Quick dialogue type insurance business process configuration method and system

Abstract

The invention discloses a quick dialogue type insurance business process configuration method and system, which can perform configuration management on a traditional insurance business system through an AI model and dialogue type process application, namely, through process intention configuration, insurance business process node page configuration and business interface configuration, the process intention of the traditional insurance business system can be quickly and accurately configured. The AI model capability is quickly called to carry out AI enabling on the insurance application, so that an insurance underwriting claim settlement dialogue type new service based on a large model is quickly created, and AI enabling transformation of a traditional insurance service is realized; therefore, the invention provides the insurance service configuration method which is accurate in intention recognition, reproducible in process configuration and capable of quickly online application, and the dialogue type insurance service processing system can be generated only by performing simple configuration in the process configuration page by developers, so that the processing efficiency is improved. According to the invention, the development efficiency of the insurance service application is improved, the service application can be quickly online, and the cost and personnel ability requirements are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent configuration of insurance business, and particularly relates to a method and system for configuring an insurance business process in a fast conversational manner. Background Art

[0002] Currently, traditional web applications in the insurance industry require professional front-end and back-end development. They connect to the core underwriting and claims settlement system of the back-end through code to implement the underwriting and claims settlement business processes of the front-end. Among them, the development time of the aforementioned insurance business applications is long, and they cannot be quickly iterated and launched, making it difficult to adapt to the ever-changing market demands. At the same time, with the booming development of AI technology, AI technology has gradually been applied to the empowerment of traditional applications. However, it also requires professional AI developers and traditional developers to combine for application development or transformation. This poses problems such as high technical requirements for developers, large docking difficulties, and it is difficult to quickly carry out AI transformation or new construction, and the development and transformation costs are also high. Therefore, based on the above deficiencies, how to provide a fast conversational insurance business process configuration method with high efficiency, low cost, and low requirements for personnel capabilities has become an urgent problem to be solved. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for configuring an insurance business process in a fast conversational manner to solve the problems of long development time, high cost, inability to be quickly iterated and launched, and high requirements for personnel existing in the prior art.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions:

[0005] In the first aspect, a method for configuring an insurance business process in a fast conversational manner is provided, including:

[0006] Obtain at least one insurance business prompt word, and perform insurance intention configuration processing based on the at least one insurance business prompt word to determine the insurance business corresponding to the at least one insurance business prompt word;

[0007] Generate a process configuration page corresponding to the insurance business according to the insurance business, wherein the process configuration page includes process configuration boxes for each process node corresponding to the insurance business;

[0008] Perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page in sequence. After the business interface configuration processing, obtain the insurance business processing page corresponding to the insurance business, and generate the insurance business processing system corresponding to the insurance business based on the insurance business processing page. Any business interface is used to call an insurance business processing thread, an insurance business model, or an insurance knowledge base, and the insurance business model includes a natural language model, an OCR model, an underwriting and claims document image recognition and classification model, a vehicle recognition model, a picture correction model, a speech-to-text conversion model, and an intent recognition model.

[0009] Based on the above-disclosed content, the present invention first performs insurance intent configuration processing according to the insurance business prompt words, so as to map and associate the insurance business prompt words with the insurance business to determine the insurance business corresponding to the insurance business prompt words; then, according to the insurance business, determine the process configuration page including the process configuration boxes corresponding to each process node in the insurance business; finally, perform process node configuration and business interface configuration processing on this process configuration page, and the page configuration and interface configuration of different process nodes of the insurance business can be realized, so as to generate a business processing page that conforms to the insurance business process, and enable each business interface in the page to call the backend insurance business processing thread, the insurance knowledge base, or each insurance business model (such as basic dialogue, intent recognition, image recognition, speech-to-text conversion, etc. models); in this way, the process configuration of the conversational insurance business can be completed, and then the conversational insurance business processing can be realized.

[0010] Through the above design, the present invention can perform configuration management on the traditional insurance business system through AI models and conversational process applications, that is, through process intent configuration, insurance business process node page configuration, and business interface configuration, quickly call the AI model capabilities to empower the insurance application with AI, so as to quickly create a new conversational business for insurance underwriting and claims based on the large model, so as to realize the AI empowerment transformation of the traditional insurance business; thus, the present invention provides an insurance business configuration method with accurate intent recognition, replicable process configuration, and rapid application launch. It only requires developers to perform simple configuration in the process configuration page to generate a conversational insurance business processing system. Therefore, the present invention improves the development efficiency of insurance business applications, can realize the rapid launch of business applications, and reduces costs and personnel capacity requirements, so it is very suitable for large-scale application and promotion.

[0011] In a possible design, performing process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page includes:

[0012] Visualize the process configuration page to generate an initial insurance business processing page in response to human-computer interaction operations for process configuration in each process configuration box on the process configuration page by the development side;

[0013] In response to human-computer interaction operations for interface configuration in each process configuration box on the initial insurance business processing page by the development side, configure business interfaces for each process configuration box on the initial insurance business processing page, so as to obtain the insurance business processing page after configuring the business interfaces.

[0014] In a possible design, the method further includes:

[0015] Obtain user usage feedback information;

[0016] Based on the user usage feedback information, perform process configuration optimization processing on the insurance business to obtain an optimized insurance business processing page after the process configuration optimization processing.

[0017] In a possible design, based on the user usage feedback information, performing process configuration optimization processing on the insurance business includes:

[0018] According to the user usage feedback information, update the insurance business prompt words corresponding to the insurance business to obtain updated insurance business prompt words;

[0019] According to the user usage feedback information, perform optimization processing on the insurance business model corresponding to the target configuration box on the process configuration page to obtain an optimized insurance business model, where the target configuration box is the process configuration box corresponding to the specified business interface on the process configuration page, and the specified business interface is used to call the insurance business large model;

[0020] Update the process configuration page corresponding to the insurance business to obtain an updated process configuration page;

[0021] Perform update processing on the business interfaces in the updated process configuration page to obtain an optimized insurance business processing page after the update processing. After the business interface update processing, the specified business interface in the updated process configuration page is used to call the optimized insurance business model, and when the optimized insurance business processing page enters the insurance processing thread, the updated insurance business prompt words are used for insurance business conversations.

[0022] In a possible design, based on the at least one insurance business prompt word, perform insurance intention configuration processing to obtain the insurance business corresponding to the at least one insurance business prompt word, including:

[0023] Using a machine learning model, perform intent recognition on the at least one insurance business prompt word to identify the insurance business corresponding to the at least one insurance business prompt word.

[0024] In a possible design, based on the insurance business processing page, generate an insurance business processing system corresponding to the insurance business, including:

[0025] Perform a publishing process on the insurance business processing page, so as to generate the insurance business processing system after the publishing process.

[0026] In a possible design, the insurance knowledge base includes: an underwriting knowledge base, a claims knowledge base, a company knowledge base, an intent knowledge base, and an image knowledge base.

[0027] In a second aspect, there is provided a fast conversational insurance business process configuration system, including:

[0028] A process intent configuration unit, configured to obtain at least one insurance business prompt word, and perform insurance intent configuration processing based on the at least one insurance business prompt word to determine the insurance business corresponding to the at least one insurance business prompt word;

[0029] A process node page configuration unit, configured to generate a process configuration page corresponding to the insurance business according to the insurance business, where the process configuration page includes process configuration boxes corresponding to each process node of the insurance business;

[0030] A process node interface configuration unit, configured to perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page in sequence, so as to obtain an insurance business processing page corresponding to the insurance business after the business interface configuration processing, and generate an insurance business processing system corresponding to the insurance business based on the insurance business processing page, where any business interface is used to call an insurance business processing thread, an insurance business model, or an insurance knowledge base, and the insurance business model includes a natural language model, an OCR model, an underwriting and claims document image recognition and classification model, a vehicle recognition model, a picture correction model, a speech-to-text conversion model, and an intent recognition model.

[0031] In a third aspect, there is provided a fast conversational insurance business process configuration device. Taking the device as an electronic device as an example, it includes a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the fast conversational insurance business process configuration method as described in the first aspect or any possible design in the first aspect.

[0032] Fourthly, a storage medium is provided, on which instructions are stored. When the instructions are run on a computer, the quick conversational insurance business process configuration method as described in the first aspect or any possible design in the first aspect is executed.

[0033] Fifthly, a computer program product containing instructions is provided. When the instructions are run on a computer, the computer is made to execute the quick conversational insurance business process configuration method as described in the first aspect or any possible design in the first aspect.

[0034] Beneficial effects:

[0035] (1) The present invention can configure and manage the traditional insurance business system through the AI model and the conversational process application, that is, through process intent configuration, insurance business process node page configuration, and business interface configuration, to quickly call the AI model capabilities to empower the insurance application with AI, so as to quickly create a new conversational insurance underwriting and claims business based on the large model, so as to realize the AI empowerment transformation of the traditional insurance business; thus, the present invention provides an insurance business configuration method with accurate intent recognition, replicable process configuration, and rapid application launch. It only requires developers to perform simple configuration in the process configuration page to generate a conversational insurance business processing system. Therefore, the present invention improves the development efficiency of insurance business applications, enables rapid launch of business applications, reduces costs and requirements for personnel capabilities, and is thus very suitable for large-scale application and promotion.

[0036] (2) During the use process of the present invention, through the user's usage feedback information, the process configuration of the insurance business can be optimized, that is, model configuration or process optimization configuration adjustment (such as prompt word adjustment, insurance business model optimization, page configuration optimization, etc.) is performed to achieve the purpose of rapid application adjustment and user imperceptibility. In this way, the steps of modifying code, packaging and releasing online required for traditional application adjustment are avoided, thereby improving the user experience. Description of the drawings

[0037] Figure 1 It is a schematic step flow diagram of the quick conversational insurance business process configuration method provided by the embodiment of the present invention;

[0038] Figure 2 It is a schematic structural diagram of the quick conversational insurance business process configuration system provided by the embodiment of the present invention;

[0039] Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the accompanying drawings and the description of the embodiments or the prior art. Obviously, the following description of the structures of the drawings is only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0041] It should be understood that although terms such as first and second may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, the first unit can be called the second unit, and similarly, the second unit can be called the first unit, without departing from the scope of the exemplary embodiments of the present invention.

[0042] It should be understood that for the term "and / or" that may appear in this article, it is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously; for the term " / and" that may appear in this article, it is a description of another association object relationship, indicating that there can be two relationships. For example, A / and B can mean: A exists alone, and A and B exist alone; in addition, for the character " / " that may appear in this article, generally it means that the front and back associated objects are an "or" relationship.

[0043] Embodiment:

[0044] See Figure 1 As shown, the fast conversational insurance business process configuration method provided in this embodiment performs configuration management through an AI model and a conversational process application, that is, through process intent configuration, insurance business process node page configuration, and business interface configuration, to quickly call the capabilities of the AI model to empower the insurance application with AI. In this way, the traditional web business applications in the insurance industry can be quickly transformed and configured into conversational applications relying on large models, and new conversational insurance underwriting and claims businesses based on large models can also be quickly created; therefore, this method has the advantages of low development cost, low requirements for personnel capabilities, fast model integration, accurate intent recognition, replicable process configuration, fast application launch, immediate presentation of real-time adjustments, and applications suitable for the elderly, etc., and is thus very suitable for large-scale application and promotion; among them, for example, this method can but is not limited to running on the insurance business configuration side. Optionally, the insurance business configuration side can but is not limited to a personal computer. It can be understood that the foregoing execution subject does not constitute a limitation to the embodiments of the present application. Correspondingly, the running steps of this method can but are not limited to the following steps S1 to S3 as shown.

[0045] S1. Obtain at least one insurance business prompt word, and based on the at least one insurance business prompt word, perform insurance intention configuration processing to determine the insurance business corresponding to the at least one insurance business prompt word; in this embodiment, this step is mainly a configuration process of associating and mapping different possible intentions of users with corresponding insurance business processes, that is, by configuring insurance business prompt words, the corresponding insurance business is associated to enter the configuration processes of different insurance businesses, which is to identify the requirements or goals expressed by developers through technologies such as semantic understanding, and then match the identified user intentions with the corresponding business processes to initiate the corresponding business processing processes; for example, associate the intention of "I want to report a claim" with the claim reporting process, and associate the intention of "I want to consult the claim settlement process" with the claim settlement process; of course, the foregoing examples are only illustrative, and different insurance business prompt words can be set according to different insurance businesses to complete the mapping between different insurance businesses and corresponding prompt words.

[0046] Optionally, for example but not limited to, use a machine learning model to perform intention recognition on the at least one insurance business prompt word to identify the insurance business corresponding to the at least one insurance business prompt word; that is, first collect the interaction data between developers and the insurance business system, including user intentions and corresponding business processes; then, use machine learning algorithms, such as intention recognition models, to train the model to recognize user intentions and associate them with the corresponding business processes; finally, deploy the trained model to the insurance business system to achieve the function of automatically identifying developer intentions and jumping to the corresponding business configuration process.

[0047] In this way, through the intention configuration corresponding to the insurance business process, when in use, different insurance businesses can be jumped to by identifying the user's intention, so as to process different insurance businesses; among them, after completing the insurance intention configuration, the configuration of the insurance business process can be entered, and the process is as shown in the following steps S2 and S3.

[0048] S2. Generate a process configuration page corresponding to the insurance service, where the process configuration page includes process configuration boxes for each process node corresponding to the insurance service. In this embodiment, the process nodes corresponding to different insurance services are stored in the insurance service configuration end. Therefore, by matching the insurance service identified by intention, the corresponding process nodes can be obtained. Then, based on the process nodes corresponding to the insurance service, the process configuration page of the insurance service can be generated. For example, if the insurance service is insurance claim settlement, one needs to report the claim first, provide information such as the insurance policy number and the name of the insured, and then prepare claim application materials such as the insurance policy, accident certificate, loss certificate, and identity certificate and upload them. Next, the insurance company conducts claim acceptance verification, and finally, the insurance company makes the payment. Therefore, the process nodes corresponding to insurance claim settlement are: the claim reporting node, the insurance policy information upload node, the claim application material upload node, etc. Based on this, the corresponding process configuration page includes the configuration boxes corresponding to the above-mentioned process nodes. Of course, the above example is only illustrative. When the insurance service is different, the corresponding process configuration page is also different, and it is not limited to the above example here.

[0049] At the same time, different process configuration page templates corresponding to insurance services can be set in advance. In this way, when in use, only the insurance service identified by intention needs to be used to match the corresponding process configuration page template. In this way, it is convenient for subsequent process node page configuration and interface configuration.

[0050] Optionally, the process node page configuration and interface configuration processes are as shown in the following step S3.

[0051] S3. Perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page in sequence. After the business interface configuration processing, an insurance service processing page corresponding to the insurance service is obtained, and based on the insurance service processing page, an insurance service processing system corresponding to the insurance service is generated, where any business interface is used to call an insurance service processing thread, an insurance service model, or an insurance knowledge base, and the insurance service model includes a natural language model, an OCR model, an underwriting and claim settlement document image recognition and classification model, a vehicle recognition model, a picture correction model, a speech-to-text conversion model, and an intention recognition model.

[0052] In this embodiment, it is equivalent to configuring process nodes on the process configuration page, that is, associating and configuring each node in the insurance business process (such as underwriting, claims settlement, consultation, etc.) with the corresponding page template. Specifically, a page template can be selected or created, page elements can be configured (that is, on the selected page template, configure the required elements, such as input boxes, buttons, pictures, etc., and set their attributes, such as size, position, color, etc.), data and functions can be associated (that is, associate page elements with backend data or functions, such as associating an input box with a user information table and associating a button with a specific function (such as submitting a form)); and visual configuration can be achieved.

[0053] The business interface configuration process refers to associating and configuring each node in the insurance business process (such as underwriting, claims settlement, consultation, etc.) with the corresponding backend service interface. Specifically, it can be: selecting or creating an interface (that is, selecting a backend service interface for each process node or creating a new interface), configuring interface parameters (such as input parameters, output parameters, request methods, and request formats, etc.), associating data and functions (that is, associating the interface with frontend page elements, such as sending form data to a specified interface and displaying the result returned by the interface on the page). In this way, through interface configuration, automatic acquisition, processing, and display of data can be achieved, thereby improving business processing efficiency.

[0054] In specific implementation, for example, but not limited to, visual display of the process configuration page can be performed to generate an initial insurance business processing page in response to a human-computer interaction operation on each process configuration box in the process configuration page by the development end; that is, developers perform page configuration for each process node, and the insurance business configuration end responds to the human-computer interaction operation of the developers to generate an initial insurance business processing page; similarly, the same is true for business interface configuration, that is, in response to a human-computer interaction operation on the interface configuration of each process configuration box in the initial insurance business processing page by the development end, business interfaces are configured for each process configuration box in the initial insurance business processing page, so that after configuring the business interfaces, the insurance business processing page can be obtained.

[0055] Furthermore, for example, the insurance knowledge base may include, but is not limited to: underwriting knowledge base, claims knowledge base, company knowledge base, intent knowledge base, and image knowledge base; and the aforementioned insurance business model is a trained model applicable to the insurance business and is pre-stored in the insurance business configuration terminal; thus, through the intent configuration in the aforementioned step S1, it is possible to achieve the jump of the user's consultation intent to different insurance business processes; through interface configuration, the background insurance business service interface can be called, thereby invoking different business logics, that is, different models are called for different business processes. For example, the classification model can be called in the claims process to automatically classify the insurance documents pictures uploaded by the user, and the language model combined with the knowledge base can be called to answer user consultations; at the same time, through the front-end page template configuration, the visualization configuration of each node page of the process can be realized, what you see is what you get; by calling the knowledge base, different types of knowledge bases can be associated with different processes, and the knowledge base can be continuously expanded and maintained; thus, through the full-process configuration, an insurance business process application with AI dialogue capabilities can be quickly assembled and built.

[0056] Based on this, through the aforementioned process configuration, functions such as intent recognition, underwriting structured parsing, claims structured parsing, conversational underwriting issuance, conversational claims reporting, underwriting and claims knowledge base Q&A, insurance document classification, insurance document recognition, and insurance voice aging-friendly services can be provided.

[0057] At the same time, after completing the insurance business process configuration, the insurance business processing page can be published, so that after the publishing process, the insurance business processing system is generated; thus, in actual use, the user only needs to input their intent, and then through the intent recognition model, they can jump to the insurance business processing process required by the user. Then, through the conversational business operation, the insurance business can be completed, that is, different insurance business processes are triggered by intent to achieve different business functions.

[0058] Based on this, through the AI model of the insurance industry and the configuration of the conversational process application in this embodiment, rapid AI empowerment of traditional insurance applications can be achieved, so that functions such as conversational underwriting issuance, conversational claims reporting, insurance document recognition, insurance document classification, extraction of insurance structured data, voice-to-text conversion, and insurance knowledge base Q&A can be realized by using the configured insurance business process. Furthermore, it can simplify the user operation while meeting the aging-friendly requirements of financial insurance, and at the same time has the advantages of real-time adjustment; based on this, it can meet the system requirement adjustment of rapid change.

[0059] Furthermore, in this embodiment, feedback information during the user's use process will be obtained in real time and used to optimize the process configuration, that is: based on the user's use feedback information, the insurance business process configuration is optimized, so that after the process configuration optimization process, an optimized insurance business processing page is obtained.

[0060] Optionally, the specific optimization process is as follows: First, update the insurance business prompt words corresponding to the insurance business according to the user usage feedback information to obtain the updated insurance business prompt words; then, optimize the insurance business model corresponding to the target configuration box in the process configuration page according to the user usage feedback information to obtain the optimized insurance business model (wherein, the target configuration box is the process configuration box corresponding to the specified service interface in the process configuration page, and the specified service interface is used to call the insurance business large model); then, update the process configuration page corresponding to the insurance business to obtain the updated process configuration page (i.e., update the elements in the page, etc.); finally, perform an update process on the service interface in the updated process configuration page, so that after the update process, an optimized insurance business processing page is obtained. After the service interface is updated, the specified service interface in the updated process configuration page is used to call the optimized insurance business model, and when the optimized insurance business processing page enters the insurance processing thread, the updated insurance business prompt words are used for insurance business conversations.

[0061] In this way, it is equivalent to monitoring the problems and customer behaviors during the use process. If it is found that the use experience is not friendly or there are problems during use, the model configuration or process optimization configuration can be adjusted at any time through the conversational application process configuration, so as to achieve the purpose of rapid application adjustment and user imperceptibility. Based on this, the steps of modifying code, packaging and releasing online, etc. required for traditional application adjustment can be avoided, thereby improving the user experience.

[0062] Through the fast conversational insurance business process configuration method described in detail in the foregoing steps S1 to S3, the present invention performs configuration management through an AI model and a conversational process application, that is, through process intent configuration, insurance business process node page configuration, and service interface configuration, to quickly call the AI model capabilities to empower the insurance application with AI. In this way, the traditional web business applications in the insurance industry can be quickly transformed and configured into conversational applications relying on large models, and new insurance underwriting and claims conversational new businesses based on large models can also be quickly created; therefore, the present invention has the advantages of low development cost, low requirements for personnel capabilities, fast model integration, accurate intent recognition, replicable process configuration, fast application online, immediate presentation of real-time adjustment, and applications suitable for the elderly, etc., and is thus very suitable for large-scale application and promotion.

[0063] As Figure 2 shown, the second aspect of this embodiment provides a hardware system for implementing the fast conversational insurance business process configuration method described in the first aspect of the embodiment, including:

[0064] A process intention configuration unit, configured to obtain at least one insurance business prompt word, and perform insurance intention configuration processing based on the at least one insurance business prompt word to determine the insurance business corresponding to the at least one insurance business prompt word.

[0065] A process node page configuration unit, configured to generate a process configuration page corresponding to the insurance business according to the insurance business, where the process configuration page includes process configuration boxes for each process node corresponding to the insurance business.

[0066] A process node interface configuration unit, configured to perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page in sequence. After the business interface configuration processing, an insurance business processing page corresponding to the insurance business is obtained, and an insurance business processing system corresponding to the insurance business is generated based on the insurance business processing page. Any business interface is used to call an insurance business processing thread, an insurance business model, or an insurance knowledge base, and the insurance business model includes a natural language model, an OCR model, an underwriting and claims document image recognition and classification model, a vehicle recognition model, a picture correction model, a speech-to-text conversion model, and an intention recognition model.

[0067] For the working process, working details, and technical effects of the system provided in this embodiment, reference may be made to the first aspect of the embodiment, which will not be elaborated here.

[0068] As Figure 3 shown, in the third aspect of this embodiment, a fast conversational insurance business process configuration device is provided. Taking the device as an electronic device as an example, it includes: a memory, a processor, and a transceiver that are communicatively connected in sequence. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the fast conversational insurance business process configuration method described in the first aspect of the embodiment.

[0069] Specifically, the memory may but is not limited to include random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO), etc.; specifically, the processor may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). At the same time, the processor may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state.

[0070] In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. For example, the processor may not be limited to using a microprocessor of the STM32F105 series, a reduced instruction set computer (RISC) microprocessor, an X86 architecture processor, or a processor integrated with an embedded neural network processor (neural-network processing units, NPU); the transceiver may but is not limited to be a Wi-Fi wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee (low-power local area network protocol based on the IEEE802.15.4 standard) wireless transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver, etc. In addition, the device may also but is not limited to include a power module, a display screen, and other necessary components.

[0071] For the working process, working details, and technical effects of the electronic device provided in this embodiment, reference may be made to the first aspect of the embodiment, which will not be elaborated here.

[0072] In the fourth aspect of this embodiment, a storage medium storing instructions for the fast conversational insurance business process configuration method described in the first aspect of the embodiment is provided, that is, instructions are stored on the storage medium, and when the instructions run on a computer, the fast conversational insurance business process configuration method described in the first aspect of the embodiment is executed.

[0073] Among them, the storage medium refers to a carrier for storing data, and can include, but is not limited to, floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or memory sticks, etc. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0074] For the working process, working details, and technical effects of the storage medium provided in this embodiment, reference can be made to the first aspect of the embodiment, and details are not described herein again.

[0075] In the fifth aspect of this embodiment, a computer program product containing instructions is provided. When the instructions run on a computer, the computer is made to execute the fast conversational insurance business process configuration method described in the first aspect of the embodiment, where the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0076] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fast conversational insurance business process configuration method, characterized in that: include: Acquire at least one insurance business prompt word, and perform insurance intention configuration processing based on the at least one insurance business prompt word to determine the insurance business corresponding to the at least one insurance business prompt word; According to the insurance business, generating a process configuration page corresponding to the insurance business, wherein the process configuration page includes a process configuration box corresponding to each process node of the insurance business; The process node configuration processing and the business interface configuration processing are performed in sequence on each process configuration box in the process configuration page, so that after the business interface configuration processing, the insurance business processing page corresponding to the insurance business is obtained, and based on the insurance business processing page, the insurance business processing system corresponding to the insurance business is generated, wherein any business interface is used to call the insurance business processing thread, the insurance business model or the insurance knowledge base, and the insurance business model includes a natural language model, an OCR model, an underwriting and claim document image recognition and classification model, a vehicle recognition model, an image correction model, a speech-to-text conversion model and an intent recognition model.

2. The method according to claim 1, characterized in that Perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page, including: Visually displaying the process configuration page to generate an initial insurance business processing page in response to the development end's process configuration human-computer interaction operation on each process configuration box in the process configuration page; In response to the development end configuring human-computer interaction operations on the interfaces of each process configuration box in the initial insurance business processing page, a business interface is configured for each process configuration box in the initial insurance business processing page, so that the insurance business processing page is obtained after the business interface is configured.

3. The method according to claim 1, characterized in that: The method further comprises: Obtain user feedback information; Based on the user feedback information, the process configuration of the insurance business is optimized, so that after the process configuration optimization, an optimized insurance business processing page is obtained.

4. The method according to claim 3, characterized in that Based on user feedback information, the process configuration of the insurance business is optimized, including: updating the insurance business prompt word corresponding to the insurance business according to the user feedback information to obtain an updated insurance business prompt word; According to the user feedback information, the insurance business model corresponding to the target configuration box in the process configuration page is optimized to obtain an optimized insurance business model, wherein the target configuration box is a process configuration box corresponding to a specified business interface in the process configuration page, and the specified business interface is used to call the insurance business model; Updating the process configuration page corresponding to the insurance business to obtain an updated process configuration page; The business interface in the updated process configuration page is updated to obtain an optimized insurance business processing page after the update, wherein after the business interface is updated, the designated business interface in the updated process configuration page is used to call the optimized insurance business model, and the optimized insurance business processing page uses the updated insurance business prompt words to conduct insurance business dialogue when entering the insurance processing thread.

5. The method according to claim 1, characterized in that Based on the at least one insurance service prompt word, insurance intention configuration processing is performed to obtain the insurance service corresponding to the at least one insurance service prompt word, including: The machine learning model is used to perform intent recognition on the at least one insurance business prompt word to identify the insurance business corresponding to the at least one insurance business prompt word.

6. The method according to claim 1, characterized in that Based on the insurance business processing page, an insurance business processing system corresponding to the insurance business is generated, including: The insurance business processing page is published to generate the insurance business processing system after the publishing process.

7. The method according to claim 1, characterized in that The insurance knowledge base includes: an underwriting knowledge base, a claims knowledge base, a company knowledge base, an intention knowledge base and an image knowledge base.

8. A fast interactive insurance business process configuration system, characterized in that: include: A process intention configuration unit, configured to obtain at least one insurance business prompt word, and perform insurance intention configuration processing based on the at least one insurance business prompt word to determine the insurance business corresponding to the at least one insurance business prompt word; A process node page configuration unit, used to generate a process configuration page corresponding to the insurance business according to the insurance business, wherein the process configuration page includes a process configuration box corresponding to each process node of the insurance business; A process node interface configuration unit is used to perform process node configuration processing and business interface configuration processing on each process configuration box in the process configuration page in sequence, so as to obtain an insurance business processing page corresponding to the insurance business after the business interface configuration processing, and generate an insurance business processing system corresponding to the insurance business based on the insurance business processing page, wherein any business interface is used to call an insurance business processing thread, an insurance business model or an insurance knowledge base, and the insurance business model includes a natural language model, an OCR model, an underwriting claim document image recognition and classification model, a vehicle recognition model, an image correction model, a speech-to-text conversion model and an intent recognition model.

9. An electronic device, characterized in that: include: A memory, a processor and a transceiver which are sequentially connected in communication, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs, and execute the fast conversational insurance business process configuration method as described in any one of claims 1 to 7.

10. A computer program product comprising instructions, characterized in that When the instructions are executed on a computer, the computer is caused to execute the fast interactive insurance business process configuration method as described in any one of claims 1 to 7.

Images