Medical data retrieval method, system, terminal and storage medium

Abstract

The present invention relates to the field of data query technology, and specifically provides a medical data retrieval method, system, terminal and storage medium, including: extracting target keywords from query statements through a semantic recognition model, and calculating the hash value of the target keywords to obtain the target hash value; querying an index matching the target hash value from an index library, the index including a set of keyword hash values ​​of medical documents and metadata of medical documents; sorting and displaying the corresponding metadata from high to low according to the degree of matching, and obtaining important metadata by monitoring mouse click events and cursor dwell time; extracting similar parameters of important metadata, querying related metadata from the index library based on the similar parameters, and pushing the related metadata to a display interface; based on the selected target metadata, retrieving target medical data from a database. The present invention realizes keyword extraction, reduces the difficulty requirements of index statements, avoids the leakage of sensitive words, and improves data security.

Description

Technical Field

[0001] The present invention belongs to the technical field of data query, and in particular relates to a medical data retrieval method, system, terminal and storage medium. Background Art

[0002] With the acceleration of the process of medical informatization and the rapid growth of medical research data, how to efficiently retrieve and deeply analyze this complex information has become a key issue that needs to be solved. Data in the medical field is known for its high degree of professionalism and complexity, requiring users to have professional knowledge background to construct accurate search queries when searching, which undoubtedly increases the difficulty and threshold of retrieval. At the same time, given that medical data often involves personal privacy and sensitive information, ensuring the security and privacy protection of data during the interaction process has become a vital task. We urgently need to strengthen the research and development and application of data security technology to ensure the legality and compliance of data use and the information rights of patients. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a medical data retrieval method, system, terminal and storage medium to solve the above-mentioned technical problems.

[0004] In a first aspect, the present invention provides a medical data retrieval method, comprising:

[0005] Extract the target keyword from the query statement through the semantic recognition model, and calculate the hash value of the target keyword to obtain the target hash value;

[0006] Querying an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document;

[0007] Sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring mouse click events and cursor dwell time;

[0008] Extract similar parameters of important metadata, query related metadata from the index library based on the similar parameters, and push the related metadata to the display interface;

[0009] Based on the selected target metadata, target medical data is retrieved from the database.

[0010] In an optional implementation, extracting a target keyword from a query statement through a semantic recognition model and calculating a hash value of the target keyword to obtain a target hash value includes:

[0011] Clean and format the query statements, remove noise data, perform word segmentation, and part-of-speech tagging to obtain query data;

[0012] Perform word sense disambiguation, named entity recognition, and sentiment analysis on the preprocessed query data to obtain semantic analysis results;

[0013] Use keyword weighting technology to extract multiple target keywords from the semantic analysis results;

[0014] Hash values ​​of multiple target keywords are calculated respectively to obtain multiple target hash values.

[0015] In an optional implementation, the corresponding metadata are sorted and displayed from high to low according to the matching degree, and important metadata are obtained by monitoring mouse click events and cursor dwell time, including:

[0016] Counting the number of target hash values ​​included in the keyword hash value set of the index, and taking the ratio of the number to the total number of target hash values ​​as the matching degree of the index;

[0017] Sort the metadata of the corresponding index according to the matching degree, and output the metadata in the order to the display interface;

[0018] Monitor the number of mouse click events and cursor dwell time corresponding to each metadata in the display interface;

[0019] Based on the preset click weight and time weight, the weighted sum of the number of mouse click events and the cursor dwell time of the metadata is calculated to obtain the interest degree of the metadata;

[0020] The metadata whose interest reaches a set interest threshold is marked as important metadata.

[0021] In an optional implementation, extracting similar parameters of important metadata, querying related metadata from an index library based on the similar parameters, and pushing the related metadata to a display interface includes:

[0022] Count the number of repetitions of various parameters of multiple important metadata;

[0023] One or more parameter items with the highest number of repetitions are taken as similar parameters;

[0024] The metadata containing the similar parameters is searched from the index library to obtain the associated metadata.

[0025] In a second aspect, the present invention provides a medical data retrieval system, comprising:

[0026] A sentence processing module is used to extract target keywords from the query sentence through a semantic recognition model, and calculate the hash value of the target keyword to obtain a target hash value;

[0027] An index matching module, used to query an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document;

[0028] The display control module is used to sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring the mouse click event and the cursor dwell time;

[0029] An associated query module, used to extract similar parameters of important metadata, query associated metadata from the index library based on the similar parameters, and push the associated metadata to the display interface;

[0030] The data retrieval module is used to retrieve target medical data from the database based on the selected target metadata.

[0031] In an optional implementation, the statement processing module includes:

[0032] The preprocessing unit is used to clean and format the query statement, remove noise data, perform word segmentation, and part-of-speech tagging to obtain query data;

[0033] A semantic analysis unit is used to perform word sense disambiguation, named entity recognition, and sentiment analysis on the preprocessed query data to obtain a semantic analysis result;

[0034] A keyword extraction unit, used to extract multiple target keywords from the semantic analysis results using keyword weighting technology;

[0035] The target encryption unit is used to calculate the hash values ​​of multiple target keywords respectively to obtain multiple target hash values.

[0036] In an optional implementation, the display control module includes:

[0037] A matching calculation unit, used to count the number of target hash values ​​included in the keyword hash value set of the index, and use the ratio of the number to the total number of target hash values ​​as the matching degree of the index;

[0038] A sequential display unit, used to sort the metadata of the corresponding index according to the matching degree, and output the sequentially arranged metadata to the display interface;

[0039] An interface monitoring unit, used to monitor the number of mouse click events and the cursor dwell time corresponding to each metadata in the display interface;

[0040] The interest quantification unit is used to calculate the weighted sum of the number of mouse click events and the cursor stay time of the metadata based on the preset click weight and time weight to obtain the interest degree of the metadata;

[0041] The interest marking unit is used to mark metadata whose interest reaches a set interest threshold as important metadata.

[0042] In an optional implementation, the association query module includes:

[0043] Repeat counting unit, used to count the number of repetitions of various parameters of multiple important metadata;

[0044] A parameter screening unit, used for selecting one or more parameter items with the highest number of repetitions as similar parameters;

[0045] The associated query unit is used to query metadata containing the similar parameters from the index library to obtain associated metadata.

[0046] In a third aspect, a terminal is provided, including:

[0047] processor, memory, wherein:

[0048] The memory is used to store computer programs.

[0049] The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0050] 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.

[0051] The beneficial effects of the present invention are that the medical data retrieval method, system, terminal and storage medium provided by the present invention realize keyword extraction by performing semantic analysis on query statements, reduce the difficulty requirements of index statements, perform associated queries based on the user's interest in metadata, expand the query scope to track the user's target medical data as much as possible, and perform query interaction through hash values ​​to avoid the leakage of sensitive words, thereby improving data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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.

[0053] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0054] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0055] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] 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.

[0057] 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.

[0058] The medical data retrieval method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the medical data retrieval system runs in the computer device.

[0059] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be a medical data retrieval system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0060] like Figure 1 As shown, the method includes:

[0061] Step 110, extracting a target keyword from the query statement through a semantic recognition model, and calculating a hash value of the target keyword to obtain a target hash value;

[0062] Step 120, searching an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document;

[0063] Step 130, sorting and displaying the corresponding metadata from high to low according to the matching degree, and acquiring important metadata by monitoring the mouse click event and the cursor stay time;

[0064] Step 140, extracting similar parameters of important metadata, querying related metadata from the index library based on the similar parameters, and pushing the related metadata to the display interface;

[0065] Step 150, based on the selected target metadata, retrieve the target medical data from the database.

[0066] In one embodiment of the present invention, the following steps are included:

[0067] First, we use an advanced semantic recognition model to deeply analyze the query statements entered by the user. This model has been trained with a large number of medical corpora and can accurately understand the semantic information in the query statements and accurately extract the target keywords that the user intends to point to. Subsequently, each target keyword is hashed to generate a unique hash value, namely the target hash value. This process ensures the unique identification of the keyword and provides a basis for subsequent rapid retrieval.

[0068] After obtaining the target hash values, the system uses these hash values ​​as query conditions to search in the pre-built and maintained index library. The index library stores the keyword hash value sets of medical files, which are closely related to the metadata of medical files. By comparing the hash values ​​in the index library, the system can quickly locate records that match or are highly similar to the target hash values, thereby obtaining the corresponding medical file keyword hash value sets and their metadata.

[0069] In order to improve the user experience, the system will sort the retrieved medical file metadata according to the degree of matching and display the sorted results to the user. At the same time, the system also has an intelligent interactive function that can monitor the user's mouse click events and the time the cursor stays on specific metadata to determine which metadata the user is more concerned about or considers more important. Based on these user behavior data, the system can automatically extract and mark important metadata.

[0070] For the extracted important metadata, the system further analyzes similar parameters, such as disease type, treatment method, drug name, etc. Then, based on these similar parameters, the system again performs an extended query in the index library to find other metadata associated with the important metadata. This step is designed to provide users with a more comprehensive and in-depth medical information association network to help users better understand and analyze the target medical data. Finally, the system pushes the queried associated metadata to the display interface for users to review.

[0071] When the user selects one or more target metadata from the display interface, the system will quickly locate and retrieve the corresponding target medical data in the database based on the identification information of these target metadata. These data may include detailed medical records, examination reports, treatment plans, etc., providing users with comprehensive and accurate medical information support. The entire retrieval process realizes a complete closed loop from user query input to target medical data display, effectively improving the efficiency and accuracy of medical information retrieval.

[0072] To facilitate understanding of the present invention, the medical data retrieval method provided by the present invention is further described below based on the principle of the medical data retrieval method of the present invention and in combination with the process of retrieving medical data in the embodiment.

[0073] Specifically, the medical data retrieval method includes:

[0074] S1. Extract target keywords from the query statement through the semantic recognition model, and calculate the hash value of the target keyword to obtain the target hash value.

[0075] The query statements are cleaned and formatted, and noise data is removed, word segmentation and part-of-speech tagging are performed to obtain query data; word sense disambiguation, named entity recognition and sentiment analysis are performed on the preprocessed query data to obtain semantic analysis results; keyword weighting technology is used to extract multiple target keywords from the semantic analysis results; hash values ​​of multiple target keywords are calculated respectively to obtain multiple target hash values.

[0076] Specifically, the query statements entered by the user are first thoroughly cleaned and formatted to remove insignificant noise data, such as punctuation marks, stop words, etc. Subsequently, the query statements are split into independent vocabulary units using word segmentation technology, and part-of-speech tagging is performed to better understand the role of each word in the sentence. Next, the system uses advanced semantic recognition models to conduct in-depth analysis of the pre-processed query data, including word sense disambiguation (solving the problem of multiple meanings of a word), named entity recognition (recognizing proper nouns such as disease names, drug names, etc.), and sentiment analysis (determining the sentiment tendency in the query statement).

[0077] Based on the above semantic analysis results, the system uses keyword weighting technology to extract multiple target keywords according to the importance of the vocabulary in the sentence (such as TF-IDF value, part-of-speech weight, etc.). These keywords can accurately reflect the user's query intent. Finally, the system calculates the hash value for each target keyword and generates multiple target hash values ​​for fast index matching in subsequent steps.

[0078] S2. Query an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical file and metadata of the medical file.

[0079] After obtaining the target hash values, the system uses these hash values ​​as query conditions to perform efficient retrieval in the pre-built and maintained index library. The index library contains a large number of indexes, which contain the keyword hash value set of medical documents and the metadata associated with them, such as file name, author, creation time, etc. The system quickly locates the keyword hash value set containing any target hash value by comparing the hash values ​​in the index library, and outputs the index to which the located keyword hash value set belongs as the matching index.

[0080] S3. Sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring mouse click events and cursor dwell time.

[0081] The number of target hash values ​​contained in the keyword hash value set of the index is counted, and the ratio of the number to the total number of target hash values ​​is used as the matching degree of the index; the metadata of the corresponding index is sorted according to the matching degree, and the metadata arranged in sequence is output to the display interface; the number of mouse click events and the cursor dwell time corresponding to each metadata in the display interface are monitored; based on the preset click weight and time weight, the weighted sum of the number of mouse click events and the cursor dwell time of the metadata is calculated to obtain the interest degree of the metadata; the metadata whose interest degree reaches the set interest threshold is marked as important metadata.

[0082] Specifically, in order to improve the user experience, the retrieved medical document metadata is sorted according to the index matching degree. The matching degree is calculated by counting the number of target hash values ​​contained in the index keyword hash value set and the ratio of the number of target hash values ​​to the total number of target hash values. The metadata with higher matching degree is more likely to meet the user's query needs, so it is displayed on the display interface first.

[0083] At the same time, the number of mouse click events and the cursor dwell time corresponding to each metadata in the display interface are monitored in real time. Based on the preset click weight and time weight, the weighted sum of the number of mouse click events and the cursor dwell time of each metadata is calculated to obtain the metadata interest. When the interest reaches the set interest threshold, the metadata is automatically marked as important metadata for further processing.

[0084] The method of obtaining interest is as follows:

[0085] Use front-end technologies (such as JavaScript, HTML5, CSS3) combined with graphics libraries (such as D3.js, ECharts) to build a real-time monitoring display interface. Capture user mouse click events and cursor stay events through event listeners (such as click, mouseover, mouseout). Use WebSocket or polling mechanism to maintain real-time communication with the back-end server to ensure synchronous data update.

[0086] Design a database model to store the number of clicks, cursor dwell time, and other information for each metadata. Implement an API interface for the front-end to send event data to the back-end and update the corresponding records in the database. Write back-end logic to regularly calculate the weighted sum (interest) of each metadata based on the preset click weight and time weight.

[0087] Administrators or system configurators are allowed to set click weights and time weights for different metadata types through the backend interface to adapt to different business scenarios and needs. Weight settings should take into account the diversity of user behavior patterns. For example, some metadata may rely more on the number of clicks, while others may focus more on the cursor dwell time.

[0088] Real-time feedback: The number of clicks and cursor dwell time for each metadata are instantly displayed on the display interface (optional, provided that it does not interfere with user operations). Interest visualization: The interest of metadata is intuitively displayed through color changes, icon size adjustments, or animation effects. Important metadata prompts: When metadata is automatically marked as important, users are notified through pop-ups, highlighting, or sound prompts.

[0089] Data cleaning: Clean the collected data to remove outliers (such as extremely short cursor dwell time) and duplicate data. Weighted calculation: Calculate the interest of each metadata based on the preset weights using a formula (such as weighted sum = number of clicks * click weight + cursor dwell time * time weight). Threshold management: Allows administrators to adjust the interest threshold based on business needs to control the sensitivity of identifying important metadata.

[0090] S4. Extract similar parameters of important metadata, query related metadata from the index library based on the similar parameters, and push the related metadata to the display interface.

[0091] Count the number of repetitions of various parameters of multiple important metadata; use one or more parameter items with the highest number of repetitions as similar parameters; and query metadata containing the similar parameters from the index library to obtain associated metadata.

[0092] Specifically, for records marked as important metadata, the various parameters are further analyzed, and the number of parameter repetitions of multiple important metadata is counted. One or more parameters with the highest number of repetitions are considered similar parameters, which reflect the focus or interest of the user's current query. Subsequently, these similar parameters are used as new query conditions to query the metadata containing these parameters in the index library to obtain related metadata. These related metadata may be highly relevant to the user's query intent, so they are pushed to the display interface for further review by the user.

[0093] S5. Based on the selected target metadata, retrieve the target medical data from the database.

[0094] Finally, when the user selects one or more target metadata from the display interface, the corresponding target medical data can be quickly located and retrieved in the database based on the identification information of these target metadata (such as file ID, record number, etc.). These data may include detailed medical records, examination reports, treatment plans and other key information. These data are presented to users in an intuitive and easy-to-read manner to help users fully understand and analyze the target medical data.

[0095] In some embodiments, the medical data retrieval system may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the medical data retrieval system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Functionality for medical data retrieval.

[0096] In this embodiment, the medical data retrieval 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 statement processing module 210, an index matching module 220, a display control module 230, an association query module 240 and a data retrieval 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.

[0097] A sentence processing module is used to extract target keywords from the query sentence through a semantic recognition model, and calculate the hash value of the target keyword to obtain a target hash value;

[0098] An index matching module, used to query an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document;

[0099] The display control module is used to sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring the mouse click event and the cursor dwell time;

[0100] An associated query module, used to extract similar parameters of important metadata, query associated metadata from the index library based on the similar parameters, and push the associated metadata to the display interface;

[0101] The data retrieval module is used to retrieve target medical data from the database based on the selected target metadata.

[0102] Optionally, as an embodiment of the present invention, the statement processing module includes:

[0103] The preprocessing unit is used to clean and format the query statement, remove noise data, perform word segmentation, and part-of-speech tagging to obtain query data;

[0104] A semantic analysis unit is used to perform word sense disambiguation, named entity recognition, and sentiment analysis on the preprocessed query data to obtain a semantic analysis result;

[0105] A keyword extraction unit, used to extract multiple target keywords from the semantic analysis results using keyword weighting technology;

[0106] The target encryption unit is used to calculate the hash values ​​of multiple target keywords respectively to obtain multiple target hash values.

[0107] Optionally, as an embodiment of the present invention, the display control module includes:

[0108] A matching calculation unit, used to count the number of target hash values ​​included in the keyword hash value set of the index, and use the ratio of the number to the total number of target hash values ​​as the matching degree of the index;

[0109] A sequential display unit, used to sort the metadata of the corresponding index according to the matching degree, and output the sequentially arranged metadata to the display interface;

[0110] An interface monitoring unit, used to monitor the number of mouse click events and the cursor dwell time corresponding to each metadata in the display interface;

[0111] The interest quantification unit is used to calculate the weighted sum of the number of mouse click events and the cursor stay time of the metadata based on the preset click weight and time weight to obtain the interest degree of the metadata;

[0112] The interest marking unit is used to mark metadata whose interest reaches a set interest threshold as important metadata.

[0113] Optionally, as an embodiment of the present invention, the association query module includes:

[0114] Repeat counting unit, used to count the number of repetitions of various parameters of multiple important metadata;

[0115] A parameter screening unit, used for selecting one or more parameter items with the highest number of repetitions as similar parameters;

[0116] The associated query unit is used to query metadata containing the similar parameters from the index library to obtain associated metadata.

[0117] Figure 3 This is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the medical data retrieval method provided in an embodiment of the present invention.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] Therefore, the present invention performs semantic analysis on query statements to achieve keyword extraction, reduces the difficulty requirement of index statements, performs associated queries based on the user's interest in metadata, expands the query scope to track the user's target medical data as much as possible, and performs query interaction through hash values ​​to avoid the leakage of sensitive words and improve data security. The technical effects that can be achieved by this embodiment can be found in the description above and will not be repeated here.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 data retrieval method, characterized in that: include: Extract the target keyword from the query statement through the semantic recognition model, and calculate the hash value of the target keyword to obtain the target hash value; Querying an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document; Sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring mouse click events and cursor dwell time; Extract similar parameters of important metadata, query related metadata from the index library based on the similar parameters, and push the related metadata to the display interface; Based on the selected target metadata, retrieve target medical data from the database; The corresponding metadata is sorted and displayed from high to low according to the matching degree, and important metadata is obtained by monitoring mouse click events and cursor dwell time, including: Counting the number of target hash values ​​included in the keyword hash value set of the index, and taking the ratio of the number to the total number of target hash values ​​as the matching degree of the index; Sort the metadata of the corresponding index according to the matching degree, and output the metadata in the order to the display interface; Monitor the number of mouse click events and cursor dwell time corresponding to each metadata in the display interface; Based on the preset click weight and time weight, the weighted sum of the number of mouse click events and the cursor dwell time of the metadata is calculated to obtain the interest degree of the metadata; The metadata whose interest reaches a set interest threshold is marked as important metadata.

2. The method according to claim 1, characterized in that The target keyword is extracted from the query statement through the semantic recognition model, and the hash value of the target keyword is calculated to obtain the target hash value, including: Clean and format the query statements, remove noise data, perform word segmentation, and part-of-speech tagging to obtain query data; Perform word sense disambiguation, named entity recognition, and sentiment analysis on the preprocessed query data to obtain semantic analysis results; Use keyword weighting technology to extract multiple target keywords from the semantic analysis results; Hash values ​​of multiple target keywords are calculated respectively to obtain multiple target hash values.

3. The method according to claim 1, characterized in that Extracting similar parameters of important metadata, querying related metadata from an index library based on the similar parameters, and pushing the related metadata to a display interface, including: Count the number of repetitions of various parameters of multiple important metadata; One or more parameter items with the highest number of repetitions are taken as similar parameters; The metadata containing the similar parameters is searched from the index library to obtain the associated metadata.

4. A medical data retrieval system, characterized in that: include: A sentence processing module is used to extract target keywords from the query sentence through a semantic recognition model, and calculate the hash value of the target keyword to obtain a target hash value; An index matching module, used to query an index matching the target hash value from an index library, wherein the index includes a set of keyword hash values ​​of the medical document and metadata of the medical document; The display control module is used to sort and display the corresponding metadata from high to low according to the matching degree, and obtain important metadata by monitoring the mouse click event and the cursor dwell time; An associated query module, used to extract similar parameters of important metadata, query associated metadata from the index library based on the similar parameters, and push the associated metadata to the display interface; A data retrieval module, used to retrieve target medical data from a database based on selected target metadata; The display control module comprises: A matching calculation unit, used to count the number of target hash values ​​included in the keyword hash value set of the index, and use the ratio of the number to the total number of target hash values ​​as the matching degree of the index; A sequential display unit, used to sort the metadata of the corresponding index according to the matching degree, and output the sequentially arranged metadata to the display interface; An interface monitoring unit, used to monitor the number of mouse click events and the cursor dwell time corresponding to each metadata in the display interface; The interest quantification unit is used to calculate the weighted sum of the number of mouse click events and the cursor stay time of the metadata based on the preset click weight and time weight to obtain the interest degree of the metadata; The interest marking unit is used to mark metadata whose interest reaches a set interest threshold as important metadata.

5. The system according to claim 4, characterized in that The statement processing module includes: The preprocessing unit is used to clean and format the query statement, remove noise data, perform word segmentation, and part-of-speech tagging to obtain query data; A semantic analysis unit is used to perform word sense disambiguation, named entity recognition, and sentiment analysis on the preprocessed query data to obtain a semantic analysis result; A keyword extraction unit, used to extract multiple target keywords from the semantic analysis results using keyword weighting technology; The target encryption unit is used to calculate the hash values ​​of multiple target keywords respectively to obtain multiple target hash values.

6. The system according to claim 4, characterized in that The associated query module includes: Repeat counting unit, used to count the number of repetitions of various parameters of multiple important metadata; A parameter screening unit, used for selecting one or more parameter items with the highest number of repetitions as similar parameters; The associated query unit is used to query metadata containing the similar parameters from the index library to obtain associated metadata.

7. A terminal, characterized in that: include: a memory for storing a medical data retrieval program; A processor, used to implement the steps of the medical data retrieval method as described in any one of claims 1-3 when executing the medical data retrieval program.

8. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a medical data retrieval program, which, when executed by a processor, implements the steps of the medical data retrieval method according to any one of claims 1 to 3.

Images