Internet Insurance Product Recommendation Method, Device and System

Abstract

The present invention discloses an Internet insurance product recommendation method, system and device, which extracts the full-text information in digital files or collects data prepared for word segmentation, inputs the data into a tagging function, performs word segmentation training on the information based on regular matching to generate tags, and according to the input parameters of the model, after integrating the tag data and the original data, inputs them into the model for entity recognition model training to produce a result set and corresponding scoring results. Through model training, the present invention solves the problems of timeliness and cost of information entity annotation for a large number of digital files, and enables non-algorithm personnel to quickly implement operations through a program implementation method, which belongs to a great innovation in the tool category. It can be widely applied to data annotation in the digital application field, provides convenience for Internet services and resource docking, etc., and greatly saves time and capital costs.

Description

Technical Field

[0001] This application is a divisional application of a Chinese patent application with an application date of July 27, 2021, an application number of CN202110848292.4, and an invention title of "Digital File Information Entity Annotation and Recognition Method, Device and System". Background Art

[0002] With the popularization of Internet technology, more and more applications have emerged. The Internet + application has become an effective means for people and society to obtain more equal and convenient medical services. For the recognition of digital files, from manual recognition to text automatic recognition and then to the application of artificial intelligence technology, due to the extremely high requirements for professional knowledge personnel, not only professional medical knowledge is needed, but also knowledge of algorithms or development, so it is not convenient enough and will greatly increase the burden. Summary of the Invention

[0003] Aiming at the above defects, the technical problem to be solved by the present invention is how to perceive and recognize various information of users with the help of artificial intelligence technology and natural language processing technology and model the subsequent decision-making process to achieve automatic execution and intelligent decision-making.

[0004] Aiming at the above defects, the purpose of the present invention is to provide an Internet insurance product recommendation method, system, electronic device, computer storage medium and program product.

[0005] Applied to the server side, extract the full text information in the digital file or collect the data prepared for word segmentation, input the data into the label function, perform word segmentation training on the information based on regular matching and generate labels. According to the input parameters of the model, after integrating the label data and the original data, input them into the model for entity recognition model training to produce a result set and corresponding scoring results.

[0006] Preferably, create a task according to the requirements, associate the training model, allocate computing space, and then upload the data set to be labeled.

[0007] Preferably, process the plain text into quadruple data in a table through a word list, including keyword, entity type, position, and text subscript.

[0008] Preferably, take the data as the input of the label function, and generate an entity for each row of data after training through the Snorkel model.

[0009] Preferably, it specifically includes:

[0010] S1. Extract the full text information from the text material input by the user;

[0011] S2. Perform word segmentation processing on the text information;

[0012] S3. Process the plain text into quadruple data in a table through a thesaurus.

[0013] S4. Associate the Snorkel training model and allocate computing space.

[0014] S5. Upload the dataset to be labeled.

[0015] S6. Generate label functions and perform model training.

[0016] S7. Output corresponding entities for the input data through Snorkel training.

[0017] S8. Integrate the labeled data with the original data to generate data for Bert training.

[0018] Preferably, the digital file is the coronary angiography report form and / or the coronary angiography case report.

[0019] Preferably, it includes:

[0020] S201. Extract full-text information, including the coronary angiography medical record number, from the coronary angiography report form and / or the coronary angiography case report through OCR.

[0021] S202. Process the plain text into quadruple data in a table through a thesaurus, numbered 1, 2,..., and the thesaurus is the left anterior descending branch, the right circumflex branch,...

[0022] S203. Use the data obtained in step S202 as the input of the label function, and output an entity for each row of data after training by Snorkel. The coronary angiography report form corresponds to the right coronary artery label, and the coronary angiography medical record number corresponds to the conventional position angiography shows label.

[0023] S204. Integrate the labeled data and the original data to generate data for Bert training.

[0024] The present invention provides an Internet insurance product recommendation method, which is applied to an Internet medical platform. Based on the user authorization obtained by the terminal device, it collects the digital files uploaded by the user and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collects data prepared for word segmentation. The data is input into the label function, and the information is segmented and trained based on regular matching to generate labels. According to the input parameters of the model, the label data and the original data are integrated and then input into the model for entity recognition model training to output a result set and corresponding scoring results, and a specific solution is output to the user in combination with the application products of the Internet medical platform.

[0025] Preferably, the Internet medical platform combines the result set and the corresponding scoring results through the diagnostic decision-making model, uses the rule engine to simulate the insurance claim review, executes the decision tree logic, and obtains and outputs an intelligent review conclusion to the user.

[0026] Preferably, the Internet medical platform combines the result set and the corresponding scoring results to calculate the recommendation decision factor, makes a decision through factor calculation, and uses the recommendation algorithm to obtain the insurance recommendation combination.

[0027] Preferably, the Internet medical platform combines the result set and the corresponding scoring results based on the rehabilitation data model, and gives relevant rehabilitation devices and recommended solutions through model calculation.

[0028] Preferably, the Internet medical platform combines the result set and the corresponding scoring results with the national hospital big database to give a recommended treatment plan or connect with medical experts.

[0029] Preferably, the Internet medical platform creates a task according to the requirement, associates the training model, allocates the computing space, and then uploads the data set to be labeled.

[0030] The present invention provides an Internet insurance product recommendation system, including at least one terminal device, at least one Internet medical platform, and at least one server. The terminal device collects the digital files uploaded by the user. The Internet medical platform obtains the user's authorization permission based on the terminal device, collects the digital files uploaded by the user and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the digital files to obtain the full-text information or collects the data prepared for word segmentation. The data is input into the tagging function, and the information is segmented and trained based on regular matching to generate tags. According to the input parameters of the model, the tag data and the original data are integrated and then input into the model for entity recognition model training to produce a result set and the corresponding scoring results, and specific solutions are output to the user in combination with the application products of the Internet medical platform.

[0031] Preferably, create a task according to the requirement, associate the training model, allocate the computing space, and then upload the data set to be labeled.

[0032] Preferably, the pure text is processed into the data quadruple data in the table through the word list, including the keyword, entity type, position, and text subscript.

[0033] The present invention provides a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0034] The present invention provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0035] The present invention provides an electronic device, comprising:

[0036] a processor; and

[0037] a memory configured to store computer-executable instructions, which when executed cause the processor to perform the following operations:

[0038] Based on the terminal device obtaining user authorization permission, the terminal device collects digital files uploaded by the user. The Internet medical platform obtains user authorization permission based on the terminal device, collects digital files uploaded by the user and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collects data prepared for word segmentation. The data is input into the label function, and word segmentation training is performed on the information based on regular matching to generate labels. According to the input parameters of the model, after integrating the label data and the original data, it is input into the model for entity recognition model training to produce a result set and corresponding scoring results, and a specific solution is output to the user in combination with the application products of the Internet medical platform.

[0039] Through model training, the present invention solves the problems of timeliness and cost of information entity annotation for a large number of digital files, and enables non-algorithm personnel to quickly implement operations through a program implementation method. It belongs to a great innovation in the tool category and can be widely applied to data annotation in the field of medical and health, providing convenience for medical insurance, health care, medical resource docking, etc., and saving a large amount of time and capital costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0041] Figure 1 Shows a schematic structural diagram of an embodiment of the Internet insurance product recommendation method of the present invention;

[0042] Figure 2 Shows a schematic structural diagram of another embodiment of the Internet insurance product recommendation method of the present invention;

[0043] Figure 3 Shows a schematic structural diagram of another embodiment of the Internet insurance product recommendation method of the present invention;

[0044] Figure 4 Shows a schematic flowchart of another embodiment of the Internet insurance product recommendation method of the present invention;

[0045] Figure 5Shows a schematic flowchart of an embodiment of the Internet insurance product recommendation system of the present invention. Detailed implementation manners

[0046] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. To make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present invention by showing examples of the present invention.

[0047] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0048] An Internet insurance product recommendation method provided by an embodiment of this specification extracts full-text information from digital files or collects data prepared for word segmentation, inputs the data into a tagging function, performs word segmentation training on the information based on regular matching and generates tags. According to the input parameters of the model, after integrating the tag data and the original data, it is input into the model for entity recognition model training to produce a result set and corresponding scoring results.

[0049] In some embodiments, a task is created according to requirements, a training model is associated, and the data set to be labeled is uploaded after allocating computing space.

[0050] In some embodiments, pure text is processed into data quadruples in a table through a word list, including keywords, entity types, positions, and text subscripts.

[0051] In some embodiments, the data is used as the input of the tagging function, and an entity is generated for each row of data after training through the Snorkel model.

[0052] Among mental illnesses, many mental illnesses and sleep disorders are caused by cardiovascular problems. Taking the coronary arteries of the cardiovascular system as an example, the digital file is this report of coronary angiography and / or the case report of coronary angiography.

[0053] As Figure 1 shown, an embodiment of the present specification provides an Internet insurance product recommendation method, including:

[0054] S101. Extract the full-text information in the digital file or collect the data prepared for word segmentation;

[0055] S102. Input the data into the tagging function;

[0056] S103. Perform word segmentation training on the information based on regular matching and generate tags;

[0057] S104. After integrating the tag data and the original data according to the input parameters of the model;

[0058] S105. Input it into the model for entity recognition model training to produce a result set and corresponding scoring results.

[0059] As Figure 2 shown, an embodiment of the present specification provides an Internet insurance product recommendation method, including:

[0060] S201. Extract the full-text information through OCR from this report of coronary angiography and / or the case report of coronary angiography, including the case number of coronary angiography;

[0061] S202. Through the word list, process the plain text into the data quadruple data in the table, numbered 1, 2,..., and the word list is the left anterior descending branch, the right circumflex branch,...;

[0062] S203. Use the data obtained in step S202 as the input of the tagging function. After training by Snorkel, an entity is produced for each row of data. The coronary angiography report corresponds to the label of the right coronary artery, and the case number of coronary angiography corresponds to the label shown in the conventional position angiography;

[0063] S204. Integrate the labeled data and the original data to generate the data for Bert training.

[0064] As Figure 3 shown, an embodiment of the present specification provides an Internet insurance product recommendation method, specifically including:

[0065] S1. Extract the full-text information from the text material input by the user;

[0066] S2. Perform word segmentation processing on the text information;

[0067] S3. Process the plain text into quadruple data in a table through a word list;

[0068] S4. Associate the Snorkel training model and allocate computing space;

[0069] S5. Upload the dataset to be labeled;

[0070] S6. Generate label functions and perform model training;

[0071] S7. Output corresponding entities for the input data through Snorkel training;

[0072] S8. Integrate the labeled data with the original data to generate data for Bert training.

[0073] This specification provides an embodiment of an Internet insurance product recommendation method, which is applied to an Internet medical platform. Based on the terminal device, it obtains user authorization permission, collects the digital files uploaded by the user and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collects data prepared for word segmentation, inputs the data into the label function, performs word segmentation training on the information based on regular matching and generates labels. According to the input parameters of the model, after integrating the label data and the original data, it is input into the model for entity recognition model training to produce a result set and corresponding scoring results, and outputs specific solutions to the user in combination with the application products of the Internet medical platform.

[0074] In some embodiments, the Internet medical platform combines the result set and the corresponding scoring results through a diagnostic decision model, uses a rule engine to simulate insurance claim review, performs decision tree logic execution, and obtains and outputs an intelligent review conclusion to the user.

[0075] In some embodiments, the Internet medical platform combines the result set and the corresponding scoring results to calculate a recommendation decision factor, makes a decision through factor calculation, and obtains an insurance recommendation combination using a recommendation algorithm.

[0076] In some embodiments, the Internet medical platform combines the result set and the corresponding scoring results based on a rehabilitation data model, and gives relevant rehabilitation devices and recommended solutions through model calculation.

[0077] In some embodiments, the Internet medical platform combines the result set and the corresponding scoring results with the national hospital big database, and gives a recommended treatment plan or connects with medical experts.

[0078] In some embodiments, the Internet medical platform creates a task according to the requirement, associates the training model, allocates computing space, and then uploads the dataset to be labeled.

[0079] Such asFigure 4 As shown, this specification provides an embodiment of an Internet insurance product recommendation system, including at least one terminal device, at least one Internet medical platform, and at least one server. The terminal device collects digital files uploaded by users. The Internet medical platform obtains user authorization based on the terminal device, collects the digital files uploaded by users, and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collects data prepared for word segmentation. The data is input into a tagging function, and word segmentation training is performed on the information based on regular matching to generate tags. According to the input parameters of the model, after integrating the tag data and the original data, it is input into the model for entity recognition model training to produce a result set and corresponding scoring results, and a specific solution is output to the user in combination with the application products of the Internet medical platform.

[0080] In some embodiments, a task is created according to requirements, a training model is associated, and after allocating computing space, the data set to be labeled is uploaded.

[0081] In some embodiments, the pure text is processed into data quadruples in a table through a word list, including keywords, entity types, positions, and text subscripts.

[0082] In a specific example, the insurance includes health insurance and life insurance, and health condition notifications are included in various insurances.

[0083] In a specific example, corresponding rehabilitation devices or suggestions are given through a recommendation algorithm model and imported into the corresponding third-party e-commerce platform.

[0084] In a specific example, in combination with the result set, the corresponding scoring results, and the national hospital big database, recommended treatment plans or connections to medical experts are given. These experts include hospitals or doctors on the online medical platform.

[0085] In some specific examples, such as neurasthenia, sleep disorders, cardiovascular diseases, etc., products or health care products such as electrocardiographs, health pillows, and melatonin that help relieve stress and improve sleep quality can be given.

[0086] In some specific examples, the digital files uploaded by users by the system include but are not limited to diagnosis certificates, case reports, prescriptions, and hospitalization records.

[0087] A computer-readable storage medium provided by an embodiment of this specification stores computer programs / instructions thereon. When the computer programs / instructions are executed by a processor, the following method is implemented: obtaining user authorization permission based on a terminal device, collecting digital files uploaded by a user and sending them to a data center processing system of a background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collect data prepared for word segmentation, inputs the data into a tagging function, performs word segmentation training on the information based on regular expression matching to generate tags, integrates the tag data and the original data according to the input parameters of the model, inputs the integrated data into the model for entity recognition model training to produce a result set and corresponding scoring results, and outputs a specific solution to the user in combination with the application products of an Internet medical platform.

[0088] A computer program product provided by an embodiment of this specification includes computer programs / instructions. When the computer programs / instructions are executed by a processor, the following method is implemented: obtaining user authorization permission based on a terminal device, collecting digital files uploaded by a user and sending them to a data center processing system of a background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collect data prepared for word segmentation, inputs the data into a tagging function, performs word segmentation training on the information based on regular expression matching to generate tags, integrates the tag data and the original data according to the input parameters of the model, inputs the integrated data into the model for entity recognition model training to produce a result set and corresponding scoring results, and outputs a specific solution to the user in combination with the application products of an Internet medical platform.

[0089] An electronic device provided by an embodiment of this specification includes:

[0090] a processor; and

[0091] a memory configured to store computer-executable instructions, and when the executable instructions are executed, the processor performs the following operations:

[0092] obtaining user authorization permission based on a terminal device, collecting digital files uploaded by a user and sending them to a data center processing system of a background server. The data center processing system performs OCR recognition on the digital files to obtain full-text information or collect data prepared for word segmentation, inputs the data into a tagging function, performs word segmentation training on the information based on regular expression matching to generate tags, integrates the tag data and the original data according to the input parameters of the model, inputs the integrated data into the model for entity recognition model training to produce a result set and corresponding scoring results, and outputs a specific solution to the user in combination with the application products of an Internet medical platform.

[0093] Through model training, the present invention solves the problems of timeliness and cost in information entity annotation of a large number of digital files, and enables non-algorithm personnel to quickly implement operations through a program implementation method, which belongs to a great innovation in the tool category and can be widely applied to data annotation in the field of medical and health, providing convenience for medical insurance, health care, medical resource docking, etc., and saving a large amount of time and capital costs.

[0094] For the convenience of description, when describing the above device, various units are described separately according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0095] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0097] The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the functions specified in one or more of the acts Figure 1 one or more acts and / or boxes Figure 1 specified in one or more boxes or boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the acts Figure 1 one or more acts and / or boxes Figure 1 specified in one or more boxes or boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0101] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

[0102] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0103] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0104] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference can be made to the corresponding part of the method embodiment for the relevant content.

[0105] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An Internet insurance product recommendation method, applied to an Internet medical platform, characterized in that A data center processing system that obtains user authorization and permission based on a terminal device, collects case reports uploaded by users and sends them to the background server for processing. The data center processing system performs OCR recognition on the case reports to obtain full-text information or collects data prepared for word segmentation. Through a thesaurus, the plain text is processed into quadruple data in a table, associated with a Snorkel training model, and computing space is allocated. The dataset to be labeled is uploaded, label functions are generated, and model training is performed. Through Snorkel training, corresponding entities are produced for the input data. The labeled data is fused with the original data to generate data for Bert training, which is input into the model for entity recognition model training to produce a result set and corresponding scoring results. The Internet medical platform combines the result set and the corresponding scoring results through a diagnostic decision model, simulates insurance claim review using a rule engine, executes decision tree logic, and obtains and outputs an intelligent review conclusion to the user. The recommendation decision factor is calculated based on the result set and the corresponding scoring results, and through factor calculation and decision-making, an insurance recommendation combination is obtained using a recommendation algorithm, specifically including: S1. Extract full-text information from the text material input by the user; S2. Perform word segmentation on the text information; S3. Through a thesaurus, process the plain text into quadruple data in a table; S4. Associate with the Snorkel training model and allocate computing space; S5. Upload the dataset to be labeled; S6. Generate label functions and perform model training; S7. Through Snorkel training, produce corresponding entities for the input data; S8. Fuse the labeled data with the original data to generate data for Bert training.

2. The method for recommending Internet insurance products according to claim 1, wherein The Internet medical platform creates tasks according to requirements, associates with the training model, allocates computing space, and then uploads the dataset to be labeled.

3. The method for recommending Internet insurance products according to claim 1 or 2, characterized in that The plain text is processed into quadruple data in a table through a thesaurus, including keywords, entity types, positions, and text subscripts.

4. The method for recommending Internet insurance products according to claim 1 or 2, characterized in that The data is used as the input of the label function, and through the training of the Snorkel model, an entity is generated for each row of data.

5. An Internet insurance product recommendation system, characterized in that, Including at least one terminal device, at least one Internet medical platform, and at least one server. The terminal device collects digital files uploaded by users. The Internet medical platform obtains user authorization permission based on the terminal device, collects case reports uploaded by users, and sends them to the data center processing system of the background server. The data center processing system performs OCR recognition on the case reports to obtain full-text information or collects data prepared for word segmentation. Through a word list, the plain text is processed into quadruple data in a table, associated with the Snorkel training model, and computing space is allocated. The data set to be labeled is uploaded, label functions are generated, and model training is carried out. Through Snorkel training, corresponding entities are output for the input data. The labeled data is fused with the original data to generate data for Bert training, which is input into the model for entity recognition model training to produce a result set and corresponding scoring results; the Internet medical platform combines the result set and corresponding scoring results through a diagnostic decision-making model, uses a rule engine to simulate insurance claim review, performs decision tree logic execution, and obtains and outputs an intelligent review conclusion to the user; combines the result set and corresponding scoring results to calculate a recommendation decision factor, makes a decision through factor calculation, and uses a recommendation algorithm to obtain an insurance recommendation combination, specifically including: S1. Extract full-text information from the text material input by the user; S2. Perform word segmentation processing on the text information; S3. Through a word list, process the plain text into quadruple data in a table; S4. Associate the Snorkel training model and allocate computing space; S5. Upload the data set to be labeled; S6. Generate label functions and perform model training; S7. Through Snorkel training, output corresponding entities for the input data; S8. Fuse the labeled data with the original data to generate data for Bert training.

6. The system according to claim 5, wherein Create a task according to requirements, associate the training model, and upload the data set to be labeled after allocating computing space.

7. The system according to claim 5 or 6, characterized in that, Process the plain text into quadruple data in a table through a word list, including keywords, entity types, positions, and text subscripts.

8. A computer-readable storage medium having computer programs / instructions stored thereon, characterized in that, When the computer program / instructions are executed by a processor, the steps of the method described in any one of claims 1-4 are implemented.

9. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the steps of the method described in any one of claims 1-4 are implemented.

10. An electronic device, comprising: A processor; And A memory configured to store computer-executable instructions, and when the executable instructions are executed, the processor is caused to perform the following operations: A data center processing system that obtains user authorization and permission based on a terminal device, collects case reports uploaded by users and sends them to the background server for processing. The data center processing system performs OCR recognition on the case reports to obtain full-text information or collects data prepared for word segmentation. Through a thesaurus, the plain text is processed into quadruple data in a table, associated with a Snorkel training model and computing space is allocated. The data set to be labeled is uploaded, label functions are generated and model training is carried out. Through Snorkel training, corresponding entities are produced for the input data. The labeled data is fused with the original data to generate data for Bert training, which is input into the model for entity recognition model training to produce a result set and corresponding scoring results. The Internet medical platform combines the result set and the corresponding scoring results through a diagnostic decision-making model, uses a rule engine to simulate insurance claim review, performs decision tree logic execution, and obtains and outputs an intelligent review conclusion to the user; calculates recommendation decision factors based on the result set and the corresponding scoring results, makes a decision through factor calculation, and uses a recommendation algorithm to obtain an insurance recommendation combination, specifically including: S1. Extract full-text information from the text material input by the user; S2. Perform word segmentation on the text information; S3. Through a thesaurus, process the plain text into quadruple data in a table; S4. Associate with the Snorkel training model and allocate computing space; S5. Upload the data set to be labeled; S6. Generate label functions and perform model training; S7. Through Snorkel training, produce corresponding entities for the input data; S8. Fuse the labeled data with the original data to generate data for Bert training.

Images