CN112328855A - Multi-source military equipment knowledge association organization method - Google Patents

Multi-source military equipment knowledge association organization method Download PDF

Info

Publication number
CN112328855A
CN112328855A CN202011168947.5A CN202011168947A CN112328855A CN 112328855 A CN112328855 A CN 112328855A CN 202011168947 A CN202011168947 A CN 202011168947A CN 112328855 A CN112328855 A CN 112328855A
Authority
CN
China
Prior art keywords
equipment
knowledge
attribute
source
military equipment
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011168947.5A
Other languages
Chinese (zh)
Inventor
张苏南
刘玉超
凌萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bocom Smart Information Technology Co ltd
Original Assignee
Bocom Smart Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bocom Smart Information Technology Co ltd filed Critical Bocom Smart Information Technology Co ltd
Priority to CN202011168947.5A priority Critical patent/CN112328855A/en
Publication of CN112328855A publication Critical patent/CN112328855A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to a multi-source military equipment knowledge association organization method, which comprises the steps of constructing a military equipment knowledge model according to a pre-established basic framework of military equipment field knowledge, wherein the basic framework comprises equipment definition, equipment function definition and the relation among equipment; obtaining multi-source military equipment knowledge from a plurality of equipment knowledge source websites through a web crawler, and storing the multi-source military equipment knowledge according to the military equipment knowledge model; and fusing the multi-source military equipment knowledge. The method introduces knowledge engineering into the field of military equipment, combines a web crawler technology and a knowledge fusion mechanism, extracts the relevant knowledge of the military equipment from the massive Internet, has high efficiency, and realizes the rapid fusion of the equipment knowledge of a plurality of data sources.

Description

Multi-source military equipment knowledge association organization method
Technical Field
The invention belongs to the technical field of lane line identification, and particularly relates to a multi-source military equipment knowledge association organization method.
Background
The internet also contains a great deal of military equipment information, including example information of the equipment, such as the type of the equipment, the performance of the equipment and the like, which is an extremely important knowledge source for military researchers. However, in the case of massive military equipment data, related personnel are difficult to further research according to the military equipment data, and the reason is considered, mainly the existing multisource military equipment knowledge is lack of association and organization, in the case of massive internet equipment information, the acquisition is carried out only by manpower, the workload is huge, the implementation is basically impossible, in unstructured webpage data of different sources, the organization modes of the equipment information are different, and the information of mutual association between the equipment is not compact.
Disclosure of Invention
Based on the technical problem, a multi-source military equipment knowledge correlation organization method is provided.
In order to solve the technical problems, the invention adopts the following technical scheme:
a multi-source military equipment knowledge correlation organization method comprises the following steps:
s101, constructing a military equipment knowledge model according to a pre-established basic framework of military equipment field knowledge, wherein the basic framework comprises equipment definition, equipment function definition and the relation between equipment;
s102, obtaining multi-source military equipment knowledge from a plurality of equipment knowledge source websites through a web crawler, and storing the multi-source military equipment knowledge according to the military equipment knowledge model;
s103, fusing the knowledge of the multi-source military equipment.
The association organization method introduces knowledge engineering into the field of military equipment, combines a web crawler technology and a knowledge fusion mechanism, extracts the relevant knowledge of the military equipment from massive Internet, has high efficiency, and realizes the rapid fusion of the equipment knowledge of a plurality of data sources.
Drawings
The invention is described in detail below with reference to the following figures and detailed description:
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a conceptual hierarchy of the equipment of the present invention;
FIG. 3 is a schematic illustration of an equipment detail page of the present invention;
FIG. 4 is a schematic diagram of the ontology mapping of the present invention;
FIG. 5 is a schematic diagram of an example fusion of the present invention.
Detailed Description
As shown in fig. 1, a multi-source military equipment knowledge correlation organization method includes:
s101, constructing a military equipment knowledge model according to a pre-established basic framework of military equipment field knowledge, wherein the basic framework comprises equipment definition, equipment function definition and relations among equipment.
The ontology technology is used, plays an important role in information isomerism and structuring, is a detailed description for conceptualization of domain knowledge, constructs a basic framework of the domain knowledge by extracting concepts acknowledged in the domain and relations among the concepts, provides unified cognition for information sharing and communication, enables all departments in the information domain to circulate unambiguously, and can effectively solve the problem that information in the domain is heterogeneous and not shareable.
The military equipment knowledge modeling method is characterized in that a military equipment body is constructed to serve as a basic framework of the field knowledge of the military equipment, and a military equipment knowledge model is constructed through a knowledge modeling tool project.
The military equipment ontology is a conceptual description of the equipment and the system thereof, and the equipment ontology not only needs to abstract the concept of the equipment, but also needs to analyze and construct the function and performance of the equipment and the incidence relation between the equipment. Knowledge in the field of equipment architecture includes both basic knowledge, performance knowledge of military equipment, and interrelationships between equipment. The military equipment knowledge model construction firstly carries out combing and definition on the concepts, the attributes and the mutual relations among the related elements.
(1) Equipment entity definition
In the field of military equipment, equipment ontology modeling needs to define not only equipment entities and equipment performance entities, but also define and describe their attributes respectively. Thereby providing uniform format support for the fusion and sharing of the following data. The equipment body and its attributes are defined as follows:
equipment entity ontology definition: the basic attribute and the object attribute are used for describing the equipment entity and are expressed as Weapon, the basic attribute is constructed as WeaID, WeaName, WeaType and SerTime and represents the number, equipment name, equipment type and service time of the equipment entity, the domain of the basic attribute is defined as Weapon, the corresponding value ranges are Integer, String and dateTime respectively, the object attribute is constructed as HasPerform and represents the performance and function of the equipment entity, the domain of the object attribute is Weapon, the corresponding value range is Perform, and the description example is shown in Table 1.
Figure BDA0002746696190000031
TABLE 1
The definition of the equipment body is applicable to all types of equipment, and in actual operation, the sub-concepts of the equipment are defined according to specific classifications.
Equipment entity ontology sub-concept definition: the method is used for describing the specific attributes of the equipment entity sub-concepts, and the sub-concepts integrate the basic attributes and the object attributes of the corresponding equipment entity bodies. For example, the Aircraft entity is defined as Aircraft, belongs to the child concept of weipon, and besides inherits the attributes of the above equipment entities, the Aircraft entity also has the specific attributes such as aerodynamic layout, number of engines and flying speed, and the corresponding definition domain is Aircraft and the value domain is String, Integer and Float.
Equipment performance entity ontology definition: the basic performance attributes are constructed as FireRange, Accuracy and Velocity, and represent the action range, action precision and running speed of the equipment entity, domains of the basic performance attributes are defined as Perform, corresponding value range domains are Integer, Float and Float, and the metering units are m,% and km/h respectively, and the description example refers to Table 2.
Figure BDA0002746696190000032
TABLE 2
Taking a armored vehicle as an example, the performance attribute TankPerform specific to the armored vehicle has a combat weight attribute and a maximum travel attribute, the domain of the armored vehicle is TankPerform, the value domain of the armored vehicle is Float and Float, and the measurement units of the armored vehicle are kg and km respectively.
Relationship definition of equipment entities: hierarchical relationships between equipment concepts. On the basis of comprehensively considering military equipment field knowledge and data sources, the core concept of military equipment is determined by analyzing the equipment classification hierarchy, and an equipment concept hierarchy structure diagram with a tree shape is obtained, wherein the structure diagram is totally divided into 8 major classes and 100 minor classes, and the diagram is shown in fig. 2.
Through the definition and description of the equipment entities and concepts, a uniform data mode is provided for the storage and sharing of equipment knowledge, the relation among the equipment is shown in a table 3, the entities are obtained through the combing of the relation, and a strong system relation is provided, so that good basic data support can be provided for the analysis and reasoning of the subsequent equipment knowledge.
Figure BDA0002746696190000041
TABLE 3
The Prot g can provide the construction of ontology concept classes, relations, attributes and examples, shield specific ontology description languages, and enable a user to construct a domain ontology model only on a concept level, and output data generated by modeling in an RDF/XML format, thereby facilitating the storage and search of subsequent knowledge.
S102, obtaining multi-source military equipment knowledge from a plurality of equipment knowledge source websites through a web crawler, and storing the multi-source military equipment knowledge according to a military equipment knowledge model. The specific process is as follows:
1. and determining a seed URL, a page important link field and an equipment information tag of each equipment knowledge source website.
The key of the web crawler is to determine a seed URL, a page important link field and an equipment information tag, wherein the seed URL is used as a starting page for acquiring equipment knowledge, the page important link field is a main source for acquiring the relation between an equipment link and equipment, and the equipment information tag is an equipment data area in web page information. For example, in the world wide web military, the seed URL is http:// webon. huangqi. com/webonlist, the equipment classification, paging, and equipment list in the page are important link fields of the page, and "< divclass ═ detail' >" in the web page information is an equipment information tag.
2. The seed URL is placed in a URL list.
3. Traversing the URL list, analyzing key fields of key links in the webpage information corresponding to each URL in the URL list, obtaining corresponding URLs, comparing the obtained URLs with the URLs in the URL list, and if the obtained URLs are new URLs, storing the new URLs in the URL list.
4. And judging whether the URL list is traversed or not, if so, executing the next step, and if not, returning to the previous step.
5. Traversing the URL list, filtering the non-equipment detail URL, analyzing the webpage information corresponding to the equipment detail URL, acquiring the field name and the field value corresponding to the equipment information tag in the equipment detail page, extracting the corresponding field value according to the military equipment knowledge model, and storing the corresponding field value in a database.
And traversing the URL list from large to small according to the PageRank value.
In this embodiment, the algorithm uses python as an implementation language, and the Beautiful Soup as a page parsing module, so that access to equipment website data and data acquisition are achieved. In order to improve the acquisition efficiency in the algorithm implementation process, the program is implemented by using Pool in multithreading multiprocessing, and the acquisition efficiency is improved by about 3 times compared with a single thread as proved by the test.
Through analysis of equipment related websites, world wide web military, Chinese weapon base and Baidu encyclopedia are selected as equipment knowledge source websites, the three websites are semi-structured encyclopedia equipment information websites with high credibility, equipment information is complete, and equipment information with high quality can be provided for military equipment workers and related personnel. We take the military network of the world wide web as an example to introduce the acquisition implementation of the equipment information. The military network of the world wide web takes a weapon base as a main entrance for equipment acquisition, so the seed URL is http:// webon.
The weapon base has 8 big classifications and 100 small classifications, and equipment information in the equipment classifications is stored in a paging mode, so that the equipment big classifications, the equipment small classifications and the equipment paging are important link fields of pages.
The URL list finally obtained by the above algorithm is an effective URL list, and includes equipment detail page URLs, equipment classification URLs, and paging URLs, where the equipment detail page is a main source of the equipment information, see fig. 3.
As shown in fig. 3, each equipment detail page corresponds to a specific example of a classification ontology, which includes an entry name of equipment, equipment basic information and an equipment detail introduction, and these pieces of information can be located and obtained by python in combination with Beautiful Soup. Meanwhile, when the webpage is analyzed, equipment information tags can be obtained: yun 20, transporter, Y20, Y-20, Sedan Ainsliao, Navignean industries, Y-20, Yun-20.
S103, fusing multi-source military equipment knowledge.
Due to the fact that the emphasis points and the expert naming habits of the equipment data examples obtained from the equipment knowledge source websites are different, the collected equipment data have the following conditions: firstly, different data sources have different naming modes for the same equipment; and the same classification equipment example data of the same data source has different attribute fields. When knowledge fusion is carried out, if an ontology is generated according to the instance attribute, a large number of ontologies exist, and the knowledge sharing and maintenance are still not facilitated; if a unified ontology is established, it is difficult to form consistent approval due to the different requirements of different users. In order to solve the above problems, a certain fusion strategy needs to be formulated to implement the fusion of equipment knowledge.
The core problem of knowledge fusion is the generation of mapping, and the fusion of ontology concepts and instances is realized mainly through the similarity of concepts or attributes. At present, a plurality of researches related to ontology concept fusion methods and example fusion methods exist, and the method for fusing multi-source military equipment knowledge by combining ontology fusion and example fusion can ensure consistency of common knowledge and meet difference of equipment knowledge of different data sources.
1. Fusing a body:
in the aspect of ontology fusion, aiming at different equipment data sources, a fusion strategy based on a global ontology and a local ontology is adopted.
A. The equipment ontology is taken as a global ontology.
B. Constructing a local ontology for each multi-source military equipment knowledge: describing the knowledge which is consistently approved among the knowledge of the multi-source military equipment through the global ontology, and expanding the attribute of the knowledge of each multi-source military equipment on the basis of the global ontology; or a local ontology of each multi-source military equipment knowledge is constructed according to the construction mode of the global ontology.
C. The direct mapping relationship between the global ontology and the local ontology is established through the classification names, and the indirect mapping relationship between the local ontology and the local ontology is established through reasoning of the global ontology, which is shown in fig. 4.
2. And (3) entity fusion: and extracting local ontology from multi-source military equipment knowledge through a learning algorithm.
The key for realizing the fusion learning algorithm is to extract attribute features from the multi-source military equipment knowledge, so that invalid features are removed and filtered, and the mapping of the same example in the multi-source military equipment knowledge is formed through attribute feature matching. Whether the feature extraction or the feature matching is performed, the matching degree of the two character strings is essentially compared. The similarity is a certain value between the intervals [0,1 ]. The invention adopts a character string similarity algorithm to measure the proportion of the parts containing the common substrings.
In the string similarity calculation method, the similarity between any two strings s and t is:
Figure BDA0002746696190000061
where x is the largest common substring of s and t.
1. The attribute feature extraction is suitable for calculating local ontology, and the specific process of extracting the attribute features from the multi-source military equipment knowledge by a character string similarity algorithm is as follows:
A. attribute x for each class instanceiWith existing attribute set (x)0，x1，...，xi-1) Comparison was made, respectively, f (k)m，xi) To classify kmMiddle attribute xiExample of (2) when xiAttribute similarity max (δ) > -, δ in existing attribute setAttribute thresholdThen x is identifiediAttribute x with maximum similarity in attribute setjSimilarly, no new attribute feature is formed, f (k)m，xi) Count plus 1, otherwise, a new attribute feature is formed, count f (k)m，xi) 1, wherein δAttribute thresholdIs the maximum value of the preset attribute threshold.
B. Defining the minimum value f (k) of the example countm，xi)＞min(km) And the classification attributes which do not meet the requirements can be abandoned to obtain a local ontology attribute list.
2. The specific process of attribute feature matching is as follows:
A. example a is calculated by the following formulaiAnd bjSimilarity D (a)j，bj)：
Figure BDA0002746696190000071
Figure BDA0002746696190000072
Wherein, S (a)i，bj) Representative example aiAnd bjStructural similarity of (a)i，bj) Representative example aiAnd bjDepth of common parent attribute in inheritance relationship, depth (ai) and depth (b)j) Respectively represent example aiAnd bjDepth in respective inheritance relationships, depth (a)i)、depth(bj) And depth (a)i，bj) Can be obtained by ontology tree structure traversal, example aiAnd bjSimilarity of attribute characteristics P (a)i，bj) Attribute value similarity V (a)i，bj) All calculated by a character string similarity algorithm formula (1), omegaiThe proportion of the feature similarity can be preset according to the experience of field experts.
B. Calculating the obtained similarity D (a)j，bj) And comparing the similarity with a similarity threshold range preset according to field expert experience to obtain the similarity, such as Sameas, Simiarto and the like.
The method combines the ontology technology and the similarity matching algorithm, and displays the mapping of the equipment knowledge by combining ontology mapping and global ontology-local ontology combination. Finally, we present the final result of instance fusion in a graph manner, and store data in the format of RDF/XML.
Fig. 5 is an example of the display effect after the fusion of the weather ontology data of the 'fighter-20 fighter' equipment from two websites of world wide web military and chinese Weapon storehouse. As can be seen from fig. 5, the global Aircraft body is Aircraft, the local Aircraft bodies are HAircraft and ZAircraft, finally, feature extraction and feature matching fusion are performed through examples, equipment example data corresponding to the global body, namely 'fighter-20 fighters', are obtained and stored uniformly, the 'fighter-20 fighter-H' contains specific engine information and serves as a specific attribute, and the 'fighter-20 fighter-H' and the 'fighter-20 fighter-Z' can obtain a relationship that the two examples are SameAs through similarity calculation.
In fig. 5, SubClassof represents the inheritance relationship between the upper and lower bits, and hasinduvidual represents a specific instance object.
The following conclusion can be obtained through fig. 5, the method constructs the mapping relation of the multi-source equipment knowledge on the basis of realizing the acquisition of the equipment knowledge, thereby not only ensuring the integrity of the knowledge, but also ensuring the uniqueness of the system, avoiding the repeated storage of the same characteristics and achieving the purpose of saving resources.
However, those skilled in the art should realize that the above embodiments are illustrative only and not limiting to the present invention, and that changes and modifications to the above described embodiments are intended to fall within the scope of the appended claims, provided they fall within the true spirit of the present invention.

Claims (10)

1. A multi-source military equipment knowledge association organization method is characterized by comprising the following steps:
s101, constructing a military equipment knowledge model according to a pre-established basic framework of military equipment field knowledge, wherein the basic framework comprises equipment definition, equipment function definition and the relation between equipment;
s102, obtaining multi-source military equipment knowledge from a plurality of equipment knowledge source websites through a web crawler, and storing the multi-source military equipment knowledge according to the military equipment knowledge model;
s103, fusing the knowledge of the multi-source military equipment.
2. The multi-source military equipment knowledge correlation organization method according to claim 1, wherein the step S101 is implemented by constructing an equipment body as a basic framework of the military equipment field knowledge and constructing a military equipment knowledge model through a knowledge modeling tool (project).
3. The multi-source military equipment knowledge correlation organization method according to claim 2, wherein the constructing equipment ontology comprises:
equipment entity ontology definition: the device comprises basic attributes and object attributes, wherein the basic attributes are expressed as Weapon, the basic attributes are constructed as WeaID, WeaName, WeaType and SerTime and represent the number, equipment name, equipment type and service time of the equipment entity, domain of the basic attributes is defined as Weapon, corresponding value ranges are Integer, String and dateTime respectively, the object attributes are constructed as HasPerform and represent the performance and function of the equipment entity, domain of the object attributes is Weapon, and corresponding value ranges are Perform;
equipment performance entity ontology definition: the method comprises the steps of describing basic performance attributes, self-specific performance attributes and measurement units of the attributes of an equipment entity, wherein the basic performance attributes are expressed as form, the basic performance attributes are constructed as FireRange, Accuracy and Velocity and represent the action range, action precision and operation speed of the equipment entity, domain of the basic performance attributes is defined as form, corresponding value range domains are Integer, Float and Float respectively, and the measurement units are m,% and km/h respectively;
relationship definition of equipment entities: hierarchical relationships between equipment concepts.
4. The multi-source military equipment knowledge correlation organization method according to claim 3, wherein the establishing of the basic framework of the military equipment field knowledge through ontology technology further comprises:
equipment entity ontology sub-concept definition: unique attributes for describing equipment entity sub-concepts that integrate base attributes and object attributes of corresponding equipment entity ontologies.
5. The multi-source military equipment knowledge correlation organization method of claim 4, wherein the step S102 further comprises:
determining seed URLs, page important link fields and equipment information tags of equipment knowledge source websites;
putting the seed URL into a URL list;
traversing the URL list, analyzing key fields of key links in the webpage information corresponding to each URL in the URL list to obtain corresponding URLs, comparing the obtained URLs with the URLs in the URL list, and if the obtained URLs are new URLs, storing the new URLs into the URL list;
judging whether the URL list is traversed or not, if so, executing the next step, and if not, returning to the previous step;
traversing the URL list, filtering the non-equipment detail URL, analyzing the webpage information corresponding to the equipment detail URL, acquiring the field name and the field value corresponding to the equipment information tag in the equipment detail page, extracting the corresponding field value according to the military equipment knowledge model and storing the corresponding field value in a database.
6. The method of claim 5, wherein traversing the list of URLs comprises: and traversing from large to small according to the PageRank value.
7. The multi-source military equipment knowledge correlation organization method of claim 6, wherein the step S103 further comprises:
fusing a body:
taking the equipment body as a global body;
constructing a local ontology for each multi-source military equipment knowledge: describing the knowledge which is agreed among the multi-source military equipment knowledge through the global ontology, and expanding the attribute of each multi-source military equipment knowledge on the basis of the global ontology; or constructing a local ontology of each multi-source military equipment knowledge according to the construction mode of the global ontology;
establishing a mapping relation between a global ontology and a local ontology through the classified names, and establishing a mapping relation between the local ontology and the local ontology through the global ontology;
and (3) entity fusion: local ontology is extracted from multi-source military equipment knowledge.
8. The method of claim 7, wherein extracting local ontology from the multi-source military equipment knowledge further comprises:
extracting attribute features from multi-source military equipment knowledge;
and forming mapping of the same example in the multi-source military equipment knowledge through attribute feature matching.
9. The multi-source military equipment knowledge correlation organization method according to claim 8, characterized in that the attribute features are extracted from the multi-source military equipment knowledge through a character string similarity algorithm:
attribute x for each class instanceiWith existing attribute set (x)0,x1,…,xi-1) Comparison was made, respectively, f (k)m,xi) To classify kmMiddle attribute xiExample of (2) when xiAttribute similarity max (δ) in existing attribute sets>＝δAttribute thresholdThen x is identifiediAttribute x with maximum similarity in attribute setjSimilarly, no new attribute feature is formed, f (k)m,xi) Count plus 1, otherwise, a new attribute feature is formed, count f (k)m,xi) 1, wherein δAttribute thresholdIs the maximum value of the preset attribute threshold;
defining the minimum value f (k) of the example countm,xi)>min(km) And obtaining a local ontology attribute list by using the effective attribute characteristics.
10. The multi-source military equipment knowledge correlation organization method of claim 8 or 9, wherein the attribute feature matching comprises:
example a was calculated by the following formulaiAnd bjSimilarity D (a)j，bj)：
Figure FDA0002746696180000031
Figure FDA0002746696180000032
Wherein, S (a)i,bj) Representative example aiAnd bjStructural similarity of (a)i,bj) Representative example aiAnd bjDepth (a) of the common parent attribute of (c) in the inheritance relationshipi) And depth (b)j) Respectively represent example aiAnd bjDepth in respective inheritance relationships, depth (a)i)、depth(bj) And depth (a)i,bj) Can be obtained by ontology tree structure traversal, example aiAnd bjSimilarity of attribute characteristics P (a)i,bj) Attribute value similarity V (a)i,bj) All calculated by a character string similarity algorithm, omegaiIs the specific gravity of the feature similarity;
calculating the obtained similarity D (a)j，bj) And comparing the similarity with a preset similarity threshold range to obtain the similarity.
CN202011168947.5A 2020-10-28 2020-10-28 Multi-source military equipment knowledge association organization method Pending CN112328855A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011168947.5A CN112328855A (en) 2020-10-28 2020-10-28 Multi-source military equipment knowledge association organization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011168947.5A CN112328855A (en) 2020-10-28 2020-10-28 Multi-source military equipment knowledge association organization method

Publications (1)

Publication Number Publication Date
CN112328855A true CN112328855A (en) 2021-02-05

Family

ID=74297749

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011168947.5A Pending CN112328855A (en) 2020-10-28 2020-10-28 Multi-source military equipment knowledge association organization method

Country Status (1)

Country Link
CN (1) CN112328855A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114328954A (en) * 2021-12-22 2022-04-12 重庆邮电大学 Internet of things field ontology construction method based on core concept ontology
CN117829731A (en) * 2023-12-29 2024-04-05 光谷技术有限公司 Military equipment warehouse management method and system based on RFID and AI vision

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111309925A (en) * 2020-02-10 2020-06-19 同方知网(北京)技术有限公司 Knowledge graph construction method of military equipment
CN111428048A (en) * 2020-03-20 2020-07-17 厦门渊亭信息科技有限公司 Cross-domain knowledge graph construction method and device based on artificial intelligence

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111309925A (en) * 2020-02-10 2020-06-19 同方知网(北京)技术有限公司 Knowledge graph construction method of military equipment
CN111428048A (en) * 2020-03-20 2020-07-17 厦门渊亭信息科技有限公司 Cross-domain knowledge graph construction method and device based on artificial intelligence

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
车金立 等: "基于百科知识的军事装备知识图谱构建与应用", 《兵器装备工程学报》, vol. 40, no. 1, pages 148 - 153 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114328954A (en) * 2021-12-22 2022-04-12 重庆邮电大学 Internet of things field ontology construction method based on core concept ontology
CN117829731A (en) * 2023-12-29 2024-04-05 光谷技术有限公司 Military equipment warehouse management method and system based on RFID and AI vision

Similar Documents

Publication Publication Date Title
Cremaschi et al. A fully automated approach to a complete semantic table interpretation
CN101901247A (en) Vertical engine searching method and system for domain body restraint
CN110633365A (en) Word vector-based hierarchical multi-label text classification method and system
CN112463981A (en) Enterprise internal operation management risk identification and extraction method and system based on deep learning
CN112328855A (en) Multi-source military equipment knowledge association organization method
CN115438199A (en) Knowledge platform system based on smart city scene data middling platform technology
Li et al. Application research of machine learning method based on distributed cluster in information retrieval
Zhu Survey on ontology mapping
CN116244497A (en) Cross-domain paper recommendation method based on heterogeneous data embedding
Cheng et al. Research on construction method of knowledge graph in the civil aviation security field
Tao et al. From citation network to study map: a novel model to reorganize academic literatures
Yang et al. Web service clustering method based on word vector and biterm topic model
Ren et al. Improving ocean data services with semantics and quick index
Chen English translation template retrieval based on semantic distance ontology knowledge recognition algorithm
CN106055702A (en) Internet-oriented unified description method of data services
Hu et al. Text mining based on domain ontology
Yin et al. Heterogeneous Network Representation Learning Method Based on Meta-path
Liu et al. Construction of a massive heterogeneous minority cultural resource integration model based on ontology
CN117151659B (en) Ecological restoration engineering full life cycle tracing method based on large language model
Li et al. Design of knowledge map construction based on convolutional neural network
Jing et al. Modeling and searching technology of distribution network data resources based on knowledge mapping
Shi et al. The Construction of Cognitive Graph of Integrated War Emergency System
Li et al. Heterogeneous embeddings for relational data integration tasks
Gao Knowledge System for Related Scholars of Specific Field Based on Collaborative Relationship
Zhang et al. Representation Learning in Academic Network Based on Research Interest and Meta-path

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination