CN110188170B - Multi-entry medical question template device and method thereof - Google Patents
Multi-entry medical question template device and method thereof Download PDFInfo
- Publication number
- CN110188170B CN110188170B CN201910450711.1A CN201910450711A CN110188170B CN 110188170 B CN110188170 B CN 110188170B CN 201910450711 A CN201910450711 A CN 201910450711A CN 110188170 B CN110188170 B CN 110188170B
- Authority
- CN
- China
- Prior art keywords
- template
- question
- medical
- user
- reasoning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Abstract
The invention discloses a multi-entry medical question template device and a method thereof, wherein the template device is a medical question conversion mechanism based on medical concepts and medical relations, which binds reasoning rules and reasoning functions in a main template structure, a near-meaning template structure and a multi-entry joint structure together, the method and the device realize the conversion of various near-meaning user questions into a multi-entry medical question template, so that corresponding answers are extracted from the UMLS medical knowledge base according to the multi-entry medical question template obtained through conversion. The invention is designed for solving the problems that knowledge and relations are complex and one question meaning needs to be interpreted through various semantic relations in an intelligent information retrieval and automatic question-answering system in the medical industry, and simultaneously, the invention also aims at improving the template design efficiency, reducing the scale of a template library and meeting the question intention of a user to the maximum extent.
Description
Technical Field
The invention belongs to the field of artificial intelligence of computers, in particular to a multi-entry medical question template device and a method thereof, which can be widely applied to intelligent information retrieval and automatic question-answering systems in the medical industry.
Background
The rapid development of internet technology makes network information exponentially grow, in order to quickly and accurately obtain needed information from the massive information, the traditional search engine can not meet the demands of users, and the intelligent information retrieval and automatic question-answering system is gradually becoming a focus and a hotspot of research because of being capable of accurately and directly answering user questions, however, because of the diversity and randomness of user questions, the semantic and expected difference of accurately obtaining the user questions is larger, so the accuracy of automatic question-answering and intelligent information retrieval answers is not high at present.
The question processing and understanding is the first execution stage in the intelligent information retrieval and automatic question and answer system, and aims to enable a computing mechanism to solve a question of a user, acquire the question intention of the user and provide basis for later information retrieval. Understanding of questions generally involves lexical analysis, syntactic analysis, and semantic analysis, which is currently the bottleneck in natural language processing. In the field-oriented information retrieval and question-answering system, the user's query has many similarities, for example, in the ontology-based knowledge base, many query the concept or entity attributes, but also the relationship between concepts and the relationship between attributes, and these question sentences can be extracted into the field ontology-based question sentence templates with representativeness and packaged semantic information, so that the complex lexical analysis, syntactic analysis and semantic analysis can be effectively avoided. Therefore, research on the question understanding method based on the semantic relation and the question template has very important significance.
At present, a semantic relation and question template-based question understanding method generally adopts a template to correspond to a semantic relation in a domain ontology or domain knowledge base. However, in a medical information system, knowledge and relationships are complex, and one question semantic needs to be interpreted by multiple semantic relationships. For example, when inquiring about symptoms associated with a disease, multiple semantic relationships are required to express, and a single semantic relationship does not fully express the disease symptoms, which cannot be described more fully. In order to make the semantics of the template more comprehensive, clear and clear, and simultaneously to improve the matching precision and the design efficiency of the template and reduce the scale of a template library, it is necessary to find a multi-entry medical question template device and an application method based on medical concepts and medical relations.
Disclosure of Invention
The invention provides a multi-entry medical question template device and a method thereof, which are designed for solving the problems that knowledge and relations are complex, and a question meaning needs to be interpreted through various semantic relations in an intelligent information retrieval and automatic question-answering system in the medical industry, and simultaneously improving the template design efficiency, reducing the scale of a template library and meeting the question intention of a user to the maximum extent.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
a multi-entry medical question template device is a medical question conversion mechanism based on medical concepts and medical relations, and binds reasoning rules and reasoning functions in a main template structure, a near-meaning template structure and a multi-entry joint structure together to realize conversion of multiple near-meaning user questions into a multi-entry medical question template so as to extract corresponding answers from a UMLS medical knowledge base according to the multi-entry medical question template obtained by conversion.
Further, the question template binds the reasoning rules and the reasoning functions in the main template structure, the near-meaning template structure and the multi-entry joint structure, and the Backus-Norwalk is defined as:
< multiple entry medical question template >: = (< master template structure >, { < near-sense template structure > }, < multiple entry association structure >) (1)
< multiple inlet joint Structure >: = ({ < inlet joint Structure > }) (2)
< entry association structure >: = ({ < synonymous template structure > }, < preferred binding structure >, { < secondary binding structure > }) (3)
< preferred binding Structure >: = (< preferred inference rule >, < preferred inference function >) (4)
< secondary binding structure >: = (< secondary inference rule >, < secondary inference function >) (5)
The main template structure is the most representative sentence structure of a question template expressed by using variables and labels, and reflects shallow question semantics of the question template;
the near-sense template structure is a template structure with similar semantics to the main template structure; one question template comprises more than one near-meaning structure;
the multi-entry joint structure is a conversion mechanism for realizing the conversion from various sub-semantics of the question template to different semantic relations in the medical knowledge system; one question template comprises more than one entry association structure; each entry joint structure represents a certain sub-semantic reasoning method of a question template where the entry joint structure is located, and the method consists of a group of synonymous template structures, preferred reasoning rules and reasoning functions thereof, and a plurality of ordered sub-choice reasoning rules and reasoning functions thereof; the system comprises a plurality of input combined structure sub-semantics, a plurality of first-choice inference rules, a plurality of second-choice inference rules, a plurality of first-choice inference rules and a plurality of second-choice inference rules, wherein the first-choice inference rules are a group of synonymous question sentence structures reflecting the input combined structure sub-semantics, each inference rule is associated with a corresponding inference function, the first-choice inference rules are answer inference methods which are most consistent with the input combined structure template structure semantics, and the second-choice inference rules are ordered according to the similarity degree of the second-choice inference rules and the template structure semantics;
The reasoning rule is a deep question meaning representing a question template, and a predicate formula based on medical concepts and medical relations is used for accurately representing the reasoning process of the expected answer and the intention of the user to question;
the reasoning function is an answer reasoning program bound with the reasoning rules, executes the reasoning function appointed by the reasoning rules, extracts corresponding answers from the medical knowledge base through semantic relations appointed by the reasoning rules, and drives the semantics to come from medical knowledge elements in the matched user questions;
the union of the main template structure and the near-sense template structure in the formula (1) is equal to the union of the synonymous template structures in the formula (3).
Furthermore, in the main template structure and the near-meaning template structure, the normalized semantic similarity of any two template structures based on core elements, variable types and sequences is smaller than 1.
Still further, a template structure is defined as a set of template elements that are arranged in a certain order using template labels and variable types, the template structure includes a main template structure, a near-meaning template structure, question semantics of a question template are characterized by variables and core elements in the template structure, and are defined as follows by the Barceish-North paradigm:
< template Structure > = (< template element 1>, < template element 2>, …, < template element n >) (6)
< template element > = (< core element >, < optional element >, < variable >) (7)
< core element > = element (8) labeled with the labels "<", ">" in the template
Optional element: = element (9) labeled with the label "[", "]" in the template
< variable > = < variable name > + ": "+ < variable type > (10)
Wherein the template label comprises: defining an optional core element in the template; [] An optional element for defining an eligibility in the template, { } represents a set of elements in the template; the i is used to separate synonyms in templates;
the variable type identifier includes: (1) concept: < c > Concept > states that template variable c is a medical Concept in the UMLS knowledge base; (2) and (3) Relation: < r > Concept > states that the template variable r is a medical relationship in the UMLS knowledge base; (3) ConceptSet: < s ConceptSet > states that the template variable s is a set of medical concepts in the UMLS knowledge base; (4) type: < t: type > states that the template variable t belongs to the Type in the UMLS knowledge base.
Further, the inference rule is a logic implication defined by a template description logic system, which is abbreviated as TDLS, and TDLS is a binary group as follows:
TDLS = (< predicate set >, < operator >)
The predicate is used for declaring, identifying and determining medical concepts and medical relations in the question template; in TDLS, three types of predicates are included: a unitary predicate, a binary predicate, and a ternary predicate; the binary predicate is used for declaring the category of medical knowledge to which the template variable belongs, and the binary predicate is used for declaring the semantic relation between two template variables; the ternary predicates are used for declaring the definition domain and the value domain of the medical relation;
the operators include: (1) symbol ". Lambda": representing conjunctive operation, representing logic AND, wherein an operation object is predicate or predicate logic expression; (2) symbol "[ V-shaped": representation disjunctive operation, representing logic OR, wherein an operation object is predicate or predicate logic expression; (3) sign symbol
Representing the full-scale word, representing any individual, and the operation object is a medical concept; (4) sign->
Representing the presence of a graduated word, representing the presence of a certain individual, and the operation object is a medical concept; (5) symbols ": type definitions representing medical knowledge variables, operands: the left side is a template variable, and the right side is a first-order template predicate; (6) sign "": a referencing operand representing a relationship of a medical concept or instance is a medical concept.
The method for carrying out answer reasoning by using the multi-entry medical question template device comprises the following steps:
s1, establishing a multi-entry medical question template library:
s11, collecting a user question set in a UMLS-based medical question-answering system, and performing root reduction on all user questions;
s12, templating a user question by using the template identifier and the variable type identifier, marking the core element, the optional element and the concept names and the relationship names of UMLS in the template identifier and the variable type identifier, and replacing each UMLS concept name, each UMLS concept name set and each UMLS relationship name by using a variable name and a variable type identifier respectively;
s13, classifying the user questions after the templated, and collecting the user questions with similar semantics together to form a template structure set of the multi-entry medical question template;
s14, repeating the step S13 until all user question sentences in the user question sentence set are classified, and forming a multi-entry medical question sentence template library only comprising a template structure set;
s15, according to different sub-semantics of the template structure, combining medical concepts and medical relations in the UMLS knowledge base, dividing a template structure set in each multi-entry medical question template into a plurality of groups to form a plurality of entry joint structures;
S16, describing a logic system by using a template, and simultaneously designing an inference rule and an inference function which accord with the entrance joint structure for each entrance joint structure of the multi-entrance medical question template library by combining medical concepts and medical relations in the UMLS knowledge base.
S2, matching the user question to be matched with a question template in the multi-entry medical question template library:
s21, preprocessing a user question to be matched as follows: firstly, performing root reduction on a user question, and marking medical concepts and relations in the user question by taking medical knowledge elements in a UMLS unified medical language system as a dictionary in the following marking modes: < medical concept: receive >, < set of medical concepts: conceptSet > vs < medical relationship: the Relation is carried out, nouns of non-medical concepts and verbs of non-medical relations in user question sentences are marked as core elements, query words and prepositions are marked as core elements, and finally user question sentences marked with the core elements and UMLS medical knowledge elements are obtained;
s22, carrying out sentence pattern similarity calculation on the preprocessed user question and question templates in the multi-entry medical question template library in sequence, and confirming the question template with the highest sentence pattern similarity as the question template matched with the user question.
S3, taking an entrance joint structure where a question template with highest matching degree with a user question is located as an execution entrance of the user question in the matched multi-entrance joint structure, and executing an inference function conforming to the entrance joint structure to complete the inference and extraction of answers.
Further, in the step S22, the calculation formula of the sentence pattern similarity between the user question and each multi-entry medical question template is as follows:
wherein, user represents a User question, MUTP represents a multi-entry medical question template in a template library, TSS represents a template structure set in the multi-entry medical question template MUTP, the multi-entry medical question template comprises a main template structure and a near-meaning template structure in the MUTP, TS is any one template structure in the template structure set TSS, struSim (User, TS) represents the structural similarity between the User question User and the template structure TS, and the calculation formula is as follows:
StruSim(User,TS)＝VarSim(User,TS)×KeySim(User,TS) (12)
wherein VarSim (User, TS) represents the similarity between the variable in the template structure TS and the UMLS medical knowledge element in the User question User, the calculation methods are shown in formulas (13) and (14), keySim (User, TS) represents the similarity between the core element in the template structure TS and the core element in the User question User, and the calculation methods are shown in formulas (15) and (16):
Wherein i is any one variable in Var, var is a variable set in a template structure TS, and j is any one UMLS medical knowledge element in UEThe element, UE represents UMLS medical knowledge element set in User question User, type (i) and Type (j) represent the Type of UMLS medical knowledge to which i and j belong,
the type of j is the same as the type of i or the type of j is contained by the type of i, m is any core element in Key, key is a core element set in a template structure TS, n is any core element in KE, KE is a core element set in a User question User, VS (i) and KS (m) respectively represent the similarity between a variable i, the core element m and the User question User in the template structure TS, sim (m, n) represents normalized word semantic similarity calculation based on a general semantic dictionary, and STH is a similarity threshold; the calculation formula of sim (m, n) is:
wherein LCS (m, n) represents the nearest common parent node in the generic semantic dictionary between core elements m, n, depth (LCS (m, n)) represents the depth of LCS (m, n) in the generic semantic dictionary, pathLen (m, n) represents the shortest path in the generic semantic dictionary between core elements m, n;
the universal semantic dictionary refers to a cross-domain computable dictionary based on a classification structure.
Further, in the step S3, executing the inference function conforming to the portal federation structure includes the following sub-steps:
s31, firstly executing the first-choice reasoning function bound with the first-choice reasoning rule, if and only if the execution of the first-choice reasoning function fails, starting to execute the second-choice reasoning function, and turning to the step S32, otherwise, returning an answer extraction result of the first-choice reasoning function and ending the execution of the reasoning function;
s32, executing a first sub-selection reasoning function, if and only if the first sub-selection reasoning function fails to be executed, starting to execute a second sub-selection reasoning function, sequentially executing all sub-selection reasoning functions bound by the template in the mode, returning failure information if all the reasoning functions fail to be executed, otherwise, returning an answer extraction result of the successfully executed reasoning function and ending the execution of the reasoning function; the reasoning function execution failure means that the reasoning function does not find that the questioning concept has a specified semantic relation record in the UMLS knowledge base.
The multi-entry medical question template device based on the medical concept and the medical relation and the application method thereof are characterized in that the multi-entry combined template obtained by the device is a question formula based on the medical concept and the medical relation, and the reasoning rules and the reasoning functions in the main template structure, the near-meaning template structure and the multi-entry combined structure are bound together to form conversion from multiple near-meaning user questions to multiple near answers, so that the template matching precision and the template design efficiency can be improved, the scale of a template library is reduced, and the question intention of a user is met to the maximum extent.
The medical knowledge base related to the multi-entry medical question template accords with a UMLS (Unified Medical Language System) unified medical language system proposed by the national medical library in the United states, namely the multi-entry medical question template is based on the medical concept and the medical relation of UMLS. UMLS is a semantic web of medical concepts, where over one million medical concepts are of 133 semantic types, and over 76 relationships are established between these concept types, then organized in a tree structure. The question template provided by the invention accords with the UMLS requirement, so that the question template can be used for extracting corresponding answers from the UMLS medical knowledge base, and the question intention of a user is met to the greatest extent.
Drawings
FIG. 1 is a schematic diagram of an application method of the present invention.
Detailed Description
The present invention is further illustrated below with reference to specific examples, but the scope of the present invention is not limited to the following examples.
Definition and structure of (one) multi-entry medical question templates
A multi-entry medical question template device is a multi-entry medical question conversion mechanism based on medical concepts and medical relations, and binds reasoning rules and reasoning functions in a main template structure, a near-meaning template structure and a multi-entry joint structure together to realize conversion of multiple near-meaning user questions into a multi-entry medical question template so as to extract corresponding answers from a UMLS medical knowledge base according to the multi-entry medical question template obtained by conversion. Wherein UMLS refers to Unified Medical Language System, unified medical language system.
Further, the question template binds the reasoning rules and the reasoning functions in the main template structure, the near-meaning template structure and the multi-entry joint structure, and defines a Barcus-North paradigm (BNF paradigm) as follows:
< multiple entry medical question template >: = (< master template structure >, { < near-sense template structure > }, < multiple entry association structure >) (1)
< multiple inlet joint Structure >: = ({ < inlet joint Structure > }) (2)
< entry association structure >: = ({ < synonymous template structure > }, < preferred binding structure >, { < secondary binding structure > }) (3)
< preferred binding Structure >: = (< preferred inference rule >, < preferred inference function >) (4)
< secondary binding structure >: = (< secondary inference rule >, < secondary inference function >) (5)
Main template structure: the most representative sentence structure of the question template expressed by the variables and the labels reflects the shallow question semantics of the question template.
The structure of the near-sense template: a template structure having similar semantics to the main template structure; a question template may contain multiple paraphrasing structures. The master template structure and the near-meaning template structure are used for matching templates.
Multiple inlet joint structure: a conversion mechanism for realizing the conversion from various sub-semantics of the question template to different semantic relations in the medical knowledge system; one question template includes more than one entry-joining structure. Each entry joint structure represents a certain sub-semantic reasoning method of a question template where the entry joint structure is located, and the method consists of a group of synonymous template structures, preferred reasoning rules and reasoning functions thereof, and a plurality of ordered sub-selected reasoning rules and reasoning functions thereof. The system comprises a plurality of input combined structure sub-semantics, a plurality of first-choice inference rules and a plurality of second-choice inference rules, wherein the first-choice inference rules are answer inference methods which are most consistent with the input combined structure sub-semantics of the template structure, and the second-choice inference rules are ranked according to the similarity degree of the second-choice inference rules and the template structure semantics;
Inference rules: the deep question semantics representing question templates accurately represent the reasoning process of the expected answers and the intention of the user to question by using predicate formulas based on medical concepts and medical relations.
Inference function: an answer reasoning program binding with the reasoning rule, it executes the reasoning function appointed by the reasoning rule, and extracts the corresponding answer from the medical knowledge base through the semantic relation appointed by the reasoning rule, its driving semantic comes from the medical knowledge element in the matched user question, and the mapping of the formal parameter of the reasoning function to the actual parameter is completed by the driving semantic.
Relationships and constraints between template structures
The union of the set of "main template structure" and "near-sense template structure" in formula (1) is equal to the union of the "synonymous template structures" in all formulas (3), i.e. the "main template structure" or "near-sense template structure" given in formula (1) appears in at least one "synonymous template structure" in formula 3.
In the main template structure and the near-meaning template structure, core elements, variable types and sequences among the core elements and the variable types in any two template structures cannot be completely the same, and the normalized semantic similarity of any two template structures based on the core elements, the variable types and the sequences is smaller than 1.
(III) question template structure based on variables and core elements
(1) Annotating symbol
The invention designs a set of template element labels for a question template structure, which are used for separating and defining various elements in a template, as shown in a table 1.
Table 1 template callout
| Annotating symbol | Interpretation of the drawings |
| <> | Defining an optional core element in a template |
| [] | Defining an elisable optional element in the template |
| {} | Representing a set of elements in a template |
| | | For separating synonyms in templates |
(2) Variable type identifier
For defining the variable types in the template structure, as shown in table 2. For example, the number of the cells to be processed,<c 1 :Concept>representing variable c 1 Is an ontology concept.
TABLE 2 variable type identifier in question template structure
| Variable type identifier | Description of the invention |
| Concept | <c:Concept>Declaring template variable c is a medical concept in the UMLS knowledge base |
| Relation | <r:Concept>Declaring the template variable r to be a medical relationship in the UMLS knowledge base |
| ConceptSet | <s:ConceptSet>The declarative template variable s is a collection of concepts in the UMLS knowledge base |
| Type | <t:Type>Declaring the template variable t to be of Type in UMLS knowledge base |
(3) Template structure
A template structure is defined as a set of template elements arranged in a certain order, using the template labels shown in table 1 and the variable types shown in table 2, the template structure comprising a main template structure, a near-meaning template structure, the question semantics of a question template being characterized by the variables and core elements in the template structure, defined as the bachel-nori paradigm (BNF paradigm):
< template Structure > = (< template element 1>, < template element 2>, …, < template element n >) (6)
< template element > = (< core element >, < optional element >, < variable >) (7)
< core element > = element (8) labeled with the labels "<", ">" in the template
Optional element: = element (9) labeled with the label "[", "]" in the template
< variable > = < variable name > + ": "+ < variable type > (10)
(IV) reasoning rules based on predicate logic
In order to accurately express the semantics of the multi-entry medical question template and define the reasoning rules in the multi-entry question template, the invention designs a set of template logic system. The logic system is a special first-order description logic for carrying out semantic operation and semantic interpretation on a multi-entry medical question template by taking medical concepts and medical relations as operation objects, and defines reasoning rules into a logic implication formula defined by the template description logic system, and the invention defines a template description logic system (Template Description Logic System) TDLS applied to the multi-entry medical question template into the following binary groups:
TDLS = (< predicate set >, < operator >)
(1) Predicates are used for declaring, identifying and determining medical concepts and medical relations in question templates; in TDLS, three types of predicates are included: a unitary predicate, a binary predicate, and a ternary predicate. The meta-predicate is used to declare the category of medical knowledge to which the template variable belongs. Binary predicates are used to declare semantic relationships between two template variables. Ternary predicates are used to declare the definition and value fields of medical relationships. Wherein, the unary predicate can also be used as a variable type identifier in the template structure annotation. Tables 3, 4 and 5 list and explain, respectively, the unary predicate, the binary predicate and the ternary predicate in the template description logic of the present invention.
Table 3 Single predicate in template logic
| Unitary predicates | Description of the invention |
| Concept(c) | Declaring template variable c is a concept in medical knowledge |
| Relation(r) | Declaring template variables r to be relationships in medical knowledge |
| Answer(s) | The declaration template variable s is a conceptual set conforming to reasoning rules in a medical knowledge base |
| ConceptSet(s) | Declarative template variables s are a collection of concepts in medical knowledge |
| Type(t) | Declaring the template variable t to be of Type in UMLS knowledge base |
Table 4 binary predicates in template logic
| Binary predicates | Description of the invention |
| SubClassOf(c 1 ,c 2 ) | Representation concept c 1 C is 2 Is a direct subclass of (2) |
| PosterityOf(c 1 ,c 2 ) | Representation concept c 1 C is 2 Offspring (offspring) class of (c) |
| EquivalenceClass(c 1 ,c 2 ) | Representation concept c 1 And c 2 Is of the equivalent class |
Table 5 triple predicates in template logic
(2) Operators: the invention further improves the expression capability of the template logic by expanding the conventional operators of the first-order predicates, and is divided into three types of operators of monocular, binocular and trinocular. Table 6 lists the operators extended herein for template logic.
TABLE 6 template operator
Fifth, the medical knowledge base (including medical concepts and medical relationships) used in the present invention conforms to the specifications
The medical knowledge base related to the multi-entry medical question template accords with UMLS (Unified Medical Language System) unified medical language system proposed by the national medical library (National Library of Medicine), namely the multi-entry medical question template is based on the medical concept and medical relation of UMLS. UMLS is a semantic web of medical concepts, where over one million medical concepts are of 133 semantic types, and over 76 relationships are established between these concept types, then organized in a tree structure.
Application method of multi-entry medical question template device
The application method specifically comprises the following steps:
S1, firstly, establishing a multi-entry medical question template library. The multi-entry medical question template library of the present invention refers to a collection of multi-entry medical question templates built in a UMLS-based medical question-answering system, it reflects the interests and needs of the user based on the medical knowledge of UMLS. The specific flow for establishing the multi-entry medical question template library is as follows:
s11, collecting a user question set in a UMLS-based medical question-answering system, and performing root reduction on all user questions;
s12, templating a user question by using a template label and a variable type label, marking the concept names and the relationship names of core elements, optional elements and UMLS in the user question, and replacing each UMLS concept name, each UMLS concept name set and each UMLS relationship name by using a variable name and a variable type label respectively;
s13, classifying the user questions after the templated, and collecting the user questions with similar semantics together to form a template structure set of the multi-entry medical question template;
s14, repeating the step S13 until all user question sentences in the user question sentence set are classified, and forming a multi-entry medical question sentence template library only comprising a template structure set;
s15, according to different sub-semantics of the template structure, combining medical concepts and medical relations in the UMLS knowledge base, dividing a template structure set in each multi-entry medical question template into a plurality of groups to form a plurality of entry joint structures;
S16, using the Template Description Logic System (TDLS), and simultaneously combining medical concepts and medical relations in the UMLS knowledge base to design an inference rule and an inference function which accord with the entrance joint structure for each entrance joint structure of the multi-entrance medical question template base.
S2, matching the user question to be matched with a question template in a multi-entry medical question template library:
s21, preprocessing a user question to be matched as follows: firstly, performing root reduction on a user question, and marking medical concepts and relations in the user question by taking medical knowledge elements in a UMLS unified medical language system as a dictionary in the following marking modes: < medical concept: receive >, < set of medical concepts: conceptSet > vs < medical relationship: relationship >, such as: < chronic podopompholyx: marking nouns of non-medical concepts in user question sentences and verbs of non-medical relations as core elements, marking query words and prepositions as core elements, and finally obtaining user question sentences marked with the core elements and UMLS medical knowledge elements; the UMLS medical knowledge elements refer to medical concepts, medical concept sets and relations in a UMLS unified medical language system;
S22, carrying out sentence pattern similarity calculation on the preprocessed user question and question templates in the multi-entry medical question template library in sequence, and confirming the question template with the highest sentence pattern similarity as the question template matched with the user question.
S3, taking an entrance joint structure where a question template with highest matching degree with a user question is located as an execution entrance of the user question in the matched multi-entrance joint structure, and executing an inference function conforming to the entrance joint structure to complete the inference and extraction of answers.
Further, in step S22, the sentence pattern similarity calculation formula of the user question and each multi-entry medical question template is:
wherein, user represents a User question, MUTP represents a multi-entry medical question template in a template library, TSS represents a template structure set in the multi-entry medical question template MUTP, the multi-entry medical question template comprises a main template structure and a near-meaning template structure in the MUTP, TS is any one template structure in the template structure set TSS, and StruSim (User, TS) represents the structural similarity between the User question User and the template structure TS. And the maximum value of the match (User, MUTP) is the question template with the highest matching degree with the User question.
The calculation formula of StruSim (User, TS) is as follows:
StruSim(User,TS)＝VarSim(User,TS)×KeySim(User,TS) (12)
Wherein VarSim (User, TS) represents the similarity between the variable in the template structure TS and the UMLS medical knowledge element in the User question User, the calculation methods are shown in formulas (13) and (14), keySim (User, TS) represents the similarity between the core element in the template structure TS and the core element in the User question User, and the calculation methods are shown in formulas (15) and (16):
wherein i is any one variable in Var, var is a variable set in a template structure TS, j is any one UMLS medical knowledge element in UE, UE represents a UMLS medical knowledge element set in a User question User, and Type (i) Type (j) represents UMLS medical knowledge to which i, j belong
The type of the material used in the process,
the type of j is the same as the type of i or the type of j is contained by the type of i, m is any core element in Key, key is a core element set in a template structure TS, n is any core element in KE, KE is a core element set in a User question User, VS (i) and KS (m) respectively represent the similarity between a variable i in the template structure TS, the core element m and the User question User, and sim (m, n) represent basesNormalized word semantic similarity calculation in a general semantic dictionary, which refers to a cross-domain computable dictionary based on a classification structure, such as WordNet at university of preston, usa or HowNet at the center of science; STH is a similarity threshold, which in this embodiment is 0.85. The calculation formula of sim (m, n) is:
Wherein LCS (m, n) represents the nearest common parent node in the generic semantic dictionary between core elements m, n, depth (LCS (m, n)) represents the depth of LCS (m, n) in the generic semantic dictionary, pathLen (m, n) represents the shortest path in the generic semantic dictionary between core elements m, n.
Further, in step S3, performing an inference function conforming to the portal federation structure includes the sub-steps of:
s31, firstly executing the first-choice reasoning function bound with the first-choice reasoning rule, if and only if the execution of the first-choice reasoning function fails, starting to execute the second-choice reasoning function, and turning to the step S32, otherwise, returning an answer extraction result of the first-choice reasoning function and ending the execution of the reasoning function;
s32, executing a first sub-selection reasoning function, if and only if the first sub-selection reasoning function fails to be executed, starting to execute a second sub-selection reasoning function, sequentially executing all sub-selection reasoning functions bound by the template in the mode, returning failure information if all the reasoning functions fail to be executed, otherwise, returning an answer extraction result of the successfully executed reasoning function and ending the execution of the reasoning function;
the reasoning function execution failure means that the reasoning function does not find that the questioning concept has a specified semantic relation record in the UMLS knowledge base.
(seventh) specific examples of multiple entry medical question templates:
in this example, the structure of the multi-entry medical question template and the definition method thereof proposed by the present invention are shown by the actual definition of two multi-entry medical question templates.
Example 1.
Question template 1: query concept contained in the part
The relation is as follows: part of relationship (id= 123005000)
Relationship with is-a (id= 116680003)
< main template structure > = < what > < do > [ the ] < c: body structure > < include|contact > [? ]
< near-sense template structure > = { < what > < category|type > < of > < c: concept > < be > < include|contact > [? ],
<what><be>[the]<category><of><c:Concept>[？]，
<what><be>[the]<part><of><c:body structure>[？]}
< entrance joint structure 1>: = = ("a")
< synonymous template Structure >: = { < what > < do > [ the ] < c: body structure > < include|contact > [? ],
<what><be>[the]<part><of><c:body structure>[？]}
< preferred Reasoning function >: =reporting_function 1 (c, pa)
< subselect inference function >: =reducing_function 1 (c, ia)
)
< entrance joint Structure 2>: = = ("a")
< synonymous template Structure > = { < what > < category|type > < of > < c: concept > < be > < include|contact > [? ],
<what><be>[the]<category|type><of><c:Concept>[？]}
< preferred function call >: =reducing_function 1 (c, ia)
< secondary function call >: =reducing_function 1 (c, pa)
)
< example sentence >: what does the Entire facial bone include?
What are the types of Colds？
Example 2.
Question template 2: interrogation of disease symptoms
The relation is as follows: associated morphology related appearance (id= 116676008)
Associated with … … (id= 47429007)
Due to reason (id= 42752001)
< main template structure > = < what > < be > [ the ] < obvious > < information > < for|of > < c: data > [? ]
< near-sense template structure >: = { < what > < do > < c: break > < related|connection|association > < to > [? ],
<what><be>[the]<obvious><indication><of|for><c:disease>[？],
<what><be>[the]<obvious><indication><for|of><patients><with><c:disease>[？],
<what><be>[the]<obvious><symptom><for|of><c:disease>[？],
<what><cause>[the]<disease><of><c:disease>[？],
<What><do><c:Concept><relate|connect|associate>to[？]}
< entrance joint structure 1>: = = ("a")
< synonymous template Structure >: = { < what > < be > [ the ] < obvious > < information > < for|of > < c: concept > [? ]
<what><be>[the]<obvious><indication><for|of><patient><with><c:Concept>[？],
<what><be>[the]<obvious><indication><of|for><c:Concept>[？],
<what><be>[the]<obvious><symptom><for|of><c:Concept>[？]}
< preferred Reasoning function >: =reducing_function 2 (c, am)
< subselect inference function 1>: =reducing_function 2 (c, aw)
< subselect inference function 2>: =reducing_function 2 (c, dt)
)
< entrance joint Structure 2>: = = ("a")
< synonymous template structure > = < what > < cause > [ the ] < treatment > < of > < c: treatment > [? ]
< preferred Reasoning function >: =reducing_function 2 (c, dt)
< subselect inference function 1>: =reducing_function 2 (c, aw)
< subselect inference function 2>: =reducing_function 2 (c, am)
)
< Inlet Combined Structure 3> = = ("A")
< synonymous template structure > = < what > < do > < c: treatment > < related|connection|association > < to > [? ]
< preferred Reasoning function >: =reporting_function 2 (c, aw)
< subselect inference function 1>: =reducing_function 2 (c, am)
< subselect inference function 2>: =reducing_function 2 (c, dt)
)
< example sentence >: what are the symptoms for Staphylococcus epidermidis meningitis?
What causes the disease of Diabetic maculopathy？
Eighth) application instance of multi-entry medical question template
In the example, the application effect of the multi-entry medical question template provided by the invention is shown through two medical question-answering systems based on SNOMED-CT. SNOMED-CT (Systematized Nomenclature of Medicine Clinical Terms, medical system nomenclature—clinical terminology) is a conceptual-based structured comprehensive set of clinical terms developed and maintained by the international health term standards-making organization IHTSDO (International Health Terminology Standards Development Organization). The concept of UMLS comes from more than one hundred different source vocabularies, SNOMED-CT being the most important source vocabulary of UMLS, i.e., the SNOMED-CT ontology is the most important subset of UMLS.
The SNOMED-CT medical ontology is a concept hierarchy in which there is a very specific root concept that contains all concept hierarchies in SNOMED-CT. In SNOMED-CT, concepts that are directly connected to the root concept by an "is-a" relationship are referred to as top-level concepts, and the remaining concepts are connected to at least one top-level concept by an "is-a" relationship. These top-level concepts have different meanings in SNOMED-CT, and all top-level concept IDs and meanings are shown in table 7 below:
TABLE 7 Top-level concept in SNOMED-CT
The medical semantic relationships that concepts in SNOMED-CT may constitute are shown in Table 8.
TABLE 8 SNOMED-CT Chinese medicine semantic relationship
SNOMED-CT is a huge medical knowledge base that today contains over 440,000 active medical concepts and over 100 tens of thousands of active medical relationship records. The embodiment takes SNOMED-CT as a knowledge base, and realizes two medical question-answering systems by respectively using a traditional single-entry and single-execution-route medical question template and a multi-entry and multi-execution-route medical question template, and by comparing and verifying the superiority of the multi-entry and multi-execution-route medical question template in the medical question-answering system, the experimental results are shown in Table 9:
TABLE 9 comparison of two SNOMED-CT ontology-based medical question-answering System Performance
| Question-answering system | Question template type | Question template library size | User satisfaction |
| System 1 | Single entry, single execution route | 150 | 78％ |
| System 2 | Multiple-entry, multiple-execution-route | 60 pieces | 85％ |
The calculation formula of the user satisfaction is as follows:
table 9 shows that the question-answering system 2 based on the template of the present invention greatly reduces the number of question templates of the question-answering system 1 based on the conventional template from 150 to 60, thereby improving the template design efficiency, which is mainly benefited by the multi-entry medical template of the present invention to concentrate the question structures with synonymous or near-sense question semantics into one template and to process them separately through a plurality of execution routes. On the other hand, table 9 also shows that the question-answering system 2 based on the template of the present invention greatly improves the user satisfaction of the question-answering system 1 based on the conventional template from 78% to 85%, which indicates that the multi-entry medical template of the present invention can significantly improve the performance of the medical question-answering system, which mainly benefits from that the multi-entry medical template of the present invention processes a matched question structure by using a plurality of bound inference functions, each of which attempts to infer an answer through a certain semantic relationship, so that when the question concept does not have the semantic relationship specified by the preferred inference function, the system attempts to acquire the answer through the remaining inference functions, thereby expanding the inference range of the answer.
Claims (4)
1. A multi-entry medical question template device is characterized in that the template device is a medical question conversion mechanism based on medical concepts and medical relations, and binds reasoning rules and reasoning functions in a main template structure, a near-meaning template structure and a multi-entry joint structure together to realize the conversion of multiple near-meaning user questions into a multi-entry medical question template so as to extract corresponding answers from a UMLS medical knowledge base according to the multi-entry medical question template obtained by conversion;
the question template binds the reasoning rules and the reasoning functions in the main template structure, the near-meaning template structure and the multi-entry joint structure, and the Bakes-Norwalk is defined as follows:
< multiple entry medical question template >: = (< master template structure >, { < near-sense template structure > }, < multiple entry association structure >) (1)
< multiple inlet joint Structure >: = ({ < inlet joint Structure > }) (2)
< entry association structure >: = ({ < synonymous template structure > }, < preferred binding structure >, { < secondary binding structure > }) (3)
< preferred binding Structure >: = (< preferred inference rule >, < preferred inference function >) (4)
< secondary binding structure >: = (< secondary inference rule >, < secondary inference function >) (5)
The main template structure is the most representative sentence structure of a question template expressed by using variables and labels, and reflects shallow question semantics of the question template;
the near-sense template structure is a template structure with similar semantics to the main template structure; one question template comprises more than one near-meaning structure;
the multi-entry joint structure is a conversion mechanism for realizing the conversion from various sub-semantics of the question template to different semantic relations in the medical knowledge system; one question template comprises more than one entry association structure; each entry joint structure represents a certain sub-semantic reasoning method of a question template where the entry joint structure is located, and the method consists of a group of synonymous template structures, preferred reasoning rules and reasoning functions thereof, and a plurality of ordered sub-choice reasoning rules and reasoning functions thereof; the system comprises a plurality of input combined structure sub-semantics, a plurality of first-choice inference rules, a plurality of second-choice inference rules, a plurality of first-choice inference rules and a plurality of second-choice inference rules, wherein the first-choice inference rules are a group of synonymous question sentence structures reflecting the input combined structure sub-semantics, each inference rule is associated with a corresponding inference function, the first-choice inference rules are answer inference methods which are most consistent with the input combined structure template structure semantics, and the second-choice inference rules are ordered according to the similarity degree of the second-choice inference rules and the template structure semantics;
The reasoning rule is a deep question meaning representing a question template, and a predicate formula based on medical concepts and medical relations is used for accurately representing the reasoning process of the expected answer and the intention of the user to question;
the reasoning function is an answer reasoning program bound with the reasoning rules, executes the reasoning function appointed by the reasoning rules, extracts corresponding answers from the medical knowledge base through semantic relations appointed by the reasoning rules, and drives the semantics to come from medical knowledge elements in the matched user questions;
the union of the main template structure and the near-sense template structure in the formula (1) is equal to the union of the synonymous template structures in the formula (3);
in the main template structure and the near-meaning template structure, the normalized semantic similarity of any two template structures based on core elements, variable types and sequences is less than 1;
the template structure is defined as a group of template elements which are marked by using a template mark symbol and a variable type symbol and are arranged in a certain sequence, the template structure comprises a main template structure and a near-meaning template structure, the question semantics of the question template are characterized by the variables and core elements in the template structure, and the template structure is defined as follows by the Barceis-North paradigm:
< template Structure > = (< template element 1>, < template element 2>, …, < template element n >) (6)
< template element > = (< core element >, < optional element >, < variable >) (7)
< core element > = element (8) labeled with the labels "<", ">" in the template
Optional element: = element (9) labeled with the label "[", "]" in the template
< variable > = < variable name > + ": "+ < variable type > (10)
Wherein the template label comprises: defining an optional core element in the template; [] An optional element for defining an eligibility in the template, { } represents a set of elements in the template; the i is used to separate synonyms in templates;
the variable type identifier includes: (1) concept: < c > Concept > states that template variable c is a medical Concept in the UMLS knowledge base; (2) and (3) Relation: < r > Concept > states that the template variable r is a medical relationship in the UMLS knowledge base; (3) ConceptSet: < s ConceptSet > states that the template variable s is a set of medical concepts in the UMLS knowledge base; (4) type: < t: type > states that the template variable t belongs to the Type in the UMLS knowledge base;
The inference rule is a logic implication formula defined by a template description logic system, wherein the template description logic system is called TDLS for short, and the TDLS is the following binary group:
TDLS = (< predicate set >, < operator >)
The predicate is used for declaring, identifying and determining medical concepts and medical relations in the question template; in TDLS, three types of predicates are included: a unitary predicate, a binary predicate, and a ternary predicate; the binary predicate is used for declaring the category of medical knowledge to which the template variable belongs, and the binary predicate is used for declaring the semantic relation between two template variables; the ternary predicates are used for declaring the definition domain and the value domain of the medical relation;
the operators include: (1) symbol ". Lambda": representing conjunctive operation, representing logic AND, wherein an operation object is predicate or predicate logic expression; (2) symbol "[ V-shaped": representation disjunctive operation, representing logic OR, wherein an operation object is predicate or predicate logic expression; (3) sign symbol
Representing the full-scale word, representing any individual, and the operation object is a medical concept; (4) sign->
Representing the presence of a graduated word, representing the presence of a certain individual, and the operation object is a medical concept; (5) symbols ": representing medical knowledge Type definitions of identification variables, operand: the left side is a template variable, and the right side is a first-order template predicate; (6) sign "": a referencing operand representing a relationship of a medical concept or instance is a medical concept.
2. A method for answer reasoning using the multi-entry medical question template apparatus of claim 1, comprising the steps of:
s1, establishing a multi-entry medical question template library:
s11, collecting a user question set in a UMLS-based medical question-answering system, and performing root reduction on all user questions;
s12, templating a user question by using the template identifier and the variable type identifier, marking the core element, the optional element and the concept names and the relationship names of UMLS in the template identifier and the variable type identifier, and replacing each UMLS concept name, each UMLS concept name set and each UMLS relationship name by using a variable name and a variable type identifier respectively;
s13, classifying the user questions after the templated, and collecting the user questions with similar semantics together to form a template structure set of the multi-entry medical question template;
s14, repeating the step S13 until all user question sentences in the user question sentence set are classified, and forming a multi-entry medical question sentence template library only comprising a template structure set;
S15, according to different sub-semantics of the template structure, combining medical concepts and medical relations in the UMLS knowledge base, dividing a template structure set in each multi-entry medical question template into a plurality of groups to form a plurality of entry joint structures;
s16, describing a logic system by using a template, and simultaneously designing an inference rule and an inference function which accord with the entrance joint structure for each entrance joint structure of the multi-entrance medical question template library by combining medical concepts and medical relations in the UMLS knowledge base;
s2, matching the user question to be matched with a question template in the multi-entry medical question template library:
s21, preprocessing a user question to be matched as follows: firstly, performing root reduction on a user question, and marking medical concepts and relations in the user question by taking medical knowledge elements in a UMLS unified medical language system as a dictionary in the following marking modes: < medical concept: receive >, < set of medical concepts: conceptSet > vs < medical relationship: the Relation is carried out, nouns of non-medical concepts and verbs of non-medical relations in user question sentences are marked as core elements, query words and prepositions are marked as core elements, and finally user question sentences marked with the core elements and UMLS medical knowledge elements are obtained;
S22, carrying out sentence pattern similarity calculation on the preprocessed user question and question templates in a multi-entry medical question template library in sequence, and confirming the question template with the highest sentence pattern similarity as a question template matched with the user question;
s3, taking an entrance joint structure where a question template with highest matching degree with a user question is located as an execution entrance of the user question in the matched multi-entrance joint structure, and executing an inference function conforming to the entrance joint structure to complete the inference and extraction of answers.
3. The method according to claim 2, characterized in that:
in the step S22, the sentence pattern similarity calculation formula of the user question and each multi-entry medical question template is:
wherein, user represents a User question, MUTP represents a multi-entry medical question template in a template library, TSS represents a template structure set in the multi-entry medical question template MUTP, the multi-entry medical question template comprises a main template structure and a near-meaning template structure in the MUTP, TS is any one template structure in the template structure set TSS, struSim (User, TS) represents the structural similarity between the User question User and the template structure TS, and the calculation formula is as follows:
StruSim(User,TS)＝VarSim(User,TS)×KeySim(User,TS) (12)
wherein VarSim (User, TS) represents the similarity between the variable in the template structure TS and the UMLS medical knowledge element in the User question User, the calculation methods are shown in formulas (13) and (14), keySim (User, TS) represents the similarity between the core element in the template structure TS and the core element in the User question User, and the calculation methods are shown in formulas (15) and (16):
Wherein i is any one variable in Var, var is a variable set in a template structure TS, j is any one UMLS medical knowledge element in UE, UE represents a UMLS medical knowledge element set in a User question User, type (i) and Type (j) represent types of UMLS medical knowledge to which i and j belong,
the type of j is the same as the type of i or the type of j is contained by the type of i, m is any core element in Key, key is a core element set in a template structure TS, n is any core element in KE, KE is a core element set in a User question User, VS (i) and KS (m) respectively represent the similarity between a variable i, the core element m and the User question User in the template structure TS, sim (m, n) represents normalized word semantic similarity based on a general semantic dictionaryCalculating the degree, wherein STH is a similarity threshold; the calculation formula of sim (m, n) is: />
Wherein LCS (m, n) represents the nearest common parent node in the generic semantic dictionary between core elements m, n, depth (LCS (m, n)) represents the depth of LCS (m, n) in the generic semantic dictionary, pathLen (m, n) represents the shortest path in the generic semantic dictionary between core elements m, n;
the universal semantic dictionary refers to a cross-domain computable dictionary based on a classification structure.
4. The method according to claim 2, characterized in that:
in the step S3, executing the inference function conforming to the portal federation structure includes the following sub-steps:
s31, firstly executing the first-choice reasoning function bound with the first-choice reasoning rule, if and only if the execution of the first-choice reasoning function fails, starting to execute the second-choice reasoning function, and turning to the step S32, otherwise, returning an answer extraction result of the first-choice reasoning function and ending the execution of the reasoning function;
s32, executing a first sub-selection reasoning function, if and only if the first sub-selection reasoning function fails to be executed, starting to execute a second sub-selection reasoning function, sequentially executing all sub-selection reasoning functions bound by the template in the mode, returning failure information if all the reasoning functions fail to be executed, otherwise, returning an answer extraction result of the successfully executed reasoning function and ending the execution of the reasoning function; the reasoning function execution failure means that the reasoning function does not find that the questioning concept has a specified semantic relation record in the UMLS knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910450711.1A CN110188170B (en) | 2019-05-28 | 2019-05-28 | Multi-entry medical question template device and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910450711.1A CN110188170B (en) | 2019-05-28 | 2019-05-28 | Multi-entry medical question template device and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110188170A CN110188170A (en) | 2019-08-30 |
| CN110188170B true CN110188170B (en) | 2023-05-09 |
Family
ID=67718315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910450711.1A Active CN110188170B (en) | 2019-05-28 | 2019-05-28 | Multi-entry medical question template device and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188170B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888969A (en) * | 2019-11-27 | 2020-03-17 | 华为技术有限公司 | Dialog response method and device |
| CN113689176A (en) * | 2021-07-15 | 2021-11-23 | 东风汽车集团股份有限公司 | Method and system for establishing vehicle function safety management process |
| CN115034204B (en) * | 2022-05-12 | 2023-05-23 | 浙江大学 | Method for generating structured medical text, computer device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584464B1 (en) * | 1999-03-19 | 2003-06-24 | Ask Jeeves, Inc. | Grammar template query system |
| CN104361127A (en) * | 2014-12-05 | 2015-02-18 | 广西师范大学 | Multilanguage question and answer interface fast constituting method based on domain ontology and template logics |
| CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
| CN105912846A (en) * | 2016-04-07 | 2016-08-31 | 南京小网科技有限责任公司 | Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique |
| CN108021703A (en) * | 2017-12-26 | 2018-05-11 | 广西师范大学 | A kind of talk formula intelligent tutoring system |
| CN109065139A (en) * | 2018-09-10 | 2018-12-21 | 平安科技（深圳）有限公司 | Medical follow up method, apparatus, computer equipment and storage medium |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
-
2019
- 2019-05-28 CN CN201910450711.1A patent/CN110188170B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584464B1 (en) * | 1999-03-19 | 2003-06-24 | Ask Jeeves, Inc. | Grammar template query system |
| CN104361127A (en) * | 2014-12-05 | 2015-02-18 | 广西师范大学 | Multilanguage question and answer interface fast constituting method based on domain ontology and template logics |
| CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
| CN105912846A (en) * | 2016-04-07 | 2016-08-31 | 南京小网科技有限责任公司 | Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique |
| CN108021703A (en) * | 2017-12-26 | 2018-05-11 | 广西师范大学 | A kind of talk formula intelligent tutoring system |
| CN109065139A (en) * | 2018-09-10 | 2018-12-21 | 平安科技（深圳）有限公司 | Medical follow up method, apparatus, computer equipment and storage medium |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
Non-Patent Citations (3)
| Title |
|---|
| A Biomedical Question Answering System Based on SNOMED-CT;Xinhua Zhu 等;《International Conference on Knowledge Science, Engineering and Management(KSEM 2018)》;20180812;第16-21页 * |
| Keyword question answering system with report generation for linked data;Sangdo Han 等;《2015 International Conference on Big Data and Smart Computing (BIGCOMP)》;20150402;第23-24页 * |
| 基于本体的自动答疑系统的研究与实现;刘汉兴 等;《计算机应用》;20100201;第30卷(第2期);第415-416页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110188170A (en) | 2019-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Höffner et al. | Survey on challenges of question answering in the semantic web | |
| US9715493B2 (en) | Method and system for monitoring social media and analyzing text to automate classification of user posts using a facet based relevance assessment model | |
| Mansingh et al. | Using ontologies to facilitate post-processing of association rules by domain experts | |
| US9058374B2 (en) | Concept driven automatic section identification | |
| Wang et al. | Structure learning via parameter learning | |
| CN110188170B (en) | Multi-entry medical question template device and method thereof | |
| Sawant et al. | Neural architecture for question answering using a knowledge graph and web corpus | |
| CN113076411B (en) | Medical query expansion method based on knowledge graph | |
| Giordani et al. | Semantic mapping between natural language questions and SQL queries via syntactic pairing | |
| Hamon et al. | Querying biomedical linked data with natural language questions | |
| Boujelben et al. | A hybrid method for extracting relations between Arabic named entities | |
| CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
| Lien et al. | Semantic parsing for textual entailment | |
| Abad-Navarro et al. | Semankey: a semantics-driven approach for querying RDF repositories using keywords | |
| Höffner et al. | Overcoming challenges of semantic question answering in the semantic web | |
| Faralli et al. | DWS at the 2016 open knowledge extraction challenge: a hearst-like pattern-based approach to hypernym extraction and class induction | |
| Ivanova | Cross-lingual and multilingual ontology mapping-survey | |
| Mannai et al. | Bayesian information extraction network for Medline abstract | |
| Luo et al. | Semi-supervised learning to identify UMLS semantic relations | |
| Kim et al. | A local tree alignment approach to relation extraction of multiple arguments | |
| CN110188169A (en) | A kind of knowledge matching process, system and equipment based on simplified label | |
| Maree et al. | Coupling semantic and statistical techniques for dynamically enriching web ontologies | |
| Bhutani et al. | Online Schemaless Querying of Heterogeneous Open Knowledge Bases | |
| CN108511044B (en) | Internet consultation triage method and system | |
| Orihuela et al. | Natural language inference over tables: Enabling explainable data exploration on data lakes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230331 Address after: Room 801, 85 Kefeng Road, Huangpu District, Guangzhou City, Guangdong Province Applicant after: Yami Technology (Guangzhou) Co.,Ltd. Address before: 541004 No. 15 Yucai Road, Qixing District, Guilin, the Guangxi Zhuang Autonomous Region Applicant before: Guangxi Normal University Effective date of registration: 20230331 Address after: 156 Shop, Fukang Road, Xintiandi Commercial Plaza, Sucheng District, Suqian City, Jiangsu Province, 223800 Applicant after: Ding Yuehui Address before: Room 801, 85 Kefeng Road, Huangpu District, Guangzhou City, Guangdong Province Applicant before: Yami Technology (Guangzhou) Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |