Medical term matching method and device, computer equipment and storage medium

By constructing mapping logic and analyzing word attributes, the problem of inflexible mapping of medical terms in the existing technology is solved, accurate matching and personalized mapping of medical terms are achieved, and the sharing and utilization efficiency of medical information is improved.

CN119066239APending Publication Date: 2024-12-03WINNING HEALTH TECHNOLOGY GROUP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310647143.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-01
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing medical term mapping methods cannot adjust the mapping logic according to the user's personal needs, resulting in the inability to meet the user's personal mapping needs, and there are problems of inconsistent medical terms, which affects the sharing and utilization of medical information.

Method used

Construct mapping logic through human-computer interaction, obtain the grammatical pattern of the medical term dictionary and standard medical term dictionary to be matched, analyze word attributes, build target grammar to match standard medical terminology, establish mapping relationships, and improve matching flexibility and accuracy .

Benefits of technology

It realizes flexible and accurate matching of medical terms, meets users' personalized needs, and improves the efficiency of sharing and utilization of medical information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066239A_ABST
    Figure CN119066239A_ABST
Patent Text Reader

Abstract

The invention provides a medical term matching method and device, computer equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps that a grammar mode A for a to-be-matched medical term dictionary and a grammar mode B for a standard medical term dictionary are obtained, the grammar mode A is composed of a trunk keyword a and a word attribute a, and the grammar mode B is composed of a trunk keyword b and a word attribute a; performing word attribute a analysis on the target to-be-matched medical term to obtain a keyword corresponding to the word attribute a as a modification keyword; according to a target grammar formed by the trunk keyword b and the modification keyword, matching the plurality of standard medical terms to obtain a target standard medical term; and establishing a mapping relationship between the target to-be-matched medical term and the target standard medical term. According to the application, the mapping logic can be flexibly constructed in a man-machine interaction mode to map the medical terms to be matched and the standard medical terms.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a medical term matching method, device, computer equipment and storage medium. Background Art

[0002] The standardization of clinical medical terminology is the basis for sharing medical information and the top priority of medical informatization construction.

[0003] Various medical terms come from many sources and are written differently. The same word may have different meanings in different sentences and usage scenarios, or the same concept may be expressed differently in different systems, which leads to great obstacles to the sharing and use of medical information.

[0004] In order to solve the problem of inconsistent terminology, each medical unit needs to map the medical terms it uses with standard medical terms. However, most of the existing term mapping methods use the underlying logic to perform similarity matching based on the attributes or meanings of words in medical terms. Users cannot adjust the mapping logic according to their personal needs, and cannot meet users' personalized mapping needs. Summary of the invention

[0005] The purpose of the present invention is to provide a medical term matching method, apparatus, computer device and storage medium to address the deficiencies in the above-mentioned prior art, so as to flexibly construct mapping logic to map the medical terms to be matched and the standard medical terms through human-computer interaction.

[0006] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0007] In a first aspect, an embodiment of the present application provides a medical term matching method, the method comprising:

[0008] Acquire a grammatical pattern A for a medical term dictionary to be matched and a grammatical pattern B for a preset standard medical term dictionary, wherein the grammatical pattern A consists of: a main keyword a and a word attribute a, and the grammatical pattern B consists of: a main keyword b and the word attribute a;

[0009] Parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtaining a keyword corresponding to the word attribute a as a modified keyword, wherein the target medical term to be matched includes: the main keyword a;

[0010] According to the target grammar formed by the main keyword b and the modified keyword, a plurality of structured standard medical terms in the standard medical term dictionary are matched to obtain a target standard medical term corresponding to the target grammar;

[0011] A mapping relationship between the target to-be-matched medical term and the target standard medical term is established.

[0012] Optionally, before parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, the method further includes:

[0013] Using the multiple word attributes in the first grammatical structure, extracting attributes of the original medical term to be matched, and determining multiple attribute keywords of the original medical term to be matched;

[0014] According to the multiple attribute keywords of the original medical term to be matched, a structured medical term to be matched is determined.

[0015] Optionally, before matching the target grammar formed by the main keyword b and the modified keyword with the plurality of structured standard medical terms in the standard medical term dictionary, the method further includes:

[0016] Using the multiple word attributes in the second grammatical structure, extracting attributes from the original standard medical term, and determining multiple attribute keywords of the original standard medical term;

[0017] A structured standard medical term is determined according to a plurality of attribute keywords of the original standard medical term.

[0018] Optionally, the target grammar further includes: the main attention degree of the main keyword b and the modified attention degree of the modified keyword. The target grammar formed by the main keyword b and the modified keyword matches a plurality of structured standard medical terms in the standard medical term dictionary to obtain the target standard medical term corresponding to the target grammar, including:

[0019] According to the target grammar formed by the main keyword b and the modified keyword, the structured multiple standard medical terms are matched to obtain a matching result 1 of at least one candidate standard medical term 1, wherein the matching result 1 is used to indicate that the candidate standard medical term 1 accurately matches the main keyword b and / or the modified keyword;

[0020] Calculating the matching degree of the at least one candidate standard medical term 1 according to the matching result 1, the trunk attention degree and the modified attention degree;

[0021] The target standard medical term is selected from the at least one candidate standard medical term 1 according to the matching degree of the at least one candidate standard medical term 1 .

[0022] Optionally, the target grammar formed by the main keyword b and the modified keyword is matched with multiple standard medical terms structured in the standard medical term dictionary to obtain target standard medical terms corresponding to the target grammar, including:

[0023] According to the word attribute b of the main keyword b, determining the extended keyword 1 that matches the main keyword b from the term set of the word attribute b;

[0025] According to the word attribute a of the modified keyword, determining the extended keyword 2 that matches the modified keyword from the term set of the word attribute a;

[0026] According to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, a plurality of structured standard medical terms in the standard medical term dictionary are matched to obtain a target standard medical term corresponding to the target grammar.

[0027] Optionally, the target grammar includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the matching of multiple structured standard medical terms in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar includes:

[0028] According to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, the structured multiple standard medical terms are matched to obtain a matching result 2 of at least one candidate standard medical term 2, wherein the matching result 2 is used to indicate that the candidate standard medical term 2 matches the main keyword b, the modified keyword, the extended keyword 1 and / or the extended keyword 2;

[0029] Calculate the matching degree of the at least one candidate standard medical term 2 according to the matching result 2, the main attention degree, the modified attention degree, the first similarity and the second similarity, wherein the first similarity is the similarity between the extended keyword 1 and the main keyword b, and the second similarity is the similarity between the extended keyword 2 and the modified keyword;

[0030] The target standard medical term is selected from the at least one candidate standard medical term 2 according to the matching degree of the at least one candidate standard medical term 2 .

[0031] Optionally, the target grammar includes: the main attention degree of the main keyword b and the modified attention degree of the modified keyword, and the target grammar formed by the main keyword b and the modified keyword matches a plurality of structured standard medical terms in the standard medical term dictionary to obtain the target standard medical term corresponding to the target grammar, including:

[0032] Performing fuzzy matching on the plurality of standard medical terms, respectively, with the main keyword b and the modified keyword, and obtaining a matching result 3 of at least one candidate standard medical term 3, wherein the matching result 3 is used to indicate that the candidate standard medical term 3 is fuzzy matched with the main keyword b and / or the modified keyword;

[0033] Calculate the matching degree of the at least one candidate standard medical term 3 according to the matching result 3, the main attention degree, the modified attention degree, the third similarity and the fourth similarity, wherein the third similarity is the similarity between the candidate standard medical term 3 and the main keyword b, and the fourth similarity is the similarity between the candidate standard medical term 3 and the modified keyword;

[0034] The target standard medical term is selected from the at least one candidate standard medical term 3 according to the matching degree of the at least one candidate standard medical term 3 .

[0035] In a second aspect, an embodiment of the present application further provides a medical term matching device, the device comprising:

[0036] A grammar pattern receiving module, used for acquiring a grammar pattern A for a medical term dictionary to be matched and a grammar pattern B for a preset standard medical term dictionary, wherein the grammar pattern A is composed of a main keyword a and a word attribute a, and the grammar pattern B is composed of a main keyword b and the word attribute a;

[0037] A word attribute parsing module is used to parse the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtain a keyword corresponding to the word attribute a as a modified keyword, wherein the target medical term to be matched includes: the main keyword a;

[0038] A medical term matching module, used for matching a plurality of standard medical terms structured in the standard medical term dictionary according to a target grammar formed by the main keyword b and the modified keyword, to obtain a target standard medical term corresponding to the target grammar;

[0039] The mapping relationship establishing module is used to establish a mapping relationship between the target to-be-matched medical term and the target standard medical term.

[0040] Optionally, the device further comprises:

[0041] The first term structuring module is used to use multiple word attributes in the first grammatical structure to extract attributes of the original medical terms to be matched, determine multiple attribute keywords of the original medical terms to be matched; and determine structured medical terms to be matched based on the multiple attribute keywords of the original medical terms to be matched.

[0042] Optionally, the device further comprises:

[0043] The second term structuring module is used to extract attributes of the original standard medical term using multiple word attributes in the second grammatical structure, and determine multiple attribute keywords of the original standard medical term; and determine structured standard medical term based on the multiple attribute keywords of the original standard medical term.

[0044] Optionally, the target grammar further includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the medical term matching module includes:

[0045] A first candidate term matching unit is used to match the structured multiple standard medical terms according to the target grammar formed by the main keyword b and the modified keyword to obtain a matching result 1 of at least one candidate standard medical term 1, wherein the matching result 1 is used to indicate that the candidate standard medical term 1 accurately matches the main keyword b and / or the modified keyword;

[0046] A first matching degree calculation unit, configured to calculate a matching degree of the at least one candidate standard medical term 1 according to the matching result 1, the trunk attention degree and the modified attention degree;

[0047] The first target term selection unit is configured to select the target standard medical term from the at least one candidate standard medical term 1 according to the matching degree of the at least one candidate standard medical term 1 .

[0048] Optionally, the medical term matching module includes:

[0049] A main keyword expansion unit, configured to determine an expansion keyword 1 matching the main keyword b from a term set of the term attribute b according to the term attribute b of the main keyword b;

[0050] A modified keyword expansion unit, configured to determine, according to the word attribute a of the modified keyword, an expanded keyword 2 that matches the modified keyword from a term set of the word attribute a;

[0051] The medical term matching unit is used to match the multiple standard medical terms structured in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar.

[0052] Optionally, the target grammar includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the medical term matching unit includes:

[0053] A second candidate term matching unit is used to match the structured multiple standard medical terms according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, to obtain a matching result 2 of at least one candidate standard medical term 2, wherein the matching result 2 is used to indicate that the candidate standard medical term 2 matches the main keyword b, the modified keyword, the extended keyword 1 and / or the extended keyword 2;

[0054] a second matching degree calculation unit, configured to calculate the matching degree of the at least one candidate standard medical term 2 according to the matching result 2, the main attention degree, the modified attention degree, the first similarity and the second similarity, wherein the first similarity is the similarity between the extended keyword 1 and the main keyword b, and the second similarity is the similarity between the extended keyword 2 and the modified keyword;

[0055] The second target term selection unit is configured to select the target standard medical term from the at least one candidate standard medical term 2 according to the matching degree of the at least one candidate standard medical term 2 .

[0056] Optionally, the target grammar includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the medical term matching module includes:

[0057] A third candidate term matching unit is used to perform fuzzy matching on the plurality of standard medical terms, the main keyword b and the modified keyword, respectively, to obtain a matching result 3 of at least one candidate standard medical term 3, wherein the matching result 3 is used to indicate that the candidate standard medical term 3 is fuzzy matched with the main keyword b and / or the modified keyword;

[0058] a third matching degree calculation unit, configured to calculate the matching degree of the at least one candidate standard medical term 3 according to the matching result 3, the trunk attention degree, the modified attention degree, a third similarity and a fourth similarity, wherein the third similarity is the similarity between the candidate standard medical term 3 and the trunk keyword b, and the fourth similarity is the similarity between the candidate standard medical term 3 and the modified keyword;

[0059] The third target term selection unit is configured to select the target standard medical term from the at least one candidate standard medical term 3 according to the matching degree of the at least one candidate standard medical term 3 .

[0060] In a third aspect, an embodiment of the present application further provides a computer device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the medical term matching method as described in any one of the first aspects.

[0061] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the medical term matching method as described in any one of the first aspects are executed.

[0062] The beneficial effects of this application are:

[0063] The present application provides a medical term matching method, apparatus, computer equipment and storage medium. On the one hand, grammar pattern A and grammar pattern B can be flexibly constructed through human-computer interaction to determine mapping logic according to target grammar generated by grammar pattern A and grammar pattern B, thereby improving the flexibility of matching medical terms to be matched and standard medical terms; on the other hand, grammar pattern A can be used to more accurately parse the medical terms to be matched, and the target grammar can be used to more accurately match the standard medical terms, thereby improving the accuracy of medical term matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0065] Figure 1 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 1 ;

[0066] Figure 2 Schematic diagram of a graphical user interface provided in an embodiment of the present application Figure 1 ;

[0067] Figure 3 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 2 ;

[0068] Figure 4 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 3 ;

[0069] Figure 5 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 4 ;

[0070] Figure 6 Schematic diagram of a graphical user interface provided in an embodiment of the present application Figure 2 ;

[0071] Figure 7 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 5 ;

[0072] Figure 8 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 6 ;

[0073] Fig. 9 Schematic diagram of the process of the medical term matching method provided in the embodiment of the present application Figure 7 ;

[0074] Fig.10 A schematic diagram of the structure of a medical term matching device provided in an embodiment of the present application;

[0075] Fig.11 A schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, 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.

[0077] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0078] In addition, the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0079] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.

[0080] Before introducing the medical term matching method provided by the present application in detail, the application scenario of the present application is described first. The medical term matching method provided by the present application is applied to a computer device running a medical term matching system, which implements the medical term matching method of the present application based on human-computer interaction through a graphical user interface provided by the computer device.

[0081] Please refer to Figure 1 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 1 ,like Figure 1 As shown, the method may include:

[0083] S10: Acquire a grammatical pattern A for the medical term dictionary to be matched and a grammatical pattern B for a preset standard medical term dictionary.

[0084] In this embodiment, in order to use and facilitate understanding in work, medical units will customize common terms according to their own circumstances. The dictionary of medical terms to be matched is generally a dictionary composed of statistics of common terms in different usage scenarios of medical units to meet clinical record needs. Usage scenarios may include inspection scenarios, testing scenarios, drug scenarios, surgical scenarios, pathology scenarios, nursing scenarios, and education scenarios.

[0085] The standard medical terminology dictionary can be the standard names of commonly used terms compiled by the national medical system, or it can be the terms used by service providers who provide business services or functions to medical units. Since the terms used by the service providers are different from the commonly used terms of the medical units, the system provided by the service providers may be incompatible with the original system of the medical units. Therefore, it is necessary to match the terms in the medical terminology dictionary to be matched and the standard medical terminology dictionary.

[0086] For example, a medical term dictionary list is provided in a graphical user interface of a computer device, wherein the medical term dictionary list includes multiple medical term dictionaries, and a medical term dictionary to be matched and a standard medical term dictionary can be selected from the multiple medical term dictionaries.

[0087] After selecting the medical terminology dictionary to be matched and the standard medical terminology dictionary through the graphical user interface, the graphical user interface jumps to display the grammar input page, and the user enters grammar pattern A for the medical terminology dictionary to be matched and grammar pattern B for the standard medical terminology dictionary through the grammar input page.

[0088] For examples, please refer to Figure 2 , which is a schematic diagram of a graphical user interface provided in an embodiment of the present application Figure 1 ,like Figure 2 As shown, the graphical user interface includes: a grammar mode A editing area 21 and a grammar mode B editing area 22. The user can input grammar mode A in the grammar mode A editing area 21 and input grammar mode B in the grammar mode B editing area 22.

[0089] Among them, grammatical pattern A consists of: main keyword a and word attribute a, and grammatical pattern B consists of: main keyword b and word attribute a.

[0090] The main keyword a is a partial keyword of any medical term to be matched in the dictionary of medical terms to be matched, the main keyword b is a partial keyword of any standard medical term in the dictionary of standard medical terms, the word attribute a is the word attribute of other keywords of any medical term to be matched and any standard medical term, and the grammar pattern A and the grammar pattern B can be constructed by the user according to the grammatical format of the medical term to be matched and the standard medical term, respectively, or can be selected from multiple grammar patterns pre-provided by the medical term matching system, and this embodiment does not limit this.

[0091] In a possible implementation, the multiple grammar patterns provided in the medical term matching system may be multiple historical grammar patterns A and multiple historical grammar patterns B input by the user.

[0092] For example, please refer to Table 1, which is a list of historical grammar patterns provided for an embodiment of the present application. As shown in Table 1, the historical grammar pattern includes multiple historical grammar patterns A and multiple historical grammar patterns B. There is a corresponding relationship between multiple historical grammar patterns A and multiple historical grammar patterns B. Click any group of historical grammar patterns A and historical grammar patterns B, and then click to confirm the operation to determine that the historical grammar pattern A is grammar pattern A and the historical grammar pattern is grammar pattern B. Grammar pattern A is generated in the grammar pattern A editing area 21, and grammar pattern B is generated in the grammar pattern B editing area 22.

[0093] Table 1 List of historical grammar patterns

[0094] Historical Grammar Model A Historical Grammar Model B a:CT a+"enhancement" bodypart:CT bodypart+"CT" bodypart:CT bodypart+":100CT" bodypart:CT bodypart+"$ultrasound:100"

[0095] Among them, the historical grammar pattern A shown in Table 1 is a:CT, and the corresponding historical grammar pattern B is a+"enhanced", which means that the modifying keywords before CT in the target medical term to be matched are extracted as a according to the historical grammar pattern A, and the target grammar can be generated according to the modifying keywords and historical grammar pattern B.

[0096] Historical grammar pattern A is bodypart:CT, and the corresponding historical grammar pattern B is bodypart+"CT", which means that the specific content of bodypart in the target medical term to be matched is extracted as the modifying keyword according to historical grammar pattern A, and the target grammar can be generated according to the modifying keyword and historical grammar pattern B.

[0097] It should be noted that, if the user is proficient in the grammatical patterns of the medical terms to be matched and the standard medical terms, the user can input the grammatical pattern A and the grammatical pattern B in the grammatical pattern A editing area 21 and the grammatical pattern B editing area 22. In addition, for the grammatical pattern A and the grammatical pattern B selected by the user from the historical grammatical patterns, the user can also modify the grammatical pattern A and the grammatical pattern B in the grammatical pattern A editing area 21 and the grammatical pattern B editing area 22, and the flexibility of the human-computer interaction is relatively high.

[0098] S20: parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtaining keywords corresponding to the word attribute a as modified keywords, wherein the target medical term to be matched includes: main keyword a.

[0099] In this embodiment, all the medical terms to be matched in the dictionary of medical terms to be matched are pre-structured medical terms. The structured medical terms to be matched are composed of a plurality of keywords, and each keyword has a corresponding word attribute.

[0100] In some embodiments, the medical terms to be matched in the dictionary of medical terms to be matched are parsed in advance, and the keywords of different word attributes of the medical terms to be matched are described by code. According to the word attribute a in the grammatical pattern A, the keywords corresponding to the word attribute a in the code description of the target medical term to be matched can be determined.

[0101] For example, the word attribute a in grammatical pattern A is bodypart (part), the target medical term to be matched is CT femur plain scan (using ECG gating) + enhanced scan, and the code description of the structured target medical term to be matched is shown below. From the code description of the target medical term to be matched, it can be parsed that the keyword corresponding to the word attribute abodypart is femur, that is, the modified keyword is femur.

[0102] source: CT femur plain scan (using ECG gating) + enhanced scan

[0103]

[0104] For example, Figure 2 As shown, the graphical user interface also includes: a list of medical terms to be matched 23, the list of medical terms to be matched includes multiple medical terms to be matched in the dictionary of medical terms to be matched, after the user enters the grammar pattern A in the grammar pattern A editing area 21, the target medical term to be matched with the main keyword a is selected from the list of medical terms to be matched 23, and the target medical term to be matched is parsed according to the word attribute a in the grammar pattern A, and the keyword corresponding to the word attribute a in the target medical term to be matched is determined as the modifying keyword.

[0105] S30: Matching multiple standard medical terms structured in the standard medical term dictionary according to the target grammar composed of the main keyword b and the modified keywords to obtain target standard medical terms corresponding to the target grammar.

[0106] In this embodiment, after determining the modifying keywords corresponding to the word attribute a from the target medical term to be matched, the word attribute a in the grammar pattern B is assigned a value according to the modifying keywords to generate the target grammar, which consists of the main keyword b and the modifying keywords.

[0107] For example, Figure 2 As shown, the graphical user interface further includes: a target grammar editing area 24. After the target grammar is generated according to the grammar pattern B and the modified keywords, the target grammar is displayed in the target grammar editing area 24.

[0108] like Figure 2 As shown, grammatical pattern A is "bodypart: CT", grammatical pattern B is "bodypart+"CT"", word attribute a is bodypart, and the target medical term to be matched selected in the list of medical terms to be matched 23 is "cardiac CT coronary angiography". Cardiac CT coronary angiography is parsed according to the word attribute abodypart, and it is determined that the keyword corresponding to the word attribute abodypart is heart, that is, the modified keyword is heart. According to the modified keyword, grammatical pattern B is assigned a value, and the generated target grammar is "cardiac CT".

[0109] All standard medical terms in the standard medical term dictionary are pre-structured medical terms. The structured standard medical terms are also composed of multiple keywords, and each keyword has corresponding word attributes.

[0110] After the target grammar is generated, in response to a search operation for the target grammar, a standard medical term matching the main keyword b and the modified keyword is determined from the standard medical term dictionary as a target standard medical term based on the main keyword b and the modified keyword in the target grammar.

[0111] In some embodiments, the user can also directly enter the target medical term to be matched in the target grammar editing area 24. This method does not require the construction of a grammar pattern, and can make term matching more convenient and faster. However, the target grammar is generated according to grammar pattern A and grammar pattern B, so that the matching results of term matching according to the target grammar are more accurate.

[0112] S40: Establishing a mapping relationship between the target to-be-matched medical term and the target standard medical term.

[0113] In this embodiment, after a target standard medical term is obtained by matching from a plurality of standard medical terms, a mapping relationship between the target to-be-matched medical term and the target standard medical term is established.

[0114] For example, Figure 2 As shown, the graphical user interface also includes: a matching result display area 25 and a mapping result display list 26, the matching result display area 25 is used to display the target standard medical term that matches the medical term to be matched, and an "adopt" control is displayed in the area where the target standard medical term is located. In response to a confirmation operation on the "adopt" control, it is determined to establish a mapping relationship between the target medical term to be matched and the target standard medical term, and the target standard medical term is displayed at a position corresponding to the medical term to be matched in the mapping result display list 26, thereby completing the establishment of the mapping relationship between the medical term to be matched and the target standard medical term.

[0115] It should be noted that if Figure 2 As shown, the graphical user interface also includes: a filtering grammar pattern editing area 27, through which a user can input a filtering grammar pattern, and in response to a click operation on the filtering control, candidate medical terms to be matched that satisfy the filtering grammar pattern are selected from the dictionary of medical terms to be matched and displayed in the list of medical terms to be matched 23, so as to select target medical terms to be matched from the candidate medical terms to be matched, wherein the filtering grammar pattern can be the same as grammar pattern A.

[0116] The medical term matching method provided in the above embodiment can, on the one hand, flexibly construct grammar pattern A and grammar pattern B through human-computer interaction, so as to determine the mapping logic according to the target grammar generated by grammar pattern A and grammar pattern B, thereby improving the flexibility of matching the medical terms to be matched and the standard medical terms; on the other hand, the medical terms to be matched can be parsed more accurately through grammar pattern A, and the standard medical terms can be matched more accurately according to the target grammar, thereby improving the accuracy of medical term matching.

[0117] The following combination Figure 3 A detailed description is given of an implementation method for structuring the medical terms to be matched in this embodiment.

[0118] Please refer to Figure 3 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 2 ,like Figure 3 As shown, before parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched in the above S20, the method may further include:

[0119] S61: Using the multiple word attributes in the first grammatical structure, extracting attributes of the original medical term to be matched, and determining multiple attribute keywords of the original medical term to be matched.

[0120] S62: Determine structured medical terms to be matched based on multiple attribute keywords of the original medical terms to be matched.

[0121] In this embodiment, since the original medical terms are described in natural language, there may be problems of difficulty in identification during the term matching process, resulting in poor term matching accuracy. In order to improve the term matching accuracy, the medical terms need to be structured before term matching.

[0122] Specifically, a first grammatical structure is constructed according to word attributes of the original medical terms to be matched, the first grammatical structure is composed of at least one word attribute, and attributes are extracted from the original medical terms to be matched according to the word attributes contained in the first grammatical structure, and attribute keywords corresponding to each word attribute in the first grammatical structure are determined, and structured medical terms to be matched are constructed according to the attribute keywords corresponding to at least one word attribute.

[0123] For example, for the medical term CT femur plain scan (using ECG gating) to be matched, a first grammatical structure = device? method? bodypart is constructed, and attributes of the medical term to be matched are extracted according to the first grammatical structure, and the attribute keywords corresponding to the word attributes device, method, and bodypart are determined to be CT, plain scan, and femur, respectively. According to each attribute keyword, a structured medical term to be matched is determined.

[0124] The following combination Figure 4 A detailed description is given of an implementation method for structuring standard medical terms in this embodiment.

[0125] Please refer to Figure 4 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 3 ,like Figure 4 As shown, before matching the plurality of structured standard medical terms in the standard medical term dictionary according to the target grammar formed by the main keyword b and the modified keywords in the above S30, the method may further include:

[0126] S63: Using the multiple word attributes in the second grammatical structure, extracting attributes of the original standard medical terminology, and determining multiple attribute keywords of the original standard medical terminology.

[0127] S64: Determine a structured standard medical term based on multiple attribute keywords of the original standard medical term.

[0128] In this embodiment, a second grammatical structure is constructed based on the word attributes of the original standard medical terminology, and the second grammatical structure is composed of at least one word attribute. Based on the word attributes contained in the second grammatical structure, attribute extraction is performed on the original standard medical terminology, and attribute keywords corresponding to each word attribute in the second grammatical structure are determined. Based on the attribute keywords corresponding to at least one word attribute, a structured standard medical terminology is constructed.

[0129] The medical term matching method provided in the above embodiment extracts attributes of the original medical terms to be matched and the standard medical terms according to the first grammatical structure and the second grammatical structure, respectively, and determines the structured medical terms to be matched and the structured standard medical terms according to the extracted attribute keywords, so as to perform term matching according to the structured medical terms to be matched and the structured standard medical terms, thereby improving the accuracy of term matching.

[0130] In a possible implementation, the method may further include: constructing a first grammatical model based on structured medical terms to be matched, constructing a second grammatical model based on structured standard medical terms, generating at least one grammatical pattern to be matched of a dictionary of medical terms to be matched based on the first grammatical model; and generating at least one standard grammatical pattern of a dictionary of standard medical terms based on the second grammatical model.

[0131] In this embodiment, a dictionary of medical terms to be matched is obtained, and for the medical terms to be matched in the dictionary of medical terms to be matched, a first grammatical structure analysis is performed on the medical terms to be matched to determine a plurality of words included in the medical terms to be matched, and a first grammatical model of the medical terms to be matched is constructed based on the plurality of words included in the medical terms to be matched and the word attributes of the plurality of words.

[0132] Similarly, a standard medical terminology dictionary is obtained, and for the standard medical terminology in the standard medical terminology dictionary, a second grammatical structure analysis is performed on the standard medical terminology to determine multiple words included in the standard medical terminology, and a second grammatical model of the standard medical terminology dictionary is constructed based on the multiple words included in the target medical terminology and the word attributes of the multiple words.

[0133] According to the first grammatical model of the dictionary of medical terms to be matched, keywords are set for a part of the word attributes in the first grammatical model, so as to generate at least one grammatical pattern to be matched according to the keywords and another part of the word attributes. Similarly, according to the second grammatical model of the standard medical terminology dictionary, keywords are set for a part of the word attributes in the second grammatical model, so as to generate at least one standard grammatical pattern according to the keywords and another part of the word attributes.

[0134] It should be noted that, generally, multiple medical terms in each usage scenario in a medical unit adopt the same grammatical structure. Therefore, the same first grammatical model can be used for all the medical terms to be matched in the dictionary of medical terms to be matched; of course, if the grammatical structures of multiple medical terms to be matched in the dictionary of medical terms to be matched are different, a first grammatical model can also be constructed separately for each medical term to be matched.

[0135] In some embodiments, the process of performing grammatical analysis on the medical terms to be matched and determining the multiple words and grammatical structures contained in the medical terms to be matched can be performed by manual grammatical analysis or by model training using a machine learning method, and the trained grammatical analysis model is used to perform grammatical analysis on the medical terms to be matched. This embodiment does not impose any restrictions on this.

[0136] For example, take the medical term to be matched "abdominal color Doppler ultrasound examination (liver, gallbladder, pancreas, spleen, and kidneys)" as an example. The medical term to be matched is a medical term for an examination scenario. By performing grammatical analysis on "abdominal color Doppler ultrasound examination (liver, gallbladder, pancreas, spleen, and kidneys)", it is determined that the medical term to be matched is a phrase or phrase composed of multiple words, and it is determined that "abdomen" is the attributive that modifies "color Doppler ultrasound examination". Therefore, the grammatical type of the medical term to be matched is determined to be a "modifier phrase". According to the grammatical logic of the "modifier phrase", the core word and modifier of the medical term to be matched are determined. The word attribute of the core word "color Doppler ultrasound examination" of "abdominal color Doppler ultrasound examination (liver, gallbladder, pancreas, spleen, and kidneys)" is the examination "method", and the word attribute of the modifier "abdomen" is the human body "part". Therefore, the first grammatical model of the dictionary of medical terms to be matched is "part" + "method".

[0137] In some embodiments, the medical terms to be matched may also include supplementary descriptions in brackets, and the word attributes of the words in the brackets may be further parsed to construct the first grammatical model of the medical term dictionary to be matched as "part" + "method" + ("part").

[0138] It should be noted that special symbols such as brackets are mainly used to construct grammatical models. When constructing a grammatical pattern based on the grammatical model, special symbols are not required. Only the words contained in the special symbols are required.

[0139] It should also be noted that by performing grammatical analysis on multiple medical terminology dictionaries containing more than 2000 medical terms, it was determined that the number of grammatical models involved in each medical terminology dictionary does not exceed 10. Therefore, there is no need to perform grammatical analysis on all medical terms in the medical terminology dictionary.

[0140] For example, for the first grammatical model of "bodypart"+"method", the keyword of "method" is set to CT, and the grammatical pattern to be matched "bodypart: CT" is generated with CT and the word attribute bodypart.

[0141] The following combination Figure 5 An implementation method of matching standard medical terms according to the target grammar in this embodiment is described in detail.

[0142] Please refer to Figure 5 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 4 ,like Figure 5As shown, the process of matching a plurality of structured standard medical terms in the standard medical term dictionary according to the target grammar composed of the main keyword b and the modified keywords to obtain the target standard medical term corresponding to the target grammar in S30 may include:

[0143] S31: Matching multiple structured standard medical terms according to the target grammar composed of the main keyword b and the modified keywords to obtain a matching result 1 of at least one candidate standard medical term 1.

[0144] Among them, the matching result 1 is used to indicate that the candidate standard medical term 1 accurately matches the main keyword b and / or the modified keyword.

[0145] In this embodiment, multiple standard medical terms are matched according to the main keyword b and the modifying keywords in the target grammar, and a standard medical term that accurately matches the main keyword b and / or the modifying keywords is determined from the multiple standard medical terms to obtain at least one candidate standard medical term 1. The matching result 1 indicates that the candidate standard medical term 1 matches the main keyword b, or matches the modifying keywords, or matches both the main keyword b and the modifying keywords.

[0146] S32: Calculate the matching degree of at least one candidate standard medical term 1 according to the matching result 1, the trunk attention degree and the modified attention degree.

[0147] In this embodiment, the target grammar also includes: the main attention degree of the main keyword b and the modification attention degree of the modification keyword, and the main attention degree and the modification attention degree are respectively used to indicate the importance of the main keyword b and the modification keyword in the target grammar.

[0148] The matching result 1 of the candidate standard medical term 1 with the main keyword b and the modified keyword includes: whether the candidate standard medical term 1 matches the main keyword b, and whether the candidate standard medical term 1 matches the modified keyword.

[0149] For example, please refer to Table 2, which is a calculation list of matching result 1 and matching degree provided in an embodiment of the present application. As shown in Table 2, the method for calculating the matching degree of candidate standard medical term 1 based on matching result 1 and trunk attention degree and modified attention degree can be: if candidate standard medical term 1 only matches trunk keyword b, then the matching degree of candidate standard medical term 1 is trunk attention degree; if candidate standard medical term 1 only matches modified keyword, then the matching degree of candidate standard medical term 1 is modified attention degree; if candidate standard medical term 1 matches both trunk keyword b and modified keyword, then the matching degree of candidate standard medical term 1 is the sum of trunk attention degree and modified attention degree.

[0150] Table 2 Matching result 1 and matching degree calculation list

[0151] Matching result 1 Match Matches the main keyword b Matching degree = main attention degree Matches modified keywords Matching degree = modified attention Matches the main keyword b and modified keywords Matching degree = main attention degree + modification attention degree

[0152] In some embodiments, the target grammar may only include the main attention of the main keyword b or the modified attention of the modified keyword, and the attention of the keyword not included in the target grammar may be the default attention. As shown in Table 1, the grammar pattern B containing the modified attention can be expressed as bodypart+“:100CT”, and the grammar pattern B containing the main attention can be expressed as bodypart+“$ultrasound:100”.

[0153] In one possible implementation, trunk attention and modification attention can be defined in grammar mode B, and the target grammar is generated based on the trunk attention and modification attention in grammar mode B, as well as modification keywords; the trunk attention and modification attention can also be edited directly in the target grammar.

[0154] For examples, please refer to Figure 6 , which is a schematic diagram of a graphical user interface provided in an embodiment of the present application Figure 2 ,like Figure 6 As shown, the target grammar is "Pelvic CT: 100", the trunk attention of the trunk keyword b "CT" is 100, and the modification attention of the modification keyword "pelvic" is 10 by default. According to the matching results of at least one candidate standard medical term 1 with the trunk keyword b "CT" and the modification keyword "pelvic", as well as the trunk attention 100 and the modification attention 10, the matching degree of at least one candidate standard medical term 1 is calculated, among which pelvic CT examination matches both the trunk keyword b "CT" and the modification keyword "pelvic", and its matching degree is 110, CT examination of the brain, CT examination of the spinal cord, etc. only match the trunk keyword b "CT", and their matching degree is 100, and pelvic ultrasound examination only matches the modification keyword "pelvic", and its matching degree is 10.

[0155] S33: Select a target standard medical term from at least one candidate standard medical term 1 according to the matching degree of at least one candidate standard medical term 1 .

[0156] In this embodiment, Figure 6 As shown in the matching result display area 25, at least one candidate standard medical term 1 can be sorted according to the matching degree of at least one candidate standard medical term 1, and the matching degree of each candidate standard medical term 1 can be displayed to the user, so that the user can select a target standard medical term from at least one candidate standard medical term 1 according to the matching degree to establish a mapping relationship between the target medical term to be matched and the target standard medical term.

[0157] The medical term matching method provided in the above embodiment calculates the matching degree of at least one candidate standard medical term 1 according to the trunk attention degree of the trunk keyword b and the modified attention degree of the modified keyword, so that the user can select the target standard medical term with a better matching attention degree according to the matching degree, thereby improving the matching accuracy of the target medical term to be matched and the target standard medical term, and the matching quality is higher; and because the trunk attention degree and the modified attention degree can be customized by the user, the matching flexibility is higher.

[0158] The following combination Figure 7 Another implementation of matching standard medical terms according to the target grammar in this embodiment is described in detail.

[0159] Please refer to Figure 7 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 5 ,like Figure 7 As shown, the process of matching a plurality of structured standard medical terms in the standard medical term dictionary according to the target grammar composed of the main keyword b and the modified keywords to obtain the target standard medical term corresponding to the target grammar in S30 may include:

[0160] S34: According to the word attribute b of the main keyword b, determine the extended keyword 1 that matches the main keyword b from the term set of the word attribute b.

[0161] In this embodiment, when performing grammatical analysis on the medical term dictionary to be matched and the standard medical term dictionary, the multiple words are stored in term sets corresponding to different term attributes according to the term attributes of the multiple words contained in each medical term; the term set corresponding to the term attribute b is obtained according to the term attribute b of the trunk keyword b, and at least one extended keyword 1 matching the trunk keyword b is selected from the term set corresponding to the term attribute b.

[0162] In some embodiments, in the term set of each word attribute, each word is divided into multiple term subsets according to the semantics of each word in the term set, and the words included in each term subset have a preset association relationship.

[0163] For example, the preset association relationship can be an inclusion relationship or a synonym relationship, for example, Doppler ultrasound, color ultrasound, TCD (Ton Crush Day, transcranial Doppler) are synonyms, magnetic resonance water imaging and MRI water imaging are synonyms, CT enhancement, CT contrast enhancement, contrast enhancement and enhancement are synonyms, endoscope and endoscope are synonyms, magnetic resonance plain scan and MRI plain scan are synonyms, magnetic resonance enhancement and MRI enhancement are synonyms; bone joints and knee joints, wrist joints, ulna and radius, elbow joints, palms, shoulder joints, calcaneus, feet, ankle joints, tibia and fibula, patella, femur, hip joints, pelvis, bone and joint system, thigh and joints are Inclusion relationship: the oral cavity and teeth are in an inclusion relationship; the maxillofacial region and the maxilla, mandible, zygomatic bone, and temporomandibular joint are in an inclusion relationship; the spine and the cervical vertebrae, lumbar vertebrae, thoracic vertebrae, and sacrum are in an inclusion relationship; the blood vessels and the carotid artery, vertebral artery, vein, deep vein, radial artery, and cephalic vein are in an inclusion relationship; the nose and the paranasal sinuses, paranasal sinuses, nose and paranasal sinuses, paranasal sinuses, nasal bones, and nasopharynx are in an inclusion relationship; the urinary system and KUB, kidneys, ureters, bladder, and prostate are in an inclusion relationship; the ear and the inner ear and middle ear are in an inclusion relationship.

[0164] It should be noted that, by checking multiple medical terminology dictionaries, it was found that there were a lot of duplicate terms in the terms involved in the multiple medical terminology dictionaries. Therefore, there is no need to create a separate term set for each medical term dictionary. It is only necessary to add the newly appeared terms to the term set of the word attribute.

[0165] S35: According to the word attribute a of the modified keyword, determine the extended keyword 2 that matches the modified keyword from the term set of the word attribute a.

[0166] In this embodiment, a term set corresponding to the word attribute a is obtained, and at least one extended keyword 2 matching the modified keyword is selected from the term set corresponding to the word attribute a.

[0167] For example, the method of determining the extended keyword 2 that matches the modified keyword is the same as the method of determining the extended keyword 1 that matches the main keyword b, and will not be described in detail here.

[0168] S36: Match multiple structured standard medical terms in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar.

[0169] In this embodiment, based on the main keyword b, modifying keywords, extended keyword 1 matched by the main keyword b, and extended keyword 2 matched by the modifying keywords in the target grammar, standard medical terms matching the main keyword b, modifying keywords, extended keyword 1 and / or extended keyword 2 are determined from multiple standard medical terms in the standard medical term dictionary as target standard medical terms.

[0170] In some embodiments, if in the process of matching the standard medical terminology dictionary, it is necessary to expand the main keyword b and / or the modified keyword according to the term set, the target grammar also includes: an extended identifier. The extended identifier in the target grammar can be generated according to the extended identifier in the grammar pattern B, or it can refer to directly editing the extended identifier in the target grammar editing area 24.

[0171] For example, as shown in Table 1, the extension identifier may be $, and the grammatical pattern Bbodypart+“$ultrasound:100” indicates that the main keyword b “ultrasound” is extended. According to the term set, the synonyms of ultrasound may be determined to be Doppler ultrasound and TCD.

[0172] The following combination Figure 8 A detailed description is given of an implementation method of matching standard medical terms according to target grammar, target keywords and target phrases in this embodiment.

[0173] Please refer to Figure 8 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 6 ,like Figure 8 As shown, the process of matching multiple structured standard medical terms in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar in S36 may include:

[0174] S361: Match multiple structured standard medical terms according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain a matching result 2 of at least one candidate standard medical term 2.

[0175] Among them, the matching result 2 is used to indicate that the candidate standard medical term 2 matches the main keyword b, the modified keyword, the extended keyword 1 and / or the extended keyword 2.

[0176] S362: Calculate the matching degree of at least one candidate standard medical term 2 according to the matching result 2, the trunk attention degree, the modified attention degree, the first similarity and the second similarity.

[0177] The first similarity is the similarity between the extended keyword 1 and the main keyword b, and the second similarity is the similarity between the extended keyword 2 and the modified keyword.

[0178] In this embodiment, the matching result 2 of the candidate standard medical term 2 with the main keyword b and the modifying keyword includes: whether the candidate standard medical term 2 matches the main keyword b, and whether the candidate standard medical term 2 matches the modifying keyword, or, whether the candidate standard medical term 2 matches a target keyword, and whether the candidate standard medical term 2 matches a target phrase.

[0179] For example, please refer to Table 3, which is a calculation list of matching results 2 and matching degrees provided in an embodiment of the present application. As shown in Table 3, the method for calculating the matching degree of candidate standard medical term 1 according to matching result 1, trunk attention degree, modified attention degree, first similarity and second similarity can be: if candidate standard medical term 2 only matches trunk keyword b, then the matching degree of candidate standard medical term 2 is trunk attention degree; if candidate standard medical term 2 only matches modified keyword, then the matching degree of candidate standard medical term 2 is modified attention degree; if candidate standard medical term 2 matches both trunk keyword b and modified keyword, then the matching degree of candidate standard medical term 2 is the sum of trunk attention degree and modified attention degree.

[0180] If the candidate standard medical term 2 only matches the extended keyword 1, the matching degree of the candidate standard medical term 2 is the attention degree of the extended keyword 1; if the candidate standard medical term 2 only matches the extended keyword 2, the matching degree of the candidate standard medical term 2 is the attention degree of the extended keyword 2; if the candidate standard medical term 2 matches the extended keyword 1 and the extended keyword 2 respectively, the matching degree of the candidate standard medical term 2 is the sum of the attention degree of the extended keyword 1 and the attention degree of the extended keyword 2; wherein, the attention degree of the extended keyword 1 is the product of the first similarity and the trunk attention degree, and the attention degree of the extended keyword 2 is the product of the second similarity and the modified attention degree.

[0181] Table 3 Matching result 2 and matching degree calculation list

[0182]

[0183] It should be noted that the similarity between extended keyword 1 and main keyword b can be calculated based on the edit distance between extended keyword 1 and main keyword b, or based on the word vector distance between extended keyword 1 and main keyword b; the similarity between extended keyword 2 and modified keyword can be calculated based on the edit distance between extended keyword 2 and modified keyword, or based on the word vector distance between extended keyword 2 and modified keyword, and this implementation does not impose any restrictions on this. Among them, the edit distance (Levenshtein distance) is a quantitative measurement of the degree of difference between two character strings, and the measurement method is to determine the number of times a character string needs to be processed to convert one character string into another character string.

[0184] S363: Select a target standard medical term from at least one candidate standard medical term 2 according to the matching degree of at least one candidate standard medical term 2.

[0185] In this embodiment, the method of selecting the target standard medical term from at least one candidate standard medical term 2 is the same as the method of selecting the target standard medical term from at least one candidate standard medical term 1 in S33 above, and will not be described in detail here.

[0186] The medical term matching method provided in the above embodiment expands the main keyword b and the modifying keyword through the term set, so as to match multiple standard medical terms in the standard medical term dictionary according to the expanded main keyword b, modifying keyword, extended keyword 1 and extended keyword 2, and fully considers the word expressions that may be used by the main keyword and the modifying keyword in the standard medical term dictionary to improve the matching accuracy; and calculates the matching degree according to the similarity between the main keyword b and the extended keyword 1, and the similarity between the modifying keyword and the extended keyword 2, so as to make the calculation result of the matching degree more accurate, so that the user can select the target standard medical term with the highest matching degree to establish a mapping relationship with the target medical term to be matched.

[0187] The following combination Fig. 9 Another implementation of matching standard medical terms according to the target grammar in this embodiment is described in detail.

[0188] Please refer to Fig. 9 , which is a flow chart of the medical term matching method provided in the embodiment of the present application Figure 7 ,like Fig. 9 As shown, the process of matching a plurality of structured standard medical terms in the standard medical term dictionary according to the target grammar composed of the main keyword b and the modified keywords to obtain the target standard medical term corresponding to the target grammar in S30 may include:

[0189] S37: Fuzzy matching is performed on multiple standard medical terms with the main keyword b and the modified keyword respectively to obtain a matching result 3 of at least one candidate standard medical term 3.

[0190] Among them, the matching result 3 is used to indicate that the candidate standard medical term 3 is fuzzy matched with the main keyword b and / or the modified keyword.

[0191] S38: Calculate the matching degree of at least one candidate standard medical term 3 according to the matching result 3, the trunk attention degree, the modified attention degree, the third similarity degree and the fourth similarity degree.

[0192] Among them, the third similarity is the similarity between the candidate standard medical term 3 and the main keyword b, and the fourth similarity is the similarity between the candidate standard medical term 3 and the modified keyword.

[0193] In this embodiment, fuzzy matching is performed on multiple standard medical terms based on the main keyword b and the modifying keywords in the target grammar, and a standard medical term similar to the main keyword b and / or the modifying keywords is determined from the multiple standard medical terms to obtain at least one candidate standard medical term 3. The matching result 3 includes: the candidate standard medical term 3 is similar to the main keyword b, or the candidate standard medical term 3 is similar to the modifying keywords, and the candidate standard medical term 3 is similar to both the main keyword b and the modifying keywords.

[0194] For example, please refer to Table 4, which is a list of matching results 3 and calculation of matching results provided in an embodiment of the present application. As shown in Table 4, if the candidate standard medical term 3 is only fuzzy matched with the main keyword b, the matching degree of the candidate standard medical term 3 is the product of the third similarity and the main attention degree; if the candidate standard medical term 3 is only fuzzy matched with the modified keyword, the matching degree of the candidate standard medical term 3 is the product of the fourth similarity and the modified attention degree; if the candidate standard medical term 3 is fuzzy matched with the main keyword b and the modified keyword respectively, the matching degree of the candidate standard medical term 3 is the product of the third similarity and the main attention degree, and the sum of the product of the fourth similarity and the modified attention degree.

[0195] Table 4 Matching result 3 and matching degree calculation list

[0196]

[0197] S39: Select a target standard medical term from at least one candidate standard medical term 3 according to the matching degree of at least one candidate standard medical term 3 .

[0198] In this embodiment, the method of selecting the target standard medical term from at least one candidate standard medical term 3 is the same as the method of selecting the target standard medical term from at least one candidate standard medical term 1 in S33 above, and will not be described in detail here.

[0199] In some embodiments, if fuzzy matching of the main keyword b and / or the modified keyword is required during the matching process of the standard medical terminology dictionary, the target grammar also includes: a fuzzy matching identifier. The fuzzy matching identifier in the target grammar can be generated based on the fuzzy matching identifier in the grammar pattern B, or it can refer to directly editing the fuzzy matching identifier in the target grammar editing area 24.

[0200] The medical term matching method provided in the above embodiment performs fuzzy matching on the standard medical term dictionary to screen all multiple standard medical terms that may match the main keyword b and the modified keyword from the standard medical term dictionary, fully considering the possible word expressions of the main keyword and the modified keyword in the standard medical term dictionary, thereby improving the matching accuracy; and the matching degree is calculated based on the similarity between the standard medical term and the main keyword b, and the similarity between the standard medical term and the modified keyword, so that the calculation result of the matching degree can be made more accurate, so that the user can select the target standard medical term with the highest matching degree to establish a mapping relationship with the target medical term to be matched.

[0201] Based on the above embodiments, the present application also provides a medical term matching device. Fig.10 , is a schematic diagram of the structure of the medical term matching device provided in an embodiment of the present application, such as Fig.10 As shown, the device comprises:

[0202] The grammar pattern receiving module 10 is used to obtain a grammar pattern A for the medical term dictionary to be matched and a grammar pattern B for the preset standard medical term dictionary, wherein the grammar pattern A is composed of: a main keyword a and a word attribute a, and the grammar pattern B is composed of: a main keyword b and a word attribute a;

[0203] The word attribute parsing module 20 is used to parse the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtain the keyword corresponding to the word attribute a as the modified keyword, and the target medical term to be matched includes: the main keyword a;

[0204] The medical term matching module 30 is used to match a plurality of standard medical terms structured in the standard medical term dictionary according to the target grammar composed of the main keyword b and the modified keywords, and obtain the target standard medical term corresponding to the target grammar;

[0205] The mapping relationship establishing module 40 is used to establish a mapping relationship between the target to-be-matched medical term and the target standard medical term.

[0206] Optionally, the device may further include:

[0207] The first term structuring module is used to extract attributes of the original medical terms to be matched by using multiple word attributes in the first grammatical structure, and determine multiple attribute keywords of the original medical terms to be matched; and determine structured medical terms to be matched based on the multiple attribute keywords of the original medical terms to be matched.

[0208] Optionally, the device may further include:

[0209] The second term structuring module is used to extract attributes of the original standard medical terms using multiple word attributes in the second grammatical structure, determine multiple attribute keywords of the original standard medical terms; and determine structured standard medical terms based on the multiple attribute keywords of the original standard medical terms.

[0210] Optionally, the target grammar further includes: the main attention of the main keyword b and the modified attention of the modified keyword. The medical term matching module 30 includes:

[0211] A first candidate term matching unit is used to match the structured multiple standard medical terms according to the target grammar composed of the main keyword b and the modified keyword, and obtain a matching result 1 of at least one candidate standard medical term 1, wherein the matching result 1 is used to indicate that the candidate standard medical term 1 accurately matches the main keyword b and / or the modified keyword;

[0212] A first matching degree calculation unit, configured to calculate a matching degree of at least one candidate standard medical term 1 according to the matching result 1, the main attention degree and the modified attention degree;

[0213] The first target term selection unit is used to select a target standard medical term from at least one candidate standard medical term 1 according to the matching degree of at least one candidate standard medical term 1 .

[0214] Optionally, the medical term matching module 30 includes:

[0215] A main keyword expansion unit, used to determine an expansion keyword 1 matching the main keyword b from a term set of the term attribute b according to the term attribute b of the main keyword b;

[0216] A modified keyword expansion unit, used to determine an expanded keyword 2 matching the modified keyword from a term set of the term attribute a according to the term attribute a of the modified keyword;

[0217] The medical term matching unit is used to match multiple standard medical terms structured in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar.

[0218] Optionally, the target grammar includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the medical term matching unit includes:

[0219] A second candidate term matching unit is used to match the structured multiple standard medical terms according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, and obtain a matching result 2 of at least one candidate standard medical term 2, wherein the matching result 2 is used to indicate that the candidate standard medical term 2 matches the main keyword b, the modified keyword, the extended keyword 1 and / or the extended keyword 2;

[0220] A second matching degree calculation unit is used to calculate the matching degree of at least one candidate standard medical term 2 according to the matching result 2, the main attention degree, the modified attention degree, the first similarity and the second similarity, wherein the first similarity is the similarity between the extended keyword 1 and the main keyword b, and the second similarity is the similarity between the extended keyword 2 and the modified keyword;

[0221] The second target term selection unit is used to select a target standard medical term from at least one candidate standard medical term 2 according to the matching degree of at least one candidate standard medical term 2.

[0222] Optionally, the target grammar includes: the main attention of the main keyword b and the modified attention of the modified keyword, and the medical term matching module 30 includes:

[0223] A third candidate term matching unit is used to perform fuzzy matching on the plurality of standard medical terms with the main keyword b and the modified keyword, respectively, to obtain a matching result 3 of at least one candidate standard medical term 3, wherein the matching result 3 is used to indicate that the candidate standard medical term 3 is fuzzy matched with the main keyword b and / or the modified keyword;

[0224] A third matching degree calculation unit is used to calculate the matching degree of at least one candidate standard medical term 3 according to the matching result 3, the main attention degree, the modified attention degree, the third similarity and the fourth similarity; wherein the third similarity is the similarity between the candidate standard medical term 3 and the main keyword b, and the fourth similarity is the similarity between the candidate standard medical term 3 and the modified keyword;

[0225] The third target term selection unit is configured to select a target standard medical term from at least one candidate standard medical term 3 according to a matching degree of at least one candidate standard medical term 3 .

[0226] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0227] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors, or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0228] Please refer to Fig.11 , is a schematic diagram of a computer device provided in an embodiment of the present application, such as Fig.11 As shown, the computer device 100 includes: a processor 101, a storage medium 102 and a bus, the storage medium 102 stores program instructions executable by the processor 101, when the computer device 100 is running, the processor 101 and the storage medium 102 communicate through the bus, and the processor 101 executes the program instructions to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0229] Optionally, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above method embodiment is executed. The specific implementation method and technical effect are similar and will not be described in detail here.

[0230] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units 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 devices or units, which can be electrical, mechanical or other forms.

[0231] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0232] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0233] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0234] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A medical term matching method, characterized in that: The method comprises: Acquire a grammatical pattern A for a medical term dictionary to be matched and a grammatical pattern B for a preset standard medical term dictionary, wherein the grammatical pattern A consists of: a main keyword a and a word attribute a, and the grammatical pattern B consists of: a main keyword b and the word attribute a; Parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtaining a keyword corresponding to the word attribute a as a modified keyword, wherein the target medical term to be matched includes: the main keyword a; According to the target grammar formed by the main keyword b and the modified keyword, a plurality of structured standard medical terms in the standard medical term dictionary are matched to obtain a target standard medical term corresponding to the target grammar; A mapping relationship between the target to-be-matched medical term and the target standard medical term is established.

2. The method according to claim 1, characterized in that Before parsing the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, the method further includes: Using the multiple word attributes in the first grammatical structure, extracting attributes of the original medical term to be matched, and determining multiple attribute keywords of the original medical term to be matched; According to the multiple attribute keywords of the original medical term to be matched, a structured medical term to be matched is determined.

3. The method according to claim 1, characterized in that Before matching the plurality of structured standard medical terms in the standard medical term dictionary according to the target grammar formed by the main keyword b and the modified keyword, the method further includes: Using the multiple word attributes in the second grammatical structure, extracting attributes from the original standard medical term, and determining multiple attribute keywords of the original standard medical term; A structured standard medical term is determined according to a plurality of attribute keywords of the original standard medical term.

4. The method according to claim 1, characterized in that The target grammar further includes: the main attention degree of the main keyword b and the modified attention degree of the modified keyword. The target grammar formed by the main keyword b and the modified keyword matches a plurality of structured standard medical terms in the standard medical term dictionary to obtain target standard medical terms corresponding to the target grammar, including: According to the target grammar formed by the main keyword b and the modified keyword, the structured multiple standard medical terms are matched to obtain a matching result 1 of at least one candidate standard medical term 1, wherein the matching result 1 is used to indicate that the candidate standard medical term 1 accurately matches the main keyword b and / or the modified keyword; Calculating the matching degree of the at least one candidate standard medical term 1 according to the matching result 1, the trunk attention degree and the modified attention degree; The target standard medical term is selected from the at least one candidate standard medical term 1 according to the matching degree of the at least one candidate standard medical term 1 .

5. The method according to claim 1, characterized in that The target grammar formed by the main keyword b and the modified keyword is matched with a plurality of structured standard medical terms in the standard medical term dictionary to obtain the target standard medical term corresponding to the target grammar, including: According to the word attribute b of the main keyword b, determining the extended keyword 1 that matches the main keyword b from the term set of the word attribute b; According to the word attribute a of the modified keyword, determining the extended keyword 2 that matches the modified keyword from the term set of the word attribute a; According to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, a plurality of structured standard medical terms in the standard medical term dictionary are matched to obtain a target standard medical term corresponding to the target grammar.

6. The method according to claim 5, characterized in that The target grammar includes: the main attention degree of the main keyword b and the modified attention degree of the modified keyword, and the matching of multiple structured standard medical terms in the standard medical term dictionary according to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2 to obtain the target standard medical term corresponding to the target grammar includes: According to the main keyword b, the modified keyword, the extended keyword 1 and the extended keyword 2, the structured multiple standard medical terms are matched to obtain a matching result 2 of at least one candidate standard medical term 2, wherein the matching result 2 is used to indicate that the candidate standard medical term 2 matches the main keyword b, the modified keyword, the extended keyword 1 and / or the extended keyword 2; Calculate the matching degree of the at least one candidate standard medical term 2 according to the matching result 2, the main attention degree, the modified attention degree, the first similarity and the second similarity, wherein the first similarity is the similarity between the extended keyword 1 and the main keyword b, and the second similarity is the similarity between the extended keyword 2 and the modified keyword; According to the matching degree of the at least one candidate standard medical term 2, In the selection of standard medical term 2, the target standard medical term is selected.

7. The method according to claim 1, characterized in that The target grammar includes: the main attention degree of the main keyword b and the modified attention degree of the modified keyword. The target grammar formed by the main keyword b and the modified keyword matches a plurality of structured standard medical terms in the standard medical term dictionary to obtain the target standard medical term corresponding to the target grammar, including: Performing fuzzy matching on the plurality of standard medical terms, respectively, with the main keyword b and the modified keyword, and obtaining a matching result 3 of at least one candidate standard medical term 3, wherein the matching result 3 is used to indicate that the candidate standard medical term 3 is fuzzy matched with the main keyword b and / or the modified keyword; Calculate the matching degree of the at least one candidate standard medical term 3 according to the matching result 3, the main attention degree, the modified attention degree, the third similarity and the fourth similarity, wherein the third similarity is the similarity between the candidate standard medical term 3 and the main keyword b, and the fourth similarity is the similarity between the candidate standard medical term 3 and the modified keyword; The target standard medical term is selected from the at least one candidate standard medical term 3 according to the matching degree of the at least one candidate standard medical term 3 .

8. A medical term matching device, characterized in that: The device comprises: A grammar pattern receiving module, used for acquiring a grammar pattern A for a medical term dictionary to be matched and a grammar pattern B for a preset standard medical term dictionary, wherein the grammar pattern A is composed of a main keyword a and a word attribute a, and the grammar pattern B is composed of a main keyword b and the word attribute a; A word attribute parsing module is used to parse the word attribute a of the structured target medical term to be matched in the dictionary of medical terms to be matched, and obtain a keyword corresponding to the word attribute a as a modified keyword, wherein the target medical term to be matched includes: the main keyword a; A medical term matching module, used for matching a plurality of structured standard medical terms in the standard medical term dictionary according to a target grammar formed by the main keyword b and the modified keyword, to obtain a target standard medical term corresponding to the target grammar; The mapping relationship establishing module is used to establish a mapping relationship between the target to-be-matched medical term and the target standard medical term.

9. A computer device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor and the storage medium communicate through the bus, and the processor executes the program instructions to perform the steps of the medical term matching method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the medical term matching method according to any one of claims 1 to 7 are executed.