Business processing method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based business processing method and device, computer equipment and a storage medium, and the method comprises the steps: receiving a business processing request triggered by a user; wherein the service processing request carries a service type; collecting initial service data of the user corresponding to the service type based on the intelligent agent; preprocessing the initial business data to obtain target business data; evaluating a model based on a target business corresponding to the business type; performing reasoning processing on the target business data to obtain an evaluation result; performing service decision processing on the evaluation result based on a knowledge base corresponding to the service type and an evaluation strategy to obtain a service decision processing result; and returning an evaluation result and a service decision processing result to the user based on the intelligent agent. In addition, the evaluation results can be stored in the block chain. The business processing method and device can be applied to business processing scenes in the financial field and the medical field, the business processing efficiency is effectively improved, and more accurate business decisions are achieved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and can be applied to fields such as fintech and digital healthcare, particularly to business processing methods, devices, computer equipment, and storage media based on artificial intelligence. Background Technology

[0002] In traditional business system operation models, many business processes rely heavily on simple, pre-defined rules and lack AI support, resulting in low efficiency. Specifically, when handling complex business tasks, traditional business systems often operate according to fixed, rigid processes, making it difficult to respond quickly and accurately based on real-time data and dynamically changing circumstances. This approach not only consumes significant manpower and time but is also prone to human error, affecting the accuracy and quality of business processing.

[0003] In the credit approval process within the financial sector, traditional methods typically rely on simple scoring and approval decisions based on a customer's basic financial information (such as income and liabilities) and credit history. For example, a debt-to-income ratio might be calculated solely based on a customer's monthly income and existing loan amount; if this ratio falls below a certain fixed threshold, the loan application is approved. However, this approach lacks in-depth analysis of multi-dimensional data, including customer consumption behavior, industry trends, and the macroeconomic environment. If a customer in an emerging industry with high growth potential is rejected for a loan due to high short-term debt, they may miss out on development opportunities, and the financial institution may lose a valuable customer. This approval method fails to comprehensively and accurately assess a customer's credit risk and repayment ability, leading to inefficient approval processes and potentially triggering non-performing loan risks.

[0004] In the field of medical diagnosis, traditional diagnostic methods rely heavily on doctors' personal experience and expertise, requiring them to spend considerable time reviewing medical records and analyzing test results. For example, when faced with complex and difficult-to-diagnose cases, doctors need to systematically rule out various possible diseases and make a diagnosis by comparing a large amount of medical literature and past cases. This process is not only time-consuming and labor-intensive, but also prone to misdiagnosis or missed diagnosis due to differences in individual doctors' experience and knowledge. Furthermore, traditional diagnostic methods struggle to quickly integrate multi-source medical data (such as imaging data and genetic data) for comprehensive analysis, failing to fully utilize the value of various data sources, thus affecting the accuracy and efficiency of diagnosis and hindering patients from receiving timely and effective treatment.

[0005] Therefore, there is an urgent need for a business processing system with AI capabilities to improve business processing efficiency, fully utilize data value, and achieve more accurate and efficient business decisions. Summary of the Invention

[0006] The purpose of this application is to propose a business processing method, apparatus, computer equipment, and storage medium based on artificial intelligence, so as to solve the technical problem that the business processing flow of existing business systems relies on simple preset rules, resulting in low business processing efficiency.

[0007] Firstly, an artificial intelligence-based business processing method is provided, including:

[0008] Receive a service processing request triggered by a user; wherein the service processing request carries a service type;

[0009] The system collects initial business data of the user corresponding to the business type based on a preset intelligent agent.

[0010] The initial business data is preprocessed to obtain the corresponding target business data;

[0011] Invoke the target business evaluation model corresponding to the business type;

[0012] Based on the target business evaluation model, the target business data is processed by reasoning to obtain the corresponding evaluation results;

[0013] Based on the knowledge base corresponding to the business type and the preset evaluation strategy, the evaluation results are processed for business decision-making to obtain the corresponding business decision-making results.

[0014] The intelligent agent returns the evaluation results and the business decision processing results to the user.

[0015] Secondly, an artificial intelligence-based business processing device is provided, including:

[0016] A receiving module is used to receive a service processing request triggered by a user; wherein the service processing request carries a service type;

[0017] The collection module is used to collect initial business data of the user corresponding to the business type based on a preset intelligent agent;

[0018] The preprocessing module is used to preprocess the initial business data to obtain the corresponding target business data;

[0019] The calling module is used to invoke the target business evaluation model corresponding to the business type.

[0020] The reasoning module is used to perform reasoning processing on the target business data based on the target business evaluation model to obtain the corresponding evaluation results;

[0021] The processing module is used to perform business decision processing on the evaluation results based on the knowledge base corresponding to the business type and the preset evaluation strategy, so as to obtain the corresponding business decision processing results.

[0022] The return module is used to return the evaluation results and the business decision processing results to the user based on the intelligent agent.

[0023] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described artificial intelligence-based business processing method.

[0024] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the aforementioned artificial intelligence-based business processing method.

[0025] In the above-mentioned scheme implemented by the AI-based business processing method, apparatus, computer equipment, and storage medium, a business processing request triggered by a user is first received; wherein the business processing request carries a business type; then, based on a preset intelligent agent, initial business data of the user corresponding to the business type is collected; and the initial business data is preprocessed to obtain corresponding target business data; then, a target business evaluation model corresponding to the business type is invoked; subsequently, the target business data is inferred based on the target business evaluation model to obtain a corresponding evaluation result; further, based on a knowledge base corresponding to the business type and a preset evaluation strategy, the evaluation result is processed into a business decision to obtain a corresponding business decision processing result; finally, the evaluation result and the business decision processing result are returned to the user based on the intelligent agent. Based on the above processing flow, this application collects initial business data from users corresponding to business types using intelligent agents, preprocesses the initial business data to obtain target business data, then uses the target business evaluation model to perform reasoning processing on the target business data to obtain evaluation results, and uses a knowledge base and preset evaluation strategies to perform business decision processing on the evaluation results to obtain business decision processing results. Finally, the evaluation results and business decision processing results are returned to the user, thereby enabling efficient and accurate processing of business processing requests, effectively improving business processing efficiency, and facilitating more accurate and efficient business decisions. Attached Figure Description

[0026] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0028] Figure 2 This is a flowchart of an embodiment of the AI-based business processing method according to this application;

[0029] Figure 3 This is a schematic diagram of a structure of an embodiment of the AI-based business processing apparatus according to this application;

[0030] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0032] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0034] like Figure 1As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0035] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0036] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0037] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0038] It should be noted that the AI-based business processing method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the AI-based business processing device is generally located in the server / terminal device.

[0039] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0040] Continue to refer to Figure 2This document illustrates a flowchart of an embodiment of the AI-based business processing method according to this application. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements. The AI-based business processing method provided in this application can be applied to any scenario requiring business processing, and thus can be applied to products in these scenarios, such as business processing scenarios in the financial and medical fields. The AI-based business processing method includes the following steps:

[0041] Step S201: Receive a service processing request triggered by a user; wherein the service processing request carries a service type.

[0042] In this embodiment, the AI-based business processing method runs on an electronic device (e.g., Figure 1 The server / terminal device shown can receive user-triggered service processing requests via wired or wireless connections. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-Width Band) connections, and other currently known or future-developed wireless connection methods. The executing entity of this application is a service processing system, which may be simply referred to as the system. The aforementioned service processing requests are user-triggered requests to perform corresponding service processing for the above-mentioned service types. This application can be applied to service processing scenarios in the financial and medical fields. The aforementioned service types may include car insurance claims scenarios, health insurance underwriting scenarios, etc., in the financial field. They may also include disease analysis assistance scenarios, medical expense review scenarios, etc., in the medical field.

[0043] Correspondingly, in the context of auto insurance claims in the financial sector, the relevant business processing may include: analyzing data such as accident scene photos, vehicle damage photos, and accident description text to arrive at a claim risk assessment result. For example, determining whether the accident involves suspected fraud, and the reasonable repair cost range corresponding to the degree of vehicle damage.

[0044] In the context of health insurance underwriting in the financial sector, the corresponding business processing may include: analyzing data such as health questionnaires, medical examination reports, and past medical history submitted by the policyholder to assess the policyholder's health risk level and expected premium. For example, based on factors such as the policyholder's age, gender, and medical history, the probability of them developing certain diseases can be determined, and the corresponding premium range can be calculated.

[0045] In the medical field, disease analysis assistance scenarios may involve analyzing patient medical images (such as X-rays, CT scans, MRI scans), medical records, and laboratory test results to provide disease analysis suggestions and severity assessments. For example, determining the probability of a patient having a certain disease, and identifying whether the disease is in its early, middle, or late stage.

[0046] In the medical field, the corresponding business processes for reviewing medical expenses may include analyzing data such as patients' medical expense lists, treatment items, and medication usage to assess the reasonableness and compliance of medical expenses. For example, determining whether there are issues such as over-treatment, duplicate charges, or illegal medication use.

[0047] Step S202: Collect initial business data of the user corresponding to the business type based on the preset intelligent agent.

[0048] In this embodiment, an Agent is pre-created in the system. This Agent is responsible for interacting with the user, collecting initial business data of the user corresponding to the above-mentioned business type, such as claims information, and passing the initial business data to the subsequent business evaluation model for processing.

[0049] Step S203: Preprocess the initial business data to obtain the corresponding target business data.

[0050] In this embodiment, the specific implementation process of preprocessing the initial business data to obtain the corresponding target business data will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0051] Step S204: Invoke the target business evaluation model corresponding to the business type.

[0052] In this embodiment, the specific construction process of the target business evaluation model will be described in more detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0053] Step S205: Based on the target business evaluation model, perform reasoning processing on the target business data to obtain the corresponding evaluation result.

[0054] In this embodiment, the target business data can be input into the target business evaluation model, which then performs inference calculations. After the model completes its calculations, the results are output in a structured manner to obtain the evaluation results. For example, the claims risk assessment results can be divided into three levels: high, medium, and low, with corresponding probability values ​​provided.

[0055] Step S206: Based on the knowledge base corresponding to the business type and the preset evaluation strategy, perform business decision processing on the evaluation results to obtain the corresponding business decision processing results.

[0056] In this embodiment, the specific implementation process of processing the evaluation results based on the knowledge base corresponding to the business type and the preset evaluation strategy to obtain the corresponding business decision processing results will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0057] Step S207: Based on the intelligent agent, return the evaluation results and the business decision processing results to the user.

[0058] In this embodiment, the generated evaluation results and business decision processing results can be fed back to the user through an intelligent agent. For example, the evaluation results and business decision processing results can be returned to the user through a user interface, thereby completing the processing of the business processing request. Further communication and processing can be carried out based on user feedback to achieve more intelligent business processing.

[0059] This application first receives a service processing request triggered by a user; wherein the service processing request carries a service type; then, based on a preset intelligent agent, it collects the user's initial service data corresponding to the service type; and preprocesses the initial service data to obtain the corresponding target service data; then, it calls the target service evaluation model corresponding to the service type; subsequently, it performs reasoning processing on the target service data based on the target service evaluation model to obtain the corresponding evaluation result; further, it performs business decision processing on the evaluation result based on the knowledge base corresponding to the service type and a preset evaluation strategy to obtain the corresponding business decision processing result; finally, it returns the evaluation result and the business decision processing result to the user based on the intelligent agent. Based on the above processing flow, this application collects initial business data from users corresponding to business types using intelligent agents, preprocesses the initial business data to obtain target business data, then uses the target business evaluation model to perform reasoning processing on the target business data to obtain evaluation results, and uses a knowledge base and preset evaluation strategies to perform business decision processing on the evaluation results to obtain business decision processing results. Finally, the evaluation results and business decision processing results are returned to the user, thereby enabling efficient and accurate processing of business processing requests, effectively improving business processing efficiency, and facilitating more accurate and efficient business decisions.

[0060] In some alternative implementations, prior to step S204, the electronic device may also perform the following steps:

[0061] Collect a certain amount of business data related to specified business requirements from the pre-set business system.

[0062] In this embodiment, the specified business requirements can be determined according to actual needs. The collection and processing of the business data includes: Integration with core business systems: A professional data integration team is formed to communicate with the maintenance personnel of the core business systems to understand the system's data structure, storage methods, and interface specifications. Based on this information, a suitable ETL tool (such as Informatica, Talend, etc.) is selected. Data extraction rules are configured through the ETL tool, such as setting scheduled tasks to automatically extract data during idle periods of the business system (such as early morning) to avoid affecting the normal operation of the business system. Structured data integration: The extracted structured data, such as premiums and claims records, is cleaned and transformed according to a preset format. For example, date formats and currency units are standardized to ensure data consistency. The cleaned data is then stored in a data lake warehouse integrated platform, and a clear metadata description is established for each data table, including data source, field meaning, data type, etc., to facilitate subsequent data management and use. Unstructured data integration: For unstructured data such as images and audio, specialized storage and indexing technologies are used. For example, for image data, object storage services can be used for storage, and a unique identifier is generated for each image file. Simultaneously, establish a link between the images and relevant business information (such as policy numbers and claims numbers) to facilitate subsequent queries and analysis. For voice data, first perform speech-to-text processing, then store the converted text along with the original voice file, and create a corresponding index.

[0063] Then, a certain amount of business data corresponding to the predetermined specified business requirements is queried from the aforementioned object storage service. The selection of this certain amount is not specifically limited and can be determined based on the actual business needs.

[0064] The business data is labeled to obtain corresponding sample data.

[0065] In this embodiment, a data annotation team and algorithm engineers jointly determine the disease features that need to be annotated in the medical records, such as the size and location of lung nodules. Algorithm engineers select appropriate semi-supervised learning algorithms, such as Mean Teacher and FixMatch, based on these features. The model is trained using a small amount of labeled data and a large amount of unlabeled data, continuously adjusting model parameters to improve annotation accuracy. A quality monitoring mechanism is established during the annotation process. Annotation results are periodically sampled and evaluated by professional medical experts. If a high error rate is found, algorithm parameters are adjusted promptly or manual annotation intervention is added to ensure annotation efficiency and quality. Simultaneously, the annotated data is updated to the integrated data lake warehouse platform in a timely manner, providing high-quality annotated data for subsequent model training.

[0066] Specifically, the aforementioned business data can be labeled based on a selected algorithm for data labeling, and the labeled data can be used as the aforementioned sample data.

[0067] Retrieve the large model for the specified vertical domain corresponding to the business requirement from the preset model library.

[0068] In this embodiment, the specified business requirements, such as claims risk assessment and premium prediction, can be analyzed. Based on the analysis results, suitable models, such as DeepSeek-R1 and ERNI Insurance, can be selected from a pre-trained model library. These vertical domain models can be identified by understanding their characteristics and advantages, such as DeepSeek-R1's excellent performance in general knowledge understanding and ERNI Insurance's deeper knowledge and better adaptability in the insurance field. This allows for the selection of specific vertical domain models that match the aforementioned business requirements.

[0069] The large model for the specified vertical domain is trained based on the sample data to obtain the corresponding first model.

[0070] In this embodiment, the model training process of the first model includes: dividing the sample data into a training set and a validation set according to a certain ratio for model training and evaluation; and using the sample data to train a large model for a specified vertical domain. During training, appropriate training parameters are set, such as learning rate, batch size, and number of training epochs. Through continuous iterative training, the model gradually learns the patterns and rules of the training data to generate a first model capable of evaluating and processing business data. Furthermore, during model training, the model's performance is periodically evaluated using the validation set. Based on the evaluation results, the model parameters are adjusted, such as adjusting the learning rate, increasing or decreasing the number of training epochs, to improve the model's evaluation accuracy.

[0071] Based on the business type, the first model is fine-tuned using a preset fine-tuning strategy to obtain the corresponding second model.

[0072] In this embodiment, the specific implementation process of fine-tuning the first model to obtain the corresponding second model based on the business type using a preset fine-tuning strategy will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0073] The second model is used as the target business evaluation model.

[0074] This application collects a certain amount of business data related to specified business needs from a pre-set business system; then, it annotates the business data to obtain corresponding sample data; next, it queries a pre-set model library to retrieve a large model for a specified vertical domain corresponding to the business needs; subsequently, it trains the large model for the specified vertical domain based on the sample data to obtain a corresponding first model; further, based on the business type, it fine-tunes the first model using a pre-set fine-tuning strategy to obtain a corresponding second model; finally, it uses the second model as the target business evaluation model. Based on the above processing flow, this application obtains sample data by annotating the business data collected from the business system, retrieves a large model for a specified vertical domain corresponding to the business needs from the model library, trains the large model for the specified vertical domain based on the sample data to obtain a first model, and then fine-tunes the first model based on the business type using a pre-set fine-tuning strategy. This allows for the efficient and accurate construction of the required target business evaluation model, improving the model construction efficiency of the target business evaluation model and ensuring its accuracy and performance.

[0075] In some optional implementations of this embodiment, the step of fine-tuning the first model using a preset fine-tuning strategy based on the business type to obtain the corresponding second model includes the following steps:

[0076] Collect the corresponding specified business data based on the business type.

[0077] In this embodiment, business data matching the aforementioned business types is collected from within the company, such as claims cases, premium data, and customer information. This data is then cleaned and preprocessed to ensure its quality and integrity, thereby obtaining the corresponding designated business data.

[0078] Select the target fine-tuning strategy that matches the scenario requirements of the business type from a variety of preset fine-tuning strategies.

[0079] In this embodiment, the aforementioned fine-tuning strategies may include at least full fine-tuning (retraining the model using all business data) or incremental fine-tuning (updating the model using only new business data). Specifically, based on the scenario requirements of the business type, a suitable strategy can be selected from the aforementioned fine-tuning strategies to be used as the target fine-tuning strategy.

[0080] Based on the target fine-tuning strategy, the first model is fine-tuned using the specified business data to obtain the corresponding processing model.

[0081] In this embodiment, the first model can be further fine-tuned and trained using the specified business data based on the strategy content of the aforementioned target fine-tuning strategy, thereby obtaining the corresponding processing model. During the fine-tuning process, by setting appropriate training parameters (such as learning rate, batch size, number of training epochs, etc.) and periodically using a validation set to evaluate the model's performance, it is ensured that the fine-tuned model can better adapt to the company's business characteristics.

[0082] The processing model is used as the second model.

[0083] In this embodiment, a Retrieval-Enhanced Generation (RAG) knowledge base related to the scenario requirements of the aforementioned business types can be constructed. This knowledge base may include documents such as insurance clauses, industry standards, and company internal policies. The documents in the knowledge base are structured, such as through chunking and indexing, so that the model can quickly retrieve relevant information. The knowledge base is then mounted onto a selected processing model via API interfaces or other technical means, enabling the processing model to retrieve and refer to the content in the knowledge base in real time when processing business transactions, thereby improving the accuracy and rationality of the processing. For example, during claims risk assessment, the model can retrieve relevant insurance clauses to determine whether the customer's claim application complies with the clauses.

[0084] This application collects corresponding specified business data based on the business type; then selects a target fine-tuning strategy that matches the scenario requirements of the business type from a variety of preset fine-tuning strategies; subsequently, based on the target fine-tuning strategy, the first model is fine-tuned using the specified business data to obtain a corresponding processing model; and finally, the processing model is used as the second model. Based on the above processing flow, this application can efficiently and accurately construct the required second model by selecting a target fine-tuning strategy that matches the scenario requirements of the business type from a variety of preset fine-tuning strategies, and then fine-tuning the first model using specified business data based on the target fine-tuning strategy. This allows the model to better adapt to business needs, thereby ensuring the timeliness, efficiency, and accuracy of business processing.

[0085] In some alternative implementations, step S206 includes the following steps:

[0086] Call the knowledge base corresponding to the business type.

[0087] In this embodiment, the system can pre-build a knowledge base locally according to its own needs to store business-related knowledge related to the aforementioned business types, providing more context and reference for business processing. For example, during claims risk assessment, it can query similar cases in historical claims to assist the AI ​​model in making more accurate judgments.

[0088] Relevant information corresponding to the evaluation result is retrieved based on the knowledge base.

[0089] In this embodiment, the aforementioned relevant information can be obtained by querying the local knowledge base in real time the context and references related to the assessment results. For example, during claims risk assessment, similar cases in historical claims can be queried to help the model make more accurate judgments.

[0090] The evaluation results are analyzed based on a preset multidimensional analysis strategy to obtain the corresponding analysis results.

[0091] In this embodiment, the analysis of the evaluation results based on the multidimensional analysis strategy includes: comprehensively analyzing the evaluation results output by the target business evaluation model from multiple dimensions. For example, in the premium forecasting scenario, the rationality of the evaluation results is analyzed, taking into account factors such as market trends, competitor pricing, and customer risk levels, to determine whether the predicted premiums are in line with the company's interests and market demand, and generating corresponding analysis results.

[0092] Based on the relevant information and the analysis results, a corresponding decision processing flow is constructed.

[0093] In this embodiment, a clear decision-making process is constructed based on the above analysis and evaluation results. For example, in a claims approval scenario, the processing paths corresponding to different risk levels are clearly defined: high-risk cases enter the manual review process, medium-risk cases are automatically approved by the system, and low-risk cases directly enter the automatic payment process.

[0094] The decision processing flow is executed to generate the corresponding business decision processing results.

[0095] In this embodiment, based on the processing steps of the aforementioned decision-making process, decision-making related to the aforementioned business processing request can be performed, and corresponding business decision-making results can be generated. During the decision execution process, automation and human collaboration are implemented. For automated decisions (such as automatic payment for low-risk claims), the business system will automatically trigger subsequent operations, such as generating a claim notification and notifying the finance department to pay the claim. For decisions requiring human intervention (such as rejecting high-risk cases), the system will generate detailed manual task orders, specifying processing steps and time limits to ensure the accuracy and timeliness of decision execution. Furthermore, an exception handling mechanism can be established to promptly handle errors or delays occurring during decision execution. For example, monitoring alarms can be set up so that when the financial payment system fails to complete the claim payment within the specified time, the exception handling process is automatically triggered, notifying relevant personnel to intervene and investigate.

[0096] This application utilizes a knowledge base corresponding to the business type; queries relevant information corresponding to the evaluation result based on the knowledge base; then analyzes the evaluation result using a preset multidimensional analysis strategy to obtain corresponding analysis results; subsequently, it constructs a corresponding decision processing flow based on the relevant information and the analysis results; and finally, it executes the decision processing flow to generate corresponding business decision processing results. Based on this processing flow, this application queries relevant information corresponding to the evaluation result using a knowledge base, analyzes the evaluation result using a preset multidimensional analysis strategy to obtain corresponding analysis results, and then constructs a corresponding decision processing flow based on the combined use of relevant information and analysis results, and executes the decision processing flow to generate business decision processing results. This enables the system to make more scientific and reasonable decisions based on the evaluation results, thereby ensuring the accuracy and rationality of the obtained business decision processing results.

[0097] In some alternative implementations, step S203 includes the following steps:

[0098] The initial business data is cleaned to obtain the corresponding first processed data.

[0099] In this embodiment, the data cleaning process includes deleting null values ​​and outliers from the initial business data to obtain the first processed data after cleaning.

[0100] The first processed data is converted to obtain the corresponding second processed data.

[0101] In this embodiment, the above-mentioned format conversion process includes: addressing the issue of inconsistent date formats by establishing a unified date format standard (such as "YYYY-MM-DD") and using data processing tools to perform batch conversion of the data. Additionally, for cases where currency units are inconsistent, such as some data being in "yuan" and others in "ten thousand yuan," the data is uniformly converted to "yuan" and corresponding numerical calculations are adjusted accordingly.

[0102] The second processed data is then validated.

[0103] In this embodiment, the data verification includes checking whether the data conforms to preset format requirements, whether there are null values, outliers, etc., and generating corresponding data verification results. The data verification results include whether the second processed data passes data verification or whether the second processed data fails data verification.

[0104] If the second processed data passes data verification, then the second processed data will be used as the target business data.

[0105] In this embodiment, if the second processed data is found to have failed data verification, the non-compliant data can be further marked and processed, such as filling in default values, correcting erroneous data, or communicating with the core business system maintenance personnel to confirm the correctness of the data.

[0106] This application cleanses the initial business data to obtain corresponding first processed data; then, it performs format conversion on the first processed data to obtain corresponding second processed data; subsequently, it verifies the second processed data; if the second processed data passes the verification, it is used as the target business data. Based on the above processing flow, this application, by performing data cleaning, format conversion, and data verification on the initial business data, can efficiently and accurately complete the preprocessing of the initial business data, effectively ensuring the accuracy and standardization of the generated target business data.

[0107] In some optional implementations of this embodiment, before step S204, the electronic device may further perform the following steps:

[0108] Acquire real-time system load data.

[0109] In this embodiment, an elastic computing power scheduling platform can be pre-built based on Kubernetes, and the platform architecture, including the configuration of compute nodes, storage nodes, network nodes, etc., can be designed. A Kubernetes cluster is installed and configured to ensure high availability and scalability. Monitoring tools are integrated to monitor the cluster's resource usage (such as CPU, memory, network bandwidth, etc.) in real time. The system's load data can be collected in real time based on the aforementioned elastic computing power scheduling platform.

[0110] A corresponding resource scheduling strategy is constructed based on the system load data.

[0111] In this embodiment, a matching resource scheduling strategy can be formulated based on the collected system load data. For example, an automatic scaling rule can be set to automatically add computing nodes when the number of service requests increases and automatically release idle computing nodes when the number of service requests decreases.

[0112] The effectiveness of the resource scheduling strategy is verified.

[0113] In this embodiment, the effectiveness of the above resource scheduling strategy can be verified through testing to ensure that the platform can concurrently process a preset number (100,000+) requests / second and control the response latency within a specified value (e.g., <200ms). Specifically, by verifying the effectiveness of the above resource scheduling strategy, if the concurrent processing capability and response latency control of the resource scheduling strategy meet the expectations, the resource scheduling strategy is determined to have passed the effectiveness verification; otherwise, the resource scheduling strategy is determined to have failed the effectiveness verification.

[0114] If the resource scheduling strategy passes the validity verification, then the corresponding model scheduling process is executed based on the resource scheduling strategy.

[0115] In this embodiment, if the above resource scheduling strategy is detected to have passed the validity verification, the corresponding model scheduling process will be executed based on the strategy content of the above resource scheduling strategy. That is, the target business evaluation model corresponding to the above business type can be called according to the resource scheduling strategy, thereby ensuring the timeliness of the business processing of the target business evaluation model.

[0116] This application acquires real-time system load data; then constructs a corresponding resource scheduling strategy based on the system load data; subsequently, it verifies the validity of the resource scheduling strategy; if the resource scheduling strategy passes the validity verification, it executes the corresponding model scheduling process based on the resource scheduling strategy. Based on the above processing flow, this application constructs a resource scheduling strategy based on real-time system load data, and after the resource scheduling strategy passes validity verification, it executes the corresponding model scheduling process based on the resource scheduling strategy. This allows subsequent calls to the target business evaluation model corresponding to the aforementioned business type through the resource scheduling strategy, thereby effectively ensuring the timeliness of business processing of the target business evaluation model.

[0117] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0118] Obtain all business processing data in the business processing process corresponding to the business processing request.

[0119] In this embodiment, all data and results from all business processing steps are pre-recorded in a database to establish a complete business processing archive, ensuring data integrity and traceability for easy subsequent querying and auditing. All business processing data contained in the business processing steps corresponding to the aforementioned business processing request can be queried from the database. Specifically, this may include user-submitted raw data, processing results, business decision records, user feedback information, etc.

[0120] Obtain the preset target indicators.

[0121] In this embodiment, the aforementioned target indicators can be set according to actual business needs, and may include indicators such as claims approval rate, claims amount distribution, and premium prediction accuracy.

[0122] Based on the target indicators, data analysis is performed on the business processing data to obtain the corresponding data analysis results.

[0123] In this embodiment, the value and trends within the aforementioned business processing data can be extracted through analysis. For example, indicators such as claims approval rate, claims amount distribution, and premium prediction accuracy can be statistically analyzed to assess the efficiency and effectiveness of business processing. An analysis report is then generated using data visualization tools and presented as the results of the data analysis to provide data support for the company's business decisions.

[0124] The business evaluation model is optimized based on the data analysis results.

[0125] In this embodiment, the business evaluation model can be optimized and adjusted based on the obtained data analysis results. Specifically, if it is found that the accuracy of the business evaluation model is low in a certain scenario, more relevant data can be collected for model fine-tuning, or new feature engineering methods can be introduced to improve model performance. At the same time, the optimized model is redeployed to the business system to continuously improve the accuracy and efficiency of business processing.

[0126] This application acquires all business processing data in the business processing process corresponding to the business processing request; then acquires preset target indicators; subsequently, it performs data analysis on the business processing data based on the target indicators to obtain corresponding data analysis results; and finally, it optimizes the business evaluation model based on the data analysis results. Based on the above processing flow, this application acquires all business processing data in the business processing process corresponding to the business processing request, performs data analysis on the business processing data based on the use of target indicators to obtain data analysis results, and then optimizes the business evaluation model based on the data analysis results. This facilitates the continuous improvement of the accuracy and efficiency of business processing based on the optimized model, thereby continuously enhancing the performance and business processing capabilities of the business system.

[0127] In some alternative implementations, the user information obtained is subject to user consent and complies with relevant laws and policies.

[0128] Furthermore, any software tools or components not belonging to our company that appear in the embodiments of this application are merely illustrative examples and do not represent actual use.

[0129] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0130] It should be emphasized that, in order to further ensure the privacy and security of the above business decision-making results, the above business decision-making results can also be stored in a blockchain node.

[0131] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0132] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0133] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0135] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0136] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of an artificial intelligence-based business processing device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0137] like Figure 3As shown, the AI-based business processing device 300 described in this embodiment includes: a receiving module 301, a collecting module 302, a preprocessing module 303, a calling module 304, an inference module 305, a processing module 306, and a return module 307. Wherein:

[0138] The receiving module 301 is used to receive a service processing request triggered by a user; wherein the service processing request carries a service type;

[0139] The collection module 302 is used to collect initial business data of the user corresponding to the business type based on a preset intelligent agent;

[0140] The preprocessing module 303 is used to preprocess the initial business data to obtain the corresponding target business data;

[0141] Module 304 is invoked to call the target business evaluation model corresponding to the business type.

[0142] The reasoning module 305 is used to perform reasoning processing on the target business data based on the target business evaluation model to obtain the corresponding evaluation result;

[0143] The processing module 306 is used to perform business decision processing on the evaluation results based on the knowledge base corresponding to the business type and the preset evaluation strategy, so as to obtain the corresponding business decision processing results.

[0144] The return module 307 is used to return the evaluation results and the business decision processing results to the user based on the intelligent agent.

[0145] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0146] In some optional implementations of this embodiment, the AI-based business processing device further includes:

[0147] The first acquisition module is used to collect a certain amount of business data related to specified business needs from a preset business system.

[0148] The annotation module is used to annotate the business data to obtain corresponding sample data;

[0149] The query module is used to query a large model in a specified vertical domain that corresponds to the business requirement from a preset model library.

[0150] The training module is used to train the large model of the specified vertical domain based on the sample data to obtain the corresponding first model;

[0151] The fine-tuning module is used to fine-tune the first model based on the business type using a preset fine-tuning strategy to obtain the corresponding second model.

[0152] A determination module is used to use the second model as the target business evaluation model.

[0153] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0154] In some optional implementations of this embodiment, the fine-tuning module includes:

[0155] The collection submodule is used to collect the corresponding specified business data based on the business type.

[0156] The filtering submodule is used to filter out the target fine-tuning strategy that matches the scenario requirements of the business type from a variety of preset fine-tuning strategies;

[0157] The fine-tuning submodule is used to fine-tune the first model based on the target fine-tuning strategy and the specified business data to obtain the corresponding processing model.

[0158] The first determining submodule is used to use the processing model as the second model.

[0159] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0160] In some optional implementations of this embodiment, the processing module 306 includes:

[0161] The submodule is invoked to call the knowledge base corresponding to the business type.

[0162] The query submodule is used to retrieve relevant information corresponding to the evaluation result based on the knowledge base.

[0163] The analysis submodule is used to analyze the evaluation results based on a preset multidimensional analysis strategy to obtain the corresponding analysis results;

[0164] A submodule is constructed to build a corresponding decision processing flow based on the relevant information and the analysis results;

[0165] The generation submodule is used to execute the decision processing flow to generate the corresponding business decision processing results.

[0166] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0167] In some optional implementations of this embodiment, the preprocessing module 303 includes:

[0168] The first processing submodule is used to perform data cleaning processing on the initial business data to obtain the corresponding first processed data.

[0169] The second processing submodule is used to perform format conversion processing on the first processed data to obtain the corresponding second processed data;

[0170] The third processing submodule is used to perform data verification on the second processed data;

[0171] The determination submodule is used to use the second processed data as the target business data if the second processed data passes data verification.

[0172] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0173] In some optional implementations of this embodiment, the AI-based business processing device further includes:

[0174] The second acquisition module is used to acquire real-time collected system load data;

[0175] The construction module is used to construct a corresponding resource scheduling strategy based on the system load data;

[0176] The verification module is used to verify the effectiveness of the resource scheduling strategy;

[0177] The execution module is used to perform corresponding model scheduling processing based on the resource scheduling strategy if the resource scheduling strategy passes the validity verification.

[0178] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0179] In some optional implementations of this embodiment, the AI-based business processing device further includes:

[0180] The third acquisition module is used to acquire all business processing data in the business processing process corresponding to the business processing request;

[0181] The fourth acquisition module is used to acquire preset target indicators;

[0182] The analysis module is used to perform data analysis on the business processing data based on the target indicators and obtain the corresponding data analysis results;

[0183] An optimization module is used to optimize the business evaluation model based on the data analysis results.

[0184] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based business processing method in the aforementioned implementation method, and will not be repeated here.

[0185] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0186] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0187] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0188] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for business processing methods based on artificial intelligence. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0189] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions of the artificial intelligence-based business processing method.

[0190] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0191] Compared with the prior art, the embodiments of this application have the following beneficial effects:

[0192] In this embodiment, the application collects initial business data from users corresponding to business types based on the use of intelligent agents, preprocesses the initial business data to obtain target business data, then uses the target business evaluation model to perform reasoning processing on the target business data to obtain evaluation results, and uses a knowledge base and preset evaluation strategies to perform business decision processing on the evaluation results to obtain business decision processing results. Subsequently, the evaluation results and business decision processing results are returned to the user, thereby enabling efficient and accurate processing of business processing requests, effectively improving business processing efficiency, and facilitating more accurate and efficient business decisions.

[0193] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence-based business processing method described above.

[0194] Compared with the prior art, the embodiments of this application have the following main advantages:

[0195] In this embodiment, the application collects initial business data from users corresponding to business types based on the use of intelligent agents, preprocesses the initial business data to obtain target business data, then uses the target business evaluation model to perform reasoning processing on the target business data to obtain evaluation results, and uses a knowledge base and preset evaluation strategies to perform business decision processing on the evaluation results to obtain business decision processing results. Subsequently, the evaluation results and business decision processing results are returned to the user, thereby enabling efficient and accurate processing of business processing requests, effectively improving business processing efficiency, and facilitating more accurate and efficient business decisions.

[0196] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0197] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A business processing method based on artificial intelligence, characterized in that, Includes the following steps: Receive a service processing request triggered by a user; wherein the service processing request carries a service type; The system collects initial business data of the user corresponding to the business type based on a preset intelligent agent. The initial business data is preprocessed to obtain the corresponding target business data; Invoke the target business evaluation model corresponding to the business type; Based on the target business evaluation model, the target business data is processed by reasoning to obtain the corresponding evaluation results; Based on the knowledge base corresponding to the business type and the preset evaluation strategy, the evaluation results are processed for business decision-making to obtain the corresponding business decision-making results. The intelligent agent returns the evaluation results and the business decision processing results to the user.

2. The business processing method based on artificial intelligence according to claim 1, characterized in that, Before the step of invoking the target business evaluation model corresponding to the business type, the method further includes: Collect a certain amount of business data related to specified business requirements from the pre-set business system; The business data is labeled to obtain corresponding sample data; Retrieve the large model for the specified vertical domain corresponding to the business requirement from the preset model library; The large model for the specified vertical domain is trained based on the sample data to obtain the corresponding first model; Based on the business type, the first model is fine-tuned using a preset fine-tuning strategy to obtain the corresponding second model; The second model is used as the target business evaluation model.

3. The business processing method based on artificial intelligence according to claim 2, characterized in that, The step of fine-tuning the first model based on the business type using a preset fine-tuning strategy to obtain the corresponding second model specifically includes: Collect the corresponding specified business data based on the business type; Select the target fine-tuning strategy that matches the scenario requirements of the business type from a variety of preset fine-tuning strategies; Based on the target fine-tuning strategy, the first model is fine-tuned using the specified business data to obtain the corresponding processing model; The processing model is used as the second model.

4. The business processing method based on artificial intelligence according to claim 1, characterized in that, The step of performing business decision processing on the evaluation results based on a knowledge base corresponding to the business type and a preset evaluation strategy to obtain the corresponding business decision processing results specifically includes: Call the knowledge base corresponding to the business type; Based on the knowledge base, relevant information corresponding to the evaluation result is retrieved; The evaluation results are analyzed based on a preset multidimensional analysis strategy to obtain corresponding analysis results. Based on the relevant information and the analysis results, a corresponding decision processing flow is constructed. The decision processing flow is executed to generate the corresponding business decision processing results.

5. The business processing method based on artificial intelligence according to claim 1, characterized in that, The step of preprocessing the initial business data to obtain the corresponding target business data specifically includes: The initial business data is cleaned to obtain the corresponding first processed data; The first processed data is converted to obtain the corresponding second processed data; Perform data verification on the second processed data; If the second processed data passes data verification, then the second processed data will be used as the target business data.

6. The business processing method based on artificial intelligence according to claim 1, characterized in that, Before the step of invoking the target business evaluation model corresponding to the business type, the method further includes: Acquire real-time system load data; Construct a corresponding resource scheduling strategy based on the system load data; The effectiveness of the resource scheduling strategy is verified. If the resource scheduling strategy passes the validity verification, then the corresponding model scheduling process is executed based on the resource scheduling strategy.

7. The business processing method based on artificial intelligence according to claim 1, characterized in that, After the step of returning the evaluation result and the business decision processing result to the user based on the intelligent agent, the method further includes: Obtain all business processing data in the business processing process corresponding to the business processing request; Obtain the preset target indicators; Based on the target indicators, data analysis is performed on the business processing data to obtain the corresponding data analysis results; The business evaluation model is optimized based on the data analysis results.

8. A business processing device based on artificial intelligence, characterized in that, include: A receiving module is used to receive a service processing request triggered by a user; wherein the service processing request carries a service type; The collection module is used to collect initial business data of the user corresponding to the business type based on a preset intelligent agent; The preprocessing module is used to preprocess the initial business data to obtain the corresponding target business data; The calling module is used to invoke the target business evaluation model corresponding to the business type. The reasoning module is used to perform reasoning processing on the target business data based on the target business evaluation model to obtain the corresponding evaluation results; The processing module is used to perform business decision processing on the evaluation results based on the knowledge base corresponding to the business type and the preset evaluation strategy, so as to obtain the corresponding business decision processing results. The return module is used to return the evaluation results and the business decision processing results to the user based on the intelligent agent.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the artificial intelligence-based business processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based business processing method as described in any one of claims 1 to 7.

Images