CN105512316B - A kind of Knowledge Service System of combination mobile terminal - Google Patents
A kind of Knowledge Service System of combination mobile terminal Download PDFInfo
- Publication number
- CN105512316B CN105512316B CN201510937756.3A CN201510937756A CN105512316B CN 105512316 B CN105512316 B CN 105512316B CN 201510937756 A CN201510937756 A CN 201510937756A CN 105512316 B CN105512316 B CN 105512316B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- node
- module
- knowledge node
- user
- 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
- 238000012800 visualization Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 241001269238 Data Species 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 20
- 235000013399 edible fruits Nutrition 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000007794 visualization technique Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
Abstract
The invention discloses a kind of Knowledge Service Systems of combination mobile terminal, including cloud service engine and mobile terminal.Cloud service engine includes: knowledge acquisition module, knowledge search module, knowledge recommendation module, knowledge reasoning module, visualization processing module, picture recognition module, knowledge data base and characteristics of image library, above-mentioned each module and library are deployed in a server, or be deployed in can be by multiple servers that high speed network mutually accesses for distribution.Mobile terminal includes: image collection module, image characteristics extraction module and subscriber interface module.The knowledge services method based on the Knowledge Service System that the present invention also provides a kind of.
Description
Technical field
The present invention relates to Computer Applied Technology and mobile communication fields, relate in particular to a kind of combination mobile terminal
Knowledge Service System.
Background technique
Knowledge services are to need targetedly to refine knowledge according to people from various dominant and implicit knowledge resource,
And it is used to solve the information service process of the advanced stage of customer problem.This its feature of service is that, it be it is a kind of towards
The service of knowledge content and solution.Knowledge services are different from traditional information service, and knowledge services are not only ownership goal
The service of driving, or the service towards value-added service, knowledge services pay close attention to and emphasize using oneself unique knowledge and ability,
Processing is carried out to ready-made information and forms the new information products with unique value, solves other knowledge and ability for user
The problem of cann't be solved.
1973, Martin library pa invented mobile phone, then tablet computer till now, and various mobile terminals become us
Indispensable a part in life.Modern mobile terminal has central processing unit, memory, input/output on hardware
Equal components;On software, mobile terminal has various dedicated operating systems;In communication capacity, mobile terminal is equipped with height
Bandwidth communication performance and flexible access way enable mobile terminal according to selected business and locating environment, certainly
Dynamic adjustment communication mode.At the same time, mobile terminal more focuses on multifunction, personalization and the experience of hommization.Exactly because
For the continuous development of mobile terminal and universal, the various application programs based on mobile terminal have become in people's living and studying
Indispensable tool.Although fast-developing in conjunction with the Knowledge Service System of mobile terminal at present;But these knowledge services
System is not sought unity of standard in knowledge organization, existing defects, also, is based primarily upon keyword rather than language in knowledge calculating
Justice, what is provided is only the knowledge services of shallow hierarchy.
With the continuous development of computer technology, the performance of computer has obtained large increase, but the mankind and computer
Between or there is the gullies of exchange.For the service for allowing user that computer is preferably utilized to provide, what we to be done is not answered
This be allow user preferably to adapt to computer, and should be allow computer adapt to the mankind, allow computer it will be appreciated that user meaning
Figure, more natural, accessible service is provided for user.And natural human-computer interaction technology is that computer is exchanged with the accessible of the mankind
Provide possibility.In addition to using text to interact with computer, we should also be by means of other interactive means by computer
Understand the intention of the mankind, for example, view-based access control model, sound, movement, expression natural interactive style.
The present invention passes through the specific knowledge services demand that combines, the relationship inside analysis knowledge, by knowledge organization at complete
This figure knowledge;In terms of knowledge reasoning, user behavior is obtained by mobile terminal, user inputs, and extracts user behavior, user
Information in input, thus more significant the reasoning results;Knowledge based obtains the knowledge data base of building, knowledge services system
System provides a user the service such as knowledge search, knowledge recommendation, knowledge reasoning;Knowledge Service System is compared and traditional text, figure
Traditional exhibition of knowledge mode such as piece, video, hyperlink, system by the way of information visualization, using basic statistical chart,
Label-cloud, mind map etc. visualize presentation mode, are more clear to user, explicitly show the knowledge contained in information;Together
When, by mobile terminal and various services, the combination of visualization technique, so that Knowledge Service System more has characteristic.
Mobile terminal combination knowledge services, only user does not provide more profound, personalized knowledge services, also allows
User can it is more convenient, comprehensively obtain knowledge services, improve user obtain and learning knowledge experience.
Summary of the invention
A kind of Knowledge Service System of combination mobile terminal, including cloud service engine and mobile terminal, in which:
Cloud service engine includes:
Knowledge acquisition module obtains knowledge by way of human-computer interaction, and carries out tissue to knowledge, manages and in knowledge
It is stored in database;
Knowledge search module, the recognition result of knowledge based database and picture recognition module provide a user knowledge and search
Rope service;
What knowledge recommendation module, knowledge based database and user's history behavior or knowledge based search module searched
Knowledge node and user's history behavior, provide a user knowledge recommendation service, and knowledge node is indicate human knowledge substantially single
Member, by the way that the knowledge of the mankind is carried out cutting, to the data that the representation of knowledge segmented can store and identify at computer, i.e.,
For knowledge node;
Knowledge reasoning module, the knowledge node and user's history behavior that knowledge based search module searches, with reference to rule
Set makes inferences, and provides a user the reasoning results;
Visualization processing module, by least one in knowledge search module, knowledge recommendation module and knowledge reasoning module
Output visualization, and visualization result is sent to mobile terminal;
Picture recognition module matches the characteristics of image received from mobile terminal, with characteristics of image library to obtain
Recognition result;
Knowledge data base, stored knowledge;And
Characteristics of image library stores the characteristics of image of multiple images,
Wherein, above-mentioned each module and library are deployed in a server, or be deployed in can be by high speed network phase for distribution
In the multiple servers mutually accessed,
Mobile terminal includes:
Image collection module obtains image;
Image characteristics extraction module, from image zooming-out feature;And
Subscriber interface module realizes the human-computer interaction with user.
The knowledge services method based on the Knowledge Service System that the present invention also provides a kind of.
Detailed description of the invention
Fig. 1 is the system construction drawing for the Knowledge Service System that the present invention combines mobile terminal;
Fig. 2 is the knowledge services method flow diagram for the Knowledge Service System that the present invention combines mobile terminal;
Fig. 3 is the system flow chart for the Knowledge Service System that the present invention combines mobile terminal;
Fig. 4 is knowledge acquisition module structure chart of the present invention;
Fig. 5 is knowledge search function structure chart of the present invention;
Fig. 6 is knowledge recommendation function structure chart of the present invention;
Fig. 7 is knowledge reasoning function structure chart of the present invention;
Fig. 8 is image collection module structure chart of the present invention;
Fig. 9 is image characteristics extraction function structure chart of the present invention;
Figure 10 is picture recognition module structure chart of the present invention;
Figure 11 a is the knowledge classification result figure in knowledge acquisition module of the present invention;
Figure 11 b is the knowledge cutting result figure in knowledge acquisition module of the present invention;
Figure 11 c is the partial knowledge node diagram inserted in civil construction in knowledge acquisition module of the present invention;
Figure 11 d is the knowledge node attributes edit interface in knowledge acquisition module of the present invention;
Figure 11 e is the knowledge node attribute modification interface in knowledge acquisition module of the present invention;
Figure 11 f is the content of " Qin Shihuang Tomb " knowledge node in knowledge acquisition module of the present invention;
Figure 12 a is the result that " Xuanzang " inquires in knowledge search module of the present invention;
Figure 12 b is the result of " permanently happy " fuzzy query in knowledge search module of the present invention;
Figure 12 c is after the knowledge node that " Xuanzang " and " permanently happy " searches in knowledge search module of the present invention assigns weight
Result;
Figure 12 d is the final result of " Xuanzang " and " permanently happy " search in knowledge search module of the present invention;
Figure 12 e is " Xuanzang " and " permanently happy " search result on mobile terminals visual in knowledge search module of the present invention
Change and result is presented;
Figure 13 a is the historical behavior data of the user 1603 in knowledge recommendation module of the present invention;
Figure 13 b is the recommendation results to user 1603 in knowledge recommendation module of the present invention;
Figure 13 c is the similar knowledge node with knowledge node " Xuanzang " in knowledge recommendation module of the present invention;
Figure 13 d is the knot with knowledge node " Xuanzang " after similar knowledge node sequence in knowledge recommendation module of the present invention
Fruit;
Figure 13 e is the visualization result of " Xuanzang " recommendation results in knowledge recommendation module of the present invention;
Figure 14 is the picture got in image collection module of the present invention;
Figure 15 is the picture feature point extracted in image characteristics extraction module of the present invention;
Figure 16 is the example of the sample in the characteristics of image library in picture recognition module of the present invention;
Specific embodiment
The technical issues of present invention is to be solved be how the profound information of abundant Extracting Knowledge, how using knowledge it is visual
Change technology realizes that the depth of knowledge is shown, and how semantic-based knowledge services is combined with mobile terminal application,
Finally it is embodied as users group and outstanding, convenient and fast knowledge services is provided, it is mobile eventually that the present invention provides a kind of combinations thus
The Knowledge Service System at end.
Technical solution provided by the invention is as follows:
Knowledge Service System is made of cloud service engine and mobile terminal, and each module for including in system two-tier system is such as
Under:
One, knowledge acquisition module, obtained by way of human-computer interaction knowledge (knowledge includes at least one of the following:
Text, picture, video and audio), and using the institutional framework of knowledge tree, tissue, pipe are carried out to knowledge and associated resource
Reason and storage, it is specific to execute following operation, comprising:
Step S101 in the present system classifies the knowledge of the mankind, and sorted knowledge is cut into knowledge again
The knowledge of the mankind is indicated that knowledge node is intended to indicate that the basic unit of human knowledge, i.e., logical by node using knowledge node
It crosses and as knows the knowledge progress cutting of the mankind the data that the representation of knowledge segmented can store and identify at computer
Know node;Wherein, knowledge node is indicated by knowledge node title, Property Name, attribute value;Therefore, knowledge is needed in this step
The knowledge of engineer's typing as needed is analyzed, and judges whether the database of current design can indicate what knowledge node included
Relationship between content and knowledge node;If current database does not support the demand of knowledge typing, step S102 is turned to;Instead
It, turns to step S103;
Step S102 redesigns knowledge data base according to the demand of knowledge typing;
Knowledge is carried out cutting according to the demand of Knowledge Service System, obtains certain particle size by step S103, knowledge engineer
Knowledge node, and obtain the title of each knowledge node;
Step S104, knowledge node are indicated by attribute, attribute value, conclude to knowledge node by knowledge engineer and be divided
Analysis obtains the attribute that knowledge node is included, and determines Property Name, i.e., when indicating a certain attribute of knowledge node, this
The title of attribute is unified;In addition, determine attribute in include field, such as resource corresponding to attribute (video, picture,
Audio), latitude and longitude information;
Step S105, knowledge node is inserted knowledge base by knowledge engineer, and knowledge node is pressed tree structure tissue, i.e.,
There is set membership, brotherhood between knowledge node;
Step S106, knowledge engineer improve the content of knowledge node, the i.e. attribute, attribute value of typing knowledge node.
Two, knowledge search module provides a user knowledge search service, specifically includes:
Step S201, search content from image recognition as a result, search content include Chinese character, English character,
Phrase, phrase, sentence etc.;
Step S202 divides the search content that step S201 is obtained using the jieba-0.35 word segmentation module of Python
Then word extracts search key according to word segmentation result;
Step S203 accurately inquires the keyword extracted in step S202, i.e., search and the pass in knowledge base
The knowledge node of keyword exact matching, and weight " 9999 " are assigned to the knowledge node found;
The knowledge node that search key exact matching whether is found in step S204, judgment step S203, if found
The knowledge node of exact matching is then transferred to step S207;Conversely, being transferred to step S205;
Step S205, it is determined whether to enable fuzzy query functions, if opening fuzzy query function, turn to step
S206;Conversely, turning to step S207;
The search key that the knowledge node of exact matching is not found in step S203 is carried out fuzzy look by step S206
It askes, i.e., searches for the knowledge node that knowledge node title includes search key in knowledge base, and assign to the knowledge node found
Give weight " 999 ";
The knowledge node that step S207, obtaining step S203 and step S206 are inquired, in knowledge base search and this
Other relevant knowledge nodes of a little knowledge nodes, and weight, weight, that is, knowledge of knowledge node are assigned to the knowledge node found
The similarity of node and search key, similarity similarity (node, keyword) calculation formula are as follows:
Similarity (node, keyword)=∑i∈attribute(node)Match (i, keyword) formula 1
Wherein, node represents knowledge node, and keyword represents search key, and i represents wherein the one of knowledge node node
A attribute, i.value represent the value (attribute value can be character string or number) of attribute i, and attribute (node) represents node
The all properties of node;Knowledge node and the similarity of search key calculate search key and knowledge node attribute value
The number matched, coupling number is higher, then knowledge node and the similarity of search key are bigger;If closed in attribute value containing search
Keyword, then the search key is matched with this attribute value of knowledge node, i.e., the value of formula (2) is 1, conversely, formula (2)
Value is 0;
Step S208, the knowledge node that step S203, step S206 and step S207 are searched for is by knowledge node institute
The knowledge tree of category is classified, and removes duplicate knowledge node;
Knowledge node after classification, duplicate removal in S208 is ranked up by the weight of knowledge node, that is, weighed by step S209
It is more forward to be worth higher knowledge node ranking;
Step S210, the knowledge node after S209 is arranged visually are presented, i.e., the search knot that will be finally obtained
Input of the fruit as visualization model (S500).
Three, knowledge recommendation module provides a user knowledge recommendation service by the way of mixed recommendation, in addition to being capable of basis
The knowledge node that knowledge search module obtains, which is done, recommends outside, additionally it is possible to which the historical behavior based on user, which is done, to be recommended, and is specifically included:
Step S301 judges whether that the historical behavior based on user is done and recommends, and recommends if done based on user's history behavior
Then turn to step S302;Conversely, turning to step S305;
Step S302, obtains the historical behavior data of user, i.e. user's knowledge node for once browsing or consulted;
Step S303 is calculated based on the user's history behavioral data that step S302 is obtained using the collaborative filtering based on user
Method (User-based Collaborative Filtering) predicts that user may interested knowledge node and user couple
The interest-degree of these knowledge nodes;User is as follows to the calculation formula of the interest-degree of knowledge node:
P (u, i)=∑V ∈ U (u, K) ∩ N (i)wuvrviFormula 3
Wherein, u indicates that user, i indicate knowledge node, and U (u, K) indicates K most like user of the behavior with user u,
I.e. if two users browse or inquired identical knowledge node, the behavior of two users is similar, and two users are clear
The identical knowledge node look at or inquired is more, then two users are more similar;rviIndicate scoring of the user v to knowledge node i,
I.e. when user v browses or inquired knowledge node i then rviEqual to 1, conversely, rviEqual to 0;wuvIndicate the phase of user u and user v
Like degree, calculation formula such as (4) is shown, wherein IuAnd IvThe knowledge node for respectively indicating user u and user v browsing or inquiring, N
(i) it indicates browsing or inquired user's set of knowledge node i, the similarity calculated between user calculates user u and user v
The ratio being overlapped in the knowledge node for browsing or inquiring;User is shown to the calculation formula such as (3) of knowledge node interest-degree, uses
Family u inquires or browsed the user of knowledge node i to the interest-degree of knowledge node i in preceding K user that is, similar with user u,
The sum of products of scoring and user u, v similarity to knowledge node i.
Step S304, the knowledge node that step S303 is recommended sort according to the user interest degree of prediction, i.e., to every
The recommendation knowledge node list of a user is sorted by interest-degree of the user to knowledge node, and the higher knowledge point ranking of interest-degree is more
It is high;
Step S305, some knowledge node that knowledge search module obtains is as the input recommended;
Step S306 calculates the similarity of knowledge node and other knowledge nodes that step S305 is obtained, between knowledge node
Similarity have been off and calculate and be stored in database, need to only search knowledge node and other in the database herein
The similarity of knowledge node, the calculating formula of similarity between knowledge node are as follows:
The formula of alpha+beta+γ=1 6
Wherein, A, B represent knowledge node, and attribute (A), attribute (B) respectively indicate knowledge node A, B packet
The attribute contained, value (A)i、value(B)iRespectively indicating the attribute value of the attribute i of knowledge node A, B, (attribute value can be word
Symbol string or number), NodeName (A), NodeName (B) respectively indicate the title of knowledge node A, B, A.TreeId,
B.TreeId respectively indicates the id of the affiliated knowledge tree of knowledge node A, B;Similarity between knowledge node is divided into three parts, each portion
Ratio shared by point is α, β, γ, and the corresponding part being multiplied of first part, i.e. α calculates the attribute that two knowledge nodes have
Similarity when similarity between relatively attribute, will first belong to since there are character string, sentence, paragraphs etc. in attribute value
Property corresponding attribute value carry out word segmentation processing and extract keyword, the similarity value between number, that is, attribute of matching keywords;The
The corresponding part being multiplied in two parts, i.e. β calculates time that a knowledge node occurs in the attribute value of another knowledge node
Number calculates the number that a knowledge node title occurs in another knowledge node attribute value;Part III, i.e. γ are corresponding
Whether the part formula (7) of multiplication, calculation knowledge node belong to same knowledge tree, if knowledge tree belonging to two knowledge nodes
Id is identical, then calculated result is 1, conversely, calculated result is 0;
Step S307 searches similarity according to the knowledge node similarity being calculated in step S306 in knowledge base
Knowledge node greater than 0;
Step S308, the knowledge node that will be found out in step S307, according to knowledge node phase obtained in step S306
It is ranked up like degree, i.e. the bigger knowledge node ranking of similarity is more forward;
The obtained recommendation results of step S304 or step S308 are carried out visualization presentation by step S309, i.e., will recommend
As a result it is put into visualization model (S500).
Four, knowledge reasoning module is made inferences using the method for forward reasoning, is specifically included:
Step S401 obtains user behavior by mobile terminal, and obtain knowledge node that knowledge search module obtains and
Image recognition as a result, the fact that obtain reasoning library;
Step S402, scanning rule set, the reasoning factbase obtained with step S401 obtain come the former piece of matching rule
Available regular collection;Wherein regular Formal Representation is as described below:
Regular Rule
IF Precondition Then Conclusion
Precondition: precondition (is patrolled by the Logic Expression that Proposition (proposition) is formed
Collect expression formula);
Conclusion: conclusion, i.e., it is true, and the logical expression being made of Proposition;
Logical expression Logic Expression: by logical word And (with), Or (or), Not (non-) etc. form logic life
Topic;
Proposition Proposition:(Predicate VariableList)
Predicate: predicate is the program worked out to realize certain function, be broken generally into it is public and dedicated,
The former such as logical comparison type > ,=, <, >=,≤and conventionally calculation type+,-, ×, ÷ etc.;In the latter such as remote sensing image processing
FFT (Fourier transformation), FeatherAbstract (feature extraction), TargetRecognize (target identification) etc., it is dedicated
Predicate is generally designed together with expert according to system requirements by knowledge engineer, the meaning of accident diagnosis in the predicate of medicine and factory
Word is made a world of difference certainly.Predicate is segmented into different group deposit predicate bases;
VariableList: argument table is parameter required for predicate is run.Type that there are three types of variables, first is that constant, such as
Number, symbol, time etc.;Second is that concept, such as " building height ", when calculating proposition, it can be obtained from the attribute of concept
Real data;Third is that another proposition, formation proposition in this way is nested;
In the applicable rule set that step S403, step S402 are obtained, if it is available rule only one, turn to step
S404;Otherwise, if available rule has multiple, conflict resolution is carried out;Wherein, conflict resolution uses LEX strategy
(lexicographic sort):
(1) the one group of rule executed is removed from conflict set;
(2) selection has one group of rule of more new data;
(3) the more detailed one group of rule of the condition of selection rule;
(4) any one group of rule is selected;
Conflict resolution is carried out according to the number order of above-mentioned strategy in conflict resolution, until can choose out a rule
When, processing terminate for conflict resolution, turns to step S404;
Step S404 executes the regular R that selects in step S403, by the conclusion of regular R right part, i.e. the new thing that obtains of reasoning
It is added to factbase in fact;
Whether step S405, the conclusion that judgment step S404 is obtained are reasoning targets, i.e., whether the new fact is that reasoning is thought
The target to be obtained, if the new fact is reasoning target, reasoning success terminates reasoning;Conversely, if the new fact is not reasoning
Target then turns to step S406;
Step S406 scans current factbase, judges whether that there are also the new facts not to use in reasoning, if there are also new
The fact is not used, then turns to step S402, continue reasoning;Conversely, reasoning fails, terminate reasoning;
The obtained the reasoning results of step S405 or step S406 are carried out visualization presentation, i.e., by reasoning knot by step S407
Fruit is put into visualization model (S500).
Five, image collection module obtains the image of mobile terminal, specifically includes:
Step S601, checks whether mobile terminal has network, if mobile terminal has network, turns to step S602;Conversely,
Turn to step S605;
Step S602, opens the camera of mobile terminal, and opens camera preview;
Step S603 allows user to choose whether to take pictures to user's display reminding information, if taking pictures, turns to
Step S604;Conversely, EP (end of program);
Step S604, user take pictures to object, store the picture taken pictures;
Step S605 prompts the user whether that setting network turns to step S601 if user setting network;Conversely, program
Terminate.
Six, image characteristics extraction module carries out feature extraction to the picture got on mobile terminal, specifically includes:
Step S701 obtains the picture that mobile terminal is taken pictures;
Step S702 extracts picture feature using ORB algorithm;
Step S703 uploads to the step S702 picture feature extracted on Cloud Server.
Seven, picture recognition module passes through obtained characteristics of image and identifies to image, specifically includes:
Step S801, obtaining step S703 upload to the characteristics of image of Cloud Server;
Whether step S802 examines the characteristics of image got correct, if input data is correct, turns to step S803;
Conversely, turning to step S807;
Step S803, scan image feature database carry out the image pattern in obtained characteristics of image and characteristics of image library
Matching;
Step S804 judges whether there is sample and the Image Feature Matching in characteristics of image library, if successful match, turns
To step S805;Conversely, turning to step S806;
Step S805 identifies the object in image by the matched sample of step S804, the image recognition knot that will be obtained
Fruit is sent to mobile terminal;
Step S806, images match failure, do not obtain picture recognition as a result, send recognition failures to mobile terminal
Information;
Step S807 sends the information of input error to mobile terminal.
Beneficial outcomes of the invention: Knowledge Service System disclosed by the invention stores this figure knowledge data, has powerful
The feature of semanteme, good knowledge reasoning ability.The specialized knowledge base for constructing domain-oriented beyond the clouds, combs the pass between knowledge
System, carries out the knowledge information management of architecture, provides intelligentized knowledge retrieval and recommendation;Using visualization technique, realization is known
The profound level of knowledge, diversification are presented;In conjunction with the application of mobile terminal, user is allowed to obtain knowledge services whenever and wherever possible.Use this hair
The method of bright offer can not only provide convenient, fast, colourful knowledge services, moreover it is possible to will be man-machine for users group
Interaction is combined with knowledge system, and working knowledge service system promotes text in the self-service guide to visitors in museum, tourist attractions and museum
Change transmission of knowledge.
With reference to the accompanying drawing, it using " Silk Road " relevant knowledge content as background, for knowledge services cell phone application, introduces
User obtains the process of diversification knowledge, and the present invention is described in more detail.
The method that the present invention uses can both have been installed simultaneously in the form of software on personal computers, industrial computers and servers
It executes, method can also be made into embedded chip and embodied in the form of hardware.
As shown in Figure 1, the invention discloses a kind of Knowledge Service System of combination mobile terminal, which is obtained by knowledge
Modulus block establishes the knowledge data base of this figure, knowledge based database knowledge search module, knowledge recommendation module, knowledge reasoning
Module, visualization model provide corresponding service;Meanwhile by cloud service engine, user accesses cloud using mobile terminal
Knowledge data, so as to use the various services that provide of knowledge services cell phone application anywhere or anytime.
As shown in figure 3, describing in the two-tier system of mobile terminal and cloud service engine, data flow between each module
Relationship:
(1) user shoots the photo of item of interest using mobile terminal;
(2) image collection module on mobile terminal (S600) obtains the picture of user's shooting, and sends the pictures to figure
As characteristic extracting module (S700);
(3) image characteristics extraction module (S700) carries out feature extraction, and the feature that will be extracted to the picture got
Data are sent to cloud service engine;
(4) picture recognition module (S900) in cloud service engine is according to obtained characteristic and characteristics of image library
(D2) image recognition is carried out, and recognition result is sent to knowledge services functional module;
(5) knowledge services functional module calls different functional modules according to the knowledge services that user goes for, wherein
The module includes knowledge search module (S200), knowledge recommendation module (S300), knowledge reasoning module (S400), the function of each module
Energy and relationship are as follows:
Knowledge search module (S200) knowledge based database (D1) scans for recognition result, searches and the identification knot
Fruit matches, relevant knowledge node, and the obtained knowledge node of search is sent to knowledge recommendation module (S300) and knowledge pushes away
It manages module (S400);
Knowledge recommendation module (S300) knowledge based database (D1) carries out two kinds of recommendation, and one is according to knowledge
The knowledge node that search module (S200) obtains, which is done, recommends;Another kind is done and is recommended based on user's history behavior, and user's history
Behavior knowledge recommending module (S300) can be obtained by mobile terminal;
The fact that knowledge reasoning module (S400) knowledge based database (D1) and reasoning library carries out knowledge reasoning;Wherein push away
Managing factbase includes the knowledge node and image recognition obtained from the user behavior of acquisition for mobile terminal, knowledge search module
As a result;
Knowledge services functional module is to knowledge search module (S200), knowledge recommendation module (S300), knowledge reasoning module
(S400) knowledge obtained is integrated, and the data integrated are sent to visualization model (S500);
(6) obtained knowledge is visually presented in visualization model (S500), and result is presented in knowledge and is sent
To subscriber interface module (S800);
(7) after the subscriber interface module on mobile terminal (S800) is adjusted according to the data that cloud service engine is sent
It is shown on mobile terminal, the result of knowledge services is presented to the user.
As shown in figure 4, knowledge acquisition module the following steps are included:
Knowledge acquisition module obtains knowledge by way of human-computer interaction, and by knowledge organization at knowledge tree, for example, being directed to
The relevant knowledge in " Silk Road " carries out knowledge acquisition:
Step S101 classifies the knowledge in " Silk Road ", and sorted knowledge is cut into knowledge node again,
Knowledge is indicated using knowledge node, knowledge is now divided into 10 classes, forms 10 knowledge trees, knowledge classification result such as Figure 11 a
It is shown;
Wherein, knowledge node is indicated by knowledge node title, Property Name, attribute value;Therefore, knowledge is needed in this step
The knowledge of engineer's typing as needed is analyzed, and judges whether the database of current design can indicate what knowledge node included
Relationship between content and knowledge node;Current database supports the demand of knowledge typing, turns to step S103;Now with history
For the tree of traces, the process of knowledge acquisition is further illustrated;
Knowledge is carried out cutting according to the demand of Knowledge Service System, obtains certain particle size by step S103, knowledge engineer
Knowledge node, and obtain the title of each knowledge node;Now by taking historic site tree as an example, the relevant knowledge of historic site is carried out
Further cutting, cutting result is as shown in figure 11b;
Step S104, knowledge engineer analyze the knowledge node for including in historic site tree, obtain all kinds of knowledge
The attribute that node includes, and determine Property Name, for example, the knowledge node in folk building includes place, character introduction, picture
This four attributes of example, building type;Mound capital construction build in knowledge node include build age, character introduction, site, mound
Base owner represents picture, picture example, buries the time, excavates the attributes such as age;In addition, determine the field for including in attribute, it is main
It to include Property Name, attribute value, longitude, latitude, resource;
Step S105, knowledge node is inserted knowledge base by knowledge engineer, and knowledge node is pressed tree structure tissue, i.e.,
There is set membership, brotherhood between knowledge node;For example, the partial knowledge node inserted in folk building such as Figure 11 c institute
Show;
Step S106, knowledge engineer improve the content of knowledge node, the i.e. attribute, attribute value of typing knowledge node, know
Know the attributes edit interface of node as illustrated in fig. 11d;
The attribute modification interface of knowledge node is as illustrated in fig. 11e;
Improve " Qin Shihuang Tomb " knowledge node of content as shown in figure 11f;
As shown in figure 5, knowledge search module the following steps are included:
Step S201, user input search content, such as " Xuanzang is permanently happy " in search box;
Step S202 divides the search content that step S201 is obtained using the jieba-0.35 word segmentation module of Python
Word, then extracts search key according to word segmentation result, and the search key of extraction is " Xuanzang ", " permanently happy ";
Step S203 accurately inquires the keyword extracted in step S202, and search key " permanently happy " is accurately looked into
Matched knowledge node is not found in inquiry, and " Xuanzang " accurately matched knowledge node, query result such as Figure 12 a institute are found in inquiry
Show, wherein the first table shows the knowledge node inquired, the second table shows the attribute of corresponding knowledge node;
Search key " Xuanzang " finds the knowledge node of exact matching in step S204, judgment step S203, is transferred to step
Rapid S207;Another search key " permanently happy " does not find the knowledge node of exact matching, is transferred to step S207;
Step S205 opens fuzzy query function and turns to step S206;
Step S206 will not find " permanently happy " progress of search key of the knowledge node of exact matching in step S203
Fuzzy query searches for the knowledge node " permanently happy door " that knowledge node title includes search key that is, in knowledge base, and to looking for
The knowledge node arrived assigns weight " 999 ", and query result is as shown in Figure 12b;
The knowledge node " Xuanzang " and " permanently happy door " that step S207, obtaining step S203 and step S206 are inquired,
Other knowledge nodes relevant to " Xuanzang " and " permanently happy door " are searched in knowledge base, and assign weight to the knowledge node found,
Weight, that is, knowledge node of knowledge node and the similarity of search key, obtained interdependent node such as Figure 12 c second and the 4th
Shown in table:
Step S208, the knowledge node that step S203, step S206 and step S207 are searched for is by knowledge node institute
The knowledge tree of category is classified, and removes duplicate knowledge node;
Knowledge node after classification, duplicate removal in S208 is ranked up by the weight of knowledge node, that is, weighed by step S209
The higher knowledge node ranking of value is more forward, and last query result is as shown in figure 12d;
Step S210, the knowledge node after S209 is arranged visually are presented, i.e., the search knot that will be finally obtained
Input of the fruit as visualization model (S500), visual result is as shown in Figure 12 e;
As shown in fig. 6, knowledge recommendation module the following steps are included:
Step S301 recommends if done for user's history behavior, such as pushes away now to the user id user for being 1603
It recommends, turns to step S302;It does and recommends for knowledge node " Xuanzang ", turn to step S305;
Step S302, obtains the historical behavior data of user, i.e. user's knowledge node for once browsing or consulted, wherein
The historical behavior data of user 1603 are as depicted in fig. 13 a;
Step S303 is calculated based on the user's history behavioral data that step S302 is obtained using the collaborative filtering based on user
Method (User-based Collaborative Filtering) predicts that user may interested knowledge node and user couple
The interest-degree of these knowledge nodes;
Step S304, the knowledge node that step S303 is recommended sort according to the user interest degree of prediction, i.e., to every
The recommendation knowledge node list of a user is sorted by interest-degree of the user to knowledge node, and the higher knowledge point ranking of interest-degree is more
Height, the recommendation list after sequence is as illustrated in fig. 13b;
Step S305, knowledge node " Xuanzang " is as the input recommended;
Step S306 calculates the similarity of knowledge node " Xuanzang " and other knowledge nodes that step S305 is obtained, knowledge
Similarity between node, which has been off, to be calculated and is stored in database, herein only need to search in the database " Xuanzang " with
The similarity of other knowledge nodes;
Step S307 searches similarity according to the knowledge node similarity being calculated in step S306 in knowledge base
Knowledge node greater than 0, the partial results of lookup are as shown in figure 13 c;
Step S308, the knowledge node that will be found out in step S307, according to knowledge node phase obtained in step S306
It is ranked up like degree, i.e. the bigger knowledge node ranking of similarity is more forward, and the result after sequence is as shown in figure 13d;
The obtained recommendation results of step S304 or step S308 are carried out visualization presentation by step S309, i.e., will recommend
As a result be put into visualization model (S500), for example, will the recommendation results about knowledge node " Xuanzang " use label-cloud mode
(first 40 of display recommendation results) are presented, as shown in figure 13e;
As shown in fig. 7, knowledge reasoning module the following steps are included:
Step S401 obtains user behavior by mobile terminal, and obtain knowledge node that knowledge search module obtains and
Image recognition as a result, the fact that obtain reasoning library, for example, the fact that obtain at present library are as follows:
A. the Tang Dynasty
B. it grows prosperity period
C. Li Long-ji (patron of actors)
The target of reasoning is desirable to find out the specific period of history in example, and the period of history uses global variable period table
Show;
Step S402, scanning rule set, the reasoning factbase obtained with step S401 obtain come the former piece of matching rule
Available regular collection;Wherein, time is that global variable indicates the time, and name is also that global variable indicates posthumous title of an emperor, regular collection
It is as follows:
Or R1:If Tang Dynasty the Tang Dynasty, time≤907 Thentime >=618and
R2:If Li Shih-min, Thenname=Tang second emperor since founding of a country
R3:If Li Long-ji (patron of actors), Thenname=Hsuan Tsung
R4:If (time≤907 time >=618and) and grows prosperity period, and the period=view of chastity controls or period=
Katyuan flourishing age
R5:If (time≤907 time >=618and) and grows prosperity period andname=Hsuan Tsung, the Katyuan period=
Flourishing age
Using a matching rule base in factbase, obtaining available regular collection is { R1 };
In the applicable rule set that step S403, step S402 are obtained, it is available rule only one, then turn to step
S404;
Step S404 executes the regular R1 selected in step S403, by the conclusion of regular R1 right part, i.e., " time >=
Factbase is added in 618and time≤907 ", obtains following fact:
d.time≥618and time≤907
Step S405, the conclusion that judgment step S404 is obtained are not reasoning targets, turn to step S406;
Step S406 scans current factbase, and there are also the new facts to be not used for discovery, then turns to step S402, continue to push away
Reason;
Subsequent reasoning process is as follows:
Second of reasoning:
Step S402, true b are matched with regular collection, and discovery can not be with matched rule;True c and regular collection
Match, obtaining available regular collection is { R3 };
In the applicable rule set that step S403, step S402 are obtained, it is available rule only one, then turn to step
S404;
Step S404 executes the regular R3 selected in step S403, by the conclusion of regular R3 right part, i.e. " name=Tang Xuan
Factbase is added in ancestor ", obtains following fact:
E.name=Hsuan Tsung
Step S405, the conclusion that judgment step S404 is obtained are not reasoning targets, turn to step S406;
Step S406 scans current factbase, and there are also the new facts to be not used for discovery, then turns to step S402, continue to push away
Reason;
Third time reasoning:
Step S402, true b, d are matched with rule R4;True b, d, e are matched with rule R5, obtain available regular collection
For { R4, R5 };
There is a plurality of rule in the applicable rule set that step S403, step S402 are obtained, carries out conflict resolution;Application collision
The LEX of resolution tactful (lexicographic sort) discovery (1), (2) cannot clear up conflict, when execution (3), discovery rule
Then the condition ratio R4 of R5 in further detail, therefore select use rule R5, steering step S404;
Step S404 executes the regular R5 selected in step S403, and by the conclusion of regular R5 right part, i.e., " period=is opened
Factbase is added in first flourishing age ", obtains following fact:
The Katyuan f.period=flourishing age
Step S405, it is period=that the conclusion that judgment step S404 is obtained, which is reasoning target to get the reasoning results arrived,
Katyuan flourishing age, reasoning success;
Step S407 carries out visualization presentation to the reasoning results that step S405 is obtained, i.e., is put into the reasoning results visually
Change module (S500);
The semantic description of entire reasoning is as follows:
It is the flouring period of the Tang Dynasty when the locating epoch, and still in Li Long-ji's period in place, then corresponding history
Period is " Katyuan flourishing age ".
As shown in figure 8, image collection module the following steps are included:
Example explanation is now done as mobile terminal using Samsung GALAXY Note II (N7100/16GB) mobile phone;
Step S601, checks whether mobile phone has network, and mobile phone connects wireless network, turns to step S602;
Step S602, opens the camera of mobile terminal, and opens camera preview;
Step S603 allows user to choose whether to take pictures to user's display reminding information, and user's selection is taken pictures,
Turn to step S604;
Step S604, user take pictures to object, store the picture taken pictures, and obtained picture is as shown in figure 14;
As shown in figure 9, image characteristics extraction module the following steps are included:
Step S701, obtains the picture that mobile phone photograph obtains, i.e. obtaining step S604 is stored in the picture on mobile phone;
Step S702 extracts picture feature, the characteristic point extracted such as the red circle institute that marks in Figure 15 using ORB algorithm
Show;
Step S703 uploads to the step S702 picture feature extracted on Cloud Server.
As shown in Figure 10, picture recognition module the following steps are included:
For example, characteristics of image library stores the feature (as shown in figure 16) of following four width pictures, be based on this characteristics of image library into
Row image recognition;
Step S801, obtaining step S703 upload to the characteristics of image of Cloud Server;
Step S802, examining the characteristics of image got is correctly, to turn to step S803;
Step S803, scan image feature database carry out the image pattern in obtained characteristics of image and characteristics of image library
Matching;
Step S804 judges whether there is sample and the Image Feature Matching in characteristics of image library, in discovery and sample database
The characteristic matching of " sets of brackets on top of the columns " this picture turns to step S805;
Step S805 identifies that the object in image is " sets of brackets on top of the columns ", the figure that will be obtained by the matched sample of step S804
As recognition result is sent on mobile phone.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
It describes in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in guarantor of the invention
Within the scope of shield.
Claims (6)
1. a kind of Knowledge Service System of combination mobile terminal, including cloud service engine and mobile terminal, in which:
Cloud service engine includes:
Knowledge acquisition module (S100) is obtained knowledge by way of human-computer interaction, and carries out tissue, management to knowledge and knowing
Know in database (D1) and is stored;
Knowledge search module (S200), the recognition result of knowledge based database (D1) and picture recognition module (S900), Xiang Yong
Family provides knowledge search service;
Knowledge recommendation module (S300), knowledge based database (D1) and user's history behavior or knowledge based search module
(S200) knowledge node and user's history behavior searched, provides a user knowledge recommendation service, and knowledge node is to indicate people
The basic unit of class knowledge can store the representation of knowledge segmented at computer by the way that the knowledge of the mankind is carried out cutting
With the data of identification, as knowledge node;
Knowledge reasoning module (S400), the knowledge node and user's history behavior that knowledge based search module (S200) searches,
It is made inferences with reference to regular collection, provides a user the reasoning results;
Visualization processing module (S500), by knowledge search module (S200), knowledge recommendation module (S300) and knowledge reasoning mould
The output of at least one in block (S400) visualizes, and sends visualization result to mobile terminal;
Picture recognition module (S900) matches the characteristics of image received from mobile terminal with characteristics of image library (D2),
To obtain recognition result;
Knowledge data base (D1), stored knowledge;And
Characteristics of image library (D2), stores the characteristics of image of multiple images,
Wherein, above-mentioned each module and library are deployed in a server, or distribution is deployed in and can mutually be exchanged visits by high speed network
In the multiple servers asked,
Mobile terminal includes:
Image collection module (S600) obtains image;
Image characteristics extraction module (S700), from image zooming-out feature;And
Subscriber interface module (S800) realizes the human-computer interaction with user;
Wherein, after getting image on mobile terminal, in image characteristics extraction module (S700) on mobile terminals, figure is carried out
As the extraction of feature, cloud service engine, the characteristics of image library of cloud service engine are sent by the image feature data extracted
(D2) in, it is stored with the image feature data for arranging and extracting in advance, these image feature datas are corresponding from knowledge point
The different angle of article and image sampling apart from size are used on used image characteristics extraction algorithm and mobile terminal
Algorithm be consistent.
2. Knowledge Service System as claimed in claim 1, which is characterized in that knowledge data base (D1) further include:
Using the institutional framework of knowledge tree, tissue, management and storage are carried out to knowledge, the knowledge includes at least one in following
Kind: text, picture, video and audio.
3. a kind of knowledge services method based on Knowledge Service System as described in claim 1, comprising:
Step S001, user shoot the photo of item of interest using mobile terminal;
Step S002, the image collection module on mobile terminal obtain the picture of user's shooting;
Step S003, image characteristics extraction module carry out feature extraction, and the characteristic that will be extracted to the picture got
It is sent to cloud service engine;
Step S004, the picture recognition module in cloud service engine are carried out according to obtained characteristic and characteristics of image library
Image recognition;
The result of image recognition is sent at least one of the following by step S005: knowledge recommendation module, knowledge search mould
Block or knowledge reasoning module;
Step S006, provides a user at least one of the following: knowledge search service, knowledge recommendation service or knowledge reasoning
Service;
The obtained knowledge of step S006 is sent to visualization model by step S007;
Step S008, visualization model visualize the knowledge received, and send movement eventually for visual result
On end, and it is presented to the user by subscriber interface module.
4. according to the method described in claim 3, wherein knowledge data base uses following organizational form:
The knowledge of the mankind is classified, and sorted knowledge is cut into knowledge node again, the knowledge node has one
Determine granularity;
Knowledge node is indicated by knowledge node title, Property Name, attribute value;
Knowledge node is pressed into tree structure tissue;
Multimedia resource relevant to knowledge node arrange and is put into resources bank, and by these resources with knowledge node is
The heart is classified, and is associated using the attribute of knowledge node with corresponding knowledge node to sorted resource.
5. according to the method described in claim 3, wherein knowledge search includes:
Step S201, search content is from image recognition as a result, search content includes at least one of the following: middle text
Symbol, English character, phrase, phrase, sentence;
Step S202 segments the search content that step S201 is obtained, and then extracts search key according to word segmentation result;
Step S203 accurately inquires the keyword extracted in step S202, i.e., search and the keyword in knowledge base
The knowledge node of exact matching, and weight " 9999 " are assigned to the knowledge node found;
Whether the knowledge node of search key exact matching is found in step S204, judgment step S203, if found completely
Matched knowledge node is then transferred to step S207;Conversely, being transferred to step S205;
Step S205, it is determined whether to enable fuzzy query functions, if opening fuzzy query function, turn to step S206;Instead
It, turns to step S207;
Step S206, the search key that the knowledge node of exact matching will not be found in step S203 carry out fuzzy query,
The knowledge node that knowledge node title includes search key is searched for i.e. in knowledge base, and assigns power to the knowledge node found
It is worth " 999 ";
The knowledge node that step S207, obtaining step S203 and step S206 are inquired is searched in knowledge base and is known with these
Know other relevant knowledge nodes of node, and assigns weight, weight, that is, knowledge node of knowledge node to the knowledge node found
With the similarity of search key, similarity similarity (node, keyword) calculation formula is as follows:
Similarity (node, keyword)=
∑i∈attribute(node)Match (i, keyword) formula 1
Wherein, node represents knowledge node, and keyword represents search key, and i represents one of category of knowledge node node
Property, i.value represent the value of attribute i and are character string or number, and attribute (node) represents all categories of node node
Property;Knowledge node and the similarity of search key calculate search key and the matched number of knowledge node attribute value,
Higher with number, then knowledge node and the similarity of search key are bigger;If containing search key in attribute value, this is searched
Rope keyword is matched with this attribute value of knowledge node, i.e., the value of formula 2 is 1, conversely, the value of formula 2 is 0;
Step S208, the knowledge node that step S203, step S206 and step S207 are searched for is by belonging to knowledge node
Knowledge tree is classified, and removes duplicate knowledge node;
Knowledge node after classification, duplicate removal in S208 is ranked up, i.e., weight is got over by step S209 by the weight of knowledge node
High knowledge node ranking is more forward;
Step S210, the knowledge node after S209 is arranged visually are presented, i.e., make the search result finally obtained
For the input of visualization processing module (S500).
6. according to the method described in claim 3, wherein knowledge recommendation includes:
Step S301 recommends if doing for user's history behavior, carries out step S302, otherwise carries out step S305;
Step S302 obtains the historical behavior data of user;
Step S303, it is pre- using the collaborative filtering based on user based on the user's history behavioral data that step S302 is obtained
The interested knowledge node of user and user are surveyed to the interest-degree of interested knowledge node;
Step S304, the interested knowledge node that step S303 is obtained, according to user to the emerging of interested knowledge node
Interesting degree is ranked up, i.e. the higher knowledge node ranking of interest-degree is more forward;
Step S305, some knowledge node is as the input recommended;
Step S306 calculates the similarity of knowledge node and other knowledge nodes that step S305 is obtained, the phase between knowledge node
It is had been off like degree and calculates and be stored in database, need to only search knowledge node and other knowledge in the database herein
The similarity of node, similarity sim (A, B) calculation formula between knowledge node are as follows:
The formula of alpha+beta+γ=1 6
Wherein, A, B represent knowledge node, and attribute (A), attribute (B) respectively indicate what knowledge node A, B was included
Attribute, value (A)i、value(B)iIt respectively indicates the attribute value of the attribute i of knowledge node A, B and can be character string or number
Word, value (B)jIndicate the attribute value of the attribute j of knowledge node B, NodeName (A), NodeName (B) respectively indicate knowledge
The title of node A, B, A.TreeId, B.TreeId respectively indicate the id of the affiliated knowledge tree of knowledge node A, B;Between knowledge node
Similarity is divided into three parts, and ratio shared by each section is α, β, γ, and the corresponding part being multiplied of first part, i.e. α calculates two
The similarity for the attribute that a knowledge node has belongs to since there are character string, sentence, paragraphs etc. in attribute value comparing
Property between similarity when, the corresponding attribute value of attribute is first subjected to word segmentation processing and extracts keyword, of matching keywords
Number is the similarity value between attribute;The corresponding part being multiplied of second part, i.e. β, calculates a knowledge node in another knowledge
The number occurred in the attribute value of node calculates what a knowledge node title occurred in another knowledge node attribute value
Number;Whether the corresponding part formula 7 being multiplied of Part III, i.e. γ, calculation knowledge node belong to same knowledge tree, if two
Knowledge tree id belonging to knowledge node is identical, then calculated result is 1, conversely, calculated result is 0;
Step S307 searches similarity in knowledge base and is greater than 0 according to the knowledge node similarity being calculated in step S306
Knowledge node;
Step S308, the knowledge node that will be found out in step S307, according to knowledge node similarity obtained in step S306
It is ranked up, i.e. the bigger knowledge node ranking of similarity is more forward;
The obtained recommendation results of step S304 or step S308 are carried out visualization presentation, i.e., by recommendation results by step S309
It is put into visualization processing module (S500).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510937756.3A CN105512316B (en) | 2015-12-15 | 2015-12-15 | A kind of Knowledge Service System of combination mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510937756.3A CN105512316B (en) | 2015-12-15 | 2015-12-15 | A kind of Knowledge Service System of combination mobile terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105512316A CN105512316A (en) | 2016-04-20 |
CN105512316B true CN105512316B (en) | 2018-12-21 |
Family
ID=55720296
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510937756.3A Active CN105512316B (en) | 2015-12-15 | 2015-12-15 | A kind of Knowledge Service System of combination mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105512316B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107256427A (en) * | 2017-06-08 | 2017-10-17 | 成都深泉科技有限公司 | Medical knowledge drawing generating method, device and diagnostic data obtain system, method |
CN107357842A (en) * | 2017-06-23 | 2017-11-17 | 华中师范大学 | A kind of multi-screen Knowledge Visualization method of knowledge based classification |
CN107392046A (en) * | 2017-07-07 | 2017-11-24 | 齐鲁工业大学 | A kind of Knowledge Management System of convenience file transmission |
CN107609559B (en) * | 2017-09-27 | 2021-08-31 | 广州市万表科技股份有限公司 | Identification method and system based on VR anti-counterfeiting technology |
CN108737530A (en) * | 2018-05-11 | 2018-11-02 | 深圳双猴科技有限公司 | A kind of content share method and system |
CN109033438B (en) * | 2018-08-15 | 2022-06-21 | 邢鲁华 | Method and device for recording learning content of user |
CN109656984A (en) * | 2018-12-21 | 2019-04-19 | 树根互联技术有限公司 | Data rule management system, method and apparatus |
CN109903186A (en) * | 2019-02-28 | 2019-06-18 | 杭州品茗安控信息技术股份有限公司 | A kind of inventory intelligence composing exes based on private clound |
CN110008340A (en) * | 2019-03-27 | 2019-07-12 | 曲阜师范大学 | A kind of multi-source text knowledge indicates, obtains and emerging system |
CN113297419B (en) * | 2021-06-23 | 2024-04-09 | 南京谦萃智能科技服务有限公司 | Video knowledge point determining method, device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567314A (en) * | 2010-12-07 | 2012-07-11 | 中国电信股份有限公司 | Device and method for inquiring knowledge |
CN103020302A (en) * | 2012-12-31 | 2013-04-03 | 中国科学院自动化研究所 | Academic core author excavation and related information extraction method and system based on complex network |
-
2015
- 2015-12-15 CN CN201510937756.3A patent/CN105512316B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567314A (en) * | 2010-12-07 | 2012-07-11 | 中国电信股份有限公司 | Device and method for inquiring knowledge |
CN103020302A (en) * | 2012-12-31 | 2013-04-03 | 中国科学院自动化研究所 | Academic core author excavation and related information extraction method and system based on complex network |
Also Published As
Publication number | Publication date |
---|---|
CN105512316A (en) | 2016-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105512316B (en) | A kind of Knowledge Service System of combination mobile terminal | |
CN110704743B (en) | Semantic search method and device based on knowledge graph | |
JP2021108183A (en) | Method, apparatus, device and storage medium for intention recommendation | |
CN104076944B (en) | A kind of method and apparatus of chatting facial expression input | |
Rubio-Drosdov et al. | Seamless human-device interaction in the internet of things | |
CN104254852B (en) | Method and system for mixed information inquiry | |
CN104854583B (en) | Search result rank and presentation | |
CN105808590B (en) | Search engine implementation method, searching method and device | |
US20100250526A1 (en) | Search System that Uses Semantic Constructs Defined by Your Social Network | |
JP2008507792A (en) | A search engine that uses the background situation placed on the network | |
CN109564571A (en) | Utilize the inquiry recommended method and system of search context | |
CN106204156A (en) | A kind of advertisement placement method for network forum and device | |
CN101124576A (en) | Search system and methods with integration of user annotations from a trust network | |
CN106663117A (en) | Constructing a graph that facilitates provision of exploratory suggestions | |
CN110457404A (en) | Social media account-classification method based on complex heterogeneous network | |
KR20180137932A (en) | Method and system for expansion to daily life language by using word vectorization technique based on social network content | |
CN111104511A (en) | Method and device for extracting hot topics and storage medium | |
CN112507246B (en) | Social recommendation method fusing global and local social interest influence | |
JP2003519841A (en) | Information modeling method and method of performing search using database constructed by information modeling | |
US8386475B2 (en) | Attribution analysis and correlation | |
CN112818195B (en) | Data acquisition method, device and system and computer storage medium | |
KR101929649B1 (en) | System and method for recommendation of open chat room through chat log keyword extraction | |
KR100925294B1 (en) | Searching system and its method for using tag data and cube structure of information | |
CN116186197A (en) | Topic recommendation method, device, electronic equipment and storage medium | |
Hoque et al. | Combining conceptual query expansion and visual search results exploration for web image retrieval |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information |
Inventor after: Lin Ziqi Inventor after: Ni Wancheng Inventor after: Zhao Meijing Inventor after: Liu Dongchang Inventor before: Ni Wancheng Inventor before: Lin Ziqi Inventor before: Zhao Meijing Inventor before: Liu Dongchang |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |