Intelligent consultation interaction method and apparatus, device, and storage medium

Abstract

An intelligent consultation interaction method and apparatus, a device, and a storage medium. The method comprises: acquiring consultation interaction information inputted by an information consultation object and associated with automobile finance (S101); on the basis of the consultation interaction information and an interaction response decision tree pre-configured for an intelligent interaction robot, determining whether AI response assistance needs to be executed (S102); and when the AI response assistance needs to be executed, determining a target response result on the basis of complete interaction information and the AI response assistance in the current consultation interaction process (S103).

Description

Intelligent consultation interaction methods, devices, equipment and storage media

[0001] This application claims priority to Chinese Patent Application No. 202510122669.6, filed with the Chinese Patent Office on January 26, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent interaction technology, such as an intelligent consultation interaction method, device, equipment, and storage medium. Background Technology

[0003] With the rapid popularization and development of artificial intelligence (AI) technology, numerous intelligent interactive robots have emerged in the market, playing an increasingly important role in various industries. In the automotive finance sector, these robots are used to handle a range of tasks, including customer inquiries, loan approvals, and risk assessments. However, the workflow control methods employed by different types of robots have a significant impact on user experience and service quality.

[0004] In the automotive finance sector, some companies use simple decision tree workflows to execute interactions, while others use AI workflows to handle responses. Simple decision tree workflows, based on pre-defined dialogue flows, struggle to respond to personalized user needs or handle complex situations. AI workflows, lacking interactive capabilities, fail to achieve the desired results and provide a poor user experience when both interactive needs and personalized or complex responses are required. Summary of the Invention

[0005] This application provides an intelligent consultation interaction method, device, equipment, and storage medium to achieve responses to high-quality and highly complex content, effectively improving the ability and quality of dialogue interaction.

[0006] This application provides an intelligent consultation interaction method applied to an intelligent interactive robot. The method includes:

[0007] Obtain consultation interaction information related to auto finance input from the information consultation recipient;

[0008] Based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot, determine whether AI response assistance is needed;

[0009] When the AI-assisted response is required, the target response result is determined based on the complete interaction information during this consultation process and the AI-assisted response.

[0010] This application provides an intelligent consultation and interaction device for use with an intelligent interactive robot. The device includes:

[0011] The interactive information acquisition module is set up to acquire interactive consultation information related to auto finance input by the information consultation recipient;

[0012] The interactive response decision module is configured to determine whether AI response assistance needs to be executed based on the consultation interaction information and the interactive response decision tree pre-configured for the intelligent interactive robot.

[0013] The response result determination module is configured to determine the target response result based on the complete interaction information during the consultation process and the AI ​​response assistance when the AI ​​response assistance needs to be executed.

[0014] This application provides an electronic device, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the intelligent consultation interaction method described in any embodiment of this application.

[0018] This application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the intelligent consultation and interaction method described in any embodiment of this application. Attached Figure Description

[0019] Figure 1 is a flowchart of an intelligent consultation interaction method provided according to Embodiment 1 of this application;

[0020] Figure 2 is a flowchart of an intelligent consultation interaction method provided according to Embodiment 2 of this application;

[0021] Figure 3 is a structural diagram of an intelligent consultation and interaction device provided according to Embodiment 3 of this application;

[0022] Figure 4 is a schematic diagram of the structure of an electronic device that implements the intelligent consultation interaction method of the present application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort should fall within the scope of protection of this application.

[0024] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] Figure 1 is a flowchart of an intelligent consultation interaction method provided in Embodiment 1 of this application. This embodiment is applicable to situations where a user consults an intelligent interactive robot about issues related to auto finance. This method can be executed by an intelligent consultation interaction device, which can be implemented in hardware and / or software and can be configured in an electronic device. As shown in Figure 1, the method includes:

[0027] S101. Obtain the consultation interaction information related to auto finance input by the information consultation object.

[0028] The recipients of information consultations can be users seeking advice related to the automotive finance sector. The consultation methods can include voice and / or text-based consultations. The consultation interaction information refers to communication related to the automotive finance sector raised by the recipients. For example, the consultation interaction information may include consultation questions, loan approval questions, and risk assessment questions.

[0029] It is worth noting that intelligent interactive robots can exist as physical mobile robots in stores, or as servers in telephone or online consultations. The configuration of intelligent interactive robots can be tailored to specific needs.

[0030] The intelligent interactive robot receives inquiries related to auto finance from users via text or voice input.

[0031] S102. Based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot, determine whether AI response assistance needs to be implemented.

[0032] The interactive response decision tree stores pre-defined response processes, preset consultation questions, and preset response results corresponding to the preset consultation questions. AI-assisted response can handle other consultation questions besides the preset ones.

[0033] For example, an interactive response decision tree includes at least response branch nodes and response result nodes. Response branch nodes can refer to branches that correspond to different consultation question conditions. Response result nodes can refer to result nodes that match the consultation question.

[0034] When the consultation interaction information entered by the person seeking information reaches the decision tree node, the system determines whether an AI response assistance process needs to be run based on the node's configuration and process.

[0035] For example, determining whether AI-assisted response needs to be executed based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot includes:

[0036] The consultation interaction information is paired with the interaction response decision tree. If a matching response exists in the interaction response decision tree, then the AI ​​response assistance is not required. If no matching response exists in the interaction response decision tree, then the AI ​​response assistance is required.

[0037] The consultation interaction information can be paired with the interaction response decision tree to determine whether a matching response exists in the decision tree. If a match exists, it is determined that the AI-assisted response is not required. If no match exists, it is determined that the AI-assisted response is required.

[0038] For example, determining whether AI-assisted response needs to be executed based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot includes:

[0039] The consultation interaction information is parsed and identified through the response nodes in the interaction response decision tree; if the response node identifies the consultation intent of the consultation interaction information, it is determined that the AI ​​response assistance does not need to be executed; if the response node does not identify the consultation intent of the consultation interaction information, it is determined that the AI ​​response assistance needs to be executed.

[0040] The interactive response decision tree includes branching decisions and response nodes. Branching decisions exist at multiple process nodes. The role of the response node is to determine the intent based on user input, determine the next step based on the user's intent, invoke AI-assisted response, or end the session.

[0041] By analyzing the consultation interaction information through the response nodes in the interactive response decision tree, AI response assistance is unnecessary when the consultation intent expressed by the interaction information can be determined. However, if the consultation intent cannot be determined, AI response assistance is required.

[0042] It is important to note that when AI-assisted response is required, it is necessary to determine whether the current response node in the interactive response decision tree has AI-assisted response enabled. If the current response node has AI-assisted response enabled, the AI-assisted response workflow can be invoked. If the current response node has not enabled AI-assisted response, the decision tree process continues.

[0043] S103. When it is necessary to execute the AI ​​response assistance, determine the target response result based on the complete interaction information and AI response assistance during this consultation interaction process.

[0044] The AI-assisted response workflow includes at least the Large Language Model (LLM), intent recognition, web search, and knowledge base recognition.

[0045] If the AI-assisted response is required, the process proceeds according to the AI-assisted response workflow, and the target response result is determined based on the AI-assisted response. If the AI-assisted response is not required, the conversation continues according to the branching conditions of the decision tree, or the target response result is generated based on the response result information corresponding to the consultation interaction information in the interaction response decision tree.

[0046] For example, after determining the target response result, the method further includes:

[0047] Continue to receive consultation interaction information input by the information consultation object until the session ends or the preset termination condition is met.

[0048] After the AI ​​workflow is completed, the obtained response results are fed back to the decision tree node. The decision tree node processes the response results (such as format adjustment, content filtering, etc.) to better present them to the user. It continues to receive consultation interaction information input by the information consultation object and continues to interact with the user in a conversation based on the branch judgment conditions of the decision tree until the conversation ends or a preset termination condition is met.

[0049] For example, determining the target response result based on the complete interaction information and AI response assistance during the consultation process includes: performing natural language understanding on the complete interaction information to generate interaction semantic information; determining the current interaction intent of the information consultation object based on the interaction semantic information; and determining the target response result based on the current interaction intent and the AI ​​response tool.

[0050] Complete interactive information refers to all the interaction information between the person seeking information and the intelligent interactive robot during this interaction. AI response tools may include, but are not limited to, web search tools, knowledge base retrieval tools, and AI large-scale model tools.

[0051] The AI ​​workflow integrates the current and historical input sessions from the current interaction with the user and inputs them into the AI ​​workflow. It then requests LLM (Local Language Management) for natural language understanding to generate semantic information about the interaction. Based on this semantic information, the workflow analyzes the user's intent to provide a more accurate response. It can search the internet for information related to the complete interaction to enrich the response, or it can consult a pre-defined knowledge base to provide a more accurate answer. In short, the AI ​​workflow executes these steps through a customized configuration to obtain the response result.

[0052] The technical solution of this application embodiment obtains consultation interaction information related to auto finance input from the user seeking information. Based on the consultation interaction information and an interaction response decision tree pre-configured for an intelligent interactive robot, it determines whether AI response assistance is needed. If AI response assistance is needed, the target response result is determined based on the complete interaction information and AI response assistance during the consultation interaction process. This application solves problems such as poor user interaction experience, low problem-solving efficiency, insufficient decision-making accuracy, high operating costs, and volatile market demands in the auto finance field. By combining decision trees and AI workflows, it provides a new solution for robot interaction process control in the auto finance field, enabling robots to be more intelligent and flexible in processing user input, significantly improving problem-solving efficiency, and reducing the need for human customer service, thereby lowering operating costs.

[0053] Example 2

[0054] Figure 2 is a flowchart of an intelligent consultation interaction method provided in Embodiment 2 of this application. This embodiment is an optional implementation of the above-mentioned multiple embodiments. As shown in Figure 2, the method includes:

[0055] (1) Initialize the decision tree flowchart and AI flowchart of the intelligent interactive robot, and implant the AI ​​workflow to be executed into the corresponding node of the decision tree flowchart;

[0056] (2) Determine whether to run AI response assistance at the decision tree node;

[0057] (3) Integrate the current input and conversation history into complete interaction information and input it into the AI ​​workflow;

[0058] (4) The AI ​​workflow works based on complete interactive information, including steps such as LLM, intent recognition, web search, and knowledge base retrieval (through configuration of custom processes);

[0059] (5) Once the AI ​​workflow is completed, the response result is obtained and fed back to the decision tree node;

[0060] (6) The decision tree node returns the reply content to the information inquiry user and continues the conversation interaction based on the branch judgment conditions.

[0061] Example 3

[0062] Figure 3 is a schematic diagram of the structure of an intelligent consultation interaction device provided in Embodiment 3 of this application. As shown in Figure 3, the device includes:

[0063] The interactive information acquisition module 301 is configured to acquire interactive consultation information related to auto finance input by the information consultation object;

[0064] The interactive response decision module 302 is configured to determine whether AI response assistance needs to be executed based on the consultation interaction information and the interactive response decision tree pre-configured for the intelligent interactive robot.

[0065] The response result determination module 303 is configured to determine the target response result based on the complete interaction information and AI response assistance during the current consultation interaction process when the AI ​​response assistance needs to be executed.

[0066] Optionally, the interactive response decision module 302 is configured as follows:

[0067] The consultation interaction information is paired with the interaction response decision tree. If it is determined that there is a response result in the interaction response decision tree that matches the consultation interaction information, then it is determined that the AI ​​response assistance does not need to be executed.

[0068] If there is no matching response in the interactive response decision tree that matches the consultation interaction information, then it is determined that the AI ​​response assistance needs to be executed.

[0069] Optionally, the response result determination module 303 is further configured as follows:

[0070] Without requiring the execution of the AI ​​response assistance, a target response result is generated based on the response result information corresponding to the consultation interaction information in the interaction response decision tree.

[0071] Optionally, the interactive response decision tree includes at least a response branch node and a response result node.

[0072] Optionally, the response result determination module 303 is configured as follows:

[0073] The complete interaction information is subjected to natural language understanding to generate interaction semantic information;

[0074] Based on the interactive semantic information, determine the current interactive intent of the information consultation object;

[0075] Based on the current interaction intent and the AI ​​response tool, determine the target response result.

[0076] Optionally, the response result determination module 303 is further configured to: after determining the target response result, continue to receive consultation interaction information input by the information consultation object until the session ends or a preset termination condition is met.

[0077] Optionally, the AI-assisted response workflow includes at least request LLM, intent recognition, web search, and knowledge base recognition.

[0078] The technical solution of this application embodiment obtains consultation interaction information related to auto finance input from the user seeking information. Based on the consultation interaction information and an interaction response decision tree pre-configured for an intelligent interactive robot, it determines whether AI response assistance is needed. If AI response assistance is needed, the target response result is determined based on the complete interaction information and AI response assistance during the consultation interaction process. This application solves problems such as poor user interaction experience, low problem-solving efficiency, insufficient decision-making accuracy, high operating costs, and volatile market demands in the auto finance field. By combining decision trees and AI workflows, it provides a new solution for robot interaction process control in the auto finance field, enabling robots to be more intelligent and flexible in processing user input, significantly improving problem-solving efficiency, and reducing the need for human customer service, thereby lowering operating costs.

[0079] The intelligent consultation and interaction device provided in this application embodiment can execute the intelligent consultation and interaction method provided in any embodiment of this application, and has the corresponding functional modules for executing the method.

[0080] Example 4

[0081] Figure 4 illustrates a schematic diagram of an electronic device 10 that can be used to implement embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0082] As shown in Figure 4, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0083] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0084] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs several of the methods and processes described above, such as intelligent consultation interaction methods.

[0085] In some embodiments, the intelligent consultation interaction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the intelligent consultation interaction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the intelligent consultation interaction method by any other suitable means (e.g., by means of firmware).

[0086] The various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0088] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. Examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0090] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0091] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0092] It should be understood that the various processes shown above can be used to rearrange, add, or delete steps. For example, the multiple steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

Claims

1. An intelligent consultation interaction method, applied to an intelligent interactive robot, comprising: Obtain consultation interaction information related to auto finance input from the information consultation recipient; Based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot, determine whether artificial intelligence (AI) response assistance is needed; When the AI-assisted response is required, the target response result is determined based on the complete interaction information during this consultation process and the AI-assisted response.

2. The method according to claim 1, wherein, The step of determining whether AI-assisted response is needed based on the consultation interaction information and the interaction response decision tree pre-configured for the intelligent interactive robot includes: The consultation interaction information is parsed and identified using the response nodes in the interaction response decision tree; If the response node recognizes the consultation intent in the consultation interaction information, it is determined that the AI ​​response assistance does not need to be executed. If the response node does not recognize the consultation intent in the consultation interaction information, then it is determined that the AI ​​response assistance needs to be executed.

3. The method according to claim 1, further comprising: Without requiring the execution of the AI ​​response assistance, a target response result is generated based on the response result information corresponding to the consultation interaction information in the interaction response decision tree.

4. The method according to claim 1, wherein, When the AI-assisted response is required, the target response result is determined based on the complete interaction information and AI-assisted response during this consultation process, including: When the AI ​​response assistance needs to be executed, determine whether the current response node in the interaction response decision tree has enabled the AI ​​response assistance; When the AI ​​response assistance is enabled at the current response node, the target response result is determined based on the complete interaction information and AI response assistance during this consultation process.

5. The method according to claim 1, characterized in that, The determination of the target response result based on the complete interaction information and AI-assisted response during this consultation process includes: The complete interaction information is subjected to natural language understanding to generate interaction semantic information; Based on the interactive semantic information, determine the current interactive intent of the information consultation object; Based on the current interaction intent and the AI ​​response tool, determine the target response result.

6. The method according to claim 1, further comprising, after determining the target response result: Continue to receive consultation interaction information input by the information consultation object until the session ends or the preset termination condition is met.

7. The method according to claim 5, wherein, The AI ​​response assistance workflow includes at least the request large language model (LLM), intent recognition, web search, and knowledge base recognition.

8. An intelligent consultation and interaction device, applied to an intelligent interactive robot, comprising: The interactive information acquisition module is set up to acquire interactive consultation information related to auto finance input by the information consultation recipient; The interactive response decision module is configured to determine whether artificial intelligence (AI) response assistance is needed based on the consultation interaction information and the interactive response decision tree pre-configured for the intelligent interactive robot. The response result determination module is configured to determine the target response result based on the complete interaction information during the consultation process and the AI ​​response assistance when the AI ​​response assistance needs to be executed.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the intelligent consultation interaction method according to any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, said computer instructions being configured to cause a processor to execute the intelligent consultation interaction method according to any one of claims 1-7.

Images