Business handling method and device and electronic equipment

Abstract

The invention discloses a business handling method and device and electronic equipment. The method comprises the following steps: displaying a business handling page of a target business corresponding to a target account, and obtaining a business handling demand of the target account; constructing a target knowledge graph matched with the business handling demand; determining a target digital person matched with the business handling demand; determining a target virtual business scene matched with the business handling demand; determining a target dialogue model based on the business handling demand; and displaying the target virtual business scene and the target digital person on the business handling page, and performing business processing through the target digital person in the target virtual business scene based on the knowledge graph and the target dialogue model. According to the invention, the problems of complex operation process and high input cost of business handling in an offline business hall in the prior art are solved; and an online business system handling mode is relatively poor in user experience and relatively low in operation efficiency.

Description

Technical Field

[0001] The present application relates to the field of metaverse, and more specifically, to a business processing method, device, and electronic device. Background Art

[0002] There are two main methods for handling business transactions. One is through offline business halls, but this method requires users to visit the business location in person, which is a complex process. Furthermore, offline business halls require a significant investment of manpower and material resources, resulting in high operating costs. The other is through online business systems, which primarily use text prompts to handle business transactions. However, this method is relatively tedious and difficult to understand, resulting in a poor user experience and low operational efficiency.

[0003] Currently, no effective solution has been proposed to the problems that the offline business hall business processing method in related technologies has a complex operation process and high investment cost; the online business system processing method has a poor user experience and low operating efficiency. Summary of the Invention

[0004] The main purpose of this application is to provide a business processing method, device and electronic equipment to solve the problems in related technologies that the offline business hall business processing method has a complicated operation process and high investment cost; the online business system processing method has a poor user experience and low operating efficiency.

[0005] To achieve the above-mentioned objectives, according to one aspect of the present application, a business processing method is provided. The method comprises: displaying a business processing page for a target business corresponding to a target account, obtaining the business processing requirements of the target account; constructing a target knowledge graph that matches the business processing requirements; determining a target digital human that matches the business processing requirements; determining a target virtual business scenario that matches the business processing requirements; determining a target dialogue model based on the business processing requirements; displaying the target virtual business scenario and target digital human on the business processing page, and performing business processing through the target digital human in the target virtual business scenario based on the target knowledge graph and target dialogue model.

[0006] Optionally, constructing a target knowledge graph that matches business processing needs includes: determining a static knowledge graph that matches the target business; determining target entities and target entity relationships that match business processing needs from the business knowledge graph, and constructing a dynamic knowledge graph based on the target entities and target entity relationships, wherein the business knowledge graph includes K entities and entity relationships between K entities, wherein the K entities include at least two of the following: account type, document materials, business-related issues, service personnel roles, virtual business scenario information, and account information; obtaining the target knowledge graph based on the static knowledge graph and the dynamic knowledge graph.

[0007] Optionally, determining a target digital person that matches the business processing requirements includes: obtaining account information corresponding to the target account; determining a user profile that matches the target account based on the account information; and determining a target digital person from N digital persons based on the user profile and the business processing requirements, where N is an integer greater than or equal to 2.

[0008] Optionally, determining a target virtual business scenario that matches the business processing requirements includes: determining a target business type requested by the target account based on the business processing requirements; determining a target virtual business scenario that matches the target business type from M virtual business scenarios, wherein the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

[0009] Optionally, based on business processing requirements, a target dialogue model is determined, including: building a target dialogue model based on a target knowledge graph and business processing requirements.

[0010] Optionally, the target virtual business scenario and target digital human are displayed on the business processing page, and based on the target knowledge graph and target dialogue model, business processing is performed through the target digital human in the target virtual business scenario, including: receiving question information input by the target account; based on the question information, querying the target knowledge graph to obtain query results; based on the question information and the query results, using the target dialogue model to obtain reply information; in the process of conducting business processing in the target virtual business scenario, the target virtual business scenario and target digital human are displayed on the business processing page, and the reply information is output in the form of voice and / or text through the target digital human.

[0011] Optionally, based on the question information, the target knowledge graph is queried to obtain query results, including: performing semantic analysis on the question information to obtain semantic analysis results, wherein the semantic analysis results include the intentions and needs of the target account; extracting key information from the semantic analysis results, wherein the key information includes information associated with entities and / or entity relationships included in the target knowledge graph; based on the key information, the target knowledge graph is queried to obtain query results.

[0012] To achieve the above-mentioned objectives, according to another aspect of the present application, a business processing device is provided. The device includes: an acquisition module for displaying a business processing page for a target business corresponding to a target account and acquiring the business processing requirements of the target account; a construction module for constructing a target knowledge graph that matches the business processing requirements; a determination module for determining a target digital human that matches the business processing requirements; a matching module for determining a target virtual business scenario that matches the business processing requirements; a dialogue module for determining a target dialogue model based on the business processing requirements; and a processing module for displaying a target virtual business scenario and a target digital human on the business processing page and, based on the target knowledge graph and the target dialogue model, performing business processing through the target digital human in the target virtual business scenario.

[0013] Optionally, the construction module includes: a first determination submodule, which is used to determine the target entity and target entity relationship that matches the business processing requirements from the business knowledge graph, wherein the business knowledge graph includes K entities and entity relationships between the K entities, wherein the K entities include at least two of the following: business type, account type, business operation steps, document materials, business rules, business-related issues, service personnel roles, virtual business scenario information, and account information; a first construction submodule, which is used to construct the target knowledge graph based on the target entity and the target entity relationship. Optionally, the determination module includes: a first acquisition submodule, which is used to obtain account information corresponding to the target account; a second determination submodule, which is used to determine the user portrait that matches the target account based on the account information; a third determination submodule, which is used to determine the target digital person from N digital people based on the user portrait and business processing requirements, wherein N is an integer greater than or equal to 2.

[0014] Optionally, the matching module includes: a fourth determination submodule, used to determine the target business type requested by the target account based on business processing requirements; a first matching submodule, used to determine a target virtual business scenario that matches the target business type from M virtual business scenarios, wherein the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

[0015] Optionally, the dialogue module includes: a first dialogue sub-module, used to build a target dialogue model based on the target knowledge graph and business processing requirements.

[0016] Optionally, the processing module includes: a first receiving sub-module, used to receive question information input by the target account; a first query sub-module, used to query the target knowledge graph based on the question information to obtain query results; a first reply module, used to obtain reply information based on the question information and the query results using the target dialogue model; a first output sub-module, used to display the target virtual business scene and the target digital person on the business processing page during the process of handling business in the target virtual business scene, and output the reply information in the form of voice and / or text through the target digital person.

[0017] Optionally, the first query sub-module also includes: a first analysis sub-module, used to perform semantic analysis on the question information to obtain a semantic analysis result, wherein the semantic analysis result includes the intention and needs of the target account; a first extraction sub-module, used to extract key information from the semantic analysis result, wherein the key information includes information associated with the entities and / or entity relationships included in the target knowledge graph; a second query sub-module, used to query the target knowledge graph based on the key information to obtain a query result.

[0018] In an embodiment of the present application, the business processing needs of the target account are obtained by displaying the business processing page of the target business corresponding to the target account; a target knowledge graph matching the business processing needs is constructed; a target digital person matching the business processing needs is determined; a target virtual business scenario matching the business processing needs is determined; a target dialogue model is determined based on the business processing needs; the target virtual business scenario and the target digital person are displayed on the business processing page, and based on the target knowledge graph and the target dialogue model, business processing is performed through the target digital person in the target virtual business scenario, thereby achieving the purpose of users efficiently and naturally conducting business in a virtual environment by interacting with intelligent digital people, thereby achieving the technical effect of improving user experience, improving the efficiency and convenience of business processing, and reducing operating costs, thereby solving the technical problems of poor user experience and low efficiency caused by high costs and boring business processing methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0020] Figure 1 A hardware structure block diagram of a computer terminal for implementing a business processing method is shown;

[0021] Figure 2 This is a flow chart of a business handling method according to an embodiment of the present application;

[0022] Figure 3is a schematic diagram of a business processing device provided according to an embodiment of the present application;

[0023] Figure 4 This is a structural block diagram of a business processing electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0025] 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 sequential order. 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 a sequence 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.

[0026] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0027] A Digital Human is a virtual image created based on computer graphics, artificial intelligence, machine learning, and other technologies. It can simulate human appearance, behavior, language, and emotions. Its working principle is similar to that of a non-player character (NPC) and it has the ability to interact with users independently. A knowledge graph (KG) is a structured semantic knowledge base that stores entities and relationships between them in the form of a graph. This graph can contain a large amount of data, such as entities such as people, places, organizations, and events, as well as various relationships between them, such as "belongs to," "is located in," and "created by." Knowledge graphs enable computers to better understand and process natural language because they provide clear links between entities and relationships, helping to improve the accuracy of search engines, the personalization of recommendation systems, and the intelligence of question-answering systems.

[0028] Natural Language Processing (NLP) refers to the use of computer science and artificial intelligence technologies to enable computers to understand, interpret, and generate human languages ​​(such as English and Chinese). This includes language recognition, semantic understanding, machine translation, speech recognition and generation, and other aspects.

[0029] The Dialog Manager (DM) is a key component in NLP and dialogue systems. It is responsible for planning and controlling the flow of dialogues, ensuring their coherence and logic, and determining the strategies for interacting with users at each stage of the dialogue.

[0030] It should 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 the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals 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 portals for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0031] Example 1

[0032] According to an embodiment of the present application, a method embodiment of business processing is also 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.

[0033] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure diagram of a computer terminal (or mobile device) for implementing a business processing method is shown in FIG. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) 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 will 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 than shown, or with Figure 1 Different configurations shown.

[0034] 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 circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] 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 business processing method 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, implementing the above-mentioned business processing method. 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 instances, the memory 104 may further include a memory remotely located 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 combinations thereof.

[0036] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0037] 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).

[0038] In the above operating environment, this application provides an optional business processing method. Figure 2 is a flow chart of a business handling method according to an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0039] Step S200: Display the target account's corresponding target business's business processing page to obtain the target account's business processing requirements;

[0040] Optionally, a customized interface can be provided based on the account characteristics of each user by displaying the business processing page of the target business corresponding to the target account. Ensure that users see information and options related to themselves when entering the business processing page, and improve the friendliness and convenience of the user interface. When obtaining the business processing needs of the target account for the target business, personalized business demand information such as the specific business type to be handled, required materials, and processing procedures can be collected from the user. This step can ensure the pertinence and efficiency of subsequent processing. By directly obtaining user needs, the user's operation steps can be reduced and processing delays caused by unclear information can be avoided. By directly displaying the business processing page related to the user account, the user's time to explore the system can be reduced, allowing the user to quickly enter the business processing state. At the same time, quickly and accurately obtaining user needs can provide users with a seamless and efficient interactive experience.

[0041] Step S202: construct a target knowledge graph that matches the business processing requirements;

[0042] Optionally, in this application, the target knowledge graph can be defined as a structured information network that is used to support the Natural Language Processing (NLP) process, especially in business processing procedures.

[0043] Optionally, by intelligently organizing and integrating business information, it can provide powerful decision-making support for subsequent business processing, optimize the understanding of user needs and the design of dialogue models, and greatly improve the efficiency, accuracy and user experience of business processing.

[0044] In an optional embodiment, a target knowledge graph that matches business processing needs is constructed, including: determining a static knowledge graph that matches the target business; determining target entities and target entity relationships that match the business processing needs from the business knowledge graph, and constructing a dynamic knowledge graph based on the target entities and target entity relationships, wherein the business knowledge graph includes K entities and entity relationships between the K entities, wherein the K entities include at least two of the following: account type, document materials, business-related issues, service personnel roles, virtual business scenario information, and account information; constructing a target knowledge graph based on the static knowledge graph and the dynamic knowledge graph.

[0045] The static knowledge graph is the knowledge graph directly associated with the target business. The information contained in this knowledge graph is determined by the business characteristics of the target business (such as business type, business operation steps, business rules, etc.). The dynamic knowledge graph, on the other hand, is determined based on the user's business processing needs and the contextual information associated with these needs. The target knowledge graph constructed by combining the static and dynamic knowledge graphs not only retains the characteristics of the business itself but can also be dynamically configured based on the user's personalized needs, maximizing user satisfaction while completing tasks and enhancing the user experience. The entities in the business knowledge graph cover multiple key aspects of business processing, including, but not limited to, business type, account type, business operation steps, documents, business rules, business-related questions, service personnel roles, virtual business scenario information, and account information. Entity relationships include, but are not limited to: Business Type & Procedure Step: which steps are included in a certain type of business process; Procedure Step & Document: which documents or materials are required to complete a specific step. Business Type & Rule: Rules corresponding to specific business types; User Type & Staff: Different types of users may be managed by specific staff or consultants; Virtual Hall & Business Type: What types of business does the virtual trading hall mainly handle; User Account Info & Condition: The relationship between user account information and the conditions required to complete a business; User Type & Condition: What conditions must a specific user type meet to conduct certain business operations; Relationships between entities such as "belong to", "associated with", and "subject to": for example, document materials belong to a specific business type, and operating procedures are subject to rules, etc.

[0046] Optionally, in the process of constructing the target knowledge graph, information related to business processing needs can be "knowledge fused" with the business knowledge graph. Based on the business processing needs, entities and entity relationships that match the business processing needs can be screened from the constructed knowledge graph (i.e., the business knowledge graph) to quickly construct a dynamic knowledge graph that matches the business processing needs. Based on the dynamic knowledge graph, combined with the static knowledge graph that matches the target business, targeted queries are conducted on user question information to achieve rapid response and accurate matching to user needs. On this basis, the results of user feedback can better meet the user's question needs, thereby improving the user experience. It should be noted that "knowledge fusion" can handle the integration of multi-source heterogeneous data and solve data consistency and conflict problems. By introducing knowledge fusion methods in the process of constructing dynamic knowledge graphs, the consistency and accuracy of newly added data (such as information related to business processing needs, such as contextual information associated with business processing needs, etc.) with the existing static knowledge graph can be ensured.

[0047] Step S204, determining a target digital person that matches the business processing requirements;

[0048] Alternatively, a digital human is a virtual image created using computer graphics, artificial intelligence, machine learning, and other technologies. It can simulate human appearance, behavior, language, and emotions. Its operating principle is similar to that of a non-player character (NPC) and it has the ability to interact independently with users. In different application scenarios, a digital human can have various functions and characteristics:

[0049] Specifically, when selecting a target Digital Human for a user, it is possible to match the user with a target Digital Human that matches their identity based on the user type and basic user information in the user's needs, so as to better achieve the interaction between the user and the Digital Human, thereby improving the user experience. Specifically, this includes:

[0050] 1) User Profile Analysis: Based on business needs, we analyze the user's profile, including basic information, interests, hobbies, cultural background, etc. This information will help select a digital person that is suitable for the user.

[0051] It should be noted that user portrait is a commonly used concept in Internet technology. It refers to a virtual model that can represent user characteristics, behaviors and preferences by collecting and analyzing user data.

[0052] 2) Select a Digital Human Avatar: Based on the user profile and business needs, select an appropriate Digital Human Avatar, including appearance, clothing, voice, language, and behavioral characteristics. For example, if the user is a child, a cute and friendly Digital Human Avatar might be appropriate; if the user requires professional training, a serious and professional Digital Human Avatar might be appropriate.

[0053] Users can also manually select their favorite digital human from multiple digital humans.

[0054] Optionally, by analyzing the business processing needs of the target account, the most suitable digital person can be determined to serve the user. The selection of digital people is based on the specific entities of the user's needs (such as business type, account type, etc.) and user portraits (including age, gender, interests, cultural background, etc.), so as to provide services that are more in line with the user's background and needs. The matched target digital person can conduct a dialogue based on the user's specific needs, which can avoid the problems of inefficiency and inaccurate information that may arise when general digital people handle specific businesses. The target digital person can quickly generate responses directly related to user needs based on the entities and relationships stored in the target knowledge graph, reduce ineffective communication and waiting time, and improve the speed of business processing. The target digital person can not only provide one or more basic question-and-answer services, business consulting services, etc., but can also be integrated with specific financial business processing scenarios based on user needs and the target knowledge graph.

[0055] Optionally, by matching a target digital human, it is possible to ensure that the digital human understands and masters the business scenario information related to specific needs, thereby guiding the user to complete business operations in the virtual business scenario. Whether it is a simple account inquiry or a complex loan application, professional support can be provided. When determining the target digital human, the complexity of the user's needs and the service capabilities of the digital human can be evaluated to reasonably allocate virtual resources. This means that for complex or high-value business needs, a higher-level digital human will be assigned, while for simple needs, more efficient automated services will be used, thereby optimizing service costs while ensuring service quality. By providing personalized, efficient, and professional services, the target digital human can significantly improve the user experience, enhance user trust and reliance on the service, and help improve user loyalty and brand favorability.

[0056] In an optional embodiment, determining a target digital person that matches the business processing requirements includes: obtaining account information corresponding to the target account; determining a user profile that matches the target account based on the account information; and determining a target digital person from N digital persons based on the user profile and the business processing requirements, where N is an integer greater than or equal to 2.

[0057] As you can understand, account information is user information, and each account corresponds to a single user. By obtaining the target account's account information, we can construct a user profile corresponding to that account, including the user's basic information, historical transaction records, preferences, and so on. Based on this user profile, we select the digital human that best matches the user's characteristics and needs to provide services.

[0058] It should be noted that when determining a target Digital Human, one can choose from N preset Digital Humans (N>1), creating a variety of Digital Human configurations, each customized to meet specific business needs and user profiles. Intelligent matching not only ensures professional and timely service, but also optimizes resource utilization and avoids waste. Furthermore, by basing the selection of target Digital Humans on the user's business needs and user profile, the Digital Human can provide the most relevant information and services during the interaction. This targeted service can significantly reduce the time users spend searching for information or understanding it, improving business efficiency.

[0059] This embodiment achieves personalized, efficient and secure services through intelligent matching of target digital humans, which not only improves the efficiency and accuracy of business processing, but also enhances user satisfaction.

[0060] Step S206, determining a target virtual business scenario that matches the business processing requirements;

[0061] Optionally, the target virtual business scenario is dynamically determined based on the user's business needs and the digital human matching results. For different business types (such as loan applications, credit card services, and financial product consultations), specially designed virtual scenarios can be provided, such as virtual loan counters and credit card service areas. This makes the business process more intuitive and user-friendly, enhancing the user's immersion and experience when handling business.

[0062] Optionally, identifying target virtual business scenarios can help rationally allocate resources, such as server resources and digital human resources, when there are a large number of accessing users, ensuring efficient resource utilization. For example, for high-frequency business needs, multiple parallel virtual scenarios can be established to reduce user wait time; for businesses requiring high-level services, higher-level virtual scenarios and digital humans can be assigned to provide in-depth consultation and services. In the target virtual business scenario, if user feedback on the scenario is detected to be poor, such as users staying in the scenario for too long or performing too many operations, the scenario layout and digital human service strategy can be automatically or manually adjusted to improve the scenario's user-friendliness and the digital human's service efficiency.

[0063] This step can significantly improve business processing efficiency, user experience and service quality through scenario customization, improved interaction efficiency, enhanced professionalism and accuracy of business guidance, reasonable resource allocation, user feedback and service adjustments, and expanded service scope and innovation.

[0064] In an optional embodiment, determining a target virtual business scenario that matches a business processing requirement includes: determining a target business type requested by a target account based on the business processing requirement; and determining a target virtual business scenario that matches the target business type from M virtual business scenarios, wherein the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

[0065] It can be understood that the M virtual business scenarios correspond to different business types, that is, each scenario is specially designed to handle a specific type of business.

[0066] Optionally, by determining the specific service type requested by the target account, users can be quickly directed to the virtual business scenario most relevant to that service type. This precise matching prevents users from wasting time in irrelevant scenarios, improving service efficiency. Furthermore, users can experience a smoother and more natural interaction by operating in a virtual scenario that closely matches their business needs. This scenario not only provides visual immersion but also, through the guidance of the target digital person, makes the business process as intuitive and convenient as interacting with a professional advisor in a real bank, thereby improving user satisfaction. The design of M virtual business scenarios increases system flexibility, facilitating the future addition of more service types or optimization of existing business processes.

[0067] Optionally, different business types can attract different types of users or preferences. By identifying target virtual business scenarios that match the business type, more personalized and customized services can be provided. For example, scenarios targeting corporate customers may focus more on professionalism and efficiency, while scenarios targeting individual customers may focus more on friendliness and interactivity, which helps to build closer user relationships.

[0068] This embodiment can achieve service efficiency, scenario consistency, improved user experience, and optimized resource allocation by accurately matching user business needs and virtual scenarios, while ensuring the flexibility and scalability of system design and the ability to provide personalized services.

[0069] Step S208: Determine the target dialogue model based on the business processing requirements;

[0070] Optionally, the target dialogue model can be customized according to the user's specific business processing needs, that is, the target dialogue model design takes into account the questions that the user may ask, the required guidance information and the process of specific business types; it can also be determined directly based on the target business request of the target account, and the target dialogue model that matches the target business type is determined from multiple dialogue models, where multiple dialogue models correspond to different business types.

[0071] Among them, the dialogue model can include but is not limited to how to understand user input, how to obtain information from the target knowledge graph, how to generate appropriate responses, etc.; the trading hall is a business hall created based on the metaverse, and the business hall can include but is not limited to: publicity area, business processing area, communication inquiry area, three-dimensional shelf display area and activity area, etc.

[0072] The dialogue model is responsible for planning the entire conversation flow and determining the next steps based on the target knowledge graph and user intent. For example, if a user requires more details about a loan, the Dialog Manager (DM) will formulate a series of questions to guide the user in providing the required information, while ensuring the coherence and logic of the conversation. The responses or questions generated by the dialogue model are then presented to the user via voice and / or text via the Digital Human.

[0073] Optionally, determining a target dialogue model helps optimize the conversation process and reduce unnecessary conversational turns. By analyzing business processing needs, the dialogue model can preset a series of structured questions and answers to guide users to quickly and accurately provide the required information. Furthermore, the target dialogue model can pre-plan information retrieval paths, ensuring that the digital human can quickly locate the specific information required by the user, such as loan interest rates and repayment terms, based on the target knowledge graph, thereby accelerating the business processing process. Furthermore, because the target dialogue model is determined based on business processing needs, the digital human can demonstrate specific business expertise when interacting with users. By dynamically constructing and adjusting the dialogue model, the dialogue model can respond to personalized user questions and unexpected situations, such as in-depth inquiries about specific business details or special issues encountered during the processing process, thereby effectively improving the user experience.

[0074] It's important to note that identifying a target conversation model helps reduce wasted system resources. By pre-analyzing business requirements and designing conversation flows, computing resources can be allocated more efficiently, avoiding the potential overconsumption of resources that can occur when processing specific business needs under a general conversation model.

[0075] In an optional embodiment, a target dialogue model is determined based on business processing requirements, including: constructing a target dialogue model based on a target knowledge graph and business processing requirements.

[0076] Optionally, by analyzing business processing requirements and integrating them with the target knowledge graph, the target conversation model can gain a deep understanding of the user's specific business needs. The target knowledge graph contains detailed information about the business process, such as steps, required materials, business rules, and other information, as well as auxiliary information such as user type and conditions. The target conversation model can access and integrate relevant knowledge from the target knowledge graph based on the user's specific needs, such as loan applications or credit card services, to provide precise guidance and services. By analyzing business processing requirements and entity relationships in the target knowledge graph, the target conversation model can generate a series of pre-defined conversation flows and strategies, including but not limited to how to understand user input, how to retrieve information from the target knowledge graph, and how to generate appropriate responses or questions. Built based on business processing requirements and the target knowledge graph, the target conversation model provides a smooth and coherent conversation experience, enabling it to not only quickly respond to user questions but also guide users through the business process, providing necessary information and guidance, thereby accelerating the business process.

[0077] This embodiment can significantly enhance the intelligence level of business processing methods and user experience by deeply understanding user needs, improving the intelligence and pertinence of conversations, optimizing user experience, improving business processing efficiency, flexibly responding to complex scenarios, and promoting personalized services.

[0078] Step S210: Display the target virtual business scenario and target digital human on the business processing page, and perform business processing through the target digital human in the target virtual business scenario based on the target knowledge graph and target dialogue model.

[0079] Alternatively, presenting the target virtual business scenario and target digital human directly on the transaction page can create an immersive virtual environment for users. This virtual environment, such as a virtual loan counter or credit card service center, can make users feel as if they are in a real-life transaction scenario, providing a more intuitive and realistic experience. The target digital human's image and interactive methods can further enhance this experience, allowing users to receive personalized guidance and assistance when handling transactions.

[0080] Optionally, business processing can be performed through a target digital human, combined with a target knowledge graph and a target dialogue model, to achieve intelligent and humanized business interactions. Based on the target knowledge graph, the digital human can provide accurate and professional business guidance, while the target dialogue model ensures the consistency and efficiency of the interaction process. This combination enables the digital human to quickly understand user needs and provide customized services. At the same time, through natural dialogue, users feel comfortable and understood, improving interaction efficiency and user satisfaction. The target virtual business scenario and the target digital human work together to optimize the entire business process.

[0081] This step can significantly improve the efficiency, user experience, and intelligence of business processing methods by creating an immersive user experience, making interactions intelligent and humane, optimizing business processes, efficiently utilizing resources, providing real-time feedback and adjustments, and continuous data-driven optimization.

[0082] In an optional embodiment, the target virtual business scenario and the target digital human are displayed on the business processing page, and based on the target knowledge graph and the target dialogue model, business processing is performed in the target virtual business scenario through the target digital human, including: receiving question information input by the target account; based on the question information, querying the target knowledge graph to obtain the query results; based on the question information and the query results, using the target dialogue model to obtain reply information; in the process of conducting business in the target virtual business scenario, the target virtual business scenario and the target digital human are displayed on the business processing page, and the reply information is output in the form of voice and / or text through the target digital human.

[0083] Optionally, the question information can be in voice and / or text form. Specifically, when a user interacts with the target digital human, the user's voice input must first be converted into text information. This step can be achieved through speech recognition technology, such as deep learning models (such as transformer-based models), which can accurately convert speech to text and maintain high recognition rates even in noisy environments. The text information obtained from speech recognition is input into the natural language understanding module. The natural language understanding (NLU) module parses the text to understand the user's intent and needs. This includes identifying entities (such as business types, user basic information, etc.), sentiment analysis, and intent recognition. NLU can use pre-trained language models, such as the Bidirectional Encoder Representations from Transformers (BERT) and the general text generation model based on the Transformer architecture (Text-to-Text Transfer Transformer (T5), to extract semantic features of the text and map these features to predefined intent categories. Once the user's intent is understood, the target digital human queries the target knowledge graph to obtain information relevant to the user's needs. The target knowledge graph is a structured data storage format that contains information about business processes, required materials, and user types. Through graph queries, digital humans can quickly and accurately locate the specific information a user needs, such as the specific process or required documents for applying for a credit card.

[0084] Optionally, NLP technology can be used to perform semantic analysis on the question information to obtain semantic analysis results, which include the target account's intentions and needs. The semantic analysis results and query results are then input into the target conversation model to generate a response. This approach ensures that the response information is not only accurate but also targeted, effectively answering the user's questions and guiding them through the transaction. Furthermore, the conversation model design considers the coherence and logic of the conversation, making the digital human's responses more natural and reducing user comprehension barriers.

[0085] Optionally, displaying the target virtual business scenario and target digital human on the business processing page can create an intuitive and immersive service environment for users. Users can directly interact with the target digital human through voice or text, asking specific questions about the business. When the target digital human receives the question information from the target account, it will query the target knowledge graph based on the question information to obtain accurate query results. The target knowledge graph may include, but is not limited to, business processes, required materials, knowledge related to user types, and relationships between entities. This enables the digital human to quickly locate the core of the user's problem and extract accurate information from the target knowledge graph, which can reduce information retrieval time and errors and improve service efficiency.

[0086] Throughout the entire transaction process, the target digital human can adjust conversation strategies based on the user's questions and the specifics of the transaction scenario. Matching the target digital human with the target virtual transaction scenario, along with customizing the target conversation model, enables personalized service. The target digital human's accurate and rapid responses, combined with the professionalism and immersiveness of the target virtual transaction scenario, help strengthen user trust in the service.

[0087] This embodiment fully leverages the synergy of the target knowledge graph, target digital human, and target dialogue model by optimizing user interaction experience, improving the accuracy and efficiency of information processing, intelligently generating reply information, enhancing the flexibility and convenience of business handling, realizing personalized services, and promoting user trust and satisfaction. It can significantly enhance the intelligence of business handling methods and the level of user experience.

[0088] In an optional embodiment, based on the question information, the target knowledge graph is queried to obtain the query results, including: performing semantic analysis on the question information to obtain the semantic analysis results, wherein the semantic analysis results include the intentions and needs of the target account; extracting key information from the semantic analysis results, wherein the key information includes information associated with entities and / or entity relationships included in the target knowledge graph; based on the key information, the target knowledge graph is queried to obtain the query results.

[0089] Optionally, key information extracted from the semantic analysis results is information closely related to entities and entity relationships in the target knowledge graph. This key information is used to perform precise queries in the target knowledge graph, avoiding the retrieval of irrelevant information and improving the efficiency and accuracy of information acquisition.

[0090] An optional key information-based query mechanism can quickly locate relevant nodes and edges in the target knowledge graph, retrieving information directly relevant to business processing needs. Query results for the target knowledge graph can include, but are not limited to, detailed information required for the target account, such as specific business processes, operational steps, required materials, and rules related to business processing. This query mechanism is not only fast but also ensures the accuracy and timeliness of information, significantly improving business processing efficiency and reducing user wait times.

[0091] This embodiment can achieve intelligent upgrades in the business processing process and significantly improve user satisfaction and system service efficiency by deeply understanding user intentions and needs, extracting key information for precise matching, efficient target knowledge graph query based on key information, real-time dynamic update of the target knowledge graph, promoting the coherence and logic of intelligent dialogues, enhancing user experience, and continuous data-driven optimization.

[0092] Based on the above embodiment and optional embodiment, the present invention proposes an optional implementation of a business processing method, which includes:

[0093] Step S1: Determine the business handling requirements, including the type of business to be handled, required materials, handling procedures, user type, user basic information, etc.

[0094] Step S2: Analyze the business processing requirements, obtain analysis results, and construct a corresponding target knowledge graph based on the analysis results. The target knowledge graph can be used to support the natural language understanding and reasoning process of the digital human.

[0095] Step S3: According to the business processing requirements, a target virtual scene is determined from multiple virtual business scenes, and a digital person that matches the business processing requirements is determined from multiple digital people. Each digital person can interact with the user through text, voice, etc.

[0096] Step S4: Design a dialogue model and select a trading hall based on the target knowledge graph and business processing requirements. Interact with the user based on the simulated dialogue model to obtain the output results of the dialogue model, and feed the output results back to the target digital human. The target digital human will then lead the user to the corresponding trading hall to process the business.

[0097] In step S5, as the target digital human guides the user through a transaction, voice interaction can occur between the user and the target digital human, guiding the user to provide relevant responses to the transaction, enabling the transaction to be completed as quickly as possible. Throughout this interaction, the target digital human recognizes the user's intent based on their voice and, based on the target knowledge graph, uses a dialogue model to generate corresponding question responses. The target digital human then interacts with the user, providing feedback to the user and guiding them to provide relevant responses. This process also includes real-time dynamic updates to the target knowledge graph.

[0098] In step S6, when the target digital person guides the user to handle business, a real-time consultation service can be set up, allowing the user to ask questions and get help from the staff at any time through the system. Through human intervention, the user's needs can be better met and the processing efficiency can be improved.

[0099] Step S7: As the target digital human guides the user through a service, a rating and user feedback function can also be provided. If the user feedback is unsatisfactory, for example, if the target digital human's answer fails to meet the user's needs, or if the service is not completed after the set interaction time has expired and the user's problem has not been successfully solved, the service will automatically switch to manual service (with the digital human's image remaining unchanged), interacting with the user through manual intervention to better solve the user's problem.

[0100] It should be noted that the business processing method provided in the embodiment of the present application obtains the business processing requirements of the target account by displaying the business processing page of the target business corresponding to the target account; constructs a target knowledge graph that matches the business processing requirements; determines a target digital person that matches the business processing requirements; determines a target virtual business scenario that matches the business processing requirements; determines a target dialogue model based on the business processing requirements; displays the target virtual business scenario and the target digital person on the business processing page, and performs business processing through the target digital person in the target virtual business scenario based on the target knowledge graph and the target dialogue model. This solves the problems of the offline business hall business processing method in the related art, which has a complicated operation process and high investment cost; and the online business system processing method has a poor user experience and low operation efficiency. Thus, the purpose of users efficiently and naturally conducting business in a virtual environment by interacting with the intelligent digital person is achieved, thereby achieving the technical effect of improving user experience, improving the efficiency and convenience of business processing, and reducing operating costs.

[0101] It should 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 the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals 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 portals for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0102] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0103] Example 2

[0104] The embodiment of the present application also provides a business processing device. It should be noted that the business processing device of the embodiment of the present application can be used to execute the business processing method provided in the embodiment of the present application. The business processing device provided in the embodiment of the present application is introduced below.

[0105] According to an embodiment of the present application, a device for implementing the above-mentioned business processing method is also provided. Figure 3 As shown, the device includes: an acquisition module 300, which is used to display the business processing page of the target business corresponding to the target account, and obtain the business processing requirements of the target account; a construction module 302, which is connected to the acquisition module 300, and is used to construct a target knowledge graph that matches the business processing requirements; a determination module 304, which is connected to the construction module 302, and is used to determine the target digital person that matches the business processing requirements; a matching module 306, which is connected to the determination module 304, and is used to determine the target virtual business scenario that matches the business processing requirements; a dialogue module 308, which is connected to the matching module 306, and is used to determine the target dialogue model based on the business processing requirements; a processing module 310, which is connected to the dialogue module 308, and is used to display the target virtual business scenario and the target digital person on the business processing page, and based on the target knowledge graph and the target dialogue model, perform business processing through the target digital person in the target virtual business scenario.

[0106] The business processing device provided by the embodiment of the present application is configured with an acquisition module 300 for displaying the business processing page of the target business corresponding to the target account, and obtaining the business processing requirements of the target account; a construction module 302, connected to the acquisition module 300, for constructing a target knowledge graph that matches the business processing requirements; a determination module 304, connected to the construction module 302, for determining a target digital person that matches the business processing requirements; a matching module 306, connected to the determination module 304, for determining a target virtual business scenario that matches the business processing requirements; a dialogue module 308, connected to the matching module 306, for determining a target dialogue model based on the business processing requirements; a processing module 310, connected to the dialogue module 308, for displaying the target virtual business scenario and the target digital person on the business processing page, and based on the target knowledge graph and the target dialogue model, performing business processing through the target digital person in the target virtual business scenario, thereby solving the problems in the related art of the offline business hall business processing method having a complicated operation process and high investment cost; and the online business system processing method having a poor user experience and low operating efficiency. This achieves the goal of enabling users to conduct business efficiently and naturally by interacting with intelligent digital humans in a virtual environment, thereby realizing the technical effect D of improving user experience, increasing the efficiency and convenience of business processing, and reducing operating costs.

[0107] Optionally, in the business processing device provided in the embodiment of the present application, the construction module includes: a first determination sub-module, used to determine a static knowledge graph that matches the target business, and determine the target entity and target entity relationship that match the business processing requirements from the business knowledge graph, wherein the business knowledge graph includes K entities and entity relationships between K entities, wherein the K entities include at least two of the following: account type, document materials, business-related issues, service personnel roles, virtual business scenario information, account information; a first construction sub-module, used to construct a dynamic knowledge graph based on the target entity and the target entity relationship; and construct a target knowledge graph based on the static knowledge graph and the dynamic knowledge graph.

[0108] Optionally, in the business processing device provided in the embodiment of the present application, the determination module includes: a first acquisition sub-module, used to obtain account information corresponding to the target account; a second determination sub-module, used to determine the user portrait matching the target account based on the account information; a third determination sub-module, used to determine the target digital person from N digital persons based on the user portrait and business processing requirements, where N is an integer greater than or equal to 2.

[0109] Optionally, in the business processing device provided in the embodiment of the present application, the matching module includes: a fourth determination sub-module, used to determine the target business type requested by the target account based on the business processing requirements; a first matching sub-module, used to determine the target virtual business scenario that matches the target business type from M virtual business scenarios, wherein the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

[0110] Optionally, in the business processing device provided in the embodiment of the present application, the dialogue module includes: a first dialogue sub-module, which is used to build a target dialogue model based on the target knowledge graph and business processing requirements.

[0111] Optionally, in the business processing device provided in the embodiment of the present application, the processing module includes: a first receiving sub-module, used to receive question information input by the target account; a first query sub-module, used to query the target knowledge graph based on the question information to obtain query results; a first reply module, used to obtain reply information based on the question information and the query results using the target dialogue model; a first output sub-module, used to display the target virtual business scene and the target digital person on the business processing page during the process of performing business processing in the target virtual business scene, and output the reply information in the form of voice and / or text through the target digital person.

[0112] Optionally, in the business processing device provided in the embodiment of the present application, the first query sub-module also includes: a first analysis sub-module, used to perform semantic analysis on the question information to obtain a semantic analysis result, wherein the semantic analysis result includes the intention and needs of the target account; a first extraction sub-module, used to extract key information from the semantic analysis result, wherein the key information includes information associated with the entities and / or entity relationships included in the target knowledge graph; a second query sub-module, used to query the target knowledge graph based on the key information to obtain a query result.

[0113] It should be noted that the acquisition module 300, construction module 302, determination module 304, matching module 306, dialogue module 308, and processing module 310 correspond to steps S200 to S210 in Example 1. The examples and application scenarios implemented by the five modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0114] Example 3

[0115] An embodiment of the present application may provide an electronic device, Figure 4 This 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) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0116] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments 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, implementing the above-mentioned method. 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 a combination thereof.

[0117] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: display the business processing page of the target business corresponding to the target account, and obtain the business processing requirements of the target account; construct a target knowledge graph that matches the business processing requirements; determine the target digital person that matches the business processing requirements; determine the target virtual business scenario that matches the business processing requirements; determine the target dialogue model based on the business processing requirements; display the target virtual business scenario and target digital person on the business processing page, and based on the target knowledge graph and target dialogue model, perform business processing through the target digital person in the target virtual business scenario.

[0118] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine a static knowledge graph that matches the target business; determine the target entity and target entity relationship that match the business processing requirements from the business knowledge graph, wherein the business knowledge graph includes K entities and entity relationships between K entities, wherein the K entities include at least two of the following: account type, document material business-related issues, service personnel roles, virtual business scenario information, account information; construct a dynamic knowledge graph based on the target entity and target entity relationship; construct a target knowledge graph based on the static knowledge graph and the dynamic knowledge graph.

[0119] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: obtain the account information corresponding to the target account; based on the account information, determine the user portrait that matches the target account; based on the user portrait and business processing requirements, determine the target digital person from N digital people, where N is an integer greater than or equal to 2.

[0120] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: determine the target business type requested by the target account based on the business processing requirements; determine the target virtual business scenario that matches the target business type from M virtual business scenarios, where the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

[0121] The processor can call the information and applications stored in the memory through the transmission device to perform the following steps: build a target dialogue model based on the target knowledge graph and business processing requirements.

[0122] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receive the question information input by the target account; based on the question information, query the target knowledge graph to obtain the query results; based on the question information and the query results, use the target dialogue model to obtain reply information; in the process of handling business in the target virtual business scenario, display the target virtual business scenario and the target digital person on the business handling page, and output the reply information in the form of voice and / or text through the target digital person.

[0123] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: perform semantic analysis on the question information to obtain a semantic analysis result, wherein the semantic analysis result includes the intention and needs of the target account; extract key information from the semantic analysis result, wherein the key information includes information associated with the entities and / or entity relationships included in the target knowledge graph; based on the key information, query the target knowledge graph to obtain a query result.

[0124] By adopting the embodiment of the present application, a business processing solution is provided. By displaying the business processing page of the target business corresponding to the target account, the business processing requirements of the target account are obtained; a target knowledge graph matching the business processing requirements is constructed; a target digital person matching the business processing requirements is determined; a target virtual business scenario matching the business processing requirements is determined; a target dialogue model is determined based on the business processing requirements; the target virtual business scenario and the target digital person are displayed on the business processing page, and based on the target knowledge graph and the target dialogue model, business processing is performed through the target digital person in the target virtual business scenario, thereby achieving the purpose of users efficiently and naturally conducting business in a virtual environment by interacting with the intelligent digital person, thereby achieving the technical effect of improving user experience, improving the efficiency and convenience of business processing, and reducing operating costs, thereby solving the technical problems of poor user experience and low efficiency caused by high costs and boring business processing methods.

[0125] 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 (MID), a PAD, or other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 4 Different configurations shown.

[0126] A person skilled in the art will 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, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0127] Example 4

[0128] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the service processing method provided in the first embodiment.

[0129] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0130] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the business handling method.

[0131] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0132] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0133] 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 is only a logical function division. In actual implementation, there may be other division methods, such as 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.

[0134] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0135] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0136] 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 is essentially 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 for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0137] 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 business handling method, characterized in that: include: Display the business processing page of the target business corresponding to the target account, and obtain the business processing requirements of the target account; Construct a target knowledge graph that matches the business processing requirements; Determine the target digital person that matches the business processing needs; Determine a target virtual business scenario that matches the business processing requirements; Determine the target dialogue model based on the business processing requirements; The target virtual business scenario and the target digital human are displayed on the business processing page, and based on the target knowledge graph and the target dialogue model, business processing is performed through the target digital human in the target virtual business scenario.

2. The method according to claim 1, characterized in that The construction of a target knowledge graph that matches the business processing requirements includes: Determine a static knowledge graph that matches the target business; Determining target entities and target entity relationships that match the business processing requirements from a business knowledge graph, and constructing a dynamic knowledge graph based on the target entities and target entity relationships, wherein the business knowledge graph includes K entities and entity relationships between the K entities, wherein the K entities include at least two of the following: account type, document material, business-related question, service personnel role, virtual business scenario information, and account information; Based on the static knowledge graph and the dynamic knowledge graph, the target knowledge graph is constructed.

3. The method according to claim 1, characterized in that Determining a target digital person that matches the business processing requirement includes: Obtaining account information corresponding to the target account; Determining a user profile that matches the target account based on the account information; Based on the user portrait and the business processing requirements, the target digital human is determined from N digital humans, where N is an integer greater than or equal to 2.

4. The method according to claim 1, wherein The determining of a target virtual business scenario that matches the business processing requirement includes: Determining the target business type requested by the target account based on the business processing requirements; The target virtual business scenario that matches the target business type is determined from M virtual business scenarios, wherein the M virtual business scenarios correspond to different business types, and M is an integer greater than or equal to 2.

5. The method according to claim 1, characterized in that Determining a target dialogue model based on the business processing requirements includes: Based on the target knowledge graph and the business processing requirements, the target dialogue model is constructed.

6. The method according to claim 1, characterized in that The target virtual business scenario and the target digital human are displayed on the business processing page, and business processing is performed by the target digital human in the target virtual business scenario based on the target knowledge graph and the target dialogue model, including: Receiving question information input by the target account; Based on the question information, query the target knowledge graph to obtain query results; Based on the question information and the query result, using the target dialogue model to obtain reply information; During the process of handling business in the target virtual business scenario, the target virtual business scenario and the target digital person are displayed on the business handling page, and the reply information is output in the form of voice and / or text through the target digital person.

7. The method according to claim 6, characterized in that The querying of the target knowledge graph based on the question information to obtain query results includes: Performing semantic analysis on the question information to obtain a semantic analysis result, wherein the semantic analysis result includes the intention and needs of the target account; Extracting key information from the semantic analysis result, wherein the key information includes information associated with entities and / or entity relationships included in the target knowledge graph; Based on the key information, the target knowledge graph is queried to obtain the query result.

8. The method according to claim 6, characterized in that After constructing the target knowledge graph that matches the business processing requirements, the method further includes: When a change in the business processing requirement is detected, the target knowledge graph is updated based on the requirement change information of the business processing requirement.

9. A business processing device, characterized in that: include: The acquisition module is used to display the business processing page of the target business corresponding to the target account and obtain the business processing requirements of the target account; Construction module, used to build target knowledge graphs that match business processing requirements; The determination module is used to determine the target digital person that matches the business processing needs; A matching module is used to determine the target virtual business scenario that matches the business processing requirements; The dialogue module is used to determine the target dialogue model based on business processing requirements; The processing module is used to display the target virtual business scenario and target digital human on the business processing page, and perform business processing through the target digital human in the target virtual business scenario based on the target knowledge graph and target dialogue model.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 8 when running.

Images