CN106326422B - A kind of method and system of the food safety data information retrieval of knowledge based ontology - Google Patents
A kind of method and system of the food safety data information retrieval of knowledge based ontology Download PDFInfo
- Publication number
- CN106326422B CN106326422B CN201610720106.8A CN201610720106A CN106326422B CN 106326422 B CN106326422 B CN 106326422B CN 201610720106 A CN201610720106 A CN 201610720106A CN 106326422 B CN106326422 B CN 106326422B
- Authority
- CN
- China
- Prior art keywords
- food
- ontologies
- relationship
- relationship object
- similarity
- 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
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
- G06F16/245—Query processing
- G06F16/2452—Query translation
- G06F16/24522—Translation of natural language queries to structured queries
-
- 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
- G06F16/21—Design, administration or maintenance of databases
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Abstract
The embodiment of the invention provides a kind of method and system of the food safety data information retrieval of knowledge based ontology, structuring food prods security knowledge ontology library first, the Food Safety Knowledge ontology library includes food ontologies and relationship object, and the relationship object will at least a pair of of food ontologies association;Then the query string inputted according to user, it is handled respectively for different situations, when the query string is natural language, it is segmented, word segmentation result is obtained, and determines the combination of food ontologies and relationship object according to word segmentation result, combination based on the food ontologies and relationship object, according to the combination of food ontologies and relationship object in Food Safety Knowledge ontology library, query object is determined, and query result is obtained according to the query object;Query result is finally returned into user.Thus solve the problems, such as that user can not accurately find resource relevant to demand.
Description
Technical field
The present invention relates to technical field of information retrieval, believe more particularly to a kind of food safety data of knowledge based ontology
Cease the method and system of retrieval.
Background technique
As network technology is widely available in people's lives, the extensive raising of social informatization degree, every field
The information resources accumulated are being skyrocketed through.For field of food safety, food safety Regulation department generates a large amount of food
The case where product safety detection data, individual data all only illustrates some element (hazardous material) in detected sample, but it is a large amount of
The set of data has contained food security information abundant.
Nowadays, the major search method of search engine is the mode of index key, and user is to pass through index key
To inquire food security information.
When inventor applies first technology, it is found that first technology has very big owe in terms of food security information precision ratio
It lacks, although internet data information is more, connection is lacked between these information, message structure is loose, and due to user query
The diversification of forms of food safety data, computer are difficult to the reasons such as complicated natural language, cause user accurate
Ground finds resource relevant to demand.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
State the method for the food safety data information retrieval of the knowledge based ontology of problem and the food peace of corresponding knowledge based ontology
The system of full data information retrieval.
According to one aspect of the present invention, a kind of side of the food safety data information retrieval of knowledge based ontology is provided
Method, comprising:
Structuring food prods security knowledge ontology library;The Food Safety Knowledge ontology library includes food ontologies and relationship pair
As;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes class relations object,
Food ontologies in generic food ontologies with father and son's hierarchical relationship are associated with by the class relations object;No
It is associated between generic food ontologies using non-class relations object;
Receive the query string of client input;
Judge that the query string is keyword, keyword combination or natural language;
If the query string is keyword, the keyword is matched with Food Safety Knowledge ontology library, is obtained
Obtain query result;
If the query string is crucial contamination, according to the key contamination determine food ontologies and
The combination of relationship object;
If the query string is natural language, the query string is segmented, obtains word segmentation result, and according to point
Word result determines the combination of food ontologies and relationship object;
Based on the combination of the food ontologies and relationship object, known according to the food in Food Safety Knowledge ontology library
The combination for knowing ontology and relationship object determines query object, and obtains query result according to the query object;
The query result is returned into client.
Optionally, after the step of structuring food prods security knowledge ontology library, further includes:
Receive the update operation in the food-safe ontologies library of user;The update operation includes: to pacify to the food
Omniscient know ontology library in food ontologies and/or food ontologies between existing relationship object addition, modification and
It deletes.
Optionally, described that the query string is segmented, word segmentation result is obtained, and determine that food is known according to word segmentation result
Know the combination of ontology and relationship object, comprising:
The query string is segmented, and is determined in word segmentation result using concept class dictionary and relation object dictionary and is respectively segmented
Part of speech;The part of speech includes food ontologies part of speech and relationship object part of speech;
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group be combined into the food ontologies and
The combination of relationship object.
Optionally, the combination based on the food ontologies and relationship object, according to Food Safety Knowledge ontology
The combination of food ontologies and relationship object in library, determines query object, comprising:
By the food ontologies in the participle of the food ontologies in query string and Food Safety Knowledge ontology library into
Row matching;
If the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library match, record
The food ontologies matched are highest similarity, and calculate the food ontologies and Food Safety Knowledge ontology library its
The first similarity between his food ontologies;
For relationship object associated by each food ontologies, calculate its with food ontologies are corresponded in query string
The second similarity between corresponding relationship object;
By the second similarity of the first similarity of food ontologies and the relationship object for being related to the food ontologies
It is multiplied, obtains total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its inquiry
Object.
Optionally, the combination based on the food ontologies and relationship object, according to Food Safety Knowledge ontology
The combination of food ontologies and relationship object in library, determines query object, further includes:
If the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library do not match, right
The word segmentation result is extended, and obtains the expanded set for corresponding to each food ontologies, and the expanded set includes at least one
The food ontologies of a extension;
The food ontologies of each extension are matched with the food ontologies in Food Safety Knowledge ontology library;
If the food ontologies of extension and the food ontologies of Food Safety Knowledge ontology library match, record
The food ontologies matched are highest similarity, and calculate the food ontologies and Food Safety Knowledge ontology library its
The first similarity between his food ontologies;
For relationship object associated by each food ontologies, it is calculated between the participle with relationship object
Second similarity;
By the second similarity of the first similarity of food ontologies and the relationship object for being related to the food ontologies
It is multiplied, obtains total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its inquiry
Object.
Optionally, the described the step of query result is returned into client, comprising:
By another food associated by the combination of the forward N number of food ontologies of total sequencing of similarity and relationship object
The information of product ontologies returns to client.
Optionally, the other food ontologies for calculating the food ontologies and Food Safety Knowledge ontology library
Between the first similarity the step of, comprising:
It utilizes formula (1)
Calculate first between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
Similarity;Wherein, the t1 is the food ontologies matched, and t2 is that other food of Food Safety Knowledge ontology library are known
Know ontology, n is the hierarchical depth of t1 and t2 in the hierarchical relationship in Food Safety Knowledge ontology library;δi(t1,t2) it is in level
When depth is i, the parent relation value between t1 and t2, whereinθiIt is
Weight.
According to another aspect of the invention, a kind of food safety data information retrieval of knowledge based ontology is provided
System, comprising:
Module is constructed, structuring food prods security knowledge ontology library is used for;The Food Safety Knowledge ontology library includes that food is known
Know ontology and relationship object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes
Class relations object, the class relations object know the food in generic food ontologies with father and son's hierarchical relationship
Know ontology relation;It is associated between different classes of food ontologies using non-class relations object;
Input module, for receiving the query string of client input;
Judgment module, for judging that the query string is keyword, crucial contamination or natural language;
If the query string is keyword, the keyword is matched with Food Safety Knowledge ontology library, is obtained
Obtain query result;
If the query string is crucial contamination, according to the key contamination determine food ontologies and
The combination of relationship object;
Word segmentation module segments the query string, is segmented if being natural language for the query string
As a result, and determining the combination of food ontologies and relationship object according to word segmentation result;
Semantic module is known for the combination based on the food ontologies and relationship object according to food safety
The combination for knowing the food ontologies and relationship object in ontology library determines query object, and is obtained according to the query object
Query result;
Return module, for client will to be returned to the query result.
Optionally, after the building module for structuring food prods security knowledge ontology library, further includes:
Update module, the update for receiving the food-safe ontologies library of user operate;The update operates
To existing relationship object between the food ontologies and/or food ontologies in the Food Safety Knowledge ontology library
Addition, modification and deletion.
Optionally, described that the query string is segmented, word segmentation result is obtained, and determine that food is known according to word segmentation result
Know the combination of ontology and relationship object, comprising:
Word segmentation module for segmenting to the query string, and is determined using concept class dictionary and relation object dictionary and is divided
The part of speech respectively segmented in word result;The part of speech includes food ontologies part of speech and relationship object part of speech;
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group be combined into the food ontologies and
The combination of relationship object.
Optionally, the combination based on the food ontologies and relationship object, according to Food Safety Knowledge ontology
The combination of food ontologies and relationship object in library, determines query object, comprising:
Matching module, for by the food in the participle of the food ontologies in query string and Food Safety Knowledge ontology library
Product ontologies are matched;
First similarity calculation module, if for the participle of food ontologies and the food of Food Safety Knowledge ontology library
Product ontologies match, then the food ontologies on record matching are highest similarity, and calculate the food ontologies
The first similarity between other food ontologies of Food Safety Knowledge ontology library;
Second similarity calculation module, for for relationship object associated by each food ontologies, calculate its with
The second similarity between the corresponding relationship object of food ontologies is corresponded in query string;
Total similarity calculation module, for the first similarity of food ontologies and will be related to the food ontologies
Second similarity of relationship object is multiplied, and obtains total similarity that food ontologies are combined with relationship object;
Query object module is selected, total sequencing of similarity for selecting food ontologies to combine with relationship object is forward
N number of combination, search its query object.
Optionally, the combination based on the food ontologies and relationship object, according to Food Safety Knowledge ontology
The combination of food ontologies and relationship object in library, determines query object, further includes:
Expansion module, if for the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library
It does not match, then the word segmentation result is extended, obtain the expanded set for corresponding to each food ontologies, the superset
Close the food ontologies including at least one extension;
Matching module, for by the food knowledge in the food ontologies of each extension and Food Safety Knowledge ontology library
Ontology is matched;
First similarity calculation module, if for the food ontologies of extension and the food of Food Safety Knowledge ontology library
Product ontologies match, then the food ontologies on record matching are highest similarity, and calculate the food ontologies
The first similarity between other food ontologies of Food Safety Knowledge ontology library;
Second similarity calculation module, for for relationship object associated by each food ontologies, calculate its with
The second similarity between participle with relationship object;
Total similarity calculation module, for the first similarity of food ontologies and will be related to the food ontologies
Second similarity of relationship object is multiplied, and obtains total similarity that food ontologies are combined with relationship object;
Query object module is selected, total sequencing of similarity for selecting food ontologies to combine with relationship object is forward
N number of combination, search its query object.
Optionally, the return module that the query result is returned to client, comprising:
Return module, for being closed the combination of the forward N number of food ontologies of total sequencing of similarity and relationship object
The information of another food ontologies of connection returns to client.
Optionally, the other food ontologies for calculating the food ontologies and Food Safety Knowledge ontology library
Between the first similarity the step of, comprising:
It utilizes formula (1)
Calculate first between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
Similarity;Wherein, the t1 is the food ontologies matched, and t2 is that other food of Food Safety Knowledge ontology library are known
Know ontology, n is the hierarchical depth of t1 and t2 in the hierarchical relationship in Food Safety Knowledge ontology library;δi(t1, t2) it is in level
When depth is i, the parent relation value between t1 and t2, whereinθiIt is power
Weight.
For first technology, the embodiment of the present invention has following advantage:
It is based on Food Safety Knowledge ontology library according to the present invention, proposes a kind of side of food safety data information retrieval
Method and system, first structuring food prods security knowledge ontology library, institute's Food Safety Knowledge ontology library includes food ontologies
And relationship object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes that classification is closed
It is object, the class relations object will have father and son's hierarchical relationship food ontologies in generic food ontologies
Association;It is associated between different classes of food ontologies using non-class relations object;Then looking into according to user's input
String is ask, judges that the query string is keyword, crucial contamination or natural language, for single keyword, by the pass
Keyword is matched with Food Safety Knowledge ontology library, obtains query result;For crucial contamination, then according to the keyword
Combination determine food ontologies and relationship object combination;For natural language, word segmentation result, root are segmented and obtained
The combination of food ontologies and relationship object is determined according to word segmentation result;According to the food knowledge in Food Safety Knowledge ontology library
The combination of ontology and relationship object determines query object, and obtains query result according to the query object;Finally inquiry is tied
Fruit returns to user.Food ontologies have hierarchical structure in the Food Safety Knowledge ontology library of building, and lead between level
Relationship object association is crossed, the logic of relations is tight between food ontologies, for the form of the food safety data of user query
It is divided, is handled respectively for different situations, and word segmentation processing can be carried out for complicated natural language, thus solved
User can not accurately find the problem of resource relevant to demand, and user is relatively accurately found and demand
Relevant resource.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the step flow chart of food safety data information retrieval method of the invention;
Figure 1A shows system basic functions structure division figure of the invention;
Figure 1B shows query string participle flow chart of the invention;
Fig. 1 C shows Food Safety Knowledge ontology library partial structure diagram of the invention;
Fig. 2 shows the structural block diagrams of food safety data information retrieval system of the invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Ontologies are the standardization descriptions of relationship between field concept and concept, this description be specification, it is specific,
Formalization, it is sharable.The target of ontologies is to capture the knowledge of related fields, provides the common reason to the domain knowledge
Solution, determines the vocabulary approved jointly in the field, and provide between these vocabulary and vocabulary from the formalization mode of different levels
Correlation explicitly defines.
Embodiment one
Referring to Fig.1, a kind of side of the food safety data information retrieval of knowledge based ontology according to the present invention is shown
The step flow chart of method embodiment, can specifically include following steps:
Step 100, structuring food prods security knowledge ontology library;The Food Safety Knowledge ontology library includes food ontologies
And relationship object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes that classification is closed
It is object, the class relations object will have father and son's hierarchical relationship food ontologies in generic food ontologies
Association;It is associated between different classes of food ontologies using non-class relations object;
A referring to Fig.1 shows system basic functions structure division figure of the invention, including structuring food prods security knowledge sheet
Body library, wherein the step of structuring food prods security knowledge ontology library includes: to the whole of food ontologies and its relationship object
Reason;Robotic description to food ontologies and its relationship object.
Wherein, the food safety data in the Food Safety Knowledge ontology library include: food name, noxious material, in
Malicious event;Collator Mode for food safety data includes: class, attribute, relationship.Class be about food name, noxious material,
The arrangement of the ensemble of all food ontologies of poisoning;Time that attribute such as poisoning occurs, place, generation
Unit, brief introduction, classification, the harm of noxious material, production, processing, means of transportation of food etc.;Relationship is such as of equal value, includes, causes
Deng.
The key data source of structuring food prods security knowledge ontology library includes:
Food safety affair is imported from current existing food safety database, artificial arrange relates in food safety affair
And the food ontologies arrived, and existing relationship object between food ontologies is analyzed, it is then added to food safety and knows
Know in ontology library;
Known using the food for obtaining field of food safety in various newspapers relevant to food safety, periodical, professional website
Know the relationship object between ontology and food ontologies, is added in Food Safety Knowledge ontology library.
The Food Safety Knowledge ontology library includes 3 elements { C, R, H }, and C represents one group with based food ontologies collection
It closes;R represents the set of relationship between food ontologies;H represents the food ontologies hierarchical system collection derived from by object
It closes.For example:
C={ things, food, food, animal food, vegetable food, dehydrated food, pickled product, bakery, tank
Hide food, wholefood, infant food, dilated food, quick-frozen food, food additives ...
R=processing situation (food, processed food | semi-finished product | undressed food), classification (food, meat | plant |
Complex class | artificial synthesized class), vegetable food classification (food, root | stem | leaf | flower | fruit | seed | skin | juice), meat food classification
(food, pork | beef | mutton | the flesh of fish | chicken), carcinogen (food, nitrous acid category | aflatoxins | BaP | clenbuterol hydrochloride
| gutter oil | formaldehyde) ... ...
H={ (things), (things, food), (things, food), (food), (food), (food, food materials), (ask by food
Inscribe food) ... }
Wherein, Elements C is represented with based food ontologies set, alternatively referred to as concept set, can be according to classification difference
It is divided into food name, noxious material, poisoning, upper example is mainly the set of food name class.Element R is food ontologies
Between relationship object set, enumerate that (separator represents simultaneously in bracket it can be seen from upper example for two food ontologies
Column relationship), the object outside bracket is the relationship object between two food ontologies.Element H is the food derived from by object
Product ontologies hierarchical system set, " things " can derive " food " and " food " two food it can be seen from upper example
Ontologies, derivative " food " and " food " two food ontologies, can be used as new derivation " parent ", and then send
Raw new food ontologies, such as: " food materials ", " problem food ", element H can make Food Safety Knowledge ontology library carry out
Expand, it is significant for the update of Food Safety Knowledge ontology library.
The Food Safety Knowledge ontology library of foundation describes the semantic relation between food ontologies, food ontologies
Between the logic of relations it is tight, support the reasoning on semantic logic, scalability is strong.
The various data in food-safe field are arranged, and are determined between food ontologies and food ontologies
Relationship object, structuring food prods security knowledge ontology library.After the Food Safety Knowledge ontology library building, using a kind of machine
The readable syntax, such as XML (Extensible Markup Language, can expand markup language) and machine are understood that
Resource description framework, for example RDF (Resource Description Framework, resource description framework) is food-safe
Ontologies library is described, serializes storage, transmission and processing to facilitate information.Wherein, the serializing of XML format indicates
It is the process that Obj State is converted to the format that can be kept or transmit, provides a kind of format of description scheme data.
Optionally, after step 100, further includes:
Step 105, after the step of structuring food prods security knowledge ontology library, further includes:
Receive the update operation in the food-safe ontologies library of user;The update operation includes: to pacify to the food
Omniscient know ontology library in food ontologies and/or food ontologies between existing relationship object addition, modification and
It deletes.
A referring to Fig.1 shows system basic functions structure division figure of the invention, including food-safe ontologies
The update in library: food-safe data are arranged, and food ontologies and/or pass in food-safe ontologies library
It is that object is added, modifies and deletes.
Deposit between artificial analysis food ontologies and food ontologies according to the food safety data of acquisition
Relationship object, deposited between the food ontologies and/or food ontologies in the Food Safety Knowledge ontology library
Relationship object be updated operation, including addition food ontologies and/or food ontologies between relationship object,
The relationship object between food ontologies and/or food ontologies is modified, food ontologies and/or food knowledge are deleted
Relationship object between ontology.
After Food Safety Knowledge ontology library building, user can carry out information retrieval with food-safe data.
Step 110, the query string for receiving user's input;
A referring to Fig.1 shows system basic functions structure division figure of the invention and first has to during semantic query
Receive the query string of user's input.
Step 120 judges that the query string is keyword, keyword combination or natural language;
Wherein, there are three kinds of situations for the query string of user's input:
(1) single keyword;
(2) combination that multiple keywords are constituted;
(3) sentence etc. that natural language is constituted.
For example, user input " which substance causes meat products carcinogenic? " the sentence that this natural language is constituted.
If step 130, the query string are keywords, the keyword and Food Safety Knowledge ontology library are carried out
Matching obtains query result.
If step 140, the query string are crucial contaminations, determine that food is known according to the key contamination
Know the combination of ontology and relationship object.
If step 150, the query string is natural language, the query string is segmented, word segmentation result is obtained,
And the combination of food ontologies and relationship object is determined according to word segmentation result;
B referring to Fig.1 shows query string participle flow chart of the invention:
When the query string of user's input is the sentence that natural language is constituted, need to look into user's input using participle
It askes string to be pre-processed, generates phrase, be converted into first two situation.
The query string is segmented, and is determined in word segmentation result using concept class dictionary and relation object dictionary and is respectively segmented
Part of speech;The part of speech includes food ontologies part of speech and relationship object part of speech.
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group be combined into the food ontologies and
The combination of relationship object.
With user input " which substance causes meat products carcinogenic? " for the sentence that this natural language is constituted, to it
It is segmented, generate phrase: " meat products ", " causing ... carcinogenic ", " which substance " later analyze these phrases,
" meat products " is food ontologies, and " causing ... carcinogenic " is relationship object.
Step 160, the combination based on the food ontologies and relationship object, according in Food Safety Knowledge ontology library
Food ontologies and relationship object combination, determine query object, and query result is obtained according to the query object.
A referring to Fig.1 shows system basic functions structure division figure of the invention, to count in the process in semantic query
Calculate similarity, comprising:
By the food ontologies in the participle of the food ontologies in query string and Food Safety Knowledge ontology library into
Row matching;
On the one hand, if the participle of food ontologies is matched with the food ontologies of Food Safety Knowledge ontology library
On, then the food ontologies on record matching are highest similarity, and calculate the food ontologies and Food Safety Knowledge
The first similarity between other food ontologies of ontology library;
For relationship object associated by each food ontologies, calculate its with food ontologies are corresponded in query string
The second similarity between corresponding relationship object;
By the second similarity of the first similarity of food ontologies and the relationship object for being related to the food ontologies
It is multiplied, obtains total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its inquiry
Object;
And query result is obtained according to the query object.
On the other hand, if the food ontologies of the participle of food ontologies and Food Safety Knowledge ontology library not
It mixes, then the word segmentation result is extended, obtain the expanded set for corresponding to each food ontologies, the expanded set packet
Include the food ontologies of at least one extension;
The food ontologies of each extension are matched with the food ontologies in Food Safety Knowledge ontology library;
If the food ontologies of extension and the food ontologies of Food Safety Knowledge ontology library match, record
The food ontologies matched are highest similarity, and calculate the food ontologies and Food Safety Knowledge ontology library its
The first similarity between his food ontologies;
For relationship object associated by each food ontologies, it is calculated between the participle with relationship object
Second similarity;
By the second similarity of the first similarity of food ontologies and the relationship object for being related to the food ontologies
It is multiplied, obtains total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its inquiry
Object;
And query result is obtained according to the query object.
If the food ontologies of extension and the food ontologies of Food Safety Knowledge ontology library do not match, return
Make the return trip empty value.
Similarity analysis method has used for reference the calculating and perception of the semantic distance in linguistics in the present invention.
Similarity definition: it sets t1 and t2 is two food ontologies or the relationship pair in Food Safety Knowledge ontology
As, S (t1, t2) indicates the similarity degree between the two food ontologies or relationship object, then there is formula:
Wherein, n is food ontologies or relationship object t1 and t2 the food knowledge sheet in Food Safety Knowledge ontology library
Depth capacity possessed by body.Such as: two food ontologies of t1 and t2 or relationship object are in Food Safety Knowledge ontology
Belong to jth layer and kth layer in library.At this point, n=max (j, k).θiIt is that weight is (desirable)。δi(t1, t2) value it is fixed
Justice is as follows:
It according to actual needs, can be to the weight θ in above-mentioned formulaiIt is adjusted.
In the following, formula is further described.Work as t1, two food ontologies of t2 or relationship object are " same
In branch ", and it belongs to jth layer and kth layer in Food Safety Knowledge ontology library, then there is a parent phase of preceding min (j, k)
Together, 0 S≤1 <, and if only if t1, when depth where two food ontologies of t2 or relationship object is identical, S=1;Work as t1,
Two food ontologies of t2 or relationship object are in " difference branch ", then without same parent class, then S=0, indicates that similarity degree is
0。
As can be seen that the range of S is 0~1, when the value of S is larger, between two food ontologies or relationship object
Similarity degree it is bigger.
C shows Food Safety Knowledge ontology library partial structure diagram of the invention referring to Fig.1:
With user input " which substance causes meat products carcinogenic? " for the sentence that this natural language is constituted, participle
After obtain " meat products " and " causing ... carcinogenic ";
If there is " meat products " " causing ... carcinogenic " in Food Safety Knowledge ontology library, similarity formula is being used
When, available similarity is 1 as a result, directly determining query object;
Directly there is " meat products " and " causing ... carcinogenic ", and " meat products " this food when if different in ontologies library
Product ontologies do not have " carcinogen " this relationship object, when scanning for similarity list, the phase of " meat products "
Like in degree list, the similarity of " meat " is strong, and the similarity of " food " is weak;" causing ... carcinogenic " this food ontologies it
Between relationship object, it is identical as relationship object " carcinogen " similarity in two parts.To sum up, server can select " meat "
The determining query object of " carcinogen " this combination, rather than " food " and " carcinogen " this combination, choose " meat "
" carcinogen " this combination corresponding " nitrite " and " clenbuterol hydrochloride ".
The query result is returned to client by step 170;
A referring to Fig.1 shows system basic functions structure division figure of the invention, during semantic query, calculates phase
Like to carry out information retrieval after degree, query result is returned into client.
C shows Food Safety Knowledge ontology library partial structure diagram of the invention referring to Fig.1:
With user input " which substance causes meat products carcinogenic? " for the sentence that this natural language is constituted, finally
" nitrite " and " clenbuterol hydrochloride " is returned into user.
For first technology, the embodiment of the present invention has following advantage:
It is based on Food Safety Knowledge ontology library according to the present invention, proposes a kind of side of food safety data information retrieval
Method, first structuring food prods security knowledge ontology library, institute's Food Safety Knowledge ontology library includes food ontologies and relationship
Object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes class relations pair
As the class relations object closes the food ontologies in generic food ontologies with father and son's hierarchical relationship
Connection;It is associated between different classes of food ontologies using non-class relations object;Then the inquiry inputted according to user
String judges that the query string is keyword, crucial contamination or natural language, for single keyword, by the key
Word is matched with Food Safety Knowledge ontology library, obtains query result;For crucial contamination, then according to the keyword
Combine the combination for determining food ontologies and relationship object;For natural language, word segmentation result is segmented and is obtained, according to
Word segmentation result determines the combination of food ontologies and relationship object;According to the food knowledge sheet in Food Safety Knowledge ontology library
The combination of body and relationship object determines query object, and obtains query result according to the query object;Finally by query result
Return to user.Food ontologies have hierarchical structure in the Food Safety Knowledge ontology library of building, and pass through between level
Relationship object association, the logic of relations is tight between food ontologies, for user query food safety data form into
Row divides, and handles respectively for different situations, and can carry out word segmentation processing for complicated natural language, thus solves use
Family can not accurately find the problem of resource relevant to demand, and user is relatively accurately found and demand phase
The resource of pass.
For embodiment of the method, for simple description, therefore, it is stated as a series of action combinations, but this field
Technical staff should be aware of, and embodiment of that present invention are not limited by the describe sequence of actions, because implementing according to the present invention
Example, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know that, specification
Described in embodiment belong to preferred embodiment, the actions involved are not necessarily necessary for embodiments of the present invention.
Embodiment two
Referring to Fig. 2, show a kind of food safety data information retrieval of knowledge based ontology according to the present invention is
The structural block diagram for embodiment of uniting, can specifically include following module:
Step 200, module is constructed, structuring food prods security knowledge ontology library is used for;The Food Safety Knowledge ontology library packet
Include food ontologies and relationship object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship
Object includes class relations object, and the class relations object will have father and son's hierarchical relationship in generic food ontologies
Food ontologies association;It is associated between different classes of food ontologies using non-class relations object;
Optionally, after step 200, further includes:
Step 205, update module, the update for receiving the food-safe ontologies library of user operate;The update
Operation includes: to existing between the food ontologies and/or food ontologies in the Food Safety Knowledge ontology library
Addition, modification and the deletion of relationship object.
After Food Safety Knowledge ontology library building, user can carry out information retrieval with food-safe data.
Step 210, input module, for receiving the query string of client input;
Step 220, judgment module, for judging that the query string is keyword, crucial contamination or natural language
Speech;
Step 230, Keywords matching module, if being keyword for the query string, by the keyword and food
Product security knowledge ontology library is matched, and query result is obtained;
Step 240, keyword combines determining module, if be crucial contamination for the query string, basis
The key contamination determines the combination of food ontologies and relationship object;
Step 250, word segmentation module segments the query string if being natural language for the query string,
Word segmentation result is obtained, and determines the combination of food ontologies and relationship object according to word segmentation result.
The query string is segmented, and is determined in word segmentation result using concept class dictionary and relation object dictionary and is respectively segmented
Part of speech;The part of speech includes food ontologies part of speech and relationship object part of speech;
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group be combined into the food ontologies and
The combination of relationship object.
Step 260, semantic module is pacified based on the combination of the food ontologies and relationship object according to food
Omniscient knows the combination of food ontologies and relationship object in ontology library, determines query object, and according to the query object
Obtain query result;
On the one hand, if the participle of food ontologies can be matched with the food ontologies of Food Safety Knowledge ontology library
It is upper:
Matching module, for by the food in the participle of the food ontologies in query string and Food Safety Knowledge ontology library
Product ontologies are matched;
First similarity calculation module, if for the participle of food ontologies and the food of Food Safety Knowledge ontology library
Product ontologies match, then the food ontologies on record matching are highest similarity, and calculate the food ontologies
The first similarity between other food ontologies of Food Safety Knowledge ontology library;
Second similarity calculation module, for for relationship object associated by each food ontologies, calculate its with
The second similarity between the corresponding relationship object of food ontologies is corresponded in query string;
Total similarity calculation module, for the first similarity of food ontologies and will be related to the food ontologies
Second similarity of relationship object is multiplied, and obtains total similarity that food ontologies are combined with relationship object;
Query object module is selected, total sequencing of similarity for selecting food ontologies to combine with relationship object is forward
N number of combination, search its query object;
Query result obtains module, for obtaining query result according to the query object.
On the other hand, if the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library fail
It matches:
Expansion module, if for the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library
It does not match, then the word segmentation result is extended, obtain the expanded set for corresponding to each food ontologies, the superset
Close the food ontologies including at least one extension;
Matching module, for by the food knowledge in the food ontologies of each extension and Food Safety Knowledge ontology library
Ontology is matched;
First similarity calculation module, if for the food ontologies of extension and the food of Food Safety Knowledge ontology library
Product ontologies match, then the food ontologies on record matching are highest similarity, and calculate the food ontologies
The first similarity between other food ontologies of Food Safety Knowledge ontology library;
Second similarity calculation module, for for relationship object associated by each food ontologies, calculate its with
The second similarity between participle with relationship object;
Total similarity calculation module, for the first similarity of food ontologies and will be related to the food ontologies
Second similarity of relationship object is multiplied, and obtains total similarity that food ontologies are combined with relationship object;
Query object module is selected, total sequencing of similarity for selecting food ontologies to combine with relationship object is forward
N number of combination, search its query object;
Query result obtains module, for obtaining query result according to the query object.
If the food ontologies of extension and the food ontologies of Food Safety Knowledge ontology library do not match, return
Make the return trip empty value.
Step 270, return module, for the query result to be returned to client.
For first technology, the embodiment of the present invention has following advantage:
Food Safety Knowledge ontology library is based on according to the present invention, propose a kind of food safety data information retrieval is
System, first structuring food prods security knowledge ontology library, institute's Food Safety Knowledge ontology library includes food ontologies and relationship
Object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes class relations pair
As the class relations object closes the food ontologies in generic food ontologies with father and son's hierarchical relationship
Connection;It is associated between different classes of food ontologies using non-class relations object;Then the inquiry inputted according to user
String judges that the query string is keyword, crucial contamination or natural language, for single keyword, by the key
Word is matched with Food Safety Knowledge ontology library, obtains query result;For crucial contamination, then according to the keyword
Combine the combination for determining food ontologies and relationship object;For natural language, word segmentation result is segmented and is obtained, according to
Word segmentation result determines the combination of food ontologies and relationship object;According to the food knowledge sheet in Food Safety Knowledge ontology library
The combination of body and relationship object determines query object, and obtains query result according to the query object;Finally by query result
Return to user.Food ontologies have hierarchical structure in the Food Safety Knowledge ontology library of building, and pass through between level
Relationship object association, the logic of relations is tight between food ontologies, for user query food safety data form into
Row divides, and handles respectively for different situations, and can carry out word segmentation processing for complicated natural language, thus solves use
Family can not accurately find the problem of resource relevant to demand, and user is relatively accurately found and demand phase
The resource of pass.
For system embodiments, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize the food safety of knowledge based ontology according to an embodiment of the present invention
The some or all functions of some or all components in the method and system equipment of data information retrieval.The present invention may be used also
To be embodied as some or all device or device programs for executing method as described herein (for example, calculating
Machine program and computer program product).It is such to realize that program of the invention can store on a computer-readable medium, or
It may be in the form of one or more signals.Such signal can be downloaded from an internet website to obtain, or carry
It provides, or is provided in any other form on body signal.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (8)
1. a kind of method of the food safety data information retrieval of knowledge based ontology characterized by comprising
Structuring food prods security knowledge ontology library;The Food Safety Knowledge ontology library includes food ontologies and relationship object;
The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes class relations object, described
Food ontologies in generic food ontologies with father and son's hierarchical relationship are associated with by class relations object;Inhomogeneity
It is associated between other food ontologies using non-class relations object;
Receive the query string of client input;
Judge that the query string is keyword, keyword combination or natural language;
If the query string is keyword, the keyword is matched with Food Safety Knowledge ontology library, is looked into
Ask result;
If the query string is crucial contamination, food ontologies and relationship are determined according to the key contamination
The combination of object;
If the query string is natural language, the query string is segmented, obtains word segmentation result, and tie according to participle
Fruit determines the combination of food ontologies and relationship object;
Based on the combination of the food ontologies and relationship object, according to the food knowledge sheet in Food Safety Knowledge ontology library
The combination of body and relationship object determines query object, and obtains query result according to the query object;
The query result is returned into client;
Wherein, the combination based on the food ontologies and relationship object, according in Food Safety Knowledge ontology library
The combination of food ontologies and relationship object, determines query object, comprising:
By the food ontologies progress in the participle of the food ontologies in query string and Food Safety Knowledge ontology library
Match;
If the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library match, record matching
On food ontologies be highest similarity, and calculate the others of the food ontologies and Food Safety Knowledge ontology library
The first similarity between food ontologies;
For relationship object associated by each food ontologies, it is corresponding to food ontologies are corresponded in query string to calculate it
Relationship object between the second similarity;
First similarity of food ontologies is multiplied with the second similarity of the relationship object for being related to the food ontologies,
Obtain total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its query object;
First calculated between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
The step of similarity, comprising:
It utilizes formula (1)
It calculates first similar between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
Degree;Wherein, the t1It is the food ontologies matched, t2It is other food knowledge sheets of Food Safety Knowledge ontology library
Body, n are t1And t2Hierarchical depth in the hierarchical relationship in Food Safety Knowledge ontology library;δi(t1, t2) it is in hierarchical depth
When for i, t1And t2Between parent relation value, whereinθiIt is weight.
2. the method as described in claim 1, which is characterized in that after the step of the structuring food prods security knowledge ontology library,
Further include:
Receive the update operation in the food-safe ontologies library of user;The update operation includes: to know the food safety
Know addition, modification and the deletion of existing relationship object between the food ontologies and/or food ontologies in ontology library.
3. obtaining participle knot the method according to claim 1, wherein described segment the query string
Fruit, and determine according to word segmentation result the combination of food ontologies and relationship object, comprising:
The query string is segmented, and determines the word respectively segmented in word segmentation result using concept class dictionary and relation object dictionary
Property;The part of speech includes food ontologies part of speech and relationship object part of speech;
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group is combined into the food ontologies and relationship
The combination of object.
4. the method according to claim 1, wherein described based on the food ontologies and relationship object
Combination, according to the combination of food ontologies and relationship object in Food Safety Knowledge ontology library, determines query object, also wraps
It includes:
If the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library do not match, to described
Word segmentation result is extended, and obtains the expanded set for corresponding to each food ontologies, and the expanded set includes at least one expansion
The food ontologies of exhibition;
The food ontologies of each extension are matched with the food ontologies in Food Safety Knowledge ontology library;
If the food ontologies of extension and the food ontologies of Food Safety Knowledge ontology library match, record matching
On food ontologies be highest similarity, and calculate the others of the food ontologies and Food Safety Knowledge ontology library
The first similarity between food ontologies;
For relationship object associated by each food ontologies, its second between the participle with relationship object is calculated
Similarity;
First similarity of food ontologies is multiplied with the second similarity of the relationship object for being related to the food ontologies,
Obtain total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its query object.
5. the method according to claim 1, wherein the step that the query result is returned to client
Suddenly, comprising:
Another food associated by the combination of the forward N number of food ontologies of total sequencing of similarity and relationship object is known
The information for knowing ontology returns to client.
6. a kind of system of the food safety data information retrieval of knowledge based ontology characterized by comprising
Module is constructed, structuring food prods security knowledge ontology library is used for;The Food Safety Knowledge ontology library includes food knowledge sheet
Body and relationship object;The relationship object will at least a pair of of food ontologies association;Wherein, the relationship object includes classification
Relationship object, the class relations object will have father and son's hierarchical relationship food knowledge sheet in generic food ontologies
Body association;It is associated between different classes of food ontologies using non-class relations object;
Input module, for receiving the query string of client input;
Judgment module, for judging that the query string is keyword, crucial contamination or natural language;
If the query string is keyword, the keyword is matched with Food Safety Knowledge ontology library, is looked into
Ask result;
If the query string is crucial contamination, food ontologies and relationship are determined according to the key contamination
The combination of object;
Word segmentation module segments the query string if being natural language for the query string, obtains participle knot
Fruit, and determine according to word segmentation result the combination of food ontologies and relationship object;
Semantic module, for the combination based on the food ontologies and relationship object, according to Food Safety Knowledge sheet
The combination of food ontologies and relationship object in body library determines query object, and is inquired according to the query object
As a result;
Return module, for client will to be returned to the query result;
Wherein, the combination based on the food ontologies and relationship object, according in Food Safety Knowledge ontology library
The combination of food ontologies and relationship object, determines query object, comprising:
By the food ontologies progress in the participle of the food ontologies in query string and Food Safety Knowledge ontology library
Match;
If the participle of food ontologies and the food ontologies of Food Safety Knowledge ontology library match, record matching
On food ontologies be highest similarity, and calculate the others of the food ontologies and Food Safety Knowledge ontology library
The first similarity between food ontologies;
For relationship object associated by each food ontologies, it is corresponding to food ontologies are corresponded in query string to calculate it
Relationship object between the second similarity;
First similarity of food ontologies is multiplied with the second similarity of the relationship object for being related to the food ontologies,
Obtain total similarity that food ontologies are combined with relationship object;
The forward N number of combination of total sequencing of similarity that selection food ontologies are combined with relationship object, searches its query object;
First calculated between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
The step of similarity, comprising:
It utilizes formula (1)
It calculates first similar between the food ontologies and other food ontologies of Food Safety Knowledge ontology library
Degree;Wherein, the t1It is the food ontologies matched, t2It is other food knowledge sheets of Food Safety Knowledge ontology library
Body, n are t1And t2Hierarchical depth in the hierarchical relationship in Food Safety Knowledge ontology library;δi(t1, t2) it is in hierarchical depth
When for i, t1And t2Between parent relation value, whereinθiIt is weight.
7. system as claimed in claim 6, which is characterized in that the building mould for structuring food prods security knowledge ontology library
After block, further includes:
Update module, the update for receiving the food-safe ontologies library of user operate;The update operation includes: to institute
State adding for existing relationship object between food ontologies and/or food ontologies in Food Safety Knowledge ontology library
Add, modify and deletes.
8. system according to claim 6, which is characterized in that it is described that the query string is segmented, obtain participle knot
Fruit, and determine according to word segmentation result the combination of food ontologies and relationship object, comprising:
Word segmentation module determines participle knot for segmenting to the query string, and using concept class dictionary and relation object dictionary
The part of speech respectively segmented in fruit;The part of speech includes food ontologies part of speech and relationship object part of speech;
By the participle of the participle of food ontologies part of speech and relationship object part of speech, group is combined into the food ontologies and relationship
The combination of object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610720106.8A CN106326422B (en) | 2016-08-24 | 2016-08-24 | A kind of method and system of the food safety data information retrieval of knowledge based ontology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610720106.8A CN106326422B (en) | 2016-08-24 | 2016-08-24 | A kind of method and system of the food safety data information retrieval of knowledge based ontology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106326422A CN106326422A (en) | 2017-01-11 |
CN106326422B true CN106326422B (en) | 2019-09-17 |
Family
ID=57791905
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610720106.8A Active CN106326422B (en) | 2016-08-24 | 2016-08-24 | A kind of method and system of the food safety data information retrieval of knowledge based ontology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106326422B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679544A (en) * | 2017-08-04 | 2018-02-09 | 平安科技(深圳)有限公司 | Automatic data matching method, electronic equipment and computer-readable recording medium |
TWI635404B (en) * | 2017-11-01 | 2018-09-11 | 張勝致 | Method for analyzing food safety and feedback using computer system |
CN110321460A (en) * | 2019-07-01 | 2019-10-11 | 成都数之联科技有限公司 | A kind of food safety association map construction method and system |
CN110781315B (en) * | 2019-10-16 | 2022-11-08 | 华中农业大学 | Food safety knowledge graph and construction method of related intelligent question-answering system |
CN111291196B (en) * | 2020-01-22 | 2024-03-22 | 腾讯科技(深圳)有限公司 | Knowledge graph perfecting method and device, and data processing method and device |
CN113590837A (en) * | 2021-07-29 | 2021-11-02 | 华中农业大学 | Deep learning-based food and health knowledge map construction method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
CN101582073A (en) * | 2008-12-31 | 2009-11-18 | 北京中机科海科技发展有限公司 | Intelligent retrieval system and method based on domain ontology |
US7937402B2 (en) * | 2006-07-10 | 2011-05-03 | Nec (China) Co., Ltd. | Natural language based location query system, keyword based location query system and a natural language and keyword based location query system |
CN102622453A (en) * | 2012-04-20 | 2012-08-01 | 北京邮电大学 | Body-based food security event semantic retrieval system |
-
2016
- 2016-08-24 CN CN201610720106.8A patent/CN106326422B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7937402B2 (en) * | 2006-07-10 | 2011-05-03 | Nec (China) Co., Ltd. | Natural language based location query system, keyword based location query system and a natural language and keyword based location query system |
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
CN101582073A (en) * | 2008-12-31 | 2009-11-18 | 北京中机科海科技发展有限公司 | Intelligent retrieval system and method based on domain ontology |
CN102622453A (en) * | 2012-04-20 | 2012-08-01 | 北京邮电大学 | Body-based food security event semantic retrieval system |
Also Published As
Publication number | Publication date |
---|---|
CN106326422A (en) | 2017-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106326422B (en) | A kind of method and system of the food safety data information retrieval of knowledge based ontology | |
US20190004873A1 (en) | Application program interface mashup generation | |
JP5989665B2 (en) | System and method for analyzing and synthesizing complex knowledge expressions | |
US20100205198A1 (en) | Search query disambiguation | |
AU2017358691A1 (en) | Apparatus and method for semantic search | |
CN103425727B (en) | Context speech polling expands method and system | |
CN104298658B (en) | The method and apparatus for obtaining search result | |
US20160275347A1 (en) | System and method for global identification in a collection of documents | |
CN104484374A (en) | Method and device for creating Internet encyclopedia entry | |
CN105095381B (en) | New word identification method and device | |
CN105975584B (en) | A kind of mathematic(al) representation similarity distance measurement method | |
CN106909628A (en) | A kind of text similarity method based on interval | |
JP2018022496A (en) | Method and equipment for creating training data to be used for natural language processing device | |
US9047561B2 (en) | Contextual network access optimizer | |
CN109933692A (en) | Establish the method and apparatus of mapping relations, the method and apparatus of information recommendation | |
CN105589976B (en) | Method and device is determined based on the target entity of semantic relevancy | |
Gupta et al. | KG4ASTRA: question answering over Indian missiles knowledge graph | |
CN103744970B (en) | A kind of method and device of the descriptor determining picture | |
Ashangani et al. | Semantic video search by automatic video annotation using TensorFlow | |
CN106934007B (en) | Associated information pushing method and device | |
RU2015141339A (en) | METHOD (OPTIONS) AND SYSTEM (OPTIONS) FOR CREATING A FORECAST MODEL AND DETERMINING THE ACCURACY OF A FORECAST MODEL | |
Algosaibi et al. | Using the semantics inherent in sitemaps to learn ontologies | |
Alpkocak et al. | DEMIR at ImageCLEFMed 2011: Evaluation of Fusion Techniques for Multimodal Content-based Medical Image Retrieval. | |
Schaer et al. | Historical Clicks for Product Search: GESIS at CLEF LL4IR 2015. | |
Mulwad et al. | Interpreting medical tables as linked data for generating meta-analysis reports |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |