CN110704639A - Method and device for generating acronym documents - Google Patents

Abstract

The present invention provides a method and device for generating an acronym document. In the process of interoperating different knowledge organization systems, terms in different source vocabularies are extracted and synonymously merged to form concepts, and an integrated vocabulary is generated. The terms include Various forms of full names and abbreviations; based on abbreviation word formation rules, identify target concepts containing abbreviations in the integrated vocabulary; extract all terms of the target concept and the attributes of each term, and determine the term type of each term; The ISO25964 international standard, normalizes the knowledge representation of the target concept and all the terms of the target concept, and generates semantically rich and standardized abbreviation documents. Among them, abbreviations and their concepts inherit the rich semantic attribute information of source vocabulary and integrated vocabulary, which reduces the problem of abbreviation ambiguity.

Description

Method and device for generating acronym documents

technical field

The present invention relates to the technical field of data processing, and more particularly, to a method and device for generating an abbreviation document.

Background technique

Abbreviation is a simplified form of the full name. In Chinese, abbreviations are words that are shortened and omitted from longer words for ease of use; in English, abbreviations are usually used for multi-syllable words. Words obtained by abbreviating, such as photo is the abbreviation of photograph.

At present, the abbreviation dictionary is generally generated by processing methods such as word segmentation and labeling combined with manual proofreading, identification and extraction of abbreviations to realize the description of abbreviations. However, the traditional abbreviation dictionary only includes abbreviations, full names, Chinese translated names and annotations. However, in practical applications, due to differences in the descriptions of abbreviations in different systems, abbreviation dictionaries are used in many fields. It is easy to cause ambiguity.

SUMMARY OF THE INVENTION

In view of this, the present invention provides a method and device for generating an abbreviation document, which establishes a unified abbreviation metadata standard based on the ISO25964 international standard, has rich semantics and standard specifications, and reduces the problem of abbreviation ambiguity.

In order to solve the above-mentioned technical problems, the specific technical solutions provided by the present invention are as follows:

A method for generating acronym documents, including:

In the process of interoperability of different knowledge organization systems, terms from different source vocabularies are extracted and synonymous to form concepts, and integrated vocabularies are generated. Terms include full names and abbreviations in various forms;

Identifying the target concept containing abbreviations in the integrated vocabulary based on the abbreviation word formation rules;

Extract the attributes of the target concept and all terms, and determine the term type of each term;

Based on the ISO25964 international standard, normalized knowledge representation is performed on the target concept and all terms of the target concept, and an abbreviation document is generated.

Optionally, identifying the target concepts containing abbreviations in the integrated vocabulary based on the abbreviation word formation rules, including:

matching the terms in each concept in the integrated vocabulary with the records in the dictionary of abbreviations;

According to the comparison result, a concept in which both the abbreviation and the corresponding full name in the abbreviation dictionary exist in the integrated vocabulary list is determined as the target concept containing the abbreviation.

Optionally, extracting the attributes of the target concept and all terms, and determining the term type of each term, including:

Extract the attributes of the target concept and all terms containing abbreviations in the integrated vocabulary. Concept attributes include concept identification, term, comment, status, subject classification, hierarchical relationship and related relationship, and the integrated vocabulary where the term is located. Attributes include term Identification, word forms, usage status, annotations and source glossaries;

Extract the first letter of each non-prepositional English word in the target term, where the target term is a term composed of multiple English words;

Splicing the capital letters corresponding to each initial letter to obtain a spliced string;

If the spliced character string exists in the integrated vocabulary target concept, the spliced character string is the target abbreviation of the target term in the target concept, wherein the term type of the target abbreviation is a canonical abbreviation, If the first letter of each non-prepositional English word of the target term is capitalized, the term type of the target term is the canonical full name; if the first letter of each non-prepositional English word of the target term is lowercase or uppercase Mixed form, the term type of the target term is the common full name.

Optionally, the method further includes:

Based on the morphological variation law, the terms in the morphological variation form of the same concept as the target term in the integrated vocabulary are extracted, and the term type of such terms is other full names.

Optionally, the method further includes:

The canonical full names and canonical abbreviations of the terms in the abbreviation document are extracted to obtain the terms whose term type is the preferred word, and the terms whose term type is the preferred word are added to the abbreviation document based on the ISO25964 international standard.

Optionally, the standardized knowledge representation is performed on the target concept and all terms of the target concept based on the ISO25964 international standard, and an abbreviation document is generated, including:

Based on the ISO25964 international standard, generate the basic information and relationship description of the target concept, as well as the basic information description and term type identification of all terms of the target concept, and these descriptive information constitute the metadata model of the abbreviation document;

The abbreviation document is generated according to the metadata model of the abbreviation document, the terms corresponding to the target concept, and the term type of each term.

A device for generating an abbreviation document, comprising:

The integrated word list generation unit is used to extract terms from different source thesaurus and synonymously merge them to form concepts during the interoperability process of different knowledge organization systems. ;

The concept identification unit is used to identify the target concept containing abbreviations in the integrated vocabulary based on the abbreviation word formation rules; the term extraction unit is used to extract the attributes of the target concept and all terms, and determine the attribute of each term. term type;

The abbreviation document generating unit is configured to perform normalized knowledge representation on the target concept and all terms of the target concept based on the ISO25964 international standard, and generate an abbreviation document.

Optionally, the concept identification unit is specifically used for:

matching the terms in each concept in the integrated vocabulary with the records in the dictionary of abbreviations;

According to the comparison result, a concept in which both the abbreviation and the corresponding full name in the abbreviation dictionary exist in the integrated vocabulary list is determined as the target concept containing the abbreviation.

Optionally, the term extraction unit is specifically used for:

Extract the attributes of the target concept and all terms containing abbreviations in the integrated vocabulary. Concept attributes include concept identification, term, comment, status, subject classification, hierarchical relationship and related relationship, and the integrated vocabulary where the term is located. Attributes include term Identification, word forms, usage status, annotations and source glossaries;

Extract the first letter of each non-prepositional English word in the target term, where the target term is a term composed of multiple English words;

Splicing the capital letters corresponding to each initial letter to obtain a spliced string;

If the spliced character string exists in the integrated vocabulary target concept, the spliced character string is the target abbreviation of the target term in the target concept, wherein the term type of the target abbreviation is a canonical abbreviation, If the first letter of each non-prepositional English word of the target term is capitalized, the term type of the target term is the canonical full name; if the first letter of each non-prepositional English word of the target term is lowercase or uppercase Mixed form, the term type of the target term is the common full name.

Optionally, the term extraction unit is further configured to extract terms in the integrated vocabulary that are in the form of morphological variants of the same concept as the target term based on the morphological variation rule, and the term type of such terms is other. Full name.

Optionally, the device further includes:

The preferred word extraction unit is used to extract the canonical full name and canonical abbreviation of the term in the abbreviation document, obtain the term with the term type as the preferred word, and add the term with the term type as the preferred word to the abbreviation document based on the ISO25964 international standard.

Optionally, the abbreviation document generation unit is specifically used for:

Based on the ISO25964 international standard, generate the basic information and relationship description of the target concept, as well as the basic information description and term type identification of all terms of the target concept, and these descriptive information constitute the metadata model of the abbreviation document;

The abbreviation document is generated according to the metadata model of the abbreviation document, the terms corresponding to the target concept, and the term type of each term.

With respect to the prior art, the beneficial effects of the present invention are as follows:

The invention discloses a method for generating an abbreviation document, by extracting terms in different source vocabularies during the interoperability process of different knowledge organization systems and merging them synonymously to form concepts, generating an integrated vocabulary, and based on abbreviations Word formation rules, identify the target concepts containing abbreviations in the integrated vocabulary, extract all the terms of the target concept and the attributes of each term, and determine the term type of each term, enrich the semantic information of abbreviations, reduce abbreviations. Abbreviation ambiguity problem, and through the standardized knowledge representation of the target concept and all terms of the target concept based on the ISO25964 international standard, the generated abbreviation documents are semantically rich and standardized.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without creative work.

1 is a schematic flowchart of a method for generating an abbreviation document disclosed in an embodiment of the present invention;

2 is a schematic flowchart of a method for extracting terms with the same concept in an integrated vocabulary according to an embodiment of the present invention;

3 is a schematic flowchart of a method for generating an abbreviation document based on ISO25964 disclosed in an embodiment of the present invention;

4 is a schematic diagram of an abbreviation document disclosed in an embodiment of the present invention;

5 is a schematic diagram of another abbreviation document disclosed in an embodiment of the present invention;

6 is a schematic diagram of another acronym document disclosed in an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of an apparatus for generating an abbreviation document disclosed in an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The inventor found through research that there are many different expressions for the same abbreviation in the source vocabulary in different knowledge organization systems, and they have rich semantic relationship attributes and disciplinary characteristics. For example, "chronic myeloid leukemia" has various English expressions such as "chronic granulocytic leukemias", "chronic granulocytic leukemia", "granulocytic leukemia, Chronic", and "congenital systemic lipodystrophy" in English. "Congenital Generalized Lipodystrophy", both of which are abbreviated as CGL.

Since the traditional dictionary of abbreviations only includes abbreviations, full names, Chinese translation names and annotations, it is impossible to accurately identify and determine its true meaning when only "CGL" appears in the text. Abbreviations documents, abbreviations and their concepts have obvious semantic relationships and disciplinary characteristics. For example, CGL (Congenital Generalized Lipodystrophy) belongs to "metabolic skin disease", "CGL (Chronic Granulocytic Leukemia)" belongs to "blood disease", "tumor" , combined with the context in which "CGL" appears, its meaning can be quickly determined, reducing ambiguity when it is applied in multiple fields.

This embodiment discloses a method for generating an abbreviation document, which is applied to a system that can be connected with different knowledge organization systems. For details, please refer to FIG. 1. The method for generating an abbreviation document disclosed in this embodiment includes the following steps :

S101: During the interoperability process of different knowledge organization systems, extract terms from different source vocabularies, synonymously merge them to form concepts, and generate integrated vocabularies. Terms include various forms of full names and abbreviations;

Knowledge organization system (KOS) is a collective term for various norms and methods for knowledge organization, and is an important means of acquiring and utilizing knowledge. Knowledge organization systems are semantic tools in specific applications. The integrated vocabulary corresponds to at least one source vocabulary, and the source vocabulary covers the traditional subject thesaurus and thesaurus, and also includes a hierarchical structure used for website navigation and browsing, or the knowledge ontology of the semantic web.

The interoperability of knowledge organization systems refers to the compatibility and exchange between different knowledge organization systems.

In the process of interoperability of different knowledge organization systems, terms in different source vocabularies are extracted and synonymous to form concepts, such as the terms "Chronic Granulocytic Leukemia", "CGL", "CGL", "chronic granulocytic leukemias", "Granulocytic Leukemia, Chronic" and "granulocytic leukemia, chronic" are synonymous to form concepts, and an integrated vocabulary is generated. The integrated vocabulary covers the terms in the source vocabulary in different knowledge organization systems and Attribute information enriches the semantic information of acronyms and concepts in the integrated vocabulary.

Among them, the term includes various forms of full name and abbreviation, for example, the full name is "Chronic Granulocytic Leukemia", and the corresponding abbreviation is "CGL".

S102: Based on the abbreviation word formation rule, identify the target concept containing the abbreviation in the integrated vocabulary;

matching the terms in each concept in the integrated vocabulary with the records in the dictionary of abbreviations;

According to the comparison result, a concept in which both the abbreviation and the corresponding full name in the abbreviation dictionary exist in the integrated vocabulary list is determined as the target concept containing the abbreviation.

For example, if the concept of the abbreviation "CGL" in the abbreviation dictionary and the corresponding full name "Chronic Granulocytic Leukemia" both exist in the integrated vocabulary, it is determined as the target concept.

S103: Extract the attributes of the target concept and all terms, and determine the term type of each term;

Chinese and English abbreviations have different word formation rules. For example, "EU" is the abbreviation of "European Union" in Chinese, and "EU" is the abbreviation of "European Union".

Taking the English abbreviation word formation rule as an example, please refer to Figure 2 to extract the attributes of the target concept and all terms, and determine the term type of each term, including the following steps:

S201: Extract the attributes of the target concept and all terms containing abbreviations in the integrated vocabulary;

Concept attributes include concept identification, term, comment, state (including disabled state, activation state, etc.), subject classification, hierarchical relationship and related relationship, and integrated vocabulary, etc. The attributes of term include term identification, word form (including English text, Chinese text, etc.), usage status (including disabled status, activated status, etc.), annotations and source vocabulary, etc.

The target term is the term currently being processed, and the target term can be any term in the integrated vocabulary.

S202: Extract the first letter of each non-prepositional English word in the target term, where the target term is a term composed of multiple English words;

Prepositions such as of, at, in, by, etc., these words have no practical meaning, and the initials of prepositions are generally not included in abbreviations. Therefore, the initials of prepositions are not extracted when extracting the initials of English words of target terms.

S203: splicing the capital letters corresponding to each initial letter to obtain a spliced string;

S204: judging whether the spliced character string exists in the integrated vocabulary target concept;

If it does not exist, S205: determine that the target term is a term without abbreviations;

If there is, S206: determine the spliced string as the target abbreviation of the target term in the target concept, and determine the term type of the target abbreviation as a canonical abbreviation;

S207: Determine whether the first letter of each non-prepositional English word of the target term is capitalized;

If it is uppercase, S208: determine that the term type of the target term is the canonical full name;

If it is not capitalized, S209: determine that the term type of the target term is a common full name.

Among them, the first letter of each non-prepositional English word of the target term is in lowercase or mixed case, and the term type of the target term is the common full name. Taking the target term as "Chronic Granulocytic Leukemia" as an example, extract the capital initial letter to form a splicing The string "CGL", if the target term is "chronic granulocytic leukemias", the extracted initials need to be converted to uppercase. If "CGL" exists in the integrated vocabulary, then "CGL" is the target abbreviation of the target term "Cronic Granulocytic Leukemia" in the target concept, the term type of "CGL" is the canonical abbreviation, and the term type of "Cronic Granulocytic Leukemia" is The canonical full name, if the target term is "chronicgranulocytic leukemias", the term type of "chronic granulocytic leukemias" is the common full name.

S104: Based on the ISO25964 international standard, perform normalized knowledge representation on the target concept and all terms of the target concept, and generate an abbreviation document.

ISO25964: "Thesauriand Interoperability withOther Vocabularies". ISO25964-1 "Thesauri for Information Retrieval" (Thesaurifor Information Retrieval) provides information on the content and compilation of monolingual and multilingual thesaurus, the principles of using thesaurus, the basic principles of thesaurus construction and management, thesaurus management The basic functions of the software and the data model of the thesaurus are described. ISO 25964-2 "Interoperation with Other Thesaurus" provides a model and mapping guidelines for mapping thesaurus to other types of knowledge organizations.

Specifically, please refer to Figure 3. The method for generating abbreviation documents based on ISO25964 specifically includes the following steps:

S301: Based on the ISO25964 international standard, generate the basic information and relationship description of the target concept, as well as the basic information description and term type identification of all terms of the target concept, and these descriptive information constitute the metadata model of the abbreviation document;

Among them, the basic information of the target concept includes the above-mentioned concept identification, term, comment, status, subject classification, etc., the relationship description of the target concept includes the above-mentioned hierarchical relationship and related relationship, etc.; the basic information description of the term includes the term identification, word form, usage status, etc. , annotations and source glossaries, etc.

S302: Generate an abbreviation document according to the metadata model of the abbreviation document, the term corresponding to the target concept, and the term type of each term.

Taking the abbreviation document shown in FIG. 4 as an example, ID is a concept identifier, AID is a term identifier, ID and AID, term type and the attribute information of the concept in the integrated vocabulary constitute the metadata model of the abbreviation document.

Metadata standard compatibility is strong, based on the vocabulary interoperability standard ISO25964-2 custom extended metadata standard, with good compatibility and interoperability.

In addition to abbreviations, full names, Chinese translated names, and comments, the abbreviation document disclosed in this embodiment also integrates rich semantic information of source concepts and current concepts to reduce ambiguity.

Preferably, on the basis of the abbreviation document disclosed in the above embodiment, the canonical full name and canonical abbreviation of the term in the abbreviation document are extracted to obtain the term whose term type is the preferred word, and the term type is preferred based on the ISO25964 international standard. Word terms are added to the abbreviations document.

Taking the abbreviation document shown in Figure 5 as an example, the term whose term type is the preferred word is GCL (Chronic Granulocytic Leukemia). ambiguity.

Extract the concepts and all terms containing abbreviations in the integrated vocabulary based on the abbreviation word formation rules, and also extract other terms with the same meaning in the integrated vocabulary based on the inflection rules. In the form, the inflection rules include singular and plural word inflections aspect, tense inflections, grammar-based inflections.

Taking the abbreviation document shown in Figure 6 as an example, "Granulocytic Leukemia, Chronic" and "granulocytic leukemia, chronic" are the grammatical variant forms of "Cronic Granulocytic Leukemia", in essence, "Granulocytic Leukemia, Chronic", " granulocytic leukemia, "chronic" and "chronic Granulocytic Leukemia" are terms with the same concept.

Based on the morphological variation rule, the terms in the morphological variation form of the same concept as the target term in the above-mentioned embodiment are extracted from the integrated vocabulary, and the term type of such terms is other full names.

It can be seen that, a method for generating acronym documents disclosed in this embodiment, by extracting terms from different source vocabularies during the interoperability process of different knowledge organization systems, and synonymously merging them to form concepts, generating an integrated vocabulary, and Based on the abbreviation word formation rules, identify the target concepts containing abbreviations in the integrated vocabulary, extract the attributes of the target concept and all terms, and determine the term type of each term, enrich the semantic information of the abbreviations and reduce the number of abbreviations. The problem of ambiguity is solved, and based on the ISO25964 international standard, the target concept and all the terms of the target concept are standardized knowledge representation, so that the generated abbreviation documents are semantically rich and standardized.

Based on the method for generating an abbreviation document disclosed in the foregoing embodiment, the present embodiment correspondingly discloses an apparatus for generating an abbreviation document, please refer to FIG. 7 , including:

The integrated word list generation sheet 701 is used to extract terms from different source word lists and synonymously merge them to form concepts during the interoperability process of different knowledge organization systems, and generate an integrated word list, including full names and abbreviations. form;

A concept identification unit 702, configured to identify target concepts containing abbreviations in the integrated vocabulary based on abbreviation word formation rules;

A term extraction unit 703, configured to extract the attributes of the target concept and all terms, and determine the term type of each term;

The abbreviation document generating unit 704 is configured to perform normalized knowledge representation on the target concept and all terms of the target concept based on the ISO25964 international standard, and generate an abbreviation document.

Optionally, the concept identification unit 702 is specifically configured to:

matching the terms in each concept in the integrated vocabulary with the records in the dictionary of abbreviations;

According to the comparison result, a concept in which both the abbreviation and the corresponding full name in the abbreviation dictionary exist in the integrated vocabulary list is determined as the target concept containing the abbreviation.

Optionally, the term extraction unit 703 is specifically configured to:

Extract the attributes of the target concept and all terms containing abbreviations in the integrated vocabulary. Concept attributes include concept identification, term, comment, status, subject classification, hierarchical relationship and related relationship, and the integrated vocabulary where the term is located. Attributes include term Identification, word forms, usage status, annotations and source glossaries;

Extract the first letter of each non-prepositional English word in the target term, where the target term is a term composed of multiple English words;

Splicing the capital letters corresponding to each initial letter to obtain a spliced string;

If the spliced character string exists in the integrated vocabulary target concept, the spliced character string is the target abbreviation of the target term in the target concept, wherein the term type of the target abbreviation is a canonical abbreviation, If the first letter of each non-prepositional English word of the target term is capitalized, the term type of the target term is the canonical full name; if the first letter of each non-prepositional English word of the target term is lowercase or uppercase Mixed form, the term type of the target term is the common full name.

Optionally, the term extraction unit 703 is further configured to, based on the morphological variation rule, extract terms in the integrated vocabulary that are in the form of morphological variants of the same concept as the target term, and the term types of such terms are: Other full names.

Optionally, the device further includes:

The preferred word extraction unit is used to extract the canonical full name and canonical abbreviation of the term in the abbreviation document, obtain the term with the term type as the preferred word, and add the term with the term type as the preferred word to the abbreviation document based on the ISO25964 international standard.

Optionally, the abbreviation document generation unit 704 is specifically used for:

Based on the ISO25964 international standard, generate the basic information and relationship description of the target concept, as well as the basic information description and term type identification of all terms of the target concept, and these descriptive information constitute the metadata model of the abbreviation document;

The abbreviation document is generated according to the metadata model of the abbreviation document, the terms corresponding to the target concept, and the term type of each term.

An apparatus for generating an abbreviation document disclosed in this embodiment, by extracting terms from different source vocabularies during the interoperability process of different knowledge organization systems and merging them synonymously to form concepts, generating an integrated vocabulary, and based on abbreviations Abbreviation word formation rules, identify the target concepts containing abbreviations in the integrated vocabulary, extract the attributes of the target concept and all terms, and determine the term type of each term, enrich the semantic information of abbreviations, and reduce the problem of abbreviation ambiguity , and through the standardized knowledge representation of the target concept and all terms of the target concept based on the ISO25964 international standard, the generated abbreviation documents are semantically rich and standardized.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method.

It should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply those entities or operations There is no such actual relationship or order between them. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or device comprising a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The steps of a method or algorithm described in conjunction with the embodiments disclosed herein may be directly implemented in hardware, a software module executed by a processor, or a combination of the two. A software module can be placed in random access memory (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other in the technical field. in any other known form of storage medium.

The above description of the disclosed embodiments enables any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (12)

1. A method for generating an abbreviation document, the method comprising:

in the interoperation process of different knowledge organization systems, extracting terms in word lists of different sources and carrying out synonymy merging on the terms to form concepts, and generating an integrated word list, wherein the terms comprise multiple forms of full names and abbreviations;

identifying a target concept containing an abbreviation in the integrated word list based on an abbreviation word construction rule;

extracting the target concept and the attributes of all terms, and determining the term type of each term;

and based on the ISO25964 international standard, carrying out normalized knowledge representation on the target concept and all terms of the target concept to generate an abbreviation document.

2. The method of claim 1, wherein the identifying target concepts in the integrated vocabulary that contain abbreviations based on abbreviation vocabulary formation rules comprises:

comparing terms in each concept in the integrated vocabulary with records in a abbreviation dictionary;

and according to the comparison result, determining the concept of the abbreviation and the corresponding full name in the abbreviation dictionary simultaneously existing in the integrated vocabulary as the target concept containing the abbreviation.

3. The method of claim 1, wherein the extracting attributes of the target concept and all terms and determining a term type for each term comprises:

extracting the attributes of the target concept and all terms containing the abbreviation in the integrated vocabulary, wherein the concept attributes comprise concept identification, terms, comments, states, subject classification, level relation, correlation and the integrated vocabulary where the concept attributes are located, and the attributes of the terms comprise term identification, word shapes, use states, comments and source vocabularies;

extracting the initial of each non-preposition English word in a target term, wherein the target term is a term formed by a plurality of English words;

splicing the capital letters corresponding to each initial letter to obtain a spliced character string;

if the splicing character string exists in the target concept of the integrated vocabulary, the splicing character string is a target abbreviation of the target term in the target concept, wherein the term type of the target abbreviation is a standard abbreviation, if the initial letter of each non-preposition English word of the target term is capitalized, the term type of the target term is a standard full name, and if the initial letter of each non-preposition English word of the target term is in a form of lowercase or mixed capitalization, the term type of the target term is a common full name.

4. The method of claim 3, further comprising:

and extracting terms in the form of the morphological variant in the integrated word list, which are in the same concept with the target term, based on the morphological variant law, wherein the term types of the terms are other full names.

5. The method of claim 3, further comprising:

extracting the standard full names and the standard abbreviations of the terms in the abbreviation document, obtaining the terms with the term types as the preferred words, and adding the terms with the term types as the preferred words to the abbreviation document based on the ISO25964 international standard.

6. The method of claim 1, wherein the normalizing knowledge representation of the target concept and all terms of the target concept based on the ISO25964 international standard to generate an abbreviation document comprises:

generating basic information and relation description of the target concept and basic information description and term type identification of all terms of the target concept based on ISO25964 international standard, wherein the descriptive information forms a metadata model of an abbreviation document;

and generating the abbreviation document according to the metadata model of the abbreviation document, the terms corresponding to the target concept and the term type of each term.

7. An apparatus for generating an abbreviation document, comprising:

the integrated word list generating unit is used for extracting terms in word lists of different sources and carrying out synonymy merging on the terms to form concepts in the interoperation process of different knowledge organization systems to generate an integrated word list, wherein the terms comprise multiple forms of full names and abbreviations;

the concept identification unit is used for identifying a target concept containing an abbreviation in the integrated word list based on an abbreviation word construction rule;

a term extraction unit for extracting the target concept and the attributes of all terms, and determining a term type of each term;

and the abbreviation document generating unit is used for carrying out normalized knowledge representation on the target concept and all terms of the target concept based on the ISO25964 international standard to generate the abbreviation document.

8. The apparatus according to claim 7, wherein the concept recognition unit is specifically configured to:

comparing terms in each concept in the integrated vocabulary with records in a abbreviation dictionary;

and according to the comparison result, determining the concept of the abbreviation and the corresponding full name in the abbreviation dictionary simultaneously existing in the integrated vocabulary as the target concept containing the abbreviation.

9. The apparatus according to claim 7, wherein the term extraction unit is specifically configured to:

extracting the target concept containing the abbreviation and the attributes of all the terms in the integrated vocabulary, wherein the concept attributes comprise concept identification, terms, comments, states, subject classification, level relation, related relation and the integrated vocabulary in which the concept attributes are located, and the attributes of the terms comprise term identification, word shapes, use states, comments and source vocabularies;

extracting the initial of each non-preposition English word in a target term, wherein the target term is a term formed by a plurality of English words;

splicing the capital letters corresponding to each initial letter to obtain a spliced character string;

if the splicing character string exists in the target concept of the integrated vocabulary, the splicing character string is a target abbreviation of the target term in the target concept, wherein the term type of the target abbreviation is a standard abbreviation, if the initial letter of each non-preposition English word of the target term is capitalized, the term type of the target term is a standard full name, and if the initial letter of each non-preposition English word of the target term is in a form of lowercase or mixed capitalization, the term type of the target term is a common full name.

10. The apparatus according to claim 9, wherein the term extracting unit is further configured to extract terms in a morphological variant form of the same concept as the target term in the integrated vocabulary based on morphological variant rules, and the term types of the terms are other full names.

11. The apparatus of claim 9, further comprising:

and the preferred word extraction unit is used for extracting the standard full names and the standard abbreviations of the terms in the abbreviation documents, obtaining the terms with the term types as the preferred words, and adding the terms with the term types as the preferred words into the abbreviation documents based on the ISO25964 international standard.

12. The apparatus according to claim 7, wherein the abbreviation document generating unit is specifically configured to:

generating basic information and relation description of the target concept and basic information description and term type identification of all terms of the target concept based on ISO25964 international standard, wherein the descriptive information forms a metadata model of an abbreviation document;

and generating the abbreviation document according to the metadata model of the abbreviation document, the terms corresponding to the target concept and the term type of each term.

Images