[0072] Strategy and risk level identification: According to the real-time interaction situation, the interaction strategy and prompt strategy are dynamically adjusted, and the risk level is divided to facilitate further decision-making.

[0073] In an embodiment of the present invention, a risk label is obtained through multiple interactions between the channel end and the intelligent customer service engine (big data center), and the risk label is returned to the risk control center for further decision-making and disposal, thereby improving the level of refinement in risk identification, achieving in-process prevention and control, and reducing the proportion of customers being deceived.

[0074] Specifically, after step S33, the method further includes: pushing the decision result to the user.

[0075] After the risk label is transmitted to the risk control center, the channel side calls the risk control center a second time to obtain the decision result and issue warnings and take measures for the user.

[0076] Specifically, after step S34, the method further includes: configuring differentiated post-position strategies and notification strategies according to expert rules based on differences among groups of people.

[0077] Conduct risk management for ongoing transactions based on decision-making results, configure differentiated early warning processing procedures for different groups of people who are susceptible to fraud, trigger multimodal interaction methods, flexibly select prompt strategies, handling strategies, post-strategy and notification strategies suitable for customers, select targeted wake-up scripts, configure different early warning processing methods for the elderly, teenagers / college students to handle risks, and use high precision models to flexibly select early warning processing methods.

[0078] The prompt strategy is to warn customers of risks during transactions, including pop-up reminders (using general reminder text, forcing customers to read), graphic reminders (revealing typical cases based on possible frauds), and video reminders (vivid and fascinating); the handling strategy is to deal with the current transaction, including facial recognition for non-personal operations, delayed arrival and withdrawal, telephone verification, and transaction blocking. The intensity of this handling directly affects the interception effect and the number of customer complaints; post-strategies include list strategies, dissuasion strategies, and police-bank linkage; notification strategies are notification reminders to customers / staff / public security, including SMS notifications, WeChat notifications, and email notifications.

[0079] For the elderly, video reminders are usually used to facilitate communication and understanding. If they choose to continue the transaction, telephone verification is used to terminate or unblock the transaction based on whether there is any risk. For risky transactions, a list strategy is used to add the receiving account to the blacklist.

[0080] For teenagers / college students, a reminder strategy with pictures and texts is usually adopted. If they choose to continue the transaction, a delayed payment disposal strategy is adopted. The transaction cancellation or automatic payment upon expiration is carried out based on whether there is a risk. For risky transactions, a list strategy is used to add the receiving account to the blacklist.

[0081] like Figure 2 As shown, the embodiment of the present invention discloses an anti-fraud risk identification system based on multimodal interaction, and its structure includes:

[0082] An interaction configuration module, used to configure interaction templates, wherein the interaction templates include prompt interaction templates and verification interaction templates;

[0083] A rule configuration module is used to configure expert rules, wherein the expert rules include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies;

[0084] The risk identification module is used to call the risk control center for risk identification after initiating a transaction, configure differentiated early warning processing methods based on population differences according to the expert rules, and select appropriate interactive modes for secondary risk identification.

[0085] By using this system, the above-mentioned operation processing method can be executed and the corresponding technical effects can be achieved.

[0086] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0087] The embodiment of the present invention further provides an electronic device for executing the above method, as a device for implementing the method, and its structure is as follows: Figure 3As shown, the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0088] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0089] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0090] The processor 301 may also include one or more processing units, for example, the processor 301 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be the nerve center and command center of the electronic device 300. The controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory may also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a high-speed cache memory. The memory may store instructions or data that the processor 301 has just used or circulated. If the processor 301 needs to use the instruction or data again, it may be directly called from the memory. Repeated access is avoided, the waiting time of the processor 301 is reduced, and the efficiency of the system is improved.

[0091] The processor 301 can run the method provided in the embodiment of the present application. The processor 301 can include different devices. For example, when a CPU and a GPU are integrated, the CPU and the GPU can cooperate to execute the method provided in the embodiment of the present application, for example, part of the algorithm in the method is executed by the CPU, and another part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0092] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0093] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0094] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the method provided in any embodiment of the present application.

[0095] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0096] The memory 303 may also store one or more computer programs corresponding to the method provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0097] Of course, the code of the method provided in the embodiment of the present application can also be stored in an external memory. In this case, the processor 301 can run the code of the method stored in the external memory through the external memory interface, and the processor 301 can control the running process.

[0098] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0099] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0102] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0104] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An anti-fraud risk identification method based on multimodal interaction, characterized in that: include: S1. Configure the interaction template, the interaction template includes a prompt interaction template and a verification interaction template; S2. Configure expert rules, which include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies; S3. After initiating the transaction, the risk control center is called to perform risk identification. Differentiated early warning processing methods are configured according to the expert rules based on differences among different groups of people, and an appropriate interactive mode is selected for secondary risk identification.

2. The method according to claim 1, characterized in that After the transaction is initiated, the risk control center is called to identify risks, differentiated early warning processing methods are configured according to the expert rules based on population differences, and appropriate interactive modes are selected for secondary risk identification, including: After initiating a transaction, call the risk control center interface to conduct a preliminary risk assessment and obtain early warning results; Based on the expert rules of the risk control center, the interaction strategy is matched according to the warning results to obtain the interaction mode and interaction results; The risk control center is called a second time according to the interaction method, expert rules are matched to make a decision, and a decision result is obtained; The risk is handled by matching the handling strategy according to the decision result.

3. The method according to claim 2, characterized in that The expert rules based on the risk control center match the interaction strategy according to the warning result to obtain the interaction mode and interaction result, including: Actively initiate multiple interactions based on the interaction template according to the warning results. The prompt interaction templates include safety reminders and full-screen reminders. The verification interaction templates include question-and-answer reminders, smart questionnaires, AI text interactions, in-terminal voice, and smart customer service outbound calls. The risk level of the transaction is determined based on the multiple interactions, and a risk label of the transaction is returned.

4. The method according to claim 3, characterized in that The determining the risk level of the transaction based on multiple interactions and returning the risk label of the transaction includes: Introducing an intention recognition model and a risk decision model, wherein the intention recognition model and the risk decision model include a multi-intention recognition module, an intention customization module, a multimodal emotion processing module, an evolutionary dialogue module, an interaction strategy module, and a risk level recognition module; Obtaining a risk level of the transaction based on the intention recognition model and the risk decision model; Based on the risk level, matching is performed according to the risk strategy library to obtain a risk label. The risk strategy library includes: an intention knowledge library, an interaction strategy library, a dialogue script library, and a security examination paper library.

5. The method according to claim 2, characterized in that After the risk control center is called twice according to the interaction mode, expert rules are matched to make a decision, and a decision result is obtained, the method further includes: The decision result is pushed to the user.

6. The method according to claim 2, characterized in that After the risk treatment is performed by matching the treatment strategy according to the decision result, the method further includes: Configure post-positioning and notification strategies based on expert rules based on population differences. 7.An anti-fraud risk identification system based on multimodal interaction, characterized in that: include: An interaction configuration module, used to configure interaction templates, wherein the interaction templates include prompt interaction templates and verification interaction templates; A rule configuration module is used to configure expert rules, wherein the expert rules include transaction channels, rule names, interaction strategies, prompt strategies, disposal strategies, post-position strategies, and notification strategies; The risk identification module is used to call the risk control center for risk identification after initiating a transaction, configure differentiated early warning processing methods based on population differences according to the expert rules, and select appropriate interactive modes for secondary risk identification.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store program instructions; The processor is configured to execute the method according to any one of claims 1 to 6 by calling program instructions.

10. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images