CN106933796B - Internet of things terminal interoperation method and device based on semantic understanding - Google Patents
Internet of things terminal interoperation method and device based on semantic understanding Download PDFInfo
- Publication number
- CN106933796B CN106933796B CN201511016885.5A CN201511016885A CN106933796B CN 106933796 B CN106933796 B CN 106933796B CN 201511016885 A CN201511016885 A CN 201511016885A CN 106933796 B CN106933796 B CN 106933796B
- Authority
- CN
- China
- Prior art keywords
- internet
- entity
- things
- semantic
- request
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24575—Query processing with adaptation to user needs using context
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a semantic understanding-based Internet of things terminal interoperation method and device, and relates to the field of Internet of things and the Internet. The method comprises the following steps: acquiring each entity oriented to the application of the Internet of things and the name of each entity in the Internet according to the internal and external knowledge bases and the data content of the Internet; calculating the correlation of each entity to form a uniform named entity name aiming at the same entity; semantic expansion is carried out on each entity and the operation function of each entity; when an internet of things request is received, determining a named entity name and an operation function corresponding to the internet of things request through semantic calculation of the internet of things entity, recording and evaluating the current operation and task completion conditions after a certain operation is completed, and reversely marking each entity realizing the operation function according to the conditions so as to obtain the optimal entity combination realizing the internet of things request when related tasks or operation requests exist in the future. Therefore, the problem of interoperation of equipment under different protocol standard systems can be solved.
Description
Technical Field
The invention relates to the field of Internet of things and Internet, in particular to a semantic understanding-based Internet of things terminal interoperation method and device.
Background
The Internet of things utilizes technologies and equipment such as two-dimensional codes, Radio Frequency Identification (RFID) and various sensors/sensitive devices to connect objects with various networks such as the Internet, so that ubiquitous real-world information is acquired, information interaction between the objects and the people is realized, intelligent informatization application is supported, comprehensive fusion of information infrastructure and physical infrastructure is realized, and finally intelligent infrastructure is formed. Essentially, the internet of things is a networking application and communication capability that is architected on a network.
Natural Language Processing (NLP), also known as Natural Language Understanding (NLU), is a core branch of the field of artificial intelligence.
Natural language processing technology mainly comprises technologies of ' Speech Recognition ' (ASR), ' Speech Synthesis ' (Speech Synthesis), ' Semantic Understanding ' (Semantic Comprehension, or Semantic interpretation) ', and with the popularization of apple SIRI, the technology attracts more and more attention in the industry. Historically, the technology has been deeply applied to information search systems and content recommendation systems such as search engines, and various companies are continuously increasing the research, development and application investment. At present, the industry generally considers that the application of intelligent voice recognition and semantic understanding technology can change the product form and develop new application and products, and the technology is a core support technology which occupies the highest market place in the internet of things.
Semantic understanding refers to the analysis, processing, and application of text-based information based on traditional Natural Language Processing (NLP) techniques. The supporting technology of the natural language processing technology is divided into: word segmentation, syntactic analysis, semantic analysis, phrase recognition, named entity recognition, concept extraction, reference resolution, context interactive logic judgment, ontology, word sense disambiguation and the like.
Because the intelligent Internet of things is information generated by the article equipment accessed to the Internet of things, automatic identification, processing and judgment can be realized, and a processing result can be fed back to the accessed article equipment. Meanwhile, the method can issue certain operation instructions to the article equipment according to the processing result, and the accessed article equipment makes certain action response. The core of the method is the intelligent application of the technology, not only the accessed sensor, the network transmission or which industry application. Therefore, how to apply the natural language processing technology in the field of internet of things is very important to form automatic control of equipment and interoperation of the equipment according to a certain purpose.
At present, the concept of semantic understanding of the internet of things based on ontology and a method for solving the problem of interoperation between internet devices are ontology methods in the field of artificial intelligence and natural language processing. As shown in fig. 1, in the prior art, an authoritative knowledge base (ontology) is used as a base, a machine needs to map document vocabularies in an actual system to existing concepts in the knowledge base according to a certain standard, and call of equipment required for equipment interoperation is completed through semantic understanding of the vocabularies.
Ontology is a general conceptual description of a certain field, and is a solution to the problem of what objects, processes, attributes, and relationships are in nature in a certain field. The Internet of things body is artificially constructed based on domain experts, and is authoritative to be an SSN body constructed by a W3C semantic sensor network incubator and the like. It has the following drawbacks:
defect 1: the manual construction is not suitable for the application of the mass information of the Internet of things. The ontologies describe the basic concepts in the field of the internet of things in a coarse-grained manner, but are limited by the limitation of manual construction speed and the rapid development of the technology of the internet of things, the ontologies lack the description of specific system characteristics and emerging concepts, are not suitable for the mutual coordination among different internet of things systems to complete a new task, and are not possible to carry out integrity labeling with strong adaptability to equipment.
Defect 2: it is more prone to logical theory and is further away from the world's existence. Ontology is considered a logical theory used to define objects, properties, relationships, events and processes in an information system that is not application and usage and operation oriented.
Defect 3: the ontology is established by using an ontology concept in natural language processing, which refers to a method for determining abstract names and functions of an entity in information according to generated background and application, but no context environment similar to natural language understanding is formed at present, and the ontology is not suitable for different external users due to the difference of background and knowledge levels.
Defect 4: terminals built for different purposes are difficult to be called by other tasks; or similar terminals (or the same terminal) built by different organizations, are difficult to be used by users outside the organizations (outside the business) due to the difference in description, and are difficult to be aggregated to complete a new task.
Disclosure of Invention
The invention aims to solve the technical problem of interoperation of devices under different standard protocols.
According to one aspect of the invention, a semantic understanding-based internet of things terminal interoperation method is provided, which comprises the following steps: according to the internal and external knowledge bases and the internet data content, naming of each entity facing the internet of things application and naming of each entity in different fields and application tasks in the internet is obtained; calculating the correlation of each entity to form a uniform named entity name aiming at the same entity; semantic expansion is carried out on each entity and the operation function of each entity; when an internet of things request is received, determining a named entity name and an operation function corresponding to the internet of things request through semantic calculation of the internet of things entity, recording and evaluating the current operation and task completion condition after a certain operation is completed, and reversely marking each entity realizing the operation function according to the operation and task completion condition so as to obtain an optimal entity combination realizing the internet of things request when a related task or operation request exists in the future.
Further, still include: evaluating the capability of each entity by recording data of different entity combinations to complete the operation function; and when the request of the Internet of things is received, acquiring the optimal combination of the entities for realizing the request of the Internet of things according to the capability of each entity.
Further, still include: and obtaining control parameters of different entities meeting the request of the Internet of things, and converting the request of the Internet of things into corresponding control parameters so as to obtain the optimal combination of the entities for realizing the request of the Internet of things.
Further, the step of obtaining each entity oriented to the application of the internet of things and naming of each entity in the internet further includes: establishing a semantic context resource library of the naming expression and the operation function of each entity so as to calculate the relevance of each entity.
Further, still include: recording the flow and steps of the related transmission data and control parameters of various entities completing the operation function in each entity; and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
Further, the semantic expansion step of each entity and the operation function of each entity includes: and decomposing each entity and the operation function of each entity, and establishing semantic expansion which belongs to different application fields and different implementation functions and combines the Internet world concept description method.
Further, still include: and semantic understanding context environment facing the operation function is formed by semantic expansion of data record and operation control record.
Further, still include: according to the fusion of the internet information and the internet of things information, a context environment for identifying, understanding and operating entities in different fields is formed.
According to another aspect of the present invention, a semantic understanding-based terminal interoperation device of an internet of things is further provided, including: the system comprises an entity obtaining unit, an entity selecting unit and an entity selecting unit, wherein the entity obtaining unit is used for obtaining each entity facing the application of the Internet of things and the name of each entity in different fields and application tasks in the Internet according to an internal knowledge base, an external knowledge base and the data content of the Internet; the correlation calculation unit is used for calculating the correlation of each entity to form a uniform named entity name aiming at the same entity; the semantic expansion unit is used for performing semantic expansion on each entity and the operation function of each entity; the task implementation unit is used for determining the name and the operation function of the named entity corresponding to the request of the internet of things through semantic calculation of the entity of the internet of things when the request of the internet of things is received, recording and evaluating the current operation and task completion conditions after a certain operation is completed, and reversely marking each entity for realizing the operation function according to the operation and task completion conditions so as to obtain the optimal entity combination for realizing the request of the internet of things when related tasks or operation requests exist in the future.
Further, still include: the capability evaluation unit is used for evaluating the capability of each entity by recording data of different entity combinations for completing the operation function; and the task realization unit is used for acquiring the optimal combination of the entities for realizing the request of the Internet of things according to the capability of each entity when the request of the Internet of things is received.
Further, the task implementation unit is used for obtaining control parameters of different entities meeting the request of the internet of things, converting the request of the internet of things into corresponding control parameters, and therefore the optimal entity combination for achieving the request of the internet of things is obtained.
Further, still include: and the resource library establishing unit is used for establishing a semantic upper and lower resource library of the naming expression and the operation function of each entity so as to calculate the correlation of each entity.
Further, the resource library establishing unit is used for recording the flow and steps of transmission data and control parameters related to various entities completing the operation function in each entity; and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
Furthermore, the semantic expansion unit is used for decomposing each entity and the operation function of each entity and establishing semantic expansion which belongs to different application fields and different implementation functions and combines the Internet world concept description method.
Furthermore, the semantic expansion unit is used for forming a semantic understanding context environment facing the operation function through semantic expansion of the data record and the operation control record.
Furthermore, the semantic expansion unit is used for forming a context environment for identifying, understanding and operating entities in different fields according to the fusion of the internet information and the internet of things information.
Compared with the prior art, the method and the system have the advantages that each entity oriented to the application of the Internet of things and the name of each entity in different fields and application tasks in the Internet are obtained according to the internal and external knowledge bases and the data content of the Internet; calculating the correlation of each entity to form a uniform named entity name aiming at the same entity; semantic expansion is carried out on each entity and the operation function of each entity, and when an Internet of things request is received, the name and the operation function of a named entity corresponding to the Internet of things request are determined through semantic calculation of the Internet of things entities; after a certain operation is finished, the operation and task completion condition of the current time is recorded and evaluated, and each entity for realizing the operation function is reversely labeled according to the operation and task completion condition so as to obtain the optimal entity combination for realizing the request of the Internet of things when a related task or operation request exists in the future. Through the implementation-oriented function, semantic resources of the Internet world are introduced, so that the natural language understanding problem of the Internet of things world becomes possible; and finally, establishing the functional entity, so that semantic understanding of the internet of things terminals in different fields is linked through the entity, and a relation between information similar to the internet world is formed. The interoperation problem of equipment under different protocol standard systems can be realized.
Furthermore, the selection problem of the target source data, a new task or a new calculation target, the acquisition of required data or the selection problem of the most suitable Internet of things terminal can be calculated under the same calculation target.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
The invention will be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
fig. 1 is a method for implementing ontology-based physical network interoperation in the prior art.
Fig. 2 is a schematic flow chart of an embodiment of the internet of things terminal interoperation method based on semantic understanding.
Fig. 3 is a schematic flow chart of another embodiment of the internet of things terminal interoperation method based on semantic understanding.
Fig. 4 is a schematic flow chart of a semantic understanding-based internet of things terminal interoperation method according to still another embodiment of the present invention.
FIG. 5 is a diagram of the construction of a standard entity library according to the present invention.
Fig. 6 is a diagram of a method for implementing the interoperation of the internet of things terminal based on semantic understanding.
Fig. 7 is a schematic structural diagram of an embodiment of the internet of things terminal interoperation device based on semantic understanding.
Fig. 8 is a schematic structural diagram of another embodiment of the internet of things terminal interoperation device based on semantic understanding.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
Fig. 2 is a schematic flow chart of an embodiment of the internet of things terminal interoperation method based on semantic understanding. The method comprises the following steps:
in step 210, naming, description or application description of each entity facing the application of the internet of things and each entity in different fields and application tasks in the internet are obtained according to the internal and external knowledge bases and the internet data content. Wherein, each entity is each internet of things terminal.
The invention introduces internal and external professional knowledge bases and semantic resources of an external Internet world, and constructs an Internet of things world semantic understanding model, a dictionary, functional concepts and a semantic context relation base which are identified by named entities as core nodes and aim at different application fields.
At step 220, the dependencies of the various entities are computed to form a unified named entity name for the same entity.
Establishing a semantic upper and lower resource library of each entity for the naming expression and the operation function of each entity so as to calculate the correlation of each entity, and recording the flow and the step of transmitting data and control parameters related to various internet of things terminals for completing the operation function in each entity in the resource library; and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
At step 230, semantic extensions are performed on the entities and the operating functions of the entities.
And decomposing each entity and operation function, and establishing semantic expansion which belongs to different application fields and different implementation functions and combines an internet world concept description method. And semantic understanding context environment facing the operation function can be formed by semantic extension of data record and operation control record. On the other hand, a context environment for identifying, understanding and operating the internet of things terminal in different fields is formed according to the fusion of the internet information and the internet of things information.
By the method, context understanding aiming at the Internet of things terminal can be quickly generated, and when a new Internet of things task (including data analysis and certain trend prejudgment) appears in the future, the Internet of things terminals in different fields can be called to form an optimal solution aiming at the task.
In step 240, when the request of the internet of things is received, the name and the operation function of the named entity corresponding to the request of the internet of things are determined through semantic calculation of the entity of the internet of things.
In step 250, after completing a certain operation, the current operation and task completion condition are recorded and evaluated, and each entity realizing the operation function is reversely labeled according to the operation and task completion condition, so as to obtain the optimal entity combination for realizing the request of the internet of things when a related task or operation request exists in the future.
The reverse labeling is similar to labeling an entity with an alias, a synonym and a synonym, and solves the problem of different naming or definition in different fields aiming at the same entity or control step. Such as a keyword a, named a + in one domain (or task) and named a-in another domain or task.
In the embodiment, according to a plurality of composition networking terminals (entities) which complete a certain kind of functions, the completed functions are taken as a core, and the semantic expansion description of the internet world is labeled to form a context environment similar to the understanding of the natural language of the internet world; by the aid of the extended semantic description of the data records and the operation control records, context environment generation aiming at certain functions can be gradually formed, and semantic calculation oriented to the completed functions of the terminal of the Internet of things is possible. The internet of things terminals established for different purposes gradually form a set for finishing certain specific functions, so that the interoperation between the internet of things terminals becomes feasible. Namely, a semantic understanding model taking a result as a core is constructed by establishing semantic descriptions of various equipment controls related to an operation process, particularly result descriptions of a final production step of a certain equipment. The problem of semantic understanding in the interoperation of the Internet of things equipment and the automatic control of the equipment in intelligent manufacturing, namely the interoperation of the equipment under different protocol standard systems, is solved.
Fig. 3 is a schematic flow chart of another embodiment of the internet of things terminal interoperation method based on semantic understanding. The method comprises the following steps:
in step 310, according to the projection relation of the internet information resources on the internet of things world, a semantic upper and lower resource library of the naming expression, operation control step and the like of the internet of things entity in the internet of things world is established.
In step 320, a semantic correlation calculation method for recognition and understanding of the entity of the internet of things is established. Namely, a method for realizing world functions and calculating similarity of operation named entities is formed.
In step 330, semantic resources of the internet world are introduced to establish an understanding and concept extension model of the internet of things world entity terminal, and a semantic extension method which belongs to different application fields and realizes functions and combines internet world concept description is established.
I.e. the step decomposition process of a certain function is completed.
In step 340, the completed operation of each terminal combination of the internet of things is recorded.
The control parameters of different internet of things terminals meeting the internet of things request can be obtained, and the internet of things request is converted into the corresponding control parameters, so that the optimal combination of the internet of things terminals for realizing the internet of things request can be obtained.
In step 350, the internet of things entity performs semantic calculation, i.e., calculates a semantic distance between the completed operation or function and the named entity.
In step 360, an equipment context is formed by identifying an entity name corresponding to a certain type of final implementation function, and reversely labeling each internet of things terminal integrated to implement the function with the acquired internet semantics.
Through semantic expansion of data records and operation control records, a semantic understanding context environment oriented to operation functions is formed, or a context environment for identifying, understanding and operating the internet of things terminal in different fields is formed according to fusion of internet information and internet of things information.
In step 370, a corresponding relationship repository between the internet of things world entity terminal operation, control expression and the internet world expression is formed.
In the example, the context environment understood by the terminal of the internet of things is formed, and the similar requirements for the interoperation and function achievement of the world of the internet of things are provided in the future. The corresponding entity internet of things terminal name and control parameter input format for executing the operation concept are obtained from the input concept, and several functions can be completed through concept conversion: (1) the method comprises the steps that context semantic calculation oriented to application is carried out, and the best internet of things terminal capable of meeting current requirements is determined in a plurality of similar internet of things terminals; (2) by decomposing different results and through technologies such as named entity recognition, the problem that the Internet of things terminal, equipment and the like are not described towards service objects in the body construction is solved. (3) The problem of semantic intercommunication among different ontology builders is solved, and the final result ontology decomposition and named entity identification technology, steps and function decomposition technology are adopted. The interoperation between the Internet of things builders subordinate to various protocols is more easily completed.
Fig. 4 is a schematic flow chart of a semantic understanding-based internet of things terminal interoperation method according to still another embodiment of the present invention.
At step 410, a plurality of internet of things devices are registered using knowledge base criteria.
In step 420, when the request of the internet of things is received, the related device control right or information is obtained through the gateway of the internet of things.
For example, a new request for the internet of things is obtained by first calculating a function to be completed by the request, calculating a function entity to which the request belongs, determining a related concept field by the entity, obtaining an operation step for completing the function and a related terminal set of the internet of things to be controlled or a data set to be acquired by the concept field, and then calling different terminal combinations in different fields of the internet of things to complete the function.
Firstly, confirming that the functions are the same, for example, obtaining a standard semantic dictionary, or adopting a semantic dictionary of 'a certain standard' as a reference dictionary; the standardized labeling of the various steps that accomplish this "function" is reverse-labeled by a standard semantic dictionary. (including the standardized names of this step, input parameters, output parameters, etc.)
Confirming the function concept comprises confirming the functions of various terminals of the Internet of things completed in certain types of confirming tasks; the same item or the same type of function can be completed by different terminals of the Internet of things; recording the sequential execution steps, the generated actions, the achieved effects and the input/output parameters of each Internet of things terminal in a certain type or in the process of completing a certain function; the method comprises the steps that a certain Internet of things is built, various final products or functions are used as main bodies, and descriptions of input/output parameters, execution actions and the like of various subdivided Internet of things terminals participating in the functions or completing the products are included. After a period of time of data accumulation, the corresponding relation between various Internet of things entities under different standard systems is obtained through establishing a semantic understanding model.
At step 430, the final result of the completed function or operation is recorded.
The capability of each internet of things terminal is evaluated by recording data of the operation functions completed by the combination of different internet of things terminals, for example, after the functions are completed, the effect, time, evaluation and the like of the completed functions are recorded, as shown in fig. 5.
In step 440, the steps of each device completing the job are back-labeled with the results.
And when the request of the Internet of things is received, acquiring the optimal combination of the entities for realizing the request of the Internet of things according to the capability of each entity. For example, reverse annotations are recorded for entities of the internet of things in different fields; the accumulation of the functions can be used for calling the most appropriate terminal combination in the world of the Internet of things for future similar function requests. Wherein the labeled parameters are completed from a labeled semantic dictionary or a description dictionary.
The invention generates a semantic entity from the final result, as shown in fig. 6.
The semantic interoperation comprises the following contents: 1) the terminal or the equipment of the Internet of things can understand the working input/output of the terminal or the equipment of the Internet of things under different standard protocols according to the final result, output objects or finished functions, so as to meet the requirement of interoperation; 2) on the basis of calculating a certain similar result by data generated by different internet of things terminals, obtaining an optimal/optimal data source for calculating a certain determined result in the future; 3) the method also comprises the step of combining and calculating the requirement of a new function by the data generated by different terminals of the Internet of things, or completing the execution of the new function.
In the embodiment, the semantic intercommunication problem among different ontology builders is solved, and the semantic context oriented to the realization function of the internet of things terminal is formed by adopting the final result ontology decomposition combined with the internet semantic description, the named entity recognition technology and the completed reverse labeling step. The interoperation between the Internet of things builders subordinate to various protocols is more easily completed. In addition, under the same calculation target, the selection problem of the target source data, the acquisition of a new task or a new calculation target, the required data and the calculation problem are more convenient to calculate.
Fig. 7 is a schematic structural diagram of an embodiment of the internet of things terminal interoperation device based on semantic understanding. The apparatus includes an acquiring entity unit 710, a relevance calculating unit 720, a semantic expanding unit 730, and a task implementing unit 740.
The entity obtaining unit 710 is configured to obtain names, descriptions, or application descriptions of entities and entities in different fields and application tasks in the internet for the application of the internet of things according to the internal and external knowledge bases and the internet data content.
The invention introduces internal and external professional knowledge bases and semantic resources of an external Internet world, and constructs an Internet of things world semantic understanding model, a dictionary, functional concepts and a semantic context relation base which are identified by named entities as core nodes and aim at different application fields.
The correlation calculation unit 720 is configured to calculate correlations of the entities to form a uniform named entity name for the same entity.
The semantic expansion unit 730 is configured to perform semantic expansion on each entity and the operation function of each entity.
The semantic expansion unit is also used for decomposing each named entity and operation function and establishing semantic expansion which belongs to different application fields and different implementation functions and combines the Internet world concept description method. And a semantic understanding context environment oriented to the operation function can be formed through semantic expansion of data records and operation control records, or a context environment for identifying, understanding and operating the internet of things terminal in different fields can be formed according to the fusion of internet information and internet of things information.
Through the operation, context understanding aiming at the Internet of things terminal can be quickly generated, and when a new Internet of things task (including data analysis and certain trend prejudgment) appears in the future, the Internet of things terminals in different fields can be called to form an optimal solution aiming at the task.
The task implementation unit 740 is configured to determine, when the request for the internet of things is received, a name and an operation function of a named entity corresponding to the request for the internet of things through semantic calculation of an entity of the internet of things, record and evaluate the current operation and task completion condition after a certain operation is completed, and reversely label, according to the operation and task completion condition, each entity that implements the operation function, so as to obtain an optimal entity combination that implements the request for the internet of things when there is a related task or operation request in the future.
The reverse labeling is similar to labeling an entity with an alias, a synonym and a synonym, and solves the problem of different naming or definition in different fields aiming at the same entity or control step. Such as a keyword a, named a + in one domain (or task) and named a-in another domain or task.
In the embodiment, according to a plurality of composition networking terminals which complete a certain kind of functions, the completed functions are taken as a core, and the semantic expansion description of the Internet world is labeled to form a context environment similar to the understanding of the natural language of the Internet world; by the aid of the extended semantic description of the data records and the operation control records, context environment generation aiming at certain functions can be gradually formed, and semantic calculation oriented to the completed functions of the terminal of the Internet of things is possible. The internet of things terminals established for different purposes gradually form a set for finishing certain specific functions, so that the interoperation between the internet of things terminals becomes feasible. Namely, a semantic understanding model taking a result as a core is constructed by establishing semantic descriptions of various equipment controls related to an operation process, particularly result descriptions of a final production step of a certain equipment. The problem of semantic understanding in the interoperation of the Internet of things equipment and the automatic control of the equipment in intelligent manufacturing, namely the interoperation of the equipment under different protocol standard systems, is solved.
Fig. 8 is a schematic structural diagram of another embodiment of the internet of things terminal interoperation device based on semantic understanding. The apparatus includes an acquiring entity unit 810, a repository establishing unit 820, a relevance calculating unit 830, a semantic expanding unit 840, a context forming unit 850, a capability evaluating unit 860, and a task implementing unit 870.
The entity obtaining unit 810 is configured to obtain each entity oriented to the application of the internet of things.
The resource library establishing unit 820 is configured to establish semantic context resource libraries of naming expression, operation control steps and the like of the internet of things entities in the internet of things world according to the projection relationship of the internet information resources on the internet of things world.
Recording the flow and the step of transmitting data and control parameters related to various internet of things terminals completing operation functions in each entity in a resource library; and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
The correlation calculation unit 830 is configured to establish a semantic correlation calculation method for recognition and understanding of an entity of the internet of things. Namely, a method for realizing world functions and calculating similarity of operation named entities is formed.
The semantic expansion unit 840 is used for introducing semantic resources of the internet world, establishing an understanding of the internet of things world entity terminal and a concept expansion model, and establishing a semantic expansion method which belongs to different application fields and realizes functions and combines internet world concept description. I.e. the step decomposition process of a certain function is completed. And recording the operation completed by each terminal combination of the Internet of things. And (4) semantic calculation of the entity of the Internet of things, namely calculating the semantic distance between the finished operation or function and the named entity.
The context environment forming unit 850 is configured to form a semantic understanding context environment for the operation function by semantic extension of the data record and the operation control record. And further forming a corresponding relation resource library between the operation and control expression of the Internet of things world entity terminal and the Internet world expression.
The capability evaluation unit 860 is used to evaluate the capabilities of the various entities by recording data of the different entity combinations to perform operational functions.
The task implementation unit 870 is configured to, when the request of the internet of things is received, obtain an optimal combination of entities for implementing the request of the internet of things according to the capabilities of the respective entities.
In the example, the context environment understood by the terminal of the internet of things is formed, and the similar requirements for the interoperation and function achievement of the world of the internet of things are provided in the future. The corresponding entity internet of things terminal name and control parameter input format for executing the operation concept are obtained from the input concept, and several functions can be completed through concept conversion: (1) the method comprises the steps that context semantic calculation oriented to application is carried out, and the best internet of things terminal capable of meeting current requirements is determined in a plurality of similar internet of things terminals; (2) by decomposing different results and through technologies such as named entity recognition, the problem that the Internet of things terminal, equipment and the like are not described towards service objects in the body construction is solved. (3) The problem of semantic intercommunication among different ontology builders is solved, and the final result ontology decomposition and named entity identification technology, steps and function decomposition technology are adopted. The interoperation between the Internet of things builders subordinate to various protocols is more easily completed.
Thus far, the present invention has been described in detail. Some details well known in the art have not been described in order to avoid obscuring the concepts of the present invention. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and apparatus of the present invention may be implemented in a number of ways. For example, the methods and apparatus of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically indicated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as a program recorded in a recording medium, the program including machine-readable instructions for implementing a method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.
Although some specific embodiments of the present invention have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for the purpose of illustration and is not intended to limit the scope of the invention. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (14)
1. A semantic understanding-based Internet of things terminal interoperation method is characterized by comprising the following steps:
according to the internal and external knowledge bases and the internet data content, obtaining each entity facing the application of the internet of things and the name of each entity in different fields and application tasks in the internet;
calculating the correlation of each entity to form a uniform named entity name aiming at the same entity;
performing semantic expansion on each entity and the operation function of each entity;
when an internet of things request is received, determining a named entity name and an operation function corresponding to the internet of things request through internet of things entity semantic calculation, recording and evaluating the current operation and task completion condition after a certain operation is completed, and reversely marking each entity for realizing the operation function according to the operation and task completion condition so as to obtain an optimal entity combination for realizing the internet of things request when a related task or operation request exists in the future;
the method comprises the steps of recording data of different entity combinations to finish operation functions, evaluating the capacity of each entity, and obtaining the optimal entity combination for realizing the request of the Internet of things according to the capacity of each entity when the request of the Internet of things is received.
2. The method of claim 1, further comprising:
and obtaining control parameters of different entities meeting the request of the Internet of things, and converting the request of the Internet of things into corresponding control parameters so as to obtain the optimal combination of the entities for realizing the request of the Internet of things.
3. The method of claim 1, wherein the step of obtaining the entities for the internet of things application and the names of the entities in the internet further comprises:
establishing a semantic context resource library of the naming expression and operation function of each entity so as to calculate the relevance of each entity.
4. The method of claim 3, further comprising:
recording the flow and the step of transmitting data and control parameters related to various entities completing the operation function in each entity;
and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
5. The method of claim 1, wherein the step of semantically extending each entity and the operational functionality of each entity comprises:
and decomposing each entity and the operation function of each entity, and establishing semantic expansion which belongs to different application fields and different implementation functions and combines the Internet world concept description method.
6. The method of claim 5, further comprising:
and semantic understanding context environment facing the operation function is formed by semantic expansion of data record and operation control record.
7. The method of claim 5, further comprising:
and forming a context environment for identifying, understanding and operating the entity aiming at different fields according to the fusion of the internet information and the internet of things information.
8. The utility model provides a thing networking terminal interoperation device based on semantic understanding which characterized in that includes:
the system comprises an entity obtaining unit, an entity selecting unit and an entity selecting unit, wherein the entity obtaining unit is used for obtaining each entity facing the application of the Internet of things and the name of each entity in different fields and application tasks in the Internet according to an internal knowledge base, an external knowledge base and the data content of the Internet;
the correlation calculation unit is used for calculating the correlation of each entity to form a uniform named entity name aiming at the same entity;
the semantic expansion unit is used for performing semantic expansion on each entity and the operation function of each entity;
the task realization unit is used for determining the name and the operation function of a named entity corresponding to the request of the Internet of things through semantic calculation of the entity of the Internet of things when the request of the Internet of things is received, recording and evaluating the current operation and task completion conditions after a certain operation is completed, and reversely marking each entity realizing the operation function according to the operation and task completion conditions so as to obtain the optimal entity combination for realizing the request of the Internet of things when related tasks or operation requests exist in the future;
and the task realization unit is also used for acquiring the optimal entity combination for realizing the request of the Internet of things according to the capabilities of the entities when the request of the Internet of things is received.
9. The apparatus of claim 8,
the task implementation unit is used for obtaining control parameters of different entities meeting the request of the Internet of things and converting the request of the Internet of things into corresponding control parameters so as to obtain the optimal combination of the entities for realizing the request of the Internet of things.
10. The apparatus of claim 8, further comprising:
and the resource library establishing unit is used for establishing a semantic upper and lower resource library of the naming expression and the operation function of each entity so as to calculate the correlation of each entity.
11. The apparatus of claim 10,
the resource library establishing unit is used for recording the flow and the step of transmitting data and control parameters related to various entities completing the operation function in each entity; and carrying out semantic normalization on the flow and the steps of transmitting the data and the control parameters.
12. The apparatus of claim 8,
the semantic expansion unit is used for decomposing each entity and the operation function of each entity and establishing semantic expansion which belongs to different application fields and different implementation functions and combines the Internet world concept description method.
13. The apparatus of claim 12,
the semantic expansion unit is used for forming a semantic understanding context environment facing the operation function through semantic expansion of data records and operation control records.
14. The apparatus of claim 12,
the semantic expansion unit is used for forming a context environment for identifying, understanding and operating the entity in different fields according to the fusion of the Internet information and the Internet of things information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511016885.5A CN106933796B (en) | 2015-12-29 | 2015-12-29 | Internet of things terminal interoperation method and device based on semantic understanding |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511016885.5A CN106933796B (en) | 2015-12-29 | 2015-12-29 | Internet of things terminal interoperation method and device based on semantic understanding |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106933796A CN106933796A (en) | 2017-07-07 |
| CN106933796B true CN106933796B (en) | 2020-04-21 |
Family
ID=59441444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511016885.5A Active CN106933796B (en) | 2015-12-29 | 2015-12-29 | Internet of things terminal interoperation method and device based on semantic understanding |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106933796B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046674B (en) * | 2019-12-20 | 2024-05-31 | 科大讯飞股份有限公司 | Semantic understanding method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102970193A (en) * | 2011-09-02 | 2013-03-13 | 海尔集团公司 | System and method for intelligent software service platform, and device and family intelligence system comprising system |
| CN103577198A (en) * | 2013-11-22 | 2014-02-12 | 中国联合网络通信集团有限公司 | User-oriented Internet of Things service platform and remote control method |
| CN103810338A (en) * | 2014-02-13 | 2014-05-21 | 北京邮电大学 | Field oriented internet of things resource modeling system |
| CN104679518A (en) * | 2015-03-10 | 2015-06-03 | 中国联合网络通信集团有限公司 | Method and device for realizing semantic modeling of Internet of things |
| CN104702651A (en) * | 2013-12-10 | 2015-06-10 | 中国科学院沈阳自动化研究所 | Internet of Things architecture model based on semantics |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5937695B2 (en) * | 2011-12-14 | 2016-06-22 | エンパイア テクノロジー ディベロップメント エルエルシー | Semantic cash cloud service for connected devices |
-
2015
- 2015-12-29 CN CN201511016885.5A patent/CN106933796B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102970193A (en) * | 2011-09-02 | 2013-03-13 | 海尔集团公司 | System and method for intelligent software service platform, and device and family intelligence system comprising system |
| CN103577198A (en) * | 2013-11-22 | 2014-02-12 | 中国联合网络通信集团有限公司 | User-oriented Internet of Things service platform and remote control method |
| CN104702651A (en) * | 2013-12-10 | 2015-06-10 | 中国科学院沈阳自动化研究所 | Internet of Things architecture model based on semantics |
| CN103810338A (en) * | 2014-02-13 | 2014-05-21 | 北京邮电大学 | Field oriented internet of things resource modeling system |
| CN104679518A (en) * | 2015-03-10 | 2015-06-03 | 中国联合网络通信集团有限公司 | Method and device for realizing semantic modeling of Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933796A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kovacs et al. | Standards-based worldwide semantic interoperability for IoT | |
| KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
| JP5651789B2 (en) | Executing queries using semantically restricted relationships | |
| CN105760397B (en) | Internet of things ontology model processing method and device | |
| WO2021169842A1 (en) | Method and apparatus for updating data, electronic device, and computer readable storage medium | |
| US10496452B2 (en) | Natural language interface to web API | |
| CN105074816A (en) | Facilitating development of a spoken natural language interface | |
| Fan et al. | An integrated personalization framework for SaaS-based cloud services | |
| KR101637504B1 (en) | System and method for processing informal data | |
| CN109829164A (en) | Method and apparatus for generating text | |
| CN112364622B (en) | Dialogue text analysis method, device, electronic device and storage medium | |
| CN116108194A (en) | Knowledge graph-based search engine method, system, storage medium and electronic equipment | |
| Gilani et al. | Semantic enablement in IoT service layers—Standard progress and challenges | |
| CN115033661A (en) | Natural language semantic understanding method and device based on vertical domain knowledge graph | |
| CN106933796B (en) | Internet of things terminal interoperation method and device based on semantic understanding | |
| CN113836932A (en) | Interaction method, device and system, and intelligent device | |
| TW578067B (en) | Knowledge graphic system and method based on ontology | |
| CN113778846A (en) | Method and apparatus for generating test data | |
| Zhai et al. | PWMDS: A system supporting provenance-based matching and discovery of workflows in proteomics data analysis | |
| CN112507127B (en) | Intelligent extraction system and method based on priori knowledge graph | |
| Both et al. | Automated performance monitoring of HVAC components by artificial intelligence | |
| Debattista et al. | Processing ubiquitous personal event streams to provide user-controlled support | |
| CN117725908B (en) | Time analysis method, device and equipment in natural language processing | |
| Sangroya et al. | Natural language business intelligence question answering through SeqtoSeq transfer learning | |
| CN116737964B (en) | Artificial intelligence brain system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |