Medical online question answering method and system based on block chain, terminal and storage medium

Abstract

The invention relates to the technical field of intelligent questioning and answering, and particularly provides a block chain-based medical online questioning and answering method and system, a terminal and a storage medium, and the method comprises the steps: dividing material data into a plurality of categories according to organs to which the material data belong, and uploading the material data of the plurality of categories to a plurality of corresponding block chains; establishing a mapping relationship between the block chain and the category; analyzing a target category of the query statement, and determining a target block chain based on the target category and the mapping relationship; generating a query request based on the query statement, and sending the query request to the target block chain; and obtaining target material data returned by the target block chain based on the query request, and generating reply data based on the target material data. According to the method, the material data are classified and uploaded to the block chains of the corresponding categories, ordered management and safe sharing of the material data are achieved, the target material data are queried from the block chains of the corresponding categories during query, the data processing amount is reduced, and the data retrieval efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent question and answer, and specifically relates to a medical online question and answer method, system, terminal and storage medium based on blockchain. Background Art

[0002] With the growing demand for medical consultation services from patients, the traditional face-to-face consultation model has been unable to meet the widespread and urgent health consultation needs due to its time, location constraints and limited professional coverage. Given the high degree of professionalism in the medical field, medical consultation has more stringent requirements on data accuracy compared to general business consultation. This means that when building a medical online question-and-answer system, the medical data used must undergo a strict review process to ensure the accuracy of the response content, thereby effectively reducing the risk of misleading.

[0003] With the rapid advancement of medical informatization, the amount of medical data has shown an explosive growth trend, which not only provides rich resources for precision medicine and personalized health services, but also brings about major challenges in how to efficiently mine and extract high-value information from massive data. Therefore, developing efficient data processing and analysis technologies to achieve accurate screening and utilization of medical data has become a key issue that needs to be broken through in the current field of medical informatization. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a medical online question-and-answer method, system, terminal and storage medium based on blockchain to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a medical online question-and-answer method based on blockchain, comprising: Divide the material data into multiple categories according to the organs they belong to, and upload the material data of multiple categories to multiple corresponding blockchains respectively; Establish a mapping relationship between blockchain and categories; Parsing the target category of the query statement, and determining the target blockchain based on the target category and the mapping relationship; Generate a query request based on the query statement, and send the query request to the target blockchain; The target material data returned by the target blockchain based on the query request is obtained, and the response data is generated based on the target material data.

[0006] In an optional implementation, the material data is divided into multiple categories according to the organs to which they belong, and the material data of the multiple categories are uploaded to multiple corresponding blockchains respectively, including: Acquire the latest material data from the shared database, wherein the material data is a material mapping consisting of symptoms, lesion locations, disease names, and diagnosis and treatment plans; Determining the category of the material data based on the organ to which the lesion location belongs, and determining the corresponding blockchain based on the category of the material data; Taking the latest material data as the query target, querying the original material data from the corresponding blockchain; Determine whether the latest material data is consistent with the original material data: If the two are consistent, the latest material data is ignored; If the two are inconsistent, a review task for the latest material data is generated, and after the review is passed, the original material data is updated to the latest material data.

[0007] In an optional implementation, establishing a mapping relationship between a blockchain and a category includes: Establish a mapping relationship between blockchain addresses and corresponding categories, and cache the mapping relationship in a specified directory.

[0008] In an optional implementation, parsing the target category of the query statement, and determining the target blockchain based on the target category and the mapping relationship, includes: Use keyword extraction technology to extract keywords and sentence intentions from query sentences; extracting category keywords from the keywords, and determining a target category of the query statement based on the category keywords; A blockchain having a mapping relationship with the target category is determined as the target blockchain.

[0009] In an optional implementation, generating a query request based on the query statement, and sending the query request to the target blockchain includes: Generate a query mapping, wherein the query mapping includes symptoms, lesion location, disease name, and diagnosis and treatment plan, wherein the symptoms, lesion location, disease name, and diagnosis and treatment plan are all variable parameter items; Fill the keyword into the query mapping, and mark the corresponding variable parameter item in the query mapping as a target query item based on the statement intention, A query request is generated based on the query mapping, and the query request is sent to the target blockchain.

[0010] In an optional embodiment, the method further comprises: If the category keyword does not exist in the keyword, the query request is sent to all blockchains; A smart contract is deployed in each blockchain in advance. After receiving a query request, the blockchain executes the smart contract, calculates the matching degree between the material data in the first N blocks and the query request, and if the matching degree exceeds a preset first matching threshold, it is recorded as 1; if the matching degree does not exceed the first matching threshold, it is recorded as 0; and the proportion of blocks recorded as 1 is calculated. If the proportion reaches a preset proportion threshold, the query request continues to be executed; if the proportion does not reach the preset proportion threshold, the query request is terminated on the current blockchain; if the matching degree reaches a preset second matching threshold, the corresponding material data is directly used as the target material data of the query request.

[0011] In an optional implementation, obtaining target material data returned by the target blockchain based on the query request, and generating reply data based on the target material data includes: generating response data based on the target material data using a large language model; The reply data is pushed to the display interface.

[0012] In a second aspect, the present invention provides a medical online question-and-answer system based on blockchain, comprising: A classification storage module is used to classify the material data into multiple categories according to the organs to which they belong, and upload the material data of multiple categories to multiple corresponding blockchains respectively; A mapping establishment module is used to establish a mapping relationship between blockchain and categories; A target determination module, used to parse the target category of the query statement, and determine the target blockchain based on the target category and the mapping relationship; A query processing module, used to generate a query request based on the query statement, and send the query request to the target blockchain; The reply generation module is used to obtain the target material data returned by the target blockchain based on the query request, and generate reply data based on the target material data.

[0013] In a third aspect, a terminal is provided, including: processor, memory, wherein: The memory is used to store computer programs. The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0014] According to a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the methods described in the above aspects.

[0015] The beneficial effect of the present invention is that the blockchain-based medical online question-and-answer method, system, terminal and storage medium provided by the present invention classify the material data and upload them to the blockchain of the corresponding category, so as to realize the orderly management and secure sharing of the material data, and query the target material data from the blockchain of the corresponding category during the query, thereby reducing the data processing volume and improving the data retrieval efficiency.

[0016] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0019] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0020] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0023] The blockchain-based medical online question-and-answer method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the blockchain-based medical online question-and-answer system runs in the computer device.

[0024] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1The execution subject can be a medical online question-and-answer system based on blockchain. According to different requirements, the order of the steps in the flowchart can be changed, and some can be omitted.

[0025] like Figure 1 As shown, the method includes: Step 110, dividing the material data into multiple categories according to the organs to which they belong, and uploading the material data of the multiple categories to multiple corresponding blockchains respectively; Step 120, establishing a mapping relationship between blockchain and category; Step 130, parsing the target category of the query statement, and determining the target blockchain based on the target category and the mapping relationship; Step 140: Generate a query request based on the query statement, and send the query request to the target blockchain; Step 150: Obtain target material data returned by the target blockchain based on the query request, and generate response data based on the target material data.

[0026] To facilitate understanding of the present invention, the following is a further description of the medical online question and answer method based on blockchain provided by the present invention based on the principle of the medical online question and answer method based on blockchain, combined with the process of building a medical online question and answer system in the embodiment.

[0027] Specifically, the blockchain-based medical online question-and-answer method includes: S1. Divide the material data into multiple categories according to the organs they belong to, and upload the material data of multiple categories to multiple corresponding blockchains respectively.

[0028] In one embodiment of the present invention, a material data classification and storage method includes: obtaining the latest material data from a shared database, wherein the material data is a material mapping consisting of symptoms, lesion location, disease name, and treatment plan; determining the category of the material data based on the organ to which the lesion location belongs, and determining the corresponding blockchain based on the category of the material data; taking the latest material data as a query target, querying the original material data from the corresponding blockchain; determining whether the latest material data is consistent with the original material data: if the two are consistent, ignoring the latest material data; if the two are inconsistent, generating an audit task for the latest material data, and updating the original material data to the latest material data after the audit is passed.

[0029] Specifically, the process includes the following: Real-time data capture: Use data stream processing technologies, such as Apache Kafka, to capture new or updated material data from a shared database in real time.

[0030] Intelligent classification: Combined with natural language processing (NLP) technology, it automatically analyzes the description of the lesion location, accurately determines the organ to which it belongs, and classifies the material data accordingly.

[0031] Blockchain selection: Automatically match the predefined blockchain list according to the data category to ensure that each category of data is uploaded to the corresponding secure and efficient blockchain.

[0032] Data verification and update: Before uploading, the consistency between the latest material data and the data on the original blockchain is checked through hash comparison. If they are different, the review process is triggered. After the review is passed, the data is updated using smart contracts or blockchain features (such as Ethereum's gas mechanism) to ensure the timeliness and accuracy of the data.

[0033] S2. Establish a mapping relationship between blockchain and category.

[0034] Establish a mapping relationship between blockchain addresses and corresponding categories, and cache the mapping relationship in a specified directory.

[0035] Specifically, dynamic mapping update: With the addition of new categories or the expansion of the blockchain network, the mapping relationship needs to be dynamically adjusted. Establish a mapping relationship management system to support administrators or automated scripts to add, delete, modify and query the mapping table. Cache optimization: To improve query efficiency, cache the mapping relationship in an in-memory database (such as Redis), and set a reasonable expiration and update strategy to ensure the consistency of cached data and blockchain status.

[0036] S3. parse the target category of the query statement, and determine the target blockchain based on the target category and the mapping relationship.

[0037] The keyword extraction technology is used to extract keywords and sentence intentions from the query statement; category keywords are extracted from the keywords, and the target category of the query statement is determined based on the category keywords; and the blockchain having a mapping relationship with the target category is determined as the target blockchain.

[0038] Specifically, the following steps are included: Advanced query parsing: Use semantic analysis technology to improve query parsing capabilities and accurately understand user intent, especially fuzzy or complex query requirements.

[0039] Optimize mapping search: Use efficient data structures such as hash tables or balanced trees to speed up the search process of mapping relationships and quickly locate the target blockchain.

[0040] S4. Generate a query request based on the query statement, and send the query request to the target blockchain.

[0041] Generate a query mapping, the query mapping including symptoms, lesion location, disease name, and treatment plan, wherein symptoms, lesion location, disease name, and treatment plan are all variable parameter items; fill the keywords into the query mapping, and mark the corresponding variable parameter items in the query mapping as target query items based on the statement intention, generate a query request based on the query mapping, and send the query request to the target blockchain.

[0042] The specific method of generating a query mapping and constructing a query request includes: Define the query mapping template: First, clarify the structure of the query mapping, which contains multiple fields, such as "symptoms", "lesion location", "disease name" and "diagnosis and treatment plan". Each field is designed as a variable parameter item that can receive different values. This template is the basic framework for building query requests.

[0043] Parsing query statements: Using natural language processing (NLP) techniques such as named entity recognition (NER) and semantic role labeling (SRL), the input query statement is deeply analyzed. This step aims to extract keywords and phrases related to symptoms, lesion locations, disease names, and treatment plans, and understand the user's query intent.

[0044] Keyword and query mapping matching: Match the parsed keywords with the variable parameter items in the query mapping template. For example, if the query statement mentions "cough" and "chest pain", these keywords will be filled in the corresponding positions of the "symptom" field respectively.

[0045] Mark target query items: Based on the overall intent of the sentence, intelligently determine which fields the user is most concerned about, that is, which are the "target query items" that need to be queried in focus. This can be achieved by analyzing emphasis words, question words, or contextual information in the sentence. For example, if the query sentence is "Query for detailed diagnosis and treatment plans for lung cancer lesion locations in the lungs", then "Disease name" (lung cancer) and "lesion location" (lungs) and "diagnosis and treatment plans" will be marked as target query items.

[0046] Constructing a query request: Based on the filled and labeled query mapping, a specific query request is constructed. This request will clearly specify the fields to be queried, the corresponding keywords, and the priority or importance of the query.

[0047] Query request optimization: Before sending a query request, some optimization operations can be performed, such as removing redundant query conditions, adjusting the query order to conform to the storage structure of data on the blockchain, etc., to improve query efficiency.

[0048] Formatting of query requests: Ensure that the format of the query request complies with the requirements of the smart contract or query interface on the target blockchain, including data type, encoding method, etc.

[0049] In addition, if there is no category keyword in the keyword, the query request is sent to all blockchains; a smart contract is deployed in each blockchain in advance, and the blockchain executes the smart contract after receiving the query request, and calculates the matching degree between the material data in the first N blocks and the query request. If the matching degree exceeds the preset first matching threshold, it is recorded as 1; if the matching degree does not exceed the first matching threshold, it is recorded as 0; the proportion of blocks recorded as 1 is calculated, and if the proportion reaches the preset proportion threshold, the query request continues to be executed; if the proportion does not reach the preset proportion threshold, the query request is terminated on the current blockchain; if the matching degree reaches the preset second matching threshold, the corresponding material data is directly used as the target material data of the query request.

[0050] After sending the query request to all blockchains, the nodes of each blockchain process the query request in parallel. Taking one of the blockchains as an example, after receiving the query request, the data contained in the query request is similarly calculated with the material data of the first block to obtain the matching degree. If the matching degree reaches the second matching threshold, the material data of the first block is directly returned to the request sender as the target material data of the query request, and the query request is determined to be completed; if the matching degree does not reach the second matching degree, the matching degree is compared with the first matching threshold. If the matching degree exceeds the preset first matching threshold, it is recorded as 1, and if the matching degree does not exceed the first matching threshold, it is recorded as 0; continue to calculate the matching degree between the material data of the second block and the data contained in the query request, and so on, until the Nth block is processed, where N is the set number, which can be set to 10. If the Nth block is executed, the proportion of the blocks recorded as 1 is counted. If the proportion reaches the preset proportion threshold (such as 80%), the query request is continued to be executed. If the proportion does not reach the preset proportion threshold, the query request is terminated in the current blockchain and the remaining blocks are no longer processed. This can greatly save computing power and reduce the amount of data processing. Concurrent processing also improves data retrieval efficiency.

[0051] S5. Obtain target material data returned by the target blockchain based on the query request, and generate response data based on the target material data.

[0052] Generate reply data based on the target material data using a large language model; and push the reply data to a display interface.

[0053] Specifically, the following steps are included: Data fusion and screening: Aggregate the material data returned by each blockchain, and use machine learning models to further screen and optimize to improve the accuracy and relevance of the responses.

[0054] Personalized answer generation: Based on large language models (such as the GPT series), combined with user historical query records and contextual information, more personalized and easy-to-understand answer data is generated.

[0055] Multimodal display: In addition to text replies, it supports multimodal data display such as images and charts to improve user experience and information communication efficiency.

[0056] Feedback loop: Collect user feedback, continuously optimize the response generation logic and display method, and form a closed-loop user experience optimization mechanism.

[0057] In some embodiments, the blockchain-based medical online question-and-answer system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the blockchain-based medical online question-and-answer system may be stored in the memory of a computer device and executed by at least one processor to execute (see Figure 1 Description) Functionality of medical online Q&A based on blockchain.

[0058] In this embodiment, the blockchain-based medical online question-and-answer system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of the system 200 may include: a classification storage module 210, a mapping establishment module 220, a target determination module 230, a query processing module 240 and a reply generation module 250. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0059] A classification storage module is used to classify the material data into multiple categories according to the organs to which they belong, and upload the material data of multiple categories to multiple corresponding blockchains respectively; A mapping establishment module is used to establish a mapping relationship between blockchain and categories; A target determination module, used to parse the target category of the query statement, and determine the target blockchain based on the target category and the mapping relationship; A query processing module, used to generate a query request based on the query statement, and send the query request to the target blockchain; The reply generation module is used to obtain the target material data returned by the target blockchain based on the query request, and generate reply data based on the target material data.

[0060] Figure 3 A schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention, wherein the terminal 300 can be used to execute the blockchain-based medical online question-and-answer method provided in an embodiment of the present invention.

[0061] The terminal 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0062] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.

[0063] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0064] The communication unit 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0065] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0066] Therefore, the present invention classifies the material data and uploads it to the blockchain of the corresponding category to achieve orderly management and secure sharing of the material data, and queries the target material data from the blockchain of the corresponding category during query, thereby reducing the amount of data processing and improving data retrieval efficiency. The technical effects that can be achieved by this embodiment can be found in the description above and will not be repeated here.

[0067] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, 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 a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0068] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0069] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0070] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0072] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A medical online question-and-answer method based on blockchain, characterized in that: include: Divide the material data into multiple categories according to the organs they belong to, and upload the material data of multiple categories to multiple corresponding blockchains respectively; Establish a mapping relationship between blockchain and categories; Parsing the target category of the query statement, and determining the target blockchain based on the target category and the mapping relationship; Generate a query request based on the query statement, and send the query request to the target blockchain; The target material data returned by the target blockchain based on the query request is obtained, and the response data is generated based on the target material data.

2. The method according to claim 1, characterized in that The material data is divided into multiple categories according to the organs to which it belongs, and the material data of multiple categories are uploaded to multiple corresponding blockchains respectively, including: Acquire the latest material data from the shared database, wherein the material data is a material mapping consisting of symptoms, lesion locations, disease names, and diagnosis and treatment plans; Determining the category of the material data based on the organ to which the lesion location belongs, and determining the corresponding blockchain based on the category of the material data; Taking the latest material data as the query target, querying the original material data from the corresponding blockchain; Determine whether the latest material data is consistent with the original material data: If the two are consistent, the latest material data is ignored; If the two are inconsistent, a review task for the latest material data is generated, and after the review is passed, the original material data is updated to the latest material data.

3. The method according to claim 1, characterized in that Establish a mapping relationship between blockchain and categories, including: Establish a mapping relationship between blockchain addresses and corresponding categories, and cache the mapping relationship in a specified directory.

4. The method according to claim 1, characterized in that Parsing the target category of the query statement, and determining the target blockchain based on the target category and the mapping relationship, including: Use keyword extraction technology to extract keywords and sentence intentions from query sentences; extracting category keywords from the keywords, and determining a target category of the query statement based on the category keywords; A blockchain having a mapping relationship with the target category is determined as the target blockchain.

5. The method according to claim 4, characterized in that Generating a query request based on the query statement, and sending the query request to the target blockchain, including: Generate a query mapping, wherein the query mapping includes symptoms, lesion location, disease name, and diagnosis and treatment plan, wherein the symptoms, lesion location, disease name, and diagnosis and treatment plan are all variable parameter items; Fill the keyword into the query mapping, and mark the corresponding variable parameter item in the query mapping as a target query item based on the statement intention, A query request is generated based on the query mapping, and the query request is sent to the target blockchain.

6. The method according to claim 5, characterized in that The method further comprises: If the category keyword does not exist in the keyword, the query request is sent to all blockchains; A smart contract is deployed in each blockchain in advance. After receiving a query request, the blockchain executes the smart contract, calculates the matching degree between the material data in the first N blocks and the query request, and if the matching degree exceeds a preset first matching threshold, it is recorded as 1; if the matching degree does not exceed the first matching threshold, it is recorded as 0; and the proportion of blocks recorded as 1 is calculated. If the proportion reaches a preset proportion threshold, the query request continues to be executed; if the proportion does not reach the preset proportion threshold, the query request is terminated on the current blockchain; if the matching degree reaches a preset second matching threshold, the corresponding material data is directly used as the target material data of the query request.

7. The method according to claim 1, characterized in that Obtaining target material data returned by the target blockchain based on the query request, and generating reply data based on the target material data, including: generating response data based on the target material data using a large language model; The reply data is pushed to the display interface.

8. A medical online question-and-answer system based on blockchain, characterized in that: include: A classification storage module is used to classify the material data into multiple categories according to the organs to which they belong, and upload the material data of multiple categories to multiple corresponding blockchains respectively; A mapping establishment module is used to establish a mapping relationship between blockchain and categories; A target determination module, used to parse the target category of the query statement, and determine the target blockchain based on the target category and the mapping relationship; A query processing module, used to generate a query request based on the query statement, and send the query request to the target blockchain; The reply generation module is used to obtain the target material data returned by the target blockchain based on the query request, and generate reply data based on the target material data.

9. A terminal, characterized in that: include: Storage device for storing the blockchain-based medical online question-and-answer program; A processor, configured to implement the steps of the medical online question-and-answer method based on blockchain as described in any one of claims 1 to 7 when executing the medical online question-and-answer program based on blockchain.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a blockchain-based medical online question-and-answer program, which, when executed by a processor, implements the steps of the blockchain-based medical online question-and-answer method as described in any one of claims 1 to 7.

Images