CN106649878A - Artificial intelligence-based internet-of-things entity search method and system - Google Patents
Artificial intelligence-based internet-of-things entity search method and system Download PDFInfo
- Publication number
- CN106649878A CN106649878A CN201710011671.1A CN201710011671A CN106649878A CN 106649878 A CN106649878 A CN 106649878A CN 201710011671 A CN201710011671 A CN 201710011671A CN 106649878 A CN106649878 A CN 106649878A
- Authority
- CN
- China
- Prior art keywords
- entity
- query
- node
- knowledge mapping
- sentence
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000010276 construction Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 3
- 238000013507 mapping Methods 0.000 claims description 71
- 230000008569 process Effects 0.000 claims description 25
- 239000000203 mixture Substances 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 239000000470 constituent Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000009795 derivation Methods 0.000 claims description 3
- 238000011049 filling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011068 loading method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 241000124008 Mammalia Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005194 fractionation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 235000015067 sauces Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- 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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system used for searching for entities in the internet of things. The method comprises the steps of processing a query statement of a user and generating an unambiguous intermediate language; analyzing the intermediate language into a system internal query statement through a knowledge graph; constructing a knowledge tree in a self-learning or manual training mode through a construction method; and performing distributed query on the system internal query statement through servers and a sensing network through distributed query method and protocol. The system comprises a search service system for performing analysis and result feedback on user query, an artificial intelligence system for maintaining the knowledge graph and providing analysis, and a server cluster and a sensing network system for retrieving the entities according to the system internal query statement. Through the method and the system, the user can search for the entities in the internet of things by using a natural language; the abstractness and divergence of the knowledge graph ensure that a search target can be any describable objective entity or virtual object; and the sensing network system and the protocol described in the system split a search task level by level and perform delegation, so that the system has the characteristics of high concurrency and strong compatibility.
Description
Technical field
The present invention relates to information technology and artificial intelligence field, it is more particularly related to be based on artificial intelligence
Internet of Things entity search method and system.
Background technology
Internet of Things is the network of the extension on Internet basic and extension, is the important composition portion of generation information technology
Point.The core of Internet of Things and basis remain internet, but extend user side by sensor network and extend to appoint
What enters row information and exchanges and communicate between article and article.This causes Internet of Things to pass through Intellisense, technology of identification and general meter
The communication cognition technology such as calculation, in being widely used in the fusion of network.Entity in a large amount of lives, such as household electrical appliances, communal facility
After Internet of Things is accessed, it will produce the entity information of magnanimity.Traditional search technique, the i.e. search technique based on keyword are very
Difficulty accomplishes the accurate effective search to entity, therefore, arisen at the historic moment based on the entity search technology of Internet of Things.
Main extraction and disambiguation, entity information classification, the entity relationship including entity attribute of technology composition of entity search
Excavate.The basis of these technologies is exactly the entity information database for needing early stage to take much time with energy to set up.Even if
After being foundation, with the complication of system, entity information database is also required to constantly update.With the expansion of Internet of Things scale,
The load of search engine system also can be increasing.The technologies such as inverted list, snapshots of web pages used in traditional search engines according to
Rely the continuous crawl to known web pages and analysis, it is difficult to real-time response is made to the change on network, but the letter in Internet of Things
What breath almost changed always, therefore with greater need for the real-time query technology of high concurrent.2 points of the above is that current Internet of Things network entity is searched
The main bugbear that rope technology faces.
The content of the invention
In view of this, the invention provides a kind of Internet of Things entity search method and system, using knowledge mapping with learn by oneself
The artificial intelligence technologys such as habit solve entity information Database and maintenance problems, and by a kind of new sensor network system
Solve a high concurrent real-time query difficult problem.
For achieving the above object, the present invention provides following technical scheme.
A kind of Internet of Things entity search method, including:
The method for processing the query statement of user and being mapped with the concept in knowledge mapping;
Semantic analysis and the method for generating query statement in system are carried out to query statement by knowledge mapping;
Construction, the method expanded, update knowledge mapping;
The method and agreement of distributed query are carried out to sensor network system.
The process that semantic analysis is carried out to query statement by knowledge mapping and query statement in system is generated includes:
Participle:Will language be divided into independent vocabulary;
Constituent analysis:Determine composition of the vocabulary in sentence, such as subject, predicate or object;
Composition completion:The composition omitted in sentence filling is complete;
Pronoun is replaced:Pronoun in sentence is substituted for into corresponding entity;
Word order is reset:The clause such as inversion sentence, question sentence, subordinate clause are ranked up and are split;
Disambiguation:By means such as probability analyses, ambiguous vocabulary is converted into unambiguously vocabulary or containing for its expression is limited
Justice;
Iteration:Repeat above step, until analysis result reaches expected precision;
The order of above procedure is not fixed, and is not often walked and all had to carry out, and is selectively entered according to the sentence of user input
OK, wherein some logic rules for using are stored in knowledge mapping.
The process that semantic analysis is carried out to query statement by knowledge mapping and query statement in system is generated includes:
Entity maps, and the word in sentence is mapped as into entity;
Non-physical maps, and the word in sentence is mapped as into non-physical;
Relationship map, the relation between analysis entities and non-physical;
Contextual analysis, the environment of content according to described by the feature such as the combination of word, order in sentence judges sentence;
Semantic analysis, parses the meaning that sentence is intended by, that is, wish what operation is system complete;
The order of above procedure is not fixed, and is not often walked and all had to carry out, and is selectively carried out according to intermediate language.
Construction, the method expanded, update knowledge mapping include:
Sample training is carried out to artificial intelligence system by guide;
Directly add content to knowledge mapping;
By carrying out cluster analysis to the information on the media such as internet, Internet of Things;
By the way that the new content of logical derivation acquisition is carried out to existing content in knowledge mapping or potential content is excavated.
Knowledge mapping includes:
The definition of entity:Entity includes the attribute such as title, the constraint to attribute, the action that can be carried out to entity, and entity can be with
Action for sending etc.;
Relation:The condition set up including relationship description, relation and the condition for disconnecting, judge method of the inter-entity with the presence or absence of relation
Deng this relation can be between multiple inter-entity and non-physical;
Non-physical definition:Non-physical refers to some not concepts with physical characteristics, and non-physical can include description information, be suitable for
Scope, application process etc..
The process of distributed query includes:
Query statement in system is transmitted to sensor network gateway the top-level entity node of sensor network system;
Top-level entity node generates subquery sentence and is issued to next layer entity node;
Each layer entity node checks whether itself meets querying condition;
The result that non-underlying physical node returns child node carries out merger and sequence;
Each layer entity node returns result to last layer entity node.
Distributed query agreement includes:
Header file:The state code of query task(Normally, mistake), type of message(Request, response, control), promoter, agreement
Version number, the form of text(Such as JSON or XML), coding(Such as GBK or UTF8), if encryption, compression etc.;
Text:Request message includes query statement, to the non-functional requirement inquired about;Response message text includes Query Result
The information such as collection, including fruiting quantities, query time, deadline, qualified list of entities;It is right that control message text includes
The control command of inquiry connection(Such as foundation, disconnection, hang-up or flow control)And connection state information;
Vlan query protocol VLAN does not specify the specific implementation inquired about.
A kind of Internet of Things entity search system, the system is divided into three layers, including:
Search application layer:The searching request of response user, calls knowledge mapping parsing query statement and visualizes presentation inquiry knot
Really;
Logical process layer:It is updated for storage system maintenance knowledge mapping and to knowledge mapping;
Entity search layer:For performing concrete query task, and merger, screening, sequence and paging activity are carried out to result.
Search application layer includes:
Generation does not have the entity mapping block of ambiguous intermediate language;
Above-mentioned intermediate language is resolved into the semantic module of query statement in system;
The result display module that query task is distributed to server cluster and shows Query Result.
Logical process layer includes:
Knowledge mapping system for storage system maintenance knowledge mapping and the people for being constructed to knowledge mapping, being expanded, updated
Work intelligence system.
Entity search layer includes:
The server cluster that result is processed and the sensor network system for performing query task.
The function of server cluster includes:
Server cluster is responsible for that the query statement of user input is converted into system into query task and sensor network system is sent to,
Then merger, screening, sequence and paging are carried out to the Query Result that sensor network system is returned, is finally returned to the result of application layer
Display module.
The structure of sensor network system includes:
Sensor network system is made up of two big class nodes, entity node and sensor node, and entity node is used to represent an entity,
All operations to this entity are all based on the node, and sensor node is used to obtain entity attributes information and preserve.
Sensor network system adopts tree topology, and pure sensor node must be leaf node, and entity node can be read under it
The attribute information of sensor node, and query statement can be handed down to fructification.Clear stipulaties are not respectively saved sensing network
The functional realiey mode of point, as long as providing the interface for being able to carry out query statement and returning result.Query task is substantial
Shared by node.
Understand that the system realizes query statement using the artificial intelligence system of knowledge based collection of illustrative plates via above-mentioned technical proposal
Semantization analysis, and distributed query is realized by sensing net node, realize high expansion, the high concurrent thing of semantization
Networked entity is searched for.
Description of the drawings
The main body for being considered the present invention is specifically noted and has been distinctly claimed in the ending of specification.Work as combination
When accompanying drawing is read, by reference to described in detail below, can be best understood by the present invention organizing and operating method and this
Bright purpose, characteristic and advantage, these accompanying drawings are:
Fig. 1 is a kind of entity search system architecture schematic diagram disclosed in embodiments in accordance with the present invention;
Fig. 2 is the query statement of user to be processed disclosed in embodiments in accordance with the present invention and is generated not having ambiguous intermediate language
Method flow chart;
Fig. 3 is that disclosed above-mentioned intermediate language being resolved in system by knowledge mapping of embodiments in accordance with the present invention is inquired about
The flow chart of the method for sentence;
Fig. 4 is a kind of Internet of Things entity search systematic search interface schematic diagram disclosed in concrete application embodiments of the invention;
Fig. 5 is a kind of structure chart of knowledge mapping disclosed in embodiments in accordance with the present invention;
Fig. 6 is the disclosed construction of embodiments in accordance with the present invention, expansion, the schematic diagram of the method for renewal knowledge mapping;
Fig. 7 is the structure chart of a kind of server and sensor network system disclosed in embodiments in accordance with the present invention;
Fig. 8 is a kind of node communication agreement schematic diagram disclosed in embodiments in accordance with the present invention;
Fig. 9 is a kind of flow chart of distributed sensing net system entity searching method disclosed in embodiments in accordance with the present invention.
To make illustration simple with clearly, the element illustrated in accompanying drawing is not drawn necessarily to scale.For example, rise in order to clear
See, the size of some elements may increase relative to other elements.If additionally, appropriate, label can accompanying drawing it
Between repeat to indicate correspondence or similar characteristic.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, and not all embodiments.However, ability
The technical staff in domain can understand and realize the present invention, therefore the common skill in this area in the case of without these specific details
Art personnel belong to the present invention based on all embodiments that the non-creativeness work that the present invention or embodiment are made is obtained
Protection domain.
From technical background, existing entity search system needs early stage to take much time with energy to set up mostly
Entity information database, even set up after database, it is still necessary to which existing information is continuously updated, is expanded;Cause
This, its range of application is also all confined to internet.And the information content of Internet of Things be conventional internet incomparable, its information
Also faster, the ageing requirement to Query Result is higher for renewal speed, hence sets up and maintenance entity information database needs pole
The technologies such as high cost, inverted list and full-text index also are difficult to improve search efficiency.
For problem above, a kind of Internet of Things entity search method and system based on artificial intelligence disclosed by the invention,
Entity information Database and maintenance problems are solved using artificial intelligence technologys such as knowledge mapping and self studies, and is passed through
A kind of new sensor network system solves a high concurrent real-time query difficult problem.Detailed process is illustrated in detail by way of the following examples:
Embodiment one
Accompanying drawing 1 is a kind of Internet of Things entity search system architecture schematic diagram disclosed in the embodiment of the present invention, is mainly included:
1st, application layer is searched for:Including generate do not have ambiguous intermediate language module, above-mentioned intermediate language resolved in system
The module of query statement and the module that query task is distributed to server cluster and shows Query Result.
Search application layer realizes the searching request of response user, calls knowledge mapping to parse query statement, and visualization
Three major functions of Query Result are presented.Its design object is to provide the interactive service of user and Internet of Things, by user input
Natural language is converted to executable instruction in computer, and the result for then performing instruction is with the output of intuitively form, it is ensured that
The good experience of man-machine interaction.It is described further below:
1.1 generate the module for not having ambiguous intermediate language:The Main Function of the module is the natural language for eliminating user input
Ambiguity, generate the intelligible character string of computer and then enter line statement constituent analysis.These operations are that computer realizes language
The basis of reason and good sense solution, is the prerequisite for generating query statement.
Accompanying drawing 2 is the flow chart that above-mentioned module generates the method for not having ambiguous intermediate language, and main process includes following
Step:
Participle:Will language be divided into independent vocabulary.First by the segmenting method based on string matching, by from knowledge
Existing vocabulary is matched in collection of illustrative plates to carry out preliminary exposition, is then carried out point using the mode based on probability statistics, word amendment, root
Determine whether phrase according to the probability of the appearance simultaneously of some words obtained by artificial intelligence system study.For example, user input " in
Department of traditional Chinese medicine institute of state ", using forward and reverse maximum matching algorithm can obtain result " China/department of traditional Chinese medicine/institute " and " China/in
Doctor/the academy of sciences ", recycles artificial intelligence system to compare the two kinds of combinations of " department of traditional Chinese medicine "+" institute " and " traditional Chinese medical science "+" academy of sciences " and occurs
Frequency, draw most possible result;
Constituent analysis:Determine composition of the vocabulary in sentence, such as subject, predicate or object.Knowledge mapping can preserve each word
Remittance possible composition in sentence, lists first all possible into subassembly of sentence, then according to artificial intelligence system
Learning outcome estimates probability highest and combines as composition analysis result.For example, " killed/hunter/dog " in it is existing can
Can be predicate (killing)+attribute (hunter)+object (dog), it is also possible to attribute (having killed hunter)+object (
Dog).Artificial intelligence system draws most possible result according to the probability of conventional two kinds combinations;
Composition completion:The composition omitted in sentence filling is complete.First by comparing complete sentence into subassembly and composition point
Based on context the composition that analysis result judgement is omitted, then guess content and the completion of omission.For example, user input " 5 classes of class
It is long ", system is inquired about first to the definition of " class " in knowledge mapping, and the implication of " class " has a lot, but is because while occurring in that " class
Long this word, so determining shown herein as school classes.Illustrate simultaneously, the title of place school of class is lacked in sentence.This is
System default query user is the subject of query statement, i.e. the main body of action, therefore system thinks user place school in sentence
Indication school, by IP address, GPS location or other means user geographical position is obtained, and searches for nearest school, and should
5 classes of school carries out entity search as query object;
Pronoun is replaced:Pronoun in sentence is substituted for into corresponding entity.Based on context, pronoun is replaced with into indication entity.
For example, user input " you how old ", pronoun " you " acquiescence refers to entity search system itself, and the result after replacement is " entity
How old is search system ";
Word order is reset:The clause such as inversion sentence, question sentence, subordinate clause are ranked up and are split.For example, subordinative compound " examine by last year
The student of first place has only examined third this year " can be split into that " student examined first place last year, and this year has examined the 3rd
Name ";
Disambiguation:By means such as probability analyses, ambiguous vocabulary is converted into unambiguously vocabulary or containing for its expression is limited
Justice.For example, " whether Zhang San sees material in office ", sees " read k ā n when, represent " guard ", read k à n when, expression " reading ".
Now, system can analyze the concrete identity of entity represented by subject, obtain its relevant information, if it find that the occupation of Zhang San is secret
Book, then represent that the probability of the latter is bigger, if Zhang San is security personnel, then the former probability is bigger.
1.2 modules that above-mentioned intermediate language is resolved to query statement in system:Natural language is converted into intermediate language
Simply pro forma conversion, and the effect of this module is then so that the implication of real " understanding " language of computer, according to character string
Object logic is constructed, then querying command is generated according to object logic.
Accompanying drawing 3 is the flow chart that intermediate language is resolved to above-mentioned module the method for query statement in system, main process
Comprise the following steps:
Entity maps:Word in sentence is mapped as into entity.For example, " apple not as jam it is nice ", " apple " and " really
Sauce " is exactly two entities, the example of certain class of correspondence in computer program.The module by by the phrase in sentence with storage
The title of entity carries out matching to recognize entity in knowledge mapping;
Non-physical maps:Word in sentence is mapped as into non-physical.For example, " apple not as jam it is nice ", " nice " just
It is a non-physical, for modifying " jam " this entity.Most of non-physical is used for limiting, modify entity, and expression, by force
Adjust the build-in attribute or emotion of entity;
Relationship map:Relation between analysis entities and non-physical.For example, " apple not as jam it is nice " in " be not so good as " i.e.
Represent a kind of relation, by inquire about knowledge mapping, can know " being not so good as " be intended to indicate that comparison between the two and the former
The latter is weaker than, the attribute for being compared is typically immediately being compared behind entity;
Contextual analysis:The environment of content according to described by the feature such as the combination of word, order in sentence judges sentence.For example it is " modern
Its weather is how ", system can create an environmental objects for the sentence, and the object includes the description such as time, space environment
Information, its time is today, and space is user geographic location.In more complicated sentence, it may appear that environmental objects are embedding
The situation of set, such as main clause local environment are the subobjects of subordinate clause environment.The environmental objects that contextual analysis is generated are to generate to look into
Ask the indispensable condition of sentence;
Semantic analysis:The implication that parsing sentence is intended by, that is, wish what operation is system complete.One is divided into four class classes behaviour
Make:Entities Matching, abstract entity matching, logical operation, main body exchange.Entities Matching is inquired about in Internet of Things and meets user
The entity of description, such as " dining room nearby ".The reality that certain class in knowledge mapping meets user's description is inquired about in abstract entity matching
Body, such as " maximum mammal in the world ".Logical operation referring to more than carry out logical operation simultaneously on the basis of operation
The search of operation result is returned, for example, " first has chicken still first to have egg ".Main body exchange refers to the system with the role and user of " I "
Engage in the dialogue, wherein the simulation comprising the content such as memory and affective state.
Intermediate language can be converted into query statement in system after the process of above step, and the sentence is used
It is character string that entity search layer can be recognized and processed similar to the interpreted languages of SQL syntax structure.
1.3 modules that query task is distributed to server cluster and shown Query Result, process query task main
Process is comprised the following steps:
WEB application server receive user inquiry request, is sent to nearest server cluster gateway;
The essential information of server cluster gateway acquisition user, such as identity information, geographical position, IP address, then by more than
Information encapsulation, according to the loading condition of artificial intelligence cluster suitable artificial intelligence node is sent to;
The query task of generation is returned to conjunction by artificial intelligence cluster after semantic parsing is completed by artificial intelligence cluster gateway
Suitable sensor network gateway;
The loading condition of server analysis query task and sensor network system, determines how fractionation query task and looks into son
Which Sensor Network is inquiry task be distributed to;
Sensor Network obtains subquery task and Query Result is returned after the completion of execution to sensor network gateway;
Sensor network gateway the above results are carried out merger, screening, sequence and paging, and by the result after process submit to WEB should
Use server;
WEB application server is rendered and is fed back to user to Query Result.
Accompanying drawing 4 is the Internet of Things entity search systematic search interface schematic diagram in the present embodiment.
2nd, logical process layer:It is responsible for providing the natural language processing services such as semantic analysis to searching for application layer.Including storage
The knowledge mapping system and the artificial intelligence system for being constructed to knowledge mapping, being expanded, updated of entity and non-physical information
System.
2.1 knowledge mapping systems:The system is used to storing that artificial intelligence system to generate after study to entity, non-reality
The data of body and its relation, semantic analysis is carried out to query statement and query statement is generated in system and as artificial intelligence system
Operation logic;Have in the system starting stage and understand, express the ability of natural language, and artificial intelligence system is obtained
Breath of winning the confidence is converted to the deep learning ability of entity in knowledge mapping, non-physical and relation.
Accompanying drawing 5 is a kind of structure chart of knowledge mapping that said system is used, and main contents include following structure:
Entity (Entity):Refer to objective reality and the object in things, Internet of Things or other Virtual Spaces that can be mutually distinguishable
Or concept can be mapped as the entity in knowledge mapping.Can be between entity combine, comprising and overlapping relation.Knowledge mapping
Middle entity is made up of attribute and behavior, the intrinsic property and real-time status of attribute description entity, and behavior then describes entity can enter
Capable action.For example, " people " can include attribute:" age ", " sex " and " body weight ";Behavior can be included:" having a meal ", " sleeps
Feel " and " walking ";
Non-physical:Refer to all abstract concepts in addition to entity that may map in knowledge mapping.Non-physical is to entity
Attribute and method it is abstract, these attributes and method are finally conceptualized as binary stream and basic logic operations and with non-physical
Form is stored in knowledge mapping.For example, using non-physical " the elderly " as to the abstract of entity " people ", refer to " age " belong to
Property more than threshold value a class " people ";
Relation:Refer in entity, non-physical, relation three itself or it is polynary between mutual constraint.Relation constraint causes knowledge
Collection of illustrative plates forms network structure, and entity and non-physical are connected as node with relation.For example, non-reality is connected by modified relationship
Body " height " and " people ", the people higher so as to represent height.
2.2 artificial intelligence systems:The system is with the data in knowledge mapping as operation logic;Knowledge mapping is driven to enter simultaneously
Row construction, expansion, renewal.
Accompanying drawing 6 is said system construction, expansion, the schematic diagram of the method for renewal knowledge mapping, and main contents include:
Training sample, artificial intelligence system is submitted to carry out depth using the logic in knowledge mapping by the guide in WEB server
Degree study.For example, an entity is defined with natural language, while submitting the 3D models of the entity to carries out sample training;
To server set pocket transmission operational order, evade the logical constraint in knowledge mapping, know from the modification of computer system level
Know the data in collection of illustrative plates;
Information on the media such as web crawlers crawl internet, Internet of Things carries out cluster analysis, if existed in knowledge mapping same
The information of class is then updated, and otherwise carries out the expansion of knowledge mapping;
By the way that the new content of logical derivation acquisition is carried out to existing content in knowledge mapping or potential content is excavated.Example
Such as, two kinds of entities are closely similar in knowledge mapping, and similar inter-entity often has certain relation, then knowledge mapping can be attempted
Create the relation of two kinds of entities of connection.
3rd, entity search layer:For carrying search application layer and logical process layer, concrete query task is performed, and to result
Carry out merger, screening, sequence and paging activity.Including server cluster and sensor network system.
Accompanying drawing 7 is the structure chart of a kind of server that entity search layer is used and sensor network system, mainly including following knot
Structure:
3.1 server clusters:As the hardware platform for carrying search application layer and logical process layer.Mainly include following structure:
WEB application server:For carrying search application layer, it is patterned with user and interacts;
Server cluster gateway:The entrance of artificial intelligence cluster is accessed as WEB application server, data also is responsible for and is encapsulated and real
The load balancing of existing server cluster;
Artificial intelligence cluster:For carrying logical process layer, wherein every computer is referred to as a node.Node type includes:
Ordinary node, key node and artificial intelligence node.Knowledge mapping is distributed on key node and ordinary node, adjacent node institute
Knowledge mapping there is correlation, and controlling these parameter can voluntarily optimize with inquiry and analysis result.Key node will
The ordinary node for possessing similar knowledge mapping is coupled together, and is connected with other key nodes for needing collaborative work, key section
Point can forward task to lower level node.Each artificial intelligent node is owned by the complete function of artificial intelligence system, but only deposits
The topological relation figure of the node that a part is interconnected in storage knowledge mapping, and structure is carried out to the knowledge mapping on these nodes
Make, expand, update.In addition, artificial intelligence node is also responsible for the inquiry request of response server cluster gateway transmission, and raw
Into corresponding parsing task delegation to connected key node, query statement turns in the system that will be generated after the completion of parsing task
It is dealt into sensor network gateway.Acquiescently, when a node cannot complete task, task can be transmitted to other by artificial intelligence node
Artificial intelligence node, if hop count is reached after certain value still without solution, triggers the construction of knowledge mapping, expansion, more
Newly, if node completes appointing for task, knowledge mapping is updated based on principle is moved back with entering to give up;
Sensor network gateway:For query statement in system to be sent into top-level entity node, and to the return of top-level entity node
Query Result carries out merger, screening, sequence and paging, and final result is submitted into WEB application server.Additionally can be to passing
The state of sense net carries out snapshot.
3.2 sensor network systems:Concrete query task is performed, and merger, sorting operation are carried out to result.
Accompanying drawing 8 is a kind of node communication agreement schematic diagram that entity search layer Sensor Network is used, and main contents include:
Header file:The state code of query task(Normally, mistake), type of message(Request, response, control), promoter, agreement
Version number, the form of text(Such as JSON or XML), coding(Such as GBK or UTF8), if encryption, compression etc.;
Text:Request message includes query statement, to the non-functional requirement inquired about;Response message text includes Query Result
Collection, including the information such as fruiting quantities, query time, deadline, qualified list of entities;It is right that control message text includes
The control command of inquiry connection(Such as foundation, disconnection, hang-up or flow control)And connection state information.
Accompanying drawing 9 is a kind of flow chart of the distributed sensing net system entity searching method disclosed in the embodiment of the present invention,
Main contents are comprised the following steps:
Query statement in system is transmitted to sensor network gateway the top-level entity node of sensor network system;
Top-level entity node generates subquery sentence and is issued to next layer entity node;
Each layer entity node checks whether itself meets querying condition;
The result that non-underlying physical node returns child node carries out merger and sequence;
Each layer entity node returns result to last layer entity node.
The relational terms of it should be noted that herein, such as " the " and " second " etc are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply presence between these entities or operation
Any this actual relation or order.And, belong to " including ", "comprising" or any other variant and be intended to non-row
His property is included, so that a series of process, method, article or equipment including key elements not only include those key elements, and
And also include other key elements being not expressly set out, either still include intrinsic for this method, article or equipment wanting
Element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that wanting including affiliated
Also there is other identical element in process, method, article or the equipment of element.
One of ordinary skill in the art will appreciate that realize that all or part of step in said method real-time mode is can
To be completed by programmed instruction related hardware, described program can be stored in computer read/write memory medium, here
The alleged storage medium for obtaining, such as:ROM, RAM, magnetic disc, CD etc..
The principle and embodiment that the foregoing is only the present invention is set forth, and the explanation of above example is only intended to
Help understands the method for the present invention and its core concept;Simultaneously for the half technical staff of this area, think of of the invention
Think, will change in specific embodiments and applications.In sum, this specification content should not be construed
Limitation of the present invention.All any modification, equivalent substitution and improvements done within the spirit and principles in the present invention etc., wrap
Containing within the scope of the present invention.
Claims (12)
1. a kind of method for Internet of Things entity search, its content includes:
The method for processing the query statement of user and being mapped with the concept in knowledge mapping;
Semantic analysis and the method for generating query statement in system are carried out to query statement by knowledge mapping;
Construction, the method expanded, update knowledge mapping;
The method and agreement of distributed query are carried out to sensor network system.
2. the method as described in claim 1, it is characterised in that process user query statement and with knowledge mapping in
The method that concept is mapped, including:
Participle:Will language be divided into independent vocabulary;
Constituent analysis:Determine composition of the vocabulary in sentence, such as subject, predicate or object;
Composition completion:The composition omitted in sentence filling is complete;
Pronoun is replaced:Pronoun in sentence is substituted for into corresponding entity;
Word order is reset:The clause such as inversion sentence, question sentence, subordinate clause are ranked up and are split;
Disambiguation:By means such as probability analyses, ambiguous vocabulary is converted into unambiguously vocabulary or containing for its expression is limited
Justice;
Iteration:Repeat above step, until analysis result reaches expected precision;
The order of above procedure is not fixed, and is not often walked and all had to carry out, and is selectively entered according to the sentence of user input
OK, wherein some logic rules for using are stored in knowledge mapping.
3. the method as described in claim 1, it is characterised in that the intermediate language and user that method is generated is to be expressed
It is corresponding relation between implication, i.e., every intermediate language can only express a kind of implication.
4. the method as described in claim 1, it is characterised in that knowledge mapping, including:
The definition of entity:Entity includes the attribute such as title, the constraint to attribute, the action that can be carried out to entity, and entity can be with
Action for sending etc.;
Relation:The condition set up including relationship description, relation and the condition for disconnecting, judge method of the inter-entity with the presence or absence of relation
Deng this relation can be between multiple inter-entity and non-physical;
Non-physical definition:Non-physical refers to some not concepts with physical characteristics, and non-physical can include description information, be suitable for
Scope, application process etc..
5. the method as described in claim 1, it is characterised in that semantic analysis is carried out to query statement by knowledge mapping
And the method for generating query statement in system, including:
Entity maps, and the word in sentence is mapped as into entity;
Non-physical maps, and the word in sentence is mapped as into non-physical;
Relationship map, the relation between analysis entities and non-physical;
Contextual analysis, the environment of content according to described by the feature such as the combination of word, order in sentence judges sentence;
Semantic analysis, parses the meaning that sentence is intended by, that is, wish what operation is system complete;
The order of above procedure is not fixed, and is not often walked and all had to carry out, and is selectively carried out according to intermediate language.
6. the method as described in claim 1, it is characterised in that construction, the method expanded, update knowledge mapping, including:
Sample training is carried out to artificial intelligence system by guide;
Directly add content to knowledge mapping;
By carrying out cluster analysis to the information on the media such as internet, Internet of Things;
By the way that the new content of logical derivation acquisition is carried out to existing content in knowledge mapping or potential content is excavated.
7. the method as described in claim 1, it is characterised in that distributed enquiring method, including:
Query statement in system is transmitted to sensor network gateway the top-level entity node of sensor network system;
Top-level entity node generates subquery sentence and is issued to next layer entity node;
Each layer entity node checks whether itself meets querying condition;
The result that non-underlying physical node returns child node carries out merger and sequence;
Each layer entity node returns result to last layer entity node.
8. the method as described in claim 1, it is characterised in that distributed query agreement, including:
Header file:The state code of query task(Normally, mistake), type of message(Request, response, control), promoter, agreement
Version number, the form of text(Such as JSON or XML), coding(Such as GBK or UTF8), if encryption, compression etc.;
Text:Request message includes query statement, to the non-functional requirement inquired about;Response message text includes Query Result
The information such as collection, including fruiting quantities, query time, deadline, qualified list of entities;It is right that control message text includes
The control command of inquiry connection(Such as foundation, disconnection, hang-up or flow control)And connection state information;
Vlan query protocol VLAN does not specify the specific implementation inquired about.
9. a kind of system for Internet of Things entity search, the system is divided into three layers, and its content includes:
Search application layer:The searching request of response user, calls knowledge mapping parsing query statement and visualizes presentation inquiry knot
Really;
Logical process layer:It is updated for storage system maintenance knowledge mapping and to knowledge mapping;
Entity search layer:For carrying search application layer and logical process layer, concrete query task is performed, and result is returned
And, screening, sequence and paging activity.
10. the system as described in claim 9, it is characterised in that search application layer, including:
Generation does not have the entity mapping block of ambiguous intermediate language;
Above-mentioned intermediate language is resolved into the semantic module of query statement in system;
The result display module that query task is distributed to server cluster and shows Query Result.
11. systems as described in claim 9, it is characterised in that logical process layer, including:
Knowledge mapping system for storage system maintenance knowledge mapping and the people for being constructed to knowledge mapping, being expanded, updated
Work intelligence system.
12. systems as described in claim 9, it is characterised in that entity search layer, including:
Server cluster:As the hardware platform for carrying search application layer and logical process layer;
Server cluster is responsible for that the query statement of user input is converted into system into query task and sensor network system is sent to,
Then merger, screening, sequence and paging are carried out to the Query Result that sensor network system is returned, is finally returned to the result of application layer
Display module;
Sensor network system:It is made up of entity node and sensor node, under conditions of distributed search agreement is met, Sensor Network
It can also be isomery or virtual;
Sensor network system uses tree topology, and its top mode must be entity node, and sensor node must be leaf segment
Point;
It can also be sensor node that the child node of entity node both can be entity node;
Entity node is used for identification and one entity of mark, and query statement is responded;
Sensor node is used to gather affiliated entity attributes information, and except real time information, sensor will also maintain going through for node
History status information;
To historical information in the near future, preserved by the way of constant duration, over a long time the historical information time it is more early interval more
Greatly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710011671.1A CN106649878A (en) | 2017-01-07 | 2017-01-07 | Artificial intelligence-based internet-of-things entity search method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710011671.1A CN106649878A (en) | 2017-01-07 | 2017-01-07 | Artificial intelligence-based internet-of-things entity search method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106649878A true CN106649878A (en) | 2017-05-10 |
Family
ID=58842723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710011671.1A Pending CN106649878A (en) | 2017-01-07 | 2017-01-07 | Artificial intelligence-based internet-of-things entity search method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106649878A (en) |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108156260A (en) * | 2018-02-09 | 2018-06-12 | 北京物联港科技发展有限公司 | A kind of across vendor equipment communication platform in Internet of Things port |
CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
CN108461151A (en) * | 2017-12-15 | 2018-08-28 | 北京大学深圳研究生院 | A kind of the logic Enhancement Method and device of knowledge mapping |
CN108848192A (en) * | 2018-08-01 | 2018-11-20 | 佛山市甜慕链客科技有限公司 | A kind of method that internet of things equipment cluster carries out distributed treatment |
CN108874907A (en) * | 2018-05-25 | 2018-11-23 | 北京明略软件系统有限公司 | A kind of data query method and apparatus, computer readable storage medium |
CN109086316A (en) * | 2018-06-27 | 2018-12-25 | 南京邮电大学 | Knowledge mapping towards industrial Internet of Things resource independently constructs system |
CN109165296A (en) * | 2018-06-27 | 2019-01-08 | 南京邮电大学 | Industrial Internet of Things resources and knowledge map construction method, readable storage medium storing program for executing and terminal |
CN109189946A (en) * | 2018-11-06 | 2019-01-11 | 湖南云智迅联科技发展有限公司 | A method of the description of equipment fault sentence is converted into knowledge mapping expression |
CN109344238A (en) * | 2018-09-18 | 2019-02-15 | 阿里巴巴集团控股有限公司 | The benefit word method and apparatus of user's question sentence |
CN109657067A (en) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | Methods of exhibiting, device, computer equipment and the storage medium of knowledge mapping |
CN109844743A (en) * | 2017-06-26 | 2019-06-04 | 微软技术许可有限责任公司 | Response is generated in automatic chatting |
WO2019144587A1 (en) * | 2018-01-24 | 2019-08-01 | 平安医疗健康管理股份有限公司 | Dynamic knowledge graph updating method fusing medical knowledge and application cases |
CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
CN110263180A (en) * | 2019-06-13 | 2019-09-20 | 北京百度网讯科技有限公司 | It is intended to knowledge mapping generation method, intension recognizing method and device |
CN110275898A (en) * | 2018-03-16 | 2019-09-24 | 埃森哲环球解决方案有限公司 | Use the integrated monitoring and communication system of the explanatory equipment management of knowledge based figure |
CN110334939A (en) * | 2019-07-01 | 2019-10-15 | 济南大学 | Door and window customizes material information quickly configuration method, system, equipment and medium |
CN110379520A (en) * | 2019-06-18 | 2019-10-25 | 北京百度网讯科技有限公司 | The method for digging and device of medical knowledge map, computer equipment and readable medium |
CN110727806A (en) * | 2019-12-17 | 2020-01-24 | 北京百度网讯科技有限公司 | Text processing method and device based on natural language and knowledge graph |
CN111353049A (en) * | 2020-02-24 | 2020-06-30 | 京东方科技集团股份有限公司 | Data updating method and device, electronic equipment and computer readable storage medium |
CN111431962A (en) * | 2020-02-20 | 2020-07-17 | 北京邮电大学 | Cross-domain resource access Internet of things service discovery method based on context awareness calculation |
CN111581237A (en) * | 2019-02-15 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Data query method, device and system and electronic equipment |
CN111611448A (en) * | 2019-02-22 | 2020-09-01 | 通用电气公司 | Knowledge-driven joint big data query and analysis platform |
CN111611304A (en) * | 2019-02-22 | 2020-09-01 | 通用电气公司 | Knowledge-driven joint big data query and analysis platform |
CN111723214A (en) * | 2020-06-09 | 2020-09-29 | 云南大学 | Mode-oriented non-functional requirement knowledge refinement method |
CN111738296A (en) * | 2020-05-22 | 2020-10-02 | 广东科学技术职业学院 | One-stop service platform based on data fusion |
CN111886601A (en) * | 2019-03-01 | 2020-11-03 | 卡德乐人工智能私人有限公司 | System and method for adaptive question answering |
CN112115276A (en) * | 2020-09-18 | 2020-12-22 | 平安科技(深圳)有限公司 | Intelligent customer service method, device, equipment and storage medium based on knowledge graph |
CN112507123A (en) * | 2020-12-04 | 2021-03-16 | 北京搜狗科技发展有限公司 | Data processing method and device |
CN113919360A (en) * | 2020-07-09 | 2022-01-11 | 阿里巴巴集团控股有限公司 | Semantic understanding method, voice interaction method, device, equipment and storage medium |
CN117422002A (en) * | 2023-12-19 | 2024-01-19 | 利尔达科技集团股份有限公司 | AIGC-based embedded product generation method, system and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510221A (en) * | 2009-02-17 | 2009-08-19 | 北京大学 | Enquiry statement analytical method and system for information retrieval |
CN104598623A (en) * | 2015-02-03 | 2015-05-06 | 东南大学 | Comprehensive sensing network stratified data management system |
CN104866593A (en) * | 2015-05-29 | 2015-08-26 | 中国电子科技集团公司第二十八研究所 | Database searching method based on knowledge graph |
US20160041986A1 (en) * | 2014-08-08 | 2016-02-11 | Cuong Duc Nguyen | Smart Search Engine |
CN105824802A (en) * | 2016-03-31 | 2016-08-03 | 清华大学 | Method and device for acquiring knowledge graph vectoring expression |
CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
-
2017
- 2017-01-07 CN CN201710011671.1A patent/CN106649878A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510221A (en) * | 2009-02-17 | 2009-08-19 | 北京大学 | Enquiry statement analytical method and system for information retrieval |
US20160041986A1 (en) * | 2014-08-08 | 2016-02-11 | Cuong Duc Nguyen | Smart Search Engine |
CN104598623A (en) * | 2015-02-03 | 2015-05-06 | 东南大学 | Comprehensive sensing network stratified data management system |
CN104866593A (en) * | 2015-05-29 | 2015-08-26 | 中国电子科技集团公司第二十八研究所 | Database searching method based on knowledge graph |
CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
CN105824802A (en) * | 2016-03-31 | 2016-08-03 | 清华大学 | Method and device for acquiring knowledge graph vectoring expression |
Non-Patent Citations (1)
Title |
---|
刘峤等: "知识图谱构建技术综述" * |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109844743A (en) * | 2017-06-26 | 2019-06-04 | 微软技术许可有限责任公司 | Response is generated in automatic chatting |
CN109844743B (en) * | 2017-06-26 | 2023-10-17 | 微软技术许可有限责任公司 | Generating responses in automated chat |
CN108461151A (en) * | 2017-12-15 | 2018-08-28 | 北京大学深圳研究生院 | A kind of the logic Enhancement Method and device of knowledge mapping |
CN108461151B (en) * | 2017-12-15 | 2021-06-15 | 北京大学深圳研究生院 | Logic enhancement method and device of knowledge graph |
CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
CN108345647B (en) * | 2018-01-18 | 2021-12-03 | 北京邮电大学 | Web-based domain knowledge graph construction system and method |
WO2019144587A1 (en) * | 2018-01-24 | 2019-08-01 | 平安医疗健康管理股份有限公司 | Dynamic knowledge graph updating method fusing medical knowledge and application cases |
CN108156260A (en) * | 2018-02-09 | 2018-06-12 | 北京物联港科技发展有限公司 | A kind of across vendor equipment communication platform in Internet of Things port |
CN110275898B (en) * | 2018-03-16 | 2023-07-21 | 埃森哲环球解决方案有限公司 | Integrated monitoring and communication system using knowledge graph-based interpretive device management |
CN110275898A (en) * | 2018-03-16 | 2019-09-24 | 埃森哲环球解决方案有限公司 | Use the integrated monitoring and communication system of the explanatory equipment management of knowledge based figure |
CN108874907A (en) * | 2018-05-25 | 2018-11-23 | 北京明略软件系统有限公司 | A kind of data query method and apparatus, computer readable storage medium |
CN109165296A (en) * | 2018-06-27 | 2019-01-08 | 南京邮电大学 | Industrial Internet of Things resources and knowledge map construction method, readable storage medium storing program for executing and terminal |
CN109086316B (en) * | 2018-06-27 | 2021-09-14 | 南京邮电大学 | Knowledge graph autonomous construction system for industrial Internet of things resources |
CN109086316A (en) * | 2018-06-27 | 2018-12-25 | 南京邮电大学 | Knowledge mapping towards industrial Internet of Things resource independently constructs system |
CN109165296B (en) * | 2018-06-27 | 2021-05-18 | 南京邮电大学 | Industrial Internet of things resource knowledge map construction method, readable storage medium and terminal |
CN108848192A (en) * | 2018-08-01 | 2018-11-20 | 佛山市甜慕链客科技有限公司 | A kind of method that internet of things equipment cluster carries out distributed treatment |
CN109344238A (en) * | 2018-09-18 | 2019-02-15 | 阿里巴巴集团控股有限公司 | The benefit word method and apparatus of user's question sentence |
CN109189946A (en) * | 2018-11-06 | 2019-01-11 | 湖南云智迅联科技发展有限公司 | A method of the description of equipment fault sentence is converted into knowledge mapping expression |
CN109657067A (en) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | Methods of exhibiting, device, computer equipment and the storage medium of knowledge mapping |
CN111581237B (en) * | 2019-02-15 | 2023-06-09 | 阿里巴巴集团控股有限公司 | Data query method, device and system and electronic equipment |
CN111581237A (en) * | 2019-02-15 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Data query method, device and system and electronic equipment |
CN111611448A (en) * | 2019-02-22 | 2020-09-01 | 通用电气公司 | Knowledge-driven joint big data query and analysis platform |
CN111611304A (en) * | 2019-02-22 | 2020-09-01 | 通用电气公司 | Knowledge-driven joint big data query and analysis platform |
CN111886601B (en) * | 2019-03-01 | 2024-03-01 | 卡德乐人工智能私人有限公司 | System and method for adaptive question-answering |
CN111886601A (en) * | 2019-03-01 | 2020-11-03 | 卡德乐人工智能私人有限公司 | System and method for adaptive question answering |
CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
CN110263180A (en) * | 2019-06-13 | 2019-09-20 | 北京百度网讯科技有限公司 | It is intended to knowledge mapping generation method, intension recognizing method and device |
CN110379520A (en) * | 2019-06-18 | 2019-10-25 | 北京百度网讯科技有限公司 | The method for digging and device of medical knowledge map, computer equipment and readable medium |
CN110334939B (en) * | 2019-07-01 | 2022-03-15 | 济南大学 | Door and window customized material information rapid configuration method, system, equipment and medium |
CN110334939A (en) * | 2019-07-01 | 2019-10-15 | 济南大学 | Door and window customizes material information quickly configuration method, system, equipment and medium |
CN110727806A (en) * | 2019-12-17 | 2020-01-24 | 北京百度网讯科技有限公司 | Text processing method and device based on natural language and knowledge graph |
CN110727806B (en) * | 2019-12-17 | 2020-08-11 | 北京百度网讯科技有限公司 | Text processing method and device based on natural language and knowledge graph |
CN111431962A (en) * | 2020-02-20 | 2020-07-17 | 北京邮电大学 | Cross-domain resource access Internet of things service discovery method based on context awareness calculation |
CN111431962B (en) * | 2020-02-20 | 2021-10-01 | 北京邮电大学 | Cross-domain resource access Internet of things service discovery method based on context awareness calculation |
CN111353049A (en) * | 2020-02-24 | 2020-06-30 | 京东方科技集团股份有限公司 | Data updating method and device, electronic equipment and computer readable storage medium |
CN111738296A (en) * | 2020-05-22 | 2020-10-02 | 广东科学技术职业学院 | One-stop service platform based on data fusion |
CN111738296B (en) * | 2020-05-22 | 2023-10-10 | 广东科学技术职业学院 | One-stop service platform based on data fusion |
CN111723214A (en) * | 2020-06-09 | 2020-09-29 | 云南大学 | Mode-oriented non-functional requirement knowledge refinement method |
CN111723214B (en) * | 2020-06-09 | 2024-05-17 | 云南大学 | Mode-oriented nonfunctional demand knowledge refinement method |
CN113919360A (en) * | 2020-07-09 | 2022-01-11 | 阿里巴巴集团控股有限公司 | Semantic understanding method, voice interaction method, device, equipment and storage medium |
CN112115276A (en) * | 2020-09-18 | 2020-12-22 | 平安科技(深圳)有限公司 | Intelligent customer service method, device, equipment and storage medium based on knowledge graph |
CN112115276B (en) * | 2020-09-18 | 2024-05-24 | 平安科技(深圳)有限公司 | Intelligent customer service method, device, equipment and storage medium based on knowledge graph |
WO2022116527A1 (en) * | 2020-12-04 | 2022-06-09 | 北京搜狗科技发展有限公司 | Data processing method and device |
CN112507123A (en) * | 2020-12-04 | 2021-03-16 | 北京搜狗科技发展有限公司 | Data processing method and device |
CN117422002A (en) * | 2023-12-19 | 2024-01-19 | 利尔达科技集团股份有限公司 | AIGC-based embedded product generation method, system and storage medium |
CN117422002B (en) * | 2023-12-19 | 2024-04-19 | 利尔达科技集团股份有限公司 | AIGC-based embedded product generation method, AIGC-based embedded product generation system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106649878A (en) | Artificial intelligence-based internet-of-things entity search method and system | |
CN109710701B (en) | Automatic construction method for big data knowledge graph in public safety field | |
US10725836B2 (en) | Intent-based organisation of APIs | |
CN104346377B (en) | A kind of data integration and transfer method based on unique mark | |
JP5904559B2 (en) | Scenario generation device and computer program therefor | |
CN111428054A (en) | Construction and storage method of knowledge graph in network space security field | |
CN103631596B (en) | Business object data typing and the configuration device and collocation method for updating rule | |
Wang et al. | NEIWalk: Community discovery in dynamic content-based networks | |
CN107341215A (en) | A kind of vertical knowledge mapping classification ensemble querying method of multi-source based on Distributed Computing Platform | |
JP6403382B2 (en) | Phrase pair collection device and computer program therefor | |
Jabbar et al. | A methodology of real-time data fusion for localized big data analytics | |
Delgado et al. | An evaluation of ontology matching techniques on geospatial ontologies | |
Pernelle et al. | An automatic key discovery approach for data linking | |
CN110309289A (en) | A kind of sentence generation method, sentence generation device and smart machine | |
JP5907393B2 (en) | Complex predicate template collection device and computer program therefor | |
CN110390352A (en) | A kind of dark data value appraisal procedure of image based on similitude Hash | |
KR102125455B1 (en) | System for establishing data of harbor management based on bim and method thereof | |
CN111191047A (en) | Knowledge graph construction method for human-computer cooperation disassembly task | |
CN109783484A (en) | The construction method and system of the data service platform of knowledge based map | |
CN109299340A (en) | A kind of microblog users forwarding relationship importing and method for visualizing based on chart database | |
CN101770473A (en) | Method for querying hierarchical semantic venation document | |
Deng et al. | Social Web Meets Sensor Web: From User-Generated Content to Linked Crowdsourced Observation Data | |
Torre-Bastida et al. | Query rewriting for an incremental search in heterogeneous linked data sources | |
CN113377739A (en) | Knowledge graph application method, knowledge graph application platform, electronic equipment and storage medium | |
Baglioni et al. | Improving geodatabase semantic querying exploiting ontologies |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170510 |
|
WD01 | Invention patent application deemed withdrawn after publication |