Insurance 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 insurance buying processing method, which comprises the steps of receiving a cargo insurance buying request; extracting a cargo list from the cargo insurance request, and verifying the cargo list; if the cargo list passes the verification, performing information identification on the cargo list to obtain target character information; performing risk scoring processing on the target text information based on the called risk assessment model to obtain a target risk score; generating a numerical value comparison result between the target risk score and a preset risk threshold value; and generating an underwriting decision result corresponding to the cargo list based on the numerical comparison result. The invention further provides an insurance processing device based on artificial intelligence, computer equipment and a storage medium. In addition, the underwriting decision result can be stored in the block chain. The method can be applied to a cargo insurance processing scene in the financial field, effectively improves the processing efficiency of cargo insurance, and guarantees the accuracy of the generated underwriting decision result.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and can be applied to the field of financial technology, and in particular to insurance processing methods, devices, computer equipment and storage media based on artificial intelligence. Background Art

[0002] Against the backdrop of global economic integration and the booming e-commerce, the global logistics industry is experiencing unprecedented rapid growth. With the increasing frequency of international trade and the continuous expansion of logistics networks, the volume of cargo transported has increased dramatically, and the types of cargo are becoming increasingly diverse, covering a wide range of areas, from high-value electronics and precision machinery to everyday consumer goods.

[0003] However, the traditional cargo insurance underwriting process relies on cumbersome rules-based processing. During the risk assessment phase after the insurance information is entered, insurance companies typically conduct cargo risk assessments based on pre-set rules and limited data sources. This approach often fails to fully and accurately reflect the cargo's actual risk profile, especially when faced with complex and changing transportation environments and new types of cargo. Furthermore, the results generation process in the traditional cargo insurance underwriting process is often inefficient. Because of its reliance on rule-based review and decision-making, insurance companies are prone to processing delays and inconsistent decisions when processing a large number of insurance applications. This results in shippers and logistics companies being unable to obtain insurance coverage in a timely manner, impacting the efficiency and reliability of logistics operations. The efficiency bottlenecks of the traditional cargo insurance underwriting process are particularly prominent when it comes to insuring large quantities of cargo in bulk, failing to meet the modern logistics industry's demand for fast, efficient, and accurate insurance services.

[0004] In summary, the traditional freight insurance underwriting process has significant deficiencies in processing efficiency and accuracy, and can no longer meet the urgent demand for freight insurance services in the modern logistics industry. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to propose an insurance processing method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problems of low processing efficiency and low accuracy in the existing freight insurance underwriting process.

[0006] First, an AI-based insurance processing method is provided, comprising:

[0007] receiving a cargo insurance request to be processed, wherein the cargo insurance request includes a cargo list;

[0008] Extracting the cargo list from the cargo insurance request, and verifying the cargo list based on a preset verification strategy;

[0009] If the cargo list passes the verification, the cargo list is identified to obtain the corresponding target text information;

[0010] Calling a preset risk assessment model; wherein the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data;

[0011] Performing risk scoring on the target text information based on the risk assessment model to obtain a corresponding target risk score;

[0012] Obtaining a preset risk threshold and generating a numerical comparison result between the target risk score and the risk threshold;

[0013] An insurance decision result corresponding to the cargo list is generated based on the numerical comparison result.

[0014] In a second aspect, an insurance processing device based on artificial intelligence is provided, comprising:

[0015] A receiving module, configured to receive a cargo insurance request to be processed; wherein the cargo insurance request carries a cargo list;

[0016] a processing module, configured to extract the cargo list from the cargo insurance request and verify the cargo list based on a preset verification strategy;

[0017] an identification module, configured to identify information on the cargo list and obtain corresponding target text information if the cargo list passes verification;

[0018] A first calling module is used to call a preset risk assessment model; wherein the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data;

[0019] An evaluation module, configured to perform risk scoring processing on the target text information based on the risk assessment model to obtain a corresponding target risk score;

[0020] A first generating module is configured to obtain a preset risk threshold and generate a numerical comparison result between the target risk score and the risk threshold;

[0021] The second generating module is used to generate an insurance decision result corresponding to the cargo list based on the numerical comparison result.

[0022] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned artificial intelligence-based insurance processing method are implemented.

[0023] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based insurance processing method are implemented.

[0024] In the solution implemented by the above-mentioned artificial intelligence-based insurance processing method, device, computer equipment and storage medium, a cargo insurance request to be processed is first received; wherein, the cargo insurance request carries a cargo list; then, the cargo list is extracted from the cargo insurance request, and the cargo list is verified based on a preset verification strategy; if the cargo list passes the verification, information recognition is performed on the cargo list to obtain corresponding target text information; then a preset risk assessment model is called; wherein, the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data; subsequently, the target text information is risk-scored based on the risk assessment model to obtain a corresponding target risk score; further, a preset risk threshold is obtained, and a numerical comparison result between the target risk score and the risk threshold is generated; finally, an insurance decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application extracts a cargo list from a received cargo insurance request to be processed, and verifies the cargo list based on the use of a verification strategy. When it is detected that the cargo list passes the verification, the cargo list is identified to obtain target text information, and then the target text information is risk-scored based on the use of a risk assessment model to obtain a target risk score, and a numerical comparison result between the target risk score and a preset risk threshold is generated, and then an underwriting decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application automatically and accurately generates an underwriting decision result corresponding to the cargo list by performing a risk assessment on the cargo list based on the use of a risk assessment model to obtain a target risk score, and then analyzing the target risk score, thereby effectively improving the processing efficiency of cargo insurance and ensuring the accuracy of the generated underwriting decision result. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0027] Figure 2 is a flow chart of an embodiment of an artificial intelligence-based insurance processing method according to the present application;

[0028] Figure 3 This is a structural diagram of an embodiment of an artificial intelligence-based insurance processing device according to the present application;

[0029] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0031] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0033] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0034] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0035] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0036] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0037] It should be noted that the artificial intelligence-based insurance processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based insurance processing device is generally set in the server / terminal device.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0039] Continue to refer Figure 2 , shows a flow chart of an embodiment of an insurance processing method based on artificial intelligence according to the present application. According to different needs, the order of the steps in the flow chart can be changed, and some steps can be omitted. The insurance processing method based on artificial intelligence provided by the embodiment of the present application can be applied to any scenario where cargo insurance is required, and the insurance processing method based on artificial intelligence can be applied to products in these scenarios, for example, cargo insurance processing in the field of financial insurance. The insurance processing method based on artificial intelligence includes the following steps:

[0040] Step S201: receiving a cargo insurance request to be processed; wherein the cargo insurance request carries a cargo list.

[0041] In this embodiment, the insurance processing method based on artificial intelligence is run on the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain the cargo list via a wired connection or a wireless connection. It should be noted that the wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future. The execution entity of this application is an insurance processing system, which can be simply referred to as the system. This application can be applied to business scenarios in the financial insurance field where insurance companies process insurance for goods. The cargo insurance request can be issued by a logistics company or a cargo owner. The system can receive the insurance request via an API interface, a web form, or a file upload. The cargo insurance request includes a cargo list, which may include at least information such as the cargo name, quantity, value, transportation route, and estimated transportation time. For example, a logistics company needs to insure a batch of electronic products it is about to transport. These electronic products include mobile phones, tablets, etc., which are valuable and fragile.

[0042] The system also features a flexible batch insurance interface, allowing users to upload multiple insurance requests simultaneously. The system automatically allocates resources for parallel processing, significantly reducing response times. It also offers customized insurance plans to meet the specific needs of diverse customers. Furthermore, leveraging cloud computing technology, the system establishes a cross-departmental and cross-enterprise collaborative platform, enabling seamless integration between insurance companies, logistics companies, and shippers. Real-time data synchronization and transparent, traceable processes strengthen trust and efficiency among partners.

[0043] Step S202: extract the cargo list from the cargo insurance request, and verify the cargo list based on a preset verification strategy.

[0044] In this embodiment, the cargo insurance request can be parsed to extract the cargo list included in the request. The specific implementation process of verifying the cargo list based on the preset verification strategy will be further described in detail in subsequent embodiments of this application and will not be elaborated on here. Furthermore, verifying the cargo list based on the verification strategy will produce a corresponding verification result, which may include whether the cargo list has passed verification or whether the cargo list has failed verification.

[0045] Step S203: If the cargo list passes the verification, information recognition is performed on the cargo list to obtain corresponding target text information.

[0046] In this embodiment, the specific implementation process of the above-mentioned information recognition of the cargo list to obtain the corresponding target text information will be further described in detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0047] Step S204: calling a preset risk assessment model.

[0048] In this embodiment, the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data. The specific process of constructing the risk assessment model will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0049] Step S205 : performing risk scoring processing on the target text information based on the risk assessment model to obtain a corresponding target risk score.

[0050] In this embodiment, the target text information can be input into the risk assessment model. The risk assessment model will perform calculations based on the input features (i.e., the target text information) and the trained parameters, and output a risk score, i.e., the target risk score. The risk score is a numerical value that reflects the degree of risk that the goods may face during transportation. The higher the score, the greater the risk. The risk score can also be explained to explain the reasons for the high or low score and possible risk factors. Based on the risk score, the insurance company can make underwriting decisions, such as approving or rejecting the insurance, or requesting adjustments to the insurance terms.

[0051] Step S206: obtaining a preset risk threshold, and generating a numerical comparison result between the target risk score and the risk threshold.

[0052] In this embodiment, a risk threshold is pre-established based on actual underwriting requirements. The specific value of this risk threshold is not limited and can be dynamically generated or adjusted. A numerical comparison result between the target risk score and the risk threshold can be generated by numerically comparing the target risk score with the risk threshold. The numerical comparison result may include the target risk score being greater than or equal to the risk threshold, or the target risk score being less than the risk threshold.

[0053] Step S207: generating an insurance decision result corresponding to the cargo list based on the numerical comparison result.

[0054] In this embodiment, the specific implementation process of generating the insurance decision result corresponding to the cargo list based on the numerical comparison result will be further described in detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0055] The present application first receives a cargo insurance request to be processed; wherein, the cargo insurance request carries a cargo list; then, the cargo list is extracted from the cargo insurance request, and the cargo list is verified based on a preset verification strategy; if the cargo list passes the verification, information recognition is performed on the cargo list to obtain corresponding target text information; then a preset risk assessment model is called; wherein, the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data; subsequently, the target text information is risk-scored based on the risk assessment model to obtain a corresponding target risk score; further, a preset risk threshold is obtained, and a numerical comparison result between the target risk score and the risk threshold is generated; finally, an insurance decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application extracts a cargo list from a received cargo insurance request to be processed, and verifies the cargo list based on the use of a verification strategy. When it is detected that the cargo list passes the verification, the cargo list is identified to obtain target text information, and then the target text information is risk-scored based on the use of a risk assessment model to obtain a target risk score, and a numerical comparison result between the target risk score and a preset risk threshold is generated, and then an underwriting decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application automatically and accurately generates an underwriting decision result corresponding to the cargo list by performing a risk assessment on the cargo list based on the use of a risk assessment model to obtain a target risk score, and then analyzing the target risk score, thereby effectively improving the processing efficiency of cargo insurance and ensuring the accuracy of the generated underwriting decision result.

[0056] In some optional implementations, before step S204, the electronic device may further perform the following steps:

[0057] Acquire pre-collected multi-dimensional data; wherein the multi-dimensional data at least includes historical claims data, cargo characteristics data, transportation route data and weather forecast data.

[0058] In this embodiment, multi-dimensional data such as historical claims data, cargo characteristics data, transportation route data, and weather forecast data can be collected from data sources such as insurance company databases, logistics company transportation records, and third-party data providers.

[0059] Corresponding multi-dimensional sample data is constructed based on the multi-dimensional data.

[0060] In this embodiment, the specific implementation process of constructing corresponding multi-dimensional sample data based on the multi-dimensional data will be further described in detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0061] The multidimensional sample data is divided into a training set and a test set.

[0062] In this embodiment, the division ratio of the training set and the test set can be determined based on the data size and characteristics of the multi-dimensional sample data. For example, a division ratio of 70% training set and 30% test set can be adopted, or a division ratio of 80% training set and 20% test set can be adopted. Alternatively, a random sampling method can be used to divide the processed multi-dimensional sample data into a training set and a test set. This helps to ensure that the training set and the test set are statistically similar, thereby improving the generalization ability of the model. In addition, when dividing the multi-dimensional sample data, it is necessary to ensure that the data in the training set and the test set are consistent in terms of feature distribution, label distribution, etc. This can be achieved through methods such as stratified sampling to avoid the impact of data bias on model performance.

[0063] Call the preset machine learning model.

[0064] In this embodiment, an appropriate machine learning model can be selected based on task requirements and data characteristics. For example, any one of a logistic regression model, a decision tree model, a random forest model, a gradient boosting tree model, etc. can be selected as the above-mentioned machine learning model. The parameters of the model are initialized based on the selected model algorithm. These parameters may include the learning rate, the number of iterations, the depth of the tree, the number of layers and nodes in the neural network, etc.

[0065] The machine learning model is trained and evaluated based on the training set and the test set, respectively, to obtain a trained first machine learning model.

[0066] In this embodiment, a training set is input into a machine learning model, and model parameters are adjusted through iterative optimization to minimize the loss function. During training, the model's training loss and validation loss are monitored to determine whether the model is overfitting or underfitting. Model parameters are then adjusted based on the changes in loss during training and the results of model performance evaluation. For example, if the model is overfitting, the learning rate can be reduced, the regularization term can be increased, or the model complexity can be reduced. If the model is underfitting, the model complexity can be increased, more training data can be added, or the feature engineering method can be adjusted. Appropriate evaluation metrics are then selected based on the task requirements and data characteristics. For example, for classification tasks, metrics such as accuracy, recall, F1 score, receiver operating characteristic (ROC) curve, and area under the curve (AUC) can be selected. Subsequently, the test set data is input into the trained model, and the evaluation metrics of the model on the test set are calculated. These metrics reflect the model's performance on unseen data. Based on the evaluation results, the model's performance is analyzed, and the model that meets the performance criteria is selected as the first machine learning model. If the model performs poorly, it is necessary to return to the feature engineering or model selection steps for further adjustments. For example, you can try different feature combinations, feature transformation methods, or model algorithms to improve the performance of the model until you obtain a model that meets the performance requirements and uses it as the first machine learning model.

[0067] Based on a preset tuning strategy, the first machine learning model is tuned to obtain a corresponding second machine learning model.

[0068] In this embodiment, the stability and generalization ability of the first machine learning model can be further verified using cross-validation. K-fold cross-validation and leave-one-out cross-validation can be used as cross-validation methods. Cross-validation can be used to determine the model's performance under different data partitions, thereby providing a more comprehensive assessment of the model's performance. The stability and generalization ability of the first machine learning model are then analyzed based on the cross-validation results. If the performance of the first machine learning model under different data partitions varies significantly, this indicates that the first machine learning model has poor stability. If the first machine learning model performs well on the training set but poorly on the test set, this indicates that the first machine learning model has poor generalization ability. Based on the validation results, the first machine learning model is then tuned. Tuning methods include adjusting hyperparameters, adding or removing features, and trying different model algorithms. Through continuous tuning, the model's performance and stability can be improved until a second machine learning model with the performance and stability requirements is obtained. Model tuning is an iterative optimization process. After each tuning, the model's performance needs to be re-evaluated, and model parameters or feature engineering methods are further adjusted based on the evaluation results. Through continuous iterative optimization, a model with even better performance can be obtained.

[0069] The second machine learning model is used as the risk assessment model.

[0070] This application obtains pre-collected multi-dimensional data; then constructs corresponding multi-dimensional sample data based on the multi-dimensional data, and divides the multi-dimensional sample data into a training set and a test set; then calls a preset machine learning model; subsequently trains and evaluates the machine learning model based on the training set and the test set, respectively, to obtain a trained first machine learning model; further performs model tuning on the first machine learning model based on a preset tuning strategy, to obtain a corresponding second machine learning model; finally, uses the second machine learning model as the risk assessment model. This application constructs multi-dimensional sample data based on pre-collected multi-dimensional data, and divides the multi-dimensional sample data into a training set and a test set; then trains and evaluates the machine learning model based on the use of the training set and the test set, respectively, to obtain a trained first machine learning model; then performs model tuning on the first machine learning model based on the use of the tuning strategy, thereby achieving efficient and accurate construction of a risk assessment model that meets the requirements, effectively improving the efficiency of constructing the risk assessment model, and ensuring the model effect of the generated risk assessment model.

[0071] In some optional implementations of this embodiment, constructing corresponding multi-dimensional sample data based on the multi-dimensional data includes the following steps:

[0072] Data preprocessing is performed on the multi-dimensional data to obtain corresponding processed data.

[0073] In this embodiment, the above-mentioned data preprocessing includes data cleaning, data conversion and data normalization. Specifically, data cleaning includes: processing missing values, outliers and duplicate values to ensure data quality. Data conversion includes: converting non-numeric data (such as cargo name, mode of transportation, etc.) into numerical data for model processing. For example, using one-hot encoding (One-Hot Encoding) or label encoding (Label Encoding). Data normalization includes: standardizing or normalizing numerical data to eliminate dimensionality effects and improve model training efficiency.

[0074] Perform feature extraction processing on the processed data to obtain corresponding first feature data.

[0075] In this embodiment, the feature extraction process includes extracting features that have a significant impact on risk assessment from the processed data. For example, features such as cargo value, perishability (which can be indirectly represented by cargo type, packaging method, etc.), transportation distance, road conditions (which can be represented by historical traffic data, road grade, etc.), and weather conditions (such as temperature, humidity, wind speed, and precipitation probability).

[0076] Get the preset feature selection algorithm.

[0077] In this embodiment, there is no specific limitation on the selection of the above-mentioned feature selection algorithm, which can be determined according to actual business needs. For example, algorithms such as correlation analysis and feature importance evaluation can be used.

[0078] Perform feature selection processing on the first feature data based on the feature selection algorithm to obtain corresponding second feature data.

[0079] In this embodiment, feature selection processing can be performed on the first feature data according to a selected feature selection algorithm to select a target number of features that contribute most to model performance from the first feature data and use them as the second feature data. The numerical value of the target number is not specifically limited and can be determined based on actual business needs.

[0080] The second feature data is used as the multi-dimensional sample data.

[0081] The present application obtains corresponding processed data by performing data preprocessing on the multidimensional data; then performs feature extraction processing on the processed data to obtain corresponding first feature data; then obtains a preset feature selection algorithm, and performs feature selection processing on the first feature data based on the feature selection algorithm to obtain corresponding second feature data; and subsequently uses the second feature data as the multidimensional sample data. The present application obtains processed data by performing data preprocessing on the multidimensional data, then performs feature extraction processing on the processed data to obtain first feature data, and then performs feature selection processing on the first feature data based on the use of a feature selection algorithm to obtain second feature data as the final multidimensional sample data, effectively ensuring the accuracy of the generated multidimensional sample data. This is conducive to the subsequent use of multidimensional sample data to train the risk assessment model, which can effectively reduce model complexity, improve training efficiency, and avoid overfitting.

[0082] In some optional implementations, the verifying the cargo list based on a preset verification strategy in step S202 includes the following steps:

[0083] Perform a completeness check on the cargo list.

[0084] In this embodiment, the integrity check includes checking whether the cargo manifest contains all necessary information fields, such as cargo name, quantity, value, weight, and volume, and generating a corresponding integrity check result. The integrity check result may include whether the cargo manifest passes the integrity check or fails the integrity check. In addition, the system will mark missing fields and prompt the user to add them.

[0085] If the cargo list passes the integrity check, the format of the cargo list is checked.

[0086] In this embodiment, the format verification includes verifying the correct format of the information in the cargo manifest. For example, quantities should be numeric, values should be in currency format, and dates should conform to a specific date format, and generating corresponding format verification results. The format verification results may include whether the cargo manifest passes the format verification or fails the format verification. Furthermore, for incorrectly formatted information, the system will convert it or prompt the user to correct it.

[0087] If the goods list passes the format check, a logic check is performed on the goods list.

[0088] In this embodiment, the logic check includes checking the information in the cargo list for logical contradictions. For example, it checks whether the total value of the goods matches the sum of the values of each item, whether the quantity of goods is a positive number, and generates a corresponding logic check result. The logic check result may include whether the cargo list passes the logic check or fails the logic check. In addition, if the information contains logical errors, the system will prompt the user to verify and correct it.

[0089] If the goods list passes the logic check, the goods list is repeatedly checked.

[0090] In this embodiment, the duplicate check includes checking whether there are duplicate items in the cargo list and generating a corresponding duplicate check result. The duplicate check result may include whether the cargo list passes the duplicate check or fails the duplicate check. In addition, for duplicate items, the system prompts the user to merge or delete them.

[0091] If the goods list passes the repeated verification, it is determined that the goods list passes the verification; otherwise, it is determined that the goods list fails the verification.

[0092] In this embodiment, the cargo list is determined to have passed the verification only when it is detected that the cargo list has passed the integrity check, format check, logic check, and duplication check at the same time. Otherwise, the cargo list is determined to have failed the verification.

[0093] The present application performs integrity verification on the cargo list; if the cargo list passes the integrity verification, the cargo list is formatted; if the cargo list passes the format verification, the cargo list is logically verified; if the cargo list passes the logical verification, the cargo list is repeated; if the cargo list passes the repeated verification, the cargo list is determined to have passed the verification, otherwise it is determined that the cargo list has not passed the verification. The present application performs integrity verification, format verification, logical verification, and repeated verification on the cargo list, thereby realizing intelligent and accurate completion of the verification process for the cargo list, and only when it is detected that the cargo list has passed the integrity verification, format verification, logical verification, and repeated verification at the same time, will the cargo list be determined to have passed the verification, thereby effectively ensuring the integrity, accuracy, standardization, and reliability of the cargo list.

[0094] In some optional implementations, step S203 includes the following steps:

[0095] The cargo list is subjected to character recognition based on a preset character recognition strategy to obtain corresponding first text information.

[0096] In this embodiment, the above-mentioned character recognition strategy may specifically adopt OCR (Optical Character Recognition) recognition technology. By using OCR recognition technology, text recognition can be performed on the cargo list in scanned or image format, and the corresponding first text information can be extracted.

[0097] The first text information is preprocessed to obtain corresponding second text information.

[0098] In this embodiment, the extracted first text information can be further preprocessed by utilizing NLP (natural language processing) technology, including word segmentation, part-of-speech tagging, named entity recognition, etc., to accurately identify key information such as the name, quantity, value, transportation route, and estimated transportation time of the goods, and use it as the corresponding second text information.

[0099] Perform format conversion on the second text information to obtain corresponding third text information.

[0100] In this embodiment, the second text information may be converted into a standardized data format, such as JSON or XML format, to facilitate subsequent processing, thereby obtaining corresponding third text information.

[0101] The third text information is used as the target text information.

[0102] The present application performs text recognition on the cargo list based on a preset character recognition strategy to obtain the corresponding first text information; then pre-processes the first text information to obtain the corresponding second text information; then performs format conversion processing on the second text information to obtain the corresponding third text information; and subsequently uses the third text information as the target text information. The present application performs text recognition on the cargo list based on the use of a character recognition strategy to obtain the first text information, then pre-processes the first text information to obtain the second text information, and then performs format conversion processing on the second text information, thereby achieving efficient and accurate completion of the information recognition processing for the cargo list, further ensuring the accuracy and standardization of the generated target text information.

[0103] In some optional implementations of this embodiment, step S207 includes the following steps:

[0104] Determine whether the numerical comparison result is that the target risk score is less than the risk threshold.

[0105] In this embodiment, the numerical comparison result includes whether the target risk score is greater than or equal to the risk threshold, or whether the target risk score is less than the risk threshold. Content analysis of the numerical comparison result can be performed to determine whether the numerical comparison result indicates that the target risk score is less than the risk threshold.

[0106] If so, a first underwriting decision result approving the insurance corresponding to the cargo list is generated.

[0107] In this embodiment, if it is detected that the numerical comparison result is that the target risk score is less than the risk threshold, it indicates that the target risk score corresponding to the above-mentioned cargo list is within an acceptable range, then the system will automatically approve the insurance and generate a first underwriting decision result indicating approval of the insurance.

[0108] If not, a second underwriting decision result of rejecting insurance corresponding to the cargo list is generated.

[0109] In this embodiment, if the numerical comparison result indicates that the target risk score is greater than or equal to the risk threshold, indicating that the target risk score corresponding to the cargo list is outside the acceptable range, the system will reject insurance and generate a second underwriting decision result indicating a rejection of insurance. Furthermore, the system may further request the logistics company or cargo owner corresponding to the cargo list to adjust the insurance terms (e.g., increase the insured amount, raise the premium, etc.) and provide detailed decision feedback to the logistics company or cargo owner, including the reason for the rejection or adjustment and the recommended insurance terms.

[0110] This application determines whether the numerical comparison result indicates that the target risk score is less than the risk threshold; if so, a first underwriting decision result is generated corresponding to the cargo list, approving the insurance; if not, a second underwriting decision result is generated corresponding to the cargo list, rejecting the insurance. This application analyzes the numerical comparison result between the target risk score generated by the risk assessment model and the risk threshold, and can then automatically and accurately generate an underwriting decision result corresponding to the cargo list based on the obtained numerical comparison result, effectively ensuring the accuracy of the generated underwriting decision result.

[0111] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0112] Determine whether the underwriting decision result is approval of underwriting.

[0113] In this embodiment, the content of the underwriting decision result is approval or rejection of underwriting. The content of the underwriting decision result can be analyzed to determine whether the underwriting decision result is approval of underwriting.

[0114] If yes, get the preset policy generation strategy.

[0115] In this embodiment, the policy generation strategy includes the following: Upon approval of the underwriting decision, the system automatically generates the corresponding policy. The policy details key terms such as the insured cargo, insured amount, premium, transportation route, and insurance period. The policy generation process also involves interacting with the insurance company's core systems to obtain the latest insurance terms and rates.

[0116] The insurance policy generation process is performed on the cargo list based on the insurance policy generation strategy to obtain a corresponding target insurance policy.

[0117] In this embodiment, the policy generation process for the above-mentioned cargo list may be executed according to the processing steps corresponding to the policy content of the above-mentioned policy generation policy, thereby obtaining the corresponding target policy.

[0118] Get the preset target output mode.

[0119] In this embodiment, there is no specific limitation on the selection of the above-mentioned target output mode, which can be determined according to actual business needs, for example, it can include email, system message or any other mode.

[0120] The target insurance policy is output-processed based on the target output method.

[0121] In this embodiment, the generated target insurance policy can be sent to the logistics company or cargo owner that issued the cargo insurance request based on the selected target output method. The sent target insurance policy will be stored in PDF or other readable format for easy confirmation and storage by the logistics company or cargo owner.

[0122] This application determines whether the underwriting decision result is an approved underwriting; if so, obtains a preset policy generation strategy; then performs policy generation processing on the cargo list based on the policy generation strategy to obtain a corresponding target policy; then obtains a preset target output method; and subsequently outputs the target policy based on the target output method. After detecting that the generated underwriting decision result is an approved underwriting, this application will intelligently and automatically perform policy generation processing on the cargo list based on the use of the policy generation strategy and obtain the corresponding target policy, and will output the target policy based on the use of the target output method, effectively improving the processing efficiency of policy generation and improving the processing intelligence of policy output.

[0123] In some optional implementations, the user information obtained is obtained with the user's consent and complies with relevant laws and policies.

[0124] In addition, any software tools or components not provided by our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0125] In addition, the bulk insurance scheme for freight insurance proposed in this application has brought about disruptive changes to the logistics industry through deep technological integration and business process innovation. It not only greatly improves the efficiency and accuracy of insurance and reduces operating costs, but also improves the competitiveness and market adaptability of insurance products through intelligent risk control. In the future, with the further integration of emerging technologies such as the Internet of Things and blockchain, this solution is expected to achieve a higher level of automation, transparency and security, safeguard the security of the global logistics supply chain, and open a new chapter in smart logistics insurance. Furthermore, the bulk insurance scheme for freight insurance proposed in this application, with its innovative technological highlights and significant application value, is expected to become a key force in promoting the digital transformation of the logistics insurance industry and promote the efficient and sustainable development of the entire industry chain.

[0126] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean 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.

[0127] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned underwriting decision results, the above-mentioned underwriting decision results can also be stored in a node of a blockchain.

[0128] The blockchain referred to in this application refers to a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (to prevent counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0129] The embodiments of the present 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 knowledge to achieve optimal results.

[0130] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0131] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0132] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified 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 of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0133] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an insurance processing device based on artificial intelligence, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0134] like Figure 3 As shown, the artificial intelligence-based insurance processing device 300 of this embodiment includes: a receiving module 301, a processing module 302, an identification module 303, a first calling module 304, an evaluation module 305, a first generating module 306, and a second generating module 307. Among them:

[0135] The receiving module 301 is configured to receive a cargo insurance request to be processed, wherein the cargo insurance request carries a cargo list;

[0136] Processing module 302, configured to extract the cargo list from the cargo insurance request and verify the cargo list based on a preset verification strategy;

[0137] The recognition module 303 is configured to perform information recognition on the cargo list to obtain corresponding target text information if the cargo list passes the verification;

[0138] A first calling module 304 is configured to call a preset risk assessment model; wherein the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data;

[0139] An evaluation module 305 is configured to perform risk scoring processing on the target text information based on the risk assessment model to obtain a corresponding target risk score;

[0140] A first generating module 306 is configured to obtain a preset risk threshold and generate a numerical comparison result between the target risk score and the risk threshold;

[0141] The second generating module 307 is configured to generate an insurance decision result corresponding to the cargo list based on the numerical comparison result.

[0142] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0143] In some optional implementations of this embodiment, the artificial intelligence-based insurance processing device further includes:

[0144] A first acquisition module is configured to acquire pre-collected multi-dimensional data; wherein the multi-dimensional data includes at least historical claims data, cargo characteristics data, transportation route data, and weather forecast data;

[0145] A construction module, configured to construct corresponding multi-dimensional sample data based on the multi-dimensional data;

[0146] A partitioning module, configured to partition the multi-dimensional sample data into a training set and a test set;

[0147] The second calling module is used to call the preset machine learning model;

[0148] A training module, configured to train and evaluate the machine learning model based on the training set and the test set, respectively, to obtain a trained first machine learning model;

[0149] A tuning module, configured to perform model tuning processing on the first machine learning model based on a preset tuning strategy to obtain a corresponding second machine learning model;

[0150] A determination module is used to use the second machine learning model as the risk assessment model.

[0151] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0152] In some optional implementations of this embodiment, the building blocks include:

[0153] A first preprocessing submodule, configured to perform data preprocessing on the multi-dimensional data to obtain corresponding processed data;

[0154] An extraction submodule, configured to perform feature extraction processing on the processed data to obtain corresponding first feature data;

[0155] Acquisition submodule, used to obtain the preset feature selection algorithm;

[0156] A selection submodule, configured to perform feature selection processing on the first feature data based on the feature selection algorithm to obtain corresponding second feature data;

[0157] The first determining submodule is configured to use the second feature data as the multi-dimensional sample data.

[0158] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0159] In some optional implementations of this embodiment, the processing module 302 includes:

[0160] A first check submodule, configured to perform integrity check on the cargo list;

[0161] A second check submodule is configured to perform a format check on the goods list if the goods list passes the integrity check;

[0162] a third check submodule, configured to perform a logic check on the goods list if the goods list passes the format check;

[0163] a fourth check submodule, configured to perform a repeat check on the goods list if the goods list passes the logic check;

[0164] The determination submodule is configured to determine that the goods list has passed the verification if the goods list passes the repeated verification, and otherwise determine that the goods list has failed the verification.

[0165] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0166] In some optional implementations of this embodiment, the identification module 303 includes:

[0167] a recognition submodule, configured to perform character recognition on the cargo list based on a preset character recognition strategy to obtain corresponding first text information;

[0168] A second preprocessing submodule, configured to preprocess the first text information to obtain corresponding second text information;

[0169] a conversion submodule, configured to perform format conversion processing on the second text information to obtain corresponding third text information;

[0170] The second determining submodule is configured to use the third text information as the target text information.

[0171] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0172] In some optional implementations of this embodiment, the numerical comparison result includes that the target risk score is greater than or equal to the risk threshold, or that the target risk score is less than the risk threshold; the second generating module 307 includes:

[0173] A first judgment submodule is configured to judge whether the numerical comparison result shows that the target risk score is less than the risk threshold;

[0174] a first generating submodule, configured to generate a first underwriting decision result approving underwriting corresponding to the cargo list if yes;

[0175] The second generating submodule is configured to generate a second underwriting decision result of rejecting insurance corresponding to the cargo list if no.

[0176] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0177] In some optional implementations of this embodiment, the artificial intelligence-based insurance processing device further includes:

[0178] A judgment module, used to judge whether the underwriting decision result is approval of underwriting;

[0179] The second acquisition module is used to obtain a preset insurance policy generation strategy if yes;

[0180] A third generation module is configured to perform policy generation processing on the cargo list based on the policy generation strategy to obtain a corresponding target policy;

[0181] The third acquisition module is used to obtain a preset target output mode;

[0182] An output module is used to perform output processing on the target insurance policy based on the target output method.

[0183] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based insurance processing method in the aforementioned embodiment, and will not be repeated here.

[0184] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0185] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 having components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform 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.

[0186] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0187] 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 can 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 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (SMC), a secure digital (SD) card, a flash memory card, etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for an artificial intelligence-based insurance processing method. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0188] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for executing the artificial intelligence-based insurance processing method.

[0189] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0190] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0191] In an embodiment of the present application, the present application extracts a cargo list from a received cargo insurance request to be processed, and verifies the cargo list based on the use of a verification strategy. When it is detected that the cargo list passes the verification, the cargo list is identified to obtain target text information, and then the target text information is risk-scored based on the use of a risk assessment model to obtain a target risk score, and a numerical comparison result between the target risk score and a preset risk threshold is generated, and then an insurance decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application automatically and accurately generates an insurance decision result corresponding to the cargo list by performing a risk assessment on the cargo list based on the use of a risk assessment model to obtain a target risk score, and then analyzing the target risk score, thereby effectively improving the processing efficiency of cargo insurance and ensuring the accuracy of the generated insurance decision result.

[0192] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based insurance processing method.

[0193] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0194] In an embodiment of the present application, the present application extracts a cargo list from a received cargo insurance request to be processed, and verifies the cargo list based on the use of a verification strategy. When it is detected that the cargo list passes the verification, the cargo list is identified to obtain target text information, and then the target text information is risk-scored based on the use of a risk assessment model to obtain a target risk score, and a numerical comparison result between the target risk score and a preset risk threshold is generated, and then an insurance decision result corresponding to the cargo list is generated based on the numerical comparison result. The present application automatically and accurately generates an insurance decision result corresponding to the cargo list by performing a risk assessment on the cargo list based on the use of a risk assessment model to obtain a target risk score, and then analyzing the target risk score, thereby effectively improving the processing efficiency of cargo insurance and ensuring the accuracy of the generated insurance decision result.

[0195] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course 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 the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0196] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. An insurance processing method based on artificial intelligence, characterized in that: The steps include: receiving a cargo insurance request to be processed, wherein the cargo insurance request includes a cargo list; Extracting the cargo list from the cargo insurance request, and verifying the cargo list based on a preset verification strategy; If the cargo list passes the verification, the cargo list is identified to obtain the corresponding target text information; Calling a preset risk assessment model; wherein the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data; Performing risk scoring on the target text information based on the risk assessment model to obtain a corresponding target risk score; Obtaining a preset risk threshold and generating a numerical comparison result between the target risk score and the risk threshold; An insurance decision result corresponding to the cargo list is generated based on the numerical comparison result.

2. The artificial intelligence-based insurance processing method according to claim 1, characterized in that: Before the step of calling the preset risk assessment model, the method further includes: Acquiring pre-collected multi-dimensional data; wherein the multi-dimensional data includes at least historical claims data, cargo characteristics data, transportation route data, and weather forecast data; Constructing corresponding multi-dimensional sample data based on the multi-dimensional data; Dividing the multidimensional sample data into a training set and a test set; Call the preset machine learning model; Performing training and evaluation on the machine learning model based on the training set and the test set, respectively, to obtain a trained first machine learning model; Performing model tuning on the first machine learning model based on a preset tuning strategy to obtain a corresponding second machine learning model; The second machine learning model is used as the risk assessment model.

3. The artificial intelligence-based insurance processing method according to claim 2, characterized in that: The step of constructing corresponding multi-dimensional sample data based on the multi-dimensional data specifically includes: Performing data preprocessing on the multi-dimensional data to obtain corresponding processed data; Performing feature extraction processing on the processed data to obtain corresponding first feature data; Get the preset feature selection algorithm; Performing feature selection processing on the first feature data based on the feature selection algorithm to obtain corresponding second feature data; The second feature data is used as the multi-dimensional sample data.

4. The artificial intelligence-based insurance processing method according to claim 1, characterized in that: The step of verifying the cargo list based on a preset verification strategy specifically includes: Conducting integrity check on the cargo list; If the cargo list passes the integrity check, then the format of the cargo list is checked; If the cargo list passes the format check, then performing a logic check on the cargo list; If the goods list passes the logic check, then repeat the check on the goods list; If the goods list passes the repeated verification, it is determined that the goods list passes the verification; otherwise, it is determined that the goods list fails the verification.

5. The artificial intelligence-based insurance processing method according to claim 1, characterized in that: The step of performing information recognition on the cargo list to obtain corresponding target text information specifically includes: Performing character recognition on the cargo list based on a preset character recognition strategy to obtain corresponding first text information; Preprocessing the first text information to obtain corresponding second text information; performing format conversion processing on the second text information to obtain corresponding third text information; The third text information is used as the target text information.

6. The artificial intelligence-based insurance processing method according to claim 1, characterized in that: The numerical comparison result includes that the target risk score is greater than or equal to the risk threshold, or that the target risk score is less than the risk threshold; The step of generating an insurance decision result corresponding to the cargo list based on the numerical comparison result specifically includes: Determining whether the numerical comparison result shows that the target risk score is less than the risk threshold; If yes, generating a first underwriting decision result approving underwriting corresponding to the cargo list; If not, a second underwriting decision result of rejecting insurance corresponding to the cargo list is generated.

7. The artificial intelligence-based insurance processing method according to claim 1, characterized in that: After the step of generating an insurance decision result corresponding to the cargo list based on the numerical comparison result, the method further includes: Determining whether the underwriting decision result is approval of underwriting; If so, obtain the preset policy generation strategy; Performing policy generation processing on the cargo list based on the policy generation strategy to obtain a corresponding target policy; Get the preset target output mode; The target insurance policy is output-processed based on the target output method.

8. An insurance processing device based on artificial intelligence, characterized in that: include: A receiving module, configured to receive a cargo insurance request to be processed; wherein the cargo insurance request carries a cargo list; a processing module, configured to extract the cargo list from the cargo insurance request and verify the cargo list based on a preset verification strategy; an identification module, configured to identify information on the cargo list and obtain corresponding target text information if the cargo list passes verification; A first calling module is used to call a preset risk assessment model; wherein the risk assessment model is a model obtained by training a machine learning model based on preset multi-dimensional sample data; An evaluation module, configured to perform risk scoring processing on the target text information based on the risk assessment model to obtain a corresponding target risk score; A first generating module is configured to obtain a preset risk threshold and generate a numerical comparison result between the target risk score and the risk threshold; The second generating module is used to generate an insurance decision result corresponding to the cargo list based on the numerical comparison result.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of the insurance processing method based on artificial intelligence 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 insurance processing method according to any one of claims 1 to 7.

Images