Virtual image generation method and device based on financial service information and electronic equipment

Abstract

The invention discloses a virtual image generation method and device based on financial service information and electronic equipment, and relates to the field of financial science and technology. The method comprises the following steps: acquiring a user portrait of a target user who handles a target financial service through a mobile client; scene features corresponding to the target financial service are extracted, and the scene features are used for representing the service scene style of the target financial service; according to the user portrait of the target user and the scene feature corresponding to the target financial service, a target virtual image corresponding to the target user is generated, and the target virtual image is used for guiding the target user to handle the target financial service. The technical problem that in the prior art, virtual images corresponding to different financial businesses are not personalized is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and more specifically, to a method, device and electronic device for generating a virtual image based on financial business information. Background Art

[0002] At present, the virtual image design for financial services usually adopts a unified and standardized virtual image. Although the unified and standardized virtual image can meet the basic visual perception of users, it cannot meet the personalized needs of users for virtual images.

[0003] For example, there is a lack of personalized and vivid virtual images for different financial services, which makes it impossible to combine the characteristics of financial services, satisfy users' visual stimulation and sense of familiarity, and enhance users' experience and satisfaction when handling financial services.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method, device and electronic device for generating a virtual image based on financial business information, so as to at least solve the technical problem in the prior art that the virtual images corresponding to different financial businesses lack personalization.

[0006] According to one aspect of an embodiment of the present application, a method for generating a virtual image based on financial business information is provided, including: obtaining a user portrait of a target user who handles a target financial business through a mobile client; extracting scene features corresponding to the target financial business, wherein the scene features are used to characterize the business scene style of the target financial business; generating a target virtual image corresponding to the target user based on the user portrait of the target user and the scene features corresponding to the target financial business, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0007] Optionally, a target virtual image corresponding to the target user is generated based on the user portrait of the target user and the scene features corresponding to the target financial business, including: converting the user portrait of the target user into a first feature vector, and converting the scene features corresponding to the target financial business into a second feature vector; inputting the first feature vector and the second feature vector into a target generator network, fusing the first feature vector and the second feature vector into a target feature vector through the target generator network, and generating a target virtual image based on the target feature vector, wherein the training data of the target generator network includes the user portrait of the reference user, the historical financial business handled by the reference user, the personnel characteristics of the service personnel who handled the historical financial business for the reference user, and the evaluation score of the reference user to the service personnel.

[0008] Optionally, the training process of the target generator network includes the following steps: determining the first category of service personnel and the second category of service personnel based on the evaluation scores of the reference users on the service personnel, wherein the evaluation scores of the reference users on the first category of service personnel are less than a preset threshold, and the evaluation scores of the reference users on the second category of service personnel are greater than or equal to the preset threshold; performing multiple iterative training on the initial generator network according to the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portraits of the reference users, and the business characteristics of historical financial business to obtain the target generator network.

[0009] Optionally, the initial generator network is iteratively trained multiple times according to the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portrait of the reference user, and the business characteristics of the historical financial business to obtain a target generator network, including: converting the user portrait of the reference user into a third feature vector, and converting the business characteristics of the historical financial business into a fourth feature vector; generating a virtual image according to the third feature vector and the fourth feature vector through the initial generator network; judging a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel, and a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel through the initial discriminator network; and training the initial generator network according to the first similarity and the second similarity until the target generator network is obtained through training.

[0010] Optionally, the initial generator network is trained according to the first similarity and the second similarity until a target generator network is obtained through training: the initial generator network is iteratively trained according to the first similarity and the second similarity until the initial generator network enters a convergence state, and the initial generator network that has entered a convergence state is used as the target generator network; wherein the virtual image generated by the initial generator network in the convergence state based on the third eigenvector and the fourth eigenvector satisfies the following conditions at the same time: a first condition that a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel is less than a first threshold; a second condition that a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel is greater than a second threshold.

[0011] Optionally, obtaining a user portrait of a target user who handles a target financial business through a mobile client includes: obtaining the network address and account registration address of the mobile client with the target user's authorization; determining the target user's location information based on the network address and account registration address of the mobile client; determining the target user's custom preference information based on the target user's location information; and generating a user portrait of the target user based on the target user's location information and custom preference information.

[0012] Optionally, obtaining a user portrait of a target user who handles a target financial business through a mobile client includes: obtaining voice information of the target user with authorization from the target user; determining the voice style of the target user based on the voice information of the target user; determining the location information of the target user based on the voice style of the target user; determining the custom preference information of the target user based on the location information of the target user, and generating a user portrait of the target user based on the location information, custom preference information and voice style of the target user.

[0013] According to another aspect of the present application, a virtual image generation device based on financial business information is also provided, which includes: an acquisition unit for acquiring a user portrait of a target user who handles a target financial business through a mobile client; a feature extraction unit for extracting scene features corresponding to the target financial business, wherein the scene features are used to characterize the business scene style of the target financial business; a processing unit for generating a target virtual image corresponding to the target user based on the user portrait of the target user and the scene features corresponding to the target financial business, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0014] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned virtual image generation method based on financial business information.

[0015] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned method for generating a virtual image based on financial business information is executed when the program is running.

[0016] According to another aspect of the present application, a computer program product is also provided, comprising computer instructions, which, when executed by a processor, implement the steps of the above-mentioned method for generating a virtual image based on financial business information.

[0017] In this application, the user portrait of the target user who handles the target financial business through the mobile client is first obtained, and then the scene features corresponding to the target financial business are extracted, wherein the scene features are used to characterize the business scene style of the target financial business. Finally, according to the user portrait of the target user and the scene features corresponding to the target financial business, a target virtual image corresponding to the target user is generated, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0018] It can be seen from the above that in this application, the user portrait contains personalized information such as the target user's living area, nationality, customs, age, gender, personality, etc., which means that the generated virtual image can be closer to the user's real identity and preferences. For example, for a user with a specific cultural background, the virtual image can wear clothing that conforms to the cultural customs and use appropriate language styles and expressions, thereby enhancing the user's sense of identity and participation. In addition, the extraction of scene features ensures that the virtual image matches the business scene style of the target financial business. For example, in the financial investment business, the virtual image shows a professional and formal image, while in the bank welfare activity scene, the virtual image is more friendly and relaxed. This improvement in matching helps users better understand and adapt to the current business environment and improve the efficiency and satisfaction of business handling.

[0019] In summary, this application generates a virtual image that is highly matched with the user and business scenario by comprehensively considering the user portrait and scenario characteristics, which not only improves the user experience when handling financial business, but also enhances the application value of the virtual image in financial services. It is an important improvement in the prior art regarding the personalized generation of virtual images, and solves the technical problem in the prior art regarding the lack of personalization of virtual images corresponding to different financial businesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for generating a virtual image based on financial business information is shown;

[0022] Figure 2 is a flowchart of an optional method for generating a virtual image based on financial business information according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of an optional virtual image generation device based on financial business information according to an embodiment of the present application;

[0024] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] It should also be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0028] According to an embodiment of the present application, an embodiment of a method for generating a virtual image based on financial business information is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for generating a virtual image based on financial business information is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0030] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components in the computer terminal 10 (or mobile device). As in the method for generating a virtual image based on financial business information involved in the embodiments of the present application, the data processing circuit serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0031] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the virtual image generation method based on financial business information in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the virtual image generation method based on financial business information is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0032] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0034] Under the above operating environment, this application provides Figure 2 The method for generating a virtual image based on financial business information is shown. Figure 2 FIG. 1 is a flowchart of an optional method for generating a virtual image based on financial business information according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0035] Step S201, obtaining a user portrait of a target user who handles a target financial service through a mobile client.

[0036] For the convenience of explanation, in an optional embodiment, a virtual image generation system can be used as the execution subject of the virtual image generation method based on financial business information in the embodiment of the present application, wherein the system can be a software system or an embedded system combining software and hardware. It is known to those skilled in the art that the execution subject of the virtual image generation method based on financial business information in the present application can also be other devices, equipment or systems, and the present application does not specifically limit the specific form of the execution subject.

[0037] Optionally, a mobile client refers to an application or software used by a user on a mobile device (such as a smartphone or tablet) to access specific services or functions. In the context of this application, a mobile client specifically refers to a mobile application or web service provided by a bank or financial institution for online financial services. Through the mobile client, users can easily perform operations such as account inquiries, transfers, loan applications, investment and financial management.

[0038] Optionally, the target financial business refers to a specific financial activity that the user currently or plans to conduct through the mobile client. Financial business includes but is not limited to bank deposits, loans, credit card services, investment and financial management, insurance purchases, fund transactions, etc. The identification of the target financial business is crucial to generating a virtual image that meets the needs of the scene, because different business types may require virtual images of different styles and professional levels to provide guidance and support.

[0039] Optionally, a user portrait is a virtual conceptual model used to describe and understand the characteristics, needs, preferences, and behavior patterns of users. In this application, the construction of user portraits is based on the following key information:

[0040] Living area: The user’s geographical location may affect his or her acceptance and preference for virtual images.

[0041] Nationality: The country to which the user belongs, which is related to cultural background and language habits.

[0042] Customs: Habits and traditions in a specific cultural context that influence users’ communication style and image preferences.

[0043] Age: The age group of the user, which may reflect their familiarity with technology and communication preferences.

[0044] Gender: Whether the user is male or female affects the gender setting and communication style of the avatar.

[0045] Personality: whether the user is introverted or extroverted, and whether they prefer direct or gentle communication methods.

[0046] Business type preference: the user's preference for financial services, such as investment, insurance, or loans.

[0047] Step S202: extracting scenario features corresponding to the target financial business, wherein the scenario features are used to characterize the business scenario style of the target financial business.

[0048] Optionally, scenario features refer to key characteristics or elements that affect the design and performance of the avatar in a certain target financial business scenario. These features can be considered from multiple dimensions, including but not limited to the formality and complexity of the business, the needs and expectations of users, and the common processes and operations of the business. The extraction of scenario features helps to accurately understand the specific requirements of the target financial business scenario and provide direction for generating avatars.

[0049] Alternatively, the business scenario style refers to the overall atmosphere or form of expression of the target financial business, which is determined by the characteristics of the scenario. For example, investment and financial services may require the avatar to show a stable and professional image and communication style; while bank welfare activities may require a relaxed, friendly and even entertaining image design. The determination of the business scenario style helps ensure that the avatar not only fits the scenario in appearance, but also adapts to the characteristics of the business in terms of communication methods and behavior.

[0050] By extracting and analyzing the scenario characteristics of the target financial business, we can ensure that the generated virtual image accurately reflects the business scenario style, thereby providing users with a personalized service experience that is closer to their needs and scenarios.

[0051] Step S203, generating a target virtual image corresponding to the target user according to the user portrait of the target user and the scene characteristics corresponding to the target financial business, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0052] Optionally, the user portrait provides detailed information about the user, including but not limited to age, gender, personality, preferences, etc., which is the basis for building a personalized virtual image. For example, if the user prefers formal communication methods and has a cautious personality, the generated virtual image will show a professional and stable image and use a formal language style. Scenario features focus on the specific needs and characteristics of the target financial business, such as the formality of the business, the required expertise, and the common procedures for handling. The identification of scenario features helps to determine the behavior patterns and functional settings of the virtual image in specific business scenarios. Combining user portraits with scenario features can ensure that the virtual image not only conforms to the user's personal preferences in appearance, but also matches the business scenario in terms of communication methods, behaviors, and services provided.

[0053] Optionally, based on the information of user portrait and scene characteristics, the target virtual image is generated through an algorithm or artificial intelligence model. This process usually includes but is not limited to: designing the appearance and clothing style of the virtual image according to the user's age, gender, preferences, etc., so that it is consistent with the user's personal characteristics and conforms to the professional or casual style of the business scenario; setting the language style, tone and expression of the virtual image according to the user's personality and communication preferences to ensure natural, smooth and efficient communication; combined with the characteristics of the business scenario, the virtual image can provide targeted guidance and services, such as explaining business rules, guiding users to complete the operation process, and providing instant feedback.

[0054] The generated target virtual image is designed to create a personalized and professional experience for users, helping users to understand and complete the processing of target financial business more easily and effectively.

[0055] Optionally, the generated target avatar will be deployed to the mobile client as a guide and assistant for users to handle financial business. By simulating human communication methods and behaviors, the avatar can interact with users, answer questions, provide information, and even enhance users' emotional connection and business experience through emotion management and personalized suggestions.

[0056] Based on the contents of the above steps S201 to S203, it can be seen that in this application, the user portrait of the target user who handles the target financial business through the mobile client is first obtained, and then the scene features corresponding to the target financial business are extracted, wherein the scene features are used to characterize the business scene style of the target financial business. Finally, according to the user portrait of the target user and the scene features corresponding to the target financial business, a target virtual image corresponding to the target user is generated, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0057] It can be seen from the above that in this application, the user portrait contains personalized information such as the target user's living area, nationality, customs, age, gender, personality, etc., which means that the generated virtual image can be closer to the user's real identity and preferences. For example, for a user with a specific cultural background, the virtual image can wear clothing that conforms to the cultural customs and use appropriate language styles and expressions, thereby enhancing the user's sense of identity and participation. In addition, the extraction of scene features ensures that the virtual image matches the business scene style of the target financial business. For example, in the financial investment business, the virtual image shows a professional and formal image, while in the bank welfare activity scene, the virtual image is more friendly and relaxed. This improvement in matching helps users better understand and adapt to the current business environment and improve the efficiency and satisfaction of business handling.

[0058] In summary, this application generates a virtual image that is highly matched with the user and business scenario by comprehensively considering the user portrait and scenario characteristics, which not only improves the user experience when handling financial business, but also enhances the application value of the virtual image in financial services. It is an important improvement in the prior art regarding the personalized generation of virtual images, and solves the technical problem in the prior art regarding the lack of personalization of virtual images corresponding to different financial businesses.

[0059] In an optional embodiment, in order to generate a target virtual image corresponding to the target user based on the user portrait of the target user and the scene features corresponding to the target financial business, the virtual image generation system may convert the user portrait of the target user into a first feature vector, and convert the scene features corresponding to the target financial business into a second feature vector. Then, the virtual image generation system may input the first feature vector and the second feature vector into a target generator network, fuse the first feature vector and the second feature vector into a target feature vector through the target generator network, and generate a target virtual image based on the target feature vector, wherein the training data of the target generator network includes the user portrait of the reference user, the historical financial business handled by the reference user, the personnel characteristics of the service personnel who handled the historical financial business for the reference user, and the evaluation score of the reference user to the service personnel.

[0060] Optionally, a user profile is a comprehensive data set that contains a user's personal attributes, preferences, and behavior patterns. In order for this information to be understood and processed by the machine learning model, the user profile needs to be converted into a numerical feature vector, namely the first feature vector. This vector can contain multiple dimensions, each of which represents an attribute or feature in the user profile, such as the user's age, gender, personality type, language preference, etc. The conversion process may involve data preprocessing techniques such as feature encoding, quantization, and dimensionality reduction to ensure the integrity and machine readability of the information.

[0061] The scenario features describe the specific environment and requirements of the target financial business, such as the formality of the business, the type of transaction, the required expertise, etc. Converting the scenario features into a second feature vector is also a data preprocessing step. Through this conversion, the information of the scenario is encoded into numerical data, which is convenient for the processing of the generated model. For example, for a complex loan application business, the second feature vector may contain elements such as the need for detailed information and the necessity of professional explanation.

[0062] The avatar generation system can input the first feature vector (user feature) and the second feature vector (scenario feature) into the target generator network. The target generator network is a trained deep learning model whose task is to fuse the input feature vectors into a comprehensive feature vector that can fully characterize the target user and target business scenario, namely, the target feature vector.

[0063] It should be noted that the core of the target generator network lies in its learning ability. The target generator network is trained with the following training data:

[0064] User portrait of reference users: historical user data collected to build a user feature database.

[0065] Refer to the historical financial transactions handled by users: the user's business records to help the model understand the needs of different business scenarios.

[0066] Personnel characteristics of service personnel: Refer to the role characteristics, communication methods, etc. of service personnel in historical services to identify which traits are more popular in different business scenarios.

[0067] Reference users’ evaluation scores of service personnel: User feedback on service personnel satisfaction is used to evaluate which characteristics and behavior patterns can best improve user satisfaction.

[0068] Through training, the target generator network can learn how to effectively integrate user features and scenario features to generate a target feature vector that can guide the design of the avatar. Based on this feature vector, the system generates a target avatar that not only conforms to the user's personalized preferences in appearance, but also matches the scenario characteristics of the target financial business in terms of communication style and the way of providing services.

[0069] The process of generating a virtual image is actually a test and application of the deep learning model. The model generates a specific virtual image instance based on the input feature vector. This instance can be an image, a 3D model, or a virtual assistant with a specific behavior pattern. The generated virtual image will show a specific appearance, language style, and behavior pattern based on the information contained in the target feature vector to meet the needs of users in specific financial business scenarios and provide a more personalized and efficient service experience.

[0070] In an optional embodiment, the training process of the target generator network includes the following steps:

[0071] The first category of service personnel and the second category of service personnel are determined based on the evaluation scores of the reference users on the service personnel, wherein the evaluation scores of the reference users on the first category of service personnel are less than a preset threshold, and the evaluation scores of the reference users on the second category of service personnel are greater than or equal to the preset threshold; based on the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portraits of the reference users, and the business characteristics of the historical financial business, the initial generator network is iteratively trained for multiple times to obtain the target generator network.

[0072] Optionally, in the training data set, service personnel are divided into two categories: first-category service personnel and second-category service personnel. The classification is based on the user's evaluation score of the service personnel. Specifically, the evaluation score of the first-category service personnel is lower than a preset threshold. The preset threshold can be set to a lower satisfaction level, such as lower than 3 points (assuming the evaluation score range is 1-5 points). This means that the first-category service personnel failed to effectively meet the user's expectations or needs in historical interactions, and there may be problems with their communication methods, service attitudes or professionalism. The evaluation score of the second-category service personnel is higher than or equal to the preset threshold. The preset threshold is usually set at a higher satisfaction level, such as above 4 points. The second-category service personnel have shown higher user satisfaction in historical interactions, and their service style, communication skills or expertise are considered to be positive and beneficial to users.

[0073] In addition, during the training process, not only the categories of service personnel were considered, but also the personnel characteristics of the first and second types of service personnel were comprehensively analyzed, with reference to the user portraits of users and the business characteristics of historical financial services. Personnel characteristics may include the service personnel's communication style, professional level, ability to solve specific problems, etc. User portraits include personal attributes and behavior patterns such as the user's age, gender, occupation, preferences, etc. Business characteristics describe scenario information such as the type, process, and professional needs of financial services.

[0074] The process of iterative training of the initial generator network is as follows:

[0075] First, an initial generator network is constructed, which will be used to learn how to generate avatars. The initial network parameters are randomly assigned.

[0076] Then, the collected personnel characteristics, user portraits, business characteristics and evaluation scores are encoded and standardized and converted into a format that can be processed by neural networks.

[0077] Secondly, based on the classification of service personnel, the characteristics of the first and second types of service personnel, user portraits, and business characteristics are input into the generator network as positive and negative samples. Positive samples represent interaction features that users are satisfied with, and negative samples represent interaction features that users are dissatisfied with.

[0078] Then, through multiple iterations, the back-propagation algorithm is used to adjust the parameters of the generator network to optimize the network's ability to generate positive samples and identify negative samples. The goal of the network is to be more inclined to the features of high user satisfaction represented by positive samples when generating virtual images, and avoid the features of low user satisfaction represented by negative samples.

[0079] During the training process, supervised learning methods may be used, that is, the network is provided with labeled training data, and the label indicates the category of the service personnel (satisfied or dissatisfied). By comparing with the label, the network can evaluate the accuracy and effectiveness of the generated virtual image and adjust its learning strategy accordingly.

[0080] After each training cycle, use an independent test data set to evaluate the performance of the network. If the network performance does not meet expectations, it may be necessary to adjust the network structure, optimize the algorithm, or collect more and higher-quality training data for further training.

[0081] Finally, after multiple iterations and optimizations, when the generator network can stably output virtual images that match the characteristics of highly satisfied service personnel and conform to user portraits and business characteristics, the target generator network is obtained. This network can automatically and efficiently generate personalized virtual images, whose communication style, professional level, appearance design, etc. will be closer to user preferences and business needs, thereby improving the user experience when handling financial services on mobile clients.

[0082] The above training process makes full use of user feedback in historical service data. Through the training of deep learning models, the generator network is continuously adjusted and optimized so that it can generate virtual images that best meet user needs. This method can not only improve the personalization level of virtual images, but also improve service quality and enhance user trust and satisfaction by imitating service personnel with outstanding performance in history.

[0083] In an optional embodiment, the initial generator network is iteratively trained multiple times based on the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portrait of the reference user, and the business characteristics of the historical financial business to obtain a target generator network, including: converting the user portrait of the reference user into a third feature vector, and converting the business characteristics of the historical financial business into a fourth feature vector; generating a virtual image based on the third feature vector and the fourth feature vector through the initial generator network; judging a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel, and a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel through the initial discriminator network; and training the initial generator network based on the first similarity and the second similarity until the target generator network is obtained through training.

[0084] First, the user profile of the reference user and the business features of the historical financial business are converted into numerical feature vectors that can be understood by the machine learning model, namely the third feature vector and the fourth feature vector. This conversion process usually includes the following steps:

[0085] Feature extraction: Extract attributes related to avatar design from user portraits, such as the user's age, gender, occupation, personality preferences, etc.; extract features such as business type, process complexity, professional requirements, etc. from historical financial business.

[0086] Encoding: Convert the extracted text or category features into numerical representations, such as using word embedding or one-hot encoding techniques.

[0087] Vectorization: Integrate the encoded features into a fixed-length vector to facilitate computational processing by the machine learning model. This may involve feature selection, dimensionality reduction, or vector fusion techniques.

[0088] Next, the initial generator network is used to generate a preliminary avatar representing the user and business scenario using the third feature vector (user feature vector) and the fourth feature vector (business feature vector) as input. The generator network attempts to generate a avatar instance that reflects user preferences and business needs by learning the distribution of the above feature vectors.

[0089] In order to evaluate whether the generated virtual image meets the target (i.e., close to the characteristics of the second type of service personnel and avoiding the characteristics of the first type of service personnel), an initial discriminator network is needed to make a judgment. The task of the discriminator network is to distinguish the similarity between the generated virtual image and the personnel characteristics of the first and second types of service personnel: First, the discriminator network calculates the first similarity (similarity with the first type of service personnel) and the second similarity (similarity with the second type of service personnel) by comparing the characteristics of the generated virtual image with the personnel characteristics of the two types of service personnel. Then, the first similarity and the second similarity are used as feedback signals to guide the training of the generator network. If the generated virtual image is more similar to the characteristics of the second type of service personnel, the generation result is considered to be better; otherwise, if it is more similar to the first type of service personnel, the parameters of the generator network need to be adjusted to avoid generating similar performances.

[0090] Based on the feedback of the first similarity and the second similarity, the parameters of the initial generator network are adjusted through an optimization algorithm (such as stochastic gradient descent, SGD) to optimize the performance of generating virtual images. This process will go through multiple training cycles (i.e. iterations) until the generated virtual image can achieve the following goals:

[0091] Maximize the similarity with the second type of service personnel, that is, improve the second similarity, to produce a virtual image with high user satisfaction.

[0092] Minimize the similarity with the first type of service personnel, that is, reduce the first similarity, to avoid generating a virtual image that the user is not satisfied with.

[0093] The training process also typically includes training the discriminator network to ensure that it can accurately distinguish the similarity between the generated virtual image and the characteristics of the two types of service personnel.

[0094] The training process continues until the generator network can stably generate virtual images that are highly similar to the characteristics of the second type of service personnel without relying on real-time adjustments, and these virtual images can meet the requirements of user portraits and business characteristics. At this point, the trained target generator network is obtained. This network can automatically and efficiently generate virtual images that meet the personalized needs of users and the style of business scenarios, thereby providing users with a better service experience.

[0095] Through the above training process, the system can not only generate virtual images that satisfy users, but also continuously optimize the generation model based on the analysis of historical service data, so that the design of virtual images is closer to actual user feedback, thereby improving the quality and personalization of financial services.

[0096] In an optional embodiment, the initial generator network is trained according to the first similarity and the second similarity until a target generator network is obtained through training, including: iteratively training the initial generator network according to the first similarity and the second similarity until the initial generator network enters a convergence state, and using the initial generator network that has entered the convergence state as the target generator network; wherein the virtual image generated by the initial generator network in the convergence state based on the third eigenvector and the fourth eigenvector satisfies the following conditions at the same time: a first condition that a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel is less than a first threshold; a second condition that a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel is greater than a second threshold.

[0097] Optionally, iterative training refers to adjusting the network parameters in the generator network through multiple cycles to gradually optimize the result of generating the virtual image. In each training iteration, the generator network generates a virtual image based on the input third feature vector (user portrait vector) and fourth feature vector (business feature vector). Subsequently, the discriminator network evaluates the similarity between the generated virtual image and the two types of service personnel, namely the first similarity and the second similarity. The goal of the generator network is to adjust its parameters so that the generated virtual image can be closer to the characteristics of the second type of service personnel while avoiding the characteristics of the first type of service personnel.

[0098] During the training process, the interaction between the generator network and the discriminator network can be seen as a game process, where the generator network tries to generate virtual images that are difficult for the discriminator network to distinguish, while the discriminator network tries to accurately distinguish the similarity between the generated virtual images and the characteristics of the two types of service personnel. In this dynamic process, the two networks jointly improve the quality of the generated results through repeated training and optimization.

[0099] Optionally, the convergence state is a key concept in machine learning, which refers to the point where the training process reaches a stable point, at which the effect of adjusting the parameters of the generator network on the generated results becomes very small, that is, the output of the network stops changing significantly. In this technical solution, the convergence state specifically refers to the initial generator network in the iterative training process, and the virtual image generated by it satisfies the following two conditions at the same time:

[0100] The first condition: the first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel is less than the first threshold (this means that the similarity between the generated virtual image's appearance, communication methods, service attitude, etc. and the characteristics of the first category of service personnel who have historically had low user evaluations has dropped below the set threshold, thereby avoiding an unsatisfactory user experience).

[0101] The second condition: the second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel is greater than the second threshold (this means that the similarity between the generated virtual image and the characteristics of the second category of service personnel who have historically received high user evaluations and good user satisfaction has reached or exceeded the preset threshold, and the virtual image exhibits the characteristics expected by users, such as professionalism, friendliness or efficiency).

[0102] In addition, once the initial generator network enters the convergence state and the generated virtual image can simultaneously meet the above two conditions, it means that the network training has achieved the predetermined goal, and the generator network at this time is determined as the target generator network. The target generator network has the ability to generate high-quality, personalized virtual images, and can generate virtual images that match user needs and business scenarios based on user portraits and business characteristics, thereby optimizing user experience and improving the personalization level of financial services.

[0103] The determination of the convergence state and the determination of the target generator network ensure that the generated avatar not only meets the personalized needs in appearance, but also meets the user's expectations for financial services in terms of communication and service, thereby providing users with a more humane online service experience. This process reflects the application value of deep learning technology in the field of financial service personalization. Through a data-driven approach, the avatar design is continuously optimized and customized to meet the needs of different users and financial business scenarios.

[0104] In an optional embodiment, obtaining a user portrait of a target user who handles a target financial business through a mobile client includes: obtaining the network address and account registration address of the mobile client with the authorization of the target user; determining the location information of the target user based on the network address and account registration address of the mobile client; determining the custom preference information of the target user based on the location information of the target user; and generating a user portrait of the target user based on the location information and custom preference information of the target user.

[0105] Optionally, the network address usually refers to the IP address of the user's device when it is connected to the Internet, which can be used to roughly locate the user's geographic location. The account registration address refers to the address information provided by the user when registering a mobile client account. By analyzing the network address and account registration address collected above, the system can determine the geographic location of the target user. This process may involve IP address resolution, which converts the IP address into a specific geographic location. The account registration address directly provides information about the user's residence or usage location.

[0106] Optionally, geographic location information is the basis for determining user customs and preferences. Users from different regions and cultural backgrounds may have unique preferences in terms of understanding of financial products, communication methods, service hours, image design, etc. For example, users in certain regions may prefer to use local languages, or have special sensitivity to specific festivals and customs. The system infers the user's customs and preferences by analyzing the cultural, language, and customs data of the user's region. Finally, based on the user's location information and customs and preferences, the system generates a detailed target user profile.

[0107] In an optional embodiment, obtaining a user portrait of a target user who handles a target financial business through a mobile client includes: obtaining voice information of the target user with authorization from the target user; determining the voice style of the target user based on the voice information of the target user; determining the location information of the target user based on the voice style of the target user; determining the custom preference information of the target user based on the location information of the target user, and generating a user portrait of the target user based on the location information, custom preference information and voice style of the target user.

[0108] Optionally, the system can collect a voice sample of the target user through a mobile client or other device, such as a voice command or call record of the user in the process of using financial services. The analysis of voice information can reveal the user's voice style, including characteristics such as speaking speed, intonation, vocabulary selection, etc. These characteristics can reflect the user's personality, emotional state and communication preferences. For example, a faster speaking speed may indicate that the user tends to communicate efficiently, while the use of specific industry terms may indicate that the user has a high level of understanding and expertise in financial services.

[0109] In addition, the user's voice information, especially the accent and language usage habits, can be used as a clue to determine their geographical location. People in different regions have significant differences in pronunciation, accent and language usage habits. By analyzing the user's voice characteristics, the system can infer the user's possible location. For example, using a dialect or a specific regional accent may indicate that the user is from a specific region.

[0110] According to another aspect of the present application, a device for generating a virtual image based on financial business information is also provided, wherein: Figure 3 is a schematic diagram of an optional virtual image generation device based on financial business information according to an embodiment of the present application, such as Figure 3 As shown, the virtual image generation device based on financial business information includes: an acquisition unit 301, a feature extraction unit 302, and a processing unit 303.

[0111] Optionally, the acquisition unit 301 is used to acquire a user portrait of a target user who handles a target financial business through a mobile client; the feature extraction unit 302 is used to extract scene features corresponding to the target financial business, wherein the scene features are used to characterize the business scene style of the target financial business; the processing unit 303 is used to generate a target virtual image corresponding to the target user based on the user portrait of the target user and the scene features corresponding to the target financial business, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0112] Optionally, the processing unit 303 includes: a first processing subunit, used to convert the user portrait of the target user into a first feature vector, and convert the scene features corresponding to the target financial business into a second feature vector; a second processing subunit, used to input the first feature vector and the second feature vector into a target generator network, fuse the first feature vector and the second feature vector into a target feature vector through the target generator network, and generate a target virtual image based on the target feature vector, wherein the training data of the target generator network includes the user portrait of the reference user, the historical financial business handled by the reference user, the personnel characteristics of the service personnel who handled the historical financial business for the reference user, and the evaluation score of the reference user to the service personnel.

[0113] Optionally, a virtual image generation device based on financial business information includes: a first determination unit, used to determine a first category of service personnel and a second category of service personnel based on an evaluation score of a reference user on the service personnel, wherein the evaluation score of the reference user on the first category of service personnel is less than a preset threshold, and the evaluation score of the reference user on the second category of service personnel is greater than or equal to the preset threshold; a training unit, used to perform multiple iterative training on the initial generator network according to the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portrait of the reference user, and the business characteristics of historical financial business to obtain a target generator network.

[0114] Optionally, the training unit includes: a third processing subunit, used to convert the user portrait of the reference user into a third feature vector, and convert the business characteristics of the historical financial business into a fourth feature vector; a fourth processing subunit, used to generate a virtual image based on the third feature vector and the fourth feature vector through an initial generator network; a fifth processing subunit, used to judge a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first category of service personnel, and a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second category of service personnel through an initial discriminator network; and a sixth processing subunit, used to train the initial generator network according to the first similarity and the second similarity until a target generator network is obtained through training.

[0115] Optionally, the sixth processing subunit includes: a first processing module, configured to iteratively train the initial generator network according to the first similarity and the second similarity until the initial generator network enters a converged state, and use the initial generator network in the converged state as the target generator network; wherein the virtual image generated by the initial generator network in the converged state according to the third eigenvector and the fourth eigenvector satisfies the following conditions at the same time:

[0116] The first condition is that the first similarity between the image characteristics of the virtual image and the personnel characteristics of the first type of service personnel is less than a first threshold;

[0117] The second condition is that the second similarity between the image characteristics of the virtual image and the personnel characteristics of the second type of service personnel is greater than a second threshold.

[0118] Optionally, the acquisition unit 301 includes: a first acquisition subunit, a first determination subunit, a second determination subunit, and a first generation subunit. The first acquisition subunit is used to acquire the network address and account registration address of the mobile client with the authorization of the target user; the first determination subunit is used to determine the location information of the target user according to the network address and account registration address of the mobile client; the second determination subunit is used to determine the custom preference information of the target user according to the location information of the target user; the first generation subunit is used to generate a user portrait of the target user according to the location information and custom preference information of the target user.

[0119] Optionally, the acquisition unit 301 includes: a second acquisition subunit, a third determination subunit, a fourth determination subunit, and a fifth determination subunit. The second acquisition subunit is used to acquire the voice information of the target user with the authorization of the target user; the third determination subunit is used to determine the voice style of the target user according to the voice information of the target user; the fourth determination subunit is used to determine the location information of the target user according to the voice style of the target user; the fifth determination subunit is used to determine the custom preference information of the target user according to the location information of the target user, and generate a user portrait of the target user based on the location information of the target user, the custom preference information and the voice style of the target user.

[0120] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 Only one is shown) a processor, a memory, a storage controller, and a peripheral interface, wherein the peripheral interface is connected to a radio frequency module, an audio module, and a display.

[0121] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the virtual image generation method and device based on financial business information in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned virtual image generation method based on financial business information. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0122] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain a user portrait of a target user who handles a target financial business through a mobile client; extract scene features corresponding to the target financial business, wherein the scene features are used to characterize the business scene style of the target financial business; generate a target virtual image corresponding to the target user based on the user portrait of the target user and the scene features corresponding to the target financial business, wherein the target virtual image is used to guide the target user to handle the target financial business.

[0123] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations shown.

[0124] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0125] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned method for generating a virtual image based on financial business information.

[0126] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product includes computer instructions, wherein when the computer instructions are executed, the device where the computer program product is located executes the above-mentioned virtual image generation method based on financial business information.

[0127] The above-mentioned embodiments or examples disclosed in the present application are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection disclosed in the present application. In the absence of contradiction, each step in a certain embodiment or example in the present application can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0128] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0134] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating a virtual image based on financial business information, characterized in that: include: Obtain user portraits of target users who handle target financial services through mobile clients; Extracting scenario features corresponding to the target financial business, wherein the scenario features are used to characterize the business scenario style of the target financial business; A target virtual image corresponding to the target user is generated according to the user portrait of the target user and the scenario characteristics corresponding to the target financial service, wherein the target virtual image is used to guide the target user to handle the target financial service.

2. The method for generating a virtual image based on financial business information according to claim 1, characterized in that: Generating a target virtual image corresponding to the target user according to the user portrait of the target user and the scenario characteristics corresponding to the target financial service, including: Converting the user profile of the target user into a first feature vector, and converting the scenario features corresponding to the target financial service into a second feature vector; The first feature vector and the second feature vector are input into a target generator network, the first feature vector and the second feature vector are fused into a target feature vector through the target generator network, and the target virtual image is generated according to the target feature vector, wherein the training data of the target generator network includes a user portrait of a reference user, historical financial transactions handled by the reference user, personnel characteristics of a service personnel who handled the historical financial transactions for the reference user, and an evaluation score of the reference user on the service personnel.

3. The method for generating a virtual image based on financial business information according to claim 2, characterized in that: The training process of the target generator network includes the following steps: Determining a first category of service personnel and a second category of service personnel according to the evaluation scores of the reference users on the service personnel, wherein the evaluation scores of the reference users on the first category of service personnel are less than a preset threshold, and the evaluation scores of the reference users on the second category of service personnel are greater than or equal to the preset threshold; According to the personnel characteristics of the first category of service personnel, the personnel characteristics of the second category of service personnel, the user portrait of the reference user and the business characteristics of the historical financial business, the initial generator network is iteratively trained multiple times to obtain the target generator network.

4. The method for generating a virtual image based on financial business information according to claim 3, characterized in that: According to the personnel characteristics of the first type of service personnel, the personnel characteristics of the second type of service personnel, the user portrait of the reference user, and the business characteristics of the historical financial business, the initial generator network is iteratively trained multiple times to obtain the target generator network, including: Converting the user profile of the reference user into a third feature vector, and converting the business features of the historical financial business into a fourth feature vector; generating a virtual image according to the third feature vector and the fourth feature vector by the initial generator network; Determining, by an initial discriminator network, a first similarity between the image features of the virtual image and the personnel features of the first type of service personnel, and a second similarity between the image features of the virtual image and the personnel features of the second type of service personnel; The initial generator network is trained according to the first similarity and the second similarity until the target generator network is obtained through training.

5. The method for generating a virtual image based on financial business information according to claim 4, characterized in that: The initial generator network is trained according to the first similarity and the second similarity until the target generator network is obtained through training, including: Iteratively training the initial generator network according to the first similarity and the second similarity until the initial generator network enters a convergence state, and using the initial generator network that has entered the convergence state as the target generator network; The virtual image generated by the initial generator network in the converged state according to the third eigenvector and the fourth eigenvector satisfies the following conditions at the same time: The first condition is that a first similarity between the image characteristics of the virtual image and the personnel characteristics of the first type of service personnel is less than a first threshold; The second condition is that a second similarity between the image characteristics of the virtual image and the personnel characteristics of the second type of service personnel is greater than a second threshold.

6. The method for generating a virtual image based on financial business information according to claim 1, characterized in that: Obtain user profiles of target users who handle target financial services through mobile clients, including: With the authorization of the target user, obtaining the network address and account registration address of the mobile client; Determine the location information of the target user according to the network address and account registration address of the mobile client; Determining the custom preference information of the target user according to the location information of the target user; A user profile of the target user is generated based on the location information and the custom preference information of the target user.

7. The method for generating a virtual image based on financial business information according to claim 1, characterized in that: Obtain user profiles of target users who handle target financial services through mobile clients, including: Acquiring voice information of the target user with authorization of the target user; Determining the voice style of the target user according to the voice information of the target user; Determine the location information of the target user according to the voice style of the target user; The custom preference information of the target user is determined according to the location information of the target user, and a user portrait of the target user is generated according to the location information of the target user, the custom preference information and the voice style of the target user.

8. A virtual image generation device based on financial business information, characterized in that: include: An acquisition unit, used to acquire a user profile of a target user who handles a target financial business through a mobile client; A feature extraction unit, used to extract scene features corresponding to the target financial business, wherein the scene features are used to characterize the business scene style of the target financial business; A processing unit is used to generate a target virtual image corresponding to the target user according to the user portrait of the target user and the scene characteristics corresponding to the target financial service, wherein the target virtual image is used to guide the target user to handle the target financial service.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the virtual image generation method based on financial business information as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the method for generating a virtual image based on financial business information as described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the steps of the method for generating a virtual image based on financial business information described in any one of claims 1 to 7 are implemented.

Images