CN115048531A - Knowledge management method, device and system for urban physical examination knowledge - Google Patents
Knowledge management method, device and system for urban physical examination knowledge Download PDFInfo
- Publication number
- CN115048531A CN115048531A CN202210647918.XA CN202210647918A CN115048531A CN 115048531 A CN115048531 A CN 115048531A CN 202210647918 A CN202210647918 A CN 202210647918A CN 115048531 A CN115048531 A CN 115048531A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- physical examination
- preset
- urban
- base
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
Abstract
The invention discloses a knowledge management method, a knowledge management device and a knowledge management system for urban physical examination knowledge. The method, the device and the system for the knowledge management improve the knowledge management efficiency of the urban physical examination knowledge by establishing the urban physical examination knowledge base in a knowledge map form according to a preset multi-department analysis and evaluation index group, the urban physical examination knowledge instance resource and an associated clustering method from the aspects of theme, index and method, so that a standardized frame is established based on different analysis and evaluation indexes, and further the universality and compatibility of the knowledge management are realized; further, the knowledge management method, the device and the system for the urban physical examination knowledge provided by the invention also timely perform reverse supplement and improvement on the urban physical examination ontology base according to the urban physical examination knowledge base, so that the accuracy of the knowledge management of the urban physical examination knowledge is improved.
Description
Technical Field
The invention relates to the technical field of knowledge management of urban physical examination knowledge, in particular to a knowledge management method, a knowledge management device, a computer-readable storage medium and a knowledge management system of urban physical examination knowledge.
Background
The knowledge graph is a semantic network for revealing the relationship between entities, and can formally describe real things and the association relationship thereof. Knowledge maps have been popularized in both academic and industrial fields, and play an important role in applications such as intelligent search, intelligent question answering, and intelligent recommendation. The city information has wide sources, various types and non-uniform formats, and brings huge challenges to data collection, association, fusion and analysis. Meanwhile, the mass data has less data useful for urban physical examination evaluation, and important knowledge is easily submerged by junk information. The knowledge map, the processing analysis and the correlation are adopted to display the multi-source heterogeneous data and knowledge, the regular evaluation of urban development characteristics and planning implementation effects is facilitated, the problems and short boards existing in the national soil space management and urban function layout are revealed in time, and the urban development quality is improved. Specifically, the urban physical examination knowledge graph relates to knowledge in multiple fields such as humanity, economy, environment and the like.
In the prior art, a knowledge graph form is adopted to process, analyze and associate to display multi-source heterogeneous data and knowledge, wherein graph construction comprises multi-level entity extraction, multi-level relation extraction, knowledge graph storage and the like.
However, the prior art still has the following defects: due to the fact that analysis and evaluation indexes of the urban physical examination are inconsistent, data processing methods are different, topics have characteristics, a semantic-based unified framework is lacked, universality and compatibility of urban physical examination knowledge map construction and knowledge service application are not strong, and knowledge management efficiency is low.
Therefore, there is a need for a method, apparatus, computer-readable storage medium, and system for knowledge management of urban physical examination knowledge that overcomes the above-mentioned deficiencies in the prior art.
Disclosure of Invention
The embodiment of the invention provides a knowledge management method, a knowledge management device, a computer readable storage medium and a knowledge management system of urban physical examination knowledge, so that the knowledge management efficiency of the urban physical examination knowledge is improved.
An embodiment of the invention provides a knowledge management method of urban physical examination knowledge, which comprises the following steps: acquiring city physical examination data through a main crawler data acquisition tool, and cleaning the city physical examination data to acquire city physical examination knowledge; classifying and summarizing the city physical examination knowledge according to a preset field category and a preset expert experience base to obtain a city physical examination ontology base; constructing an urban physical examination knowledge instance resource according to a preset first external knowledge base and the urban physical examination ontology base; and establishing an urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis evaluation index group, the urban physical examination knowledge instance resource and an associated clustering method from the aspects of theme, index and method.
As an improvement of the above scheme, in terms of a theme, an index and a method, according to a preset multi-department analysis and evaluation index group, the city physical examination knowledge instance resource and an associated clustering method, a city physical examination knowledge base is established, which specifically includes: acquiring a preset multi-department analysis evaluation index group; the multi-department analysis and evaluation index group comprises analysis and evaluation indexes and corresponding analysis and evaluation index connotations; calculating the analysis evaluation index by adopting a hidden Dirichlet distribution model to establish an index library; performing feature mining on the analysis evaluation index content to establish a method library; extracting the analysis evaluation index according to a correlation clustering method to obtain a theme group, and performing clustering analysis on the theme group to obtain a theme library; and establishing an urban physical examination knowledge base according to the index base, the method base and the subject base.
As an improvement of the above scheme, according to a preset domain category and a preset expert experience library, classifying and summarizing the city physical examination knowledge to obtain a city physical examination ontology library, specifically comprising: acquiring a preset field category and a preset expert experience library; according to the expert experience base and the field categories, determining city physical examination body ranges corresponding to the field categories from the city physical examination knowledge; respectively extracting from the urban physical examination knowledge range through a preset first high-frequency calculation method and a preset second high-frequency calculation method to correspondingly obtain a first keyword group and a second keyword group, and fusing and de-duplicating the first keyword group and the second keyword group to correspondingly obtain field concepts corresponding to all field categories; iteratively extracting to obtain the domain relation among the domain categories according to a preset second external knowledge base, a preset matching method and a preset scoring evaluation formula; and constructing a city physical examination ontology library according to the field concept and the field relation.
As an improvement of the above scheme, the score evaluation formula specifically includes:
wherein N is the total number of candidate relations mined by the candidate word list P, and F is the number of relation entities which are already in the entity dictionary and are mined by the candidate word list P;indicating the accuracy, log, of the candidate vocabulary P 2 (F +1) indicates the recall capability of the candidate vocabulary P.
As an improvement of the above scheme, calculating the analysis evaluation index by using a hidden dirichlet allocation model to establish an index library, specifically including: establishing an analysis evaluation index set according to the analysis evaluation indexes; performing data preprocessing on the analysis evaluation index set to obtain a department analysis evaluation index set; the department analysis evaluation index set comprises a plurality of department analysis evaluation indexes; and calculating and confirming index keywords corresponding to the department analysis evaluation indexes according to a hidden Dirichlet distribution model and a preset target function corresponding to the keywords, and establishing an index library according to the entanglement degree, the department analysis evaluation indexes and the index keywords.
As an improvement of the above scheme, the preset target function corresponding to the keyword specifically includes:
where α and β are iterable hyper-parameters.
As an improvement of the above scheme, the method of extracting the analysis evaluation index according to a correlation clustering method to obtain a topic group, and performing cluster analysis on the topic group to obtain a topic library specifically includes: under the different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence; calculating the theme content association degree among the theme contents according to a preset theme content association degree formula, theme semantic similarity, index unit similarity and calculation method similarity; clustering the theme connotations according to an association clustering algorithm to obtain a theme group; the theme group comprises a plurality of theme vocabularies; and calculating the similarity between the subject vocabulary and the subject connotation according to a preset similarity calculation formula, and clustering the subject vocabulary and the subject connotation according to a preset classification threshold and the similarity to obtain a subject library.
As an improvement of the above scheme, the preset theme content association formula specifically includes:
SC ═ a × topic semantic similarity + b × index semantic similarity + c × index unit similarity + d ×, and
calculating method similarity;
wherein SC is the theme connotation relevance degree; a, b, c, d are weighting factors, respectively, and a, b, c, d are belonged to (0, 1).
As an improvement of the above scheme, the preset similarity calculation formula is specifically:
wherein S is a subject vocabulary; c is the theme connotation.
As an improvement of the above scheme, the iterative extraction is performed according to a preset second external knowledge base, a preset matching method, and a preset score evaluation formula to obtain the domain relationship among the domain categories, and specifically includes: referring to a preset second external knowledge base, inducing and acquiring the relationship types among the entities, and storing the relationship types and the urban physical examination knowledge into an entity dictionary; matching the city physical examination knowledge with the relation type through a boot removing method, and storing a matching result into a candidate word list; according to a preset scoring evaluation formula, evaluating and scoring the matching result in the candidate word list, and judging whether the evaluation scoring result is converged according to a preset iteration number and a preset convergence precision; and if the evaluation scoring result is converged, outputting the relationship type corresponding to the evaluation scoring result as the field relationship between the corresponding fields.
As an improvement of the above, the knowledge management method further includes: and reversely supplementing and perfecting the urban physical examination ontology base according to the urban physical examination knowledge base.
The invention correspondingly provides a knowledge management device of urban physical examination knowledge, which comprises a data acquisition unit, a classification and induction unit, an example construction unit and a knowledge base establishment unit, wherein the data acquisition unit is used for acquiring urban physical examination data through a main crawler data acquisition tool and cleaning the urban physical examination data to acquire the urban physical examination knowledge; the classification induction unit is used for classifying and inducing the urban physical examination knowledge according to a preset field category and a preset expert experience base to obtain an urban physical examination ontology base; the example construction unit is used for constructing an urban physical examination knowledge example resource according to a preset first external knowledge base and the urban physical examination ontology base; the knowledge base establishing unit is used for establishing the urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis and evaluation index group, the urban physical examination knowledge instance resources and an associated clustering method from the aspects of theme, indexes and methods.
As an improvement of the above solution, the knowledge base establishing unit is further configured to: acquiring a preset multi-department analysis evaluation index group; the multi-department analysis and evaluation index group comprises analysis and evaluation indexes and corresponding analysis and evaluation index connotations; calculating the analysis evaluation index by adopting a hidden Dirichlet distribution model to establish an index library; performing feature mining on the analysis evaluation index content to establish a method library; extracting the analysis evaluation index according to a correlation clustering method to obtain a theme group, and performing clustering analysis on the theme group to obtain a theme library; and establishing an urban physical examination knowledge base according to the index base, the method base and the subject base.
As an improvement of the above solution, the knowledge base establishing unit is further configured to: establishing an analysis evaluation index set according to the analysis evaluation indexes; performing data preprocessing on the analysis evaluation index set to obtain a department analysis evaluation index set; the department analysis evaluation index set comprises a plurality of department analysis evaluation indexes; and calculating and confirming index keywords corresponding to the department analysis evaluation indexes according to a hidden Dirichlet distribution model and a preset target function corresponding to the keywords, and establishing an index library according to the entanglement degree, the department analysis evaluation indexes and the index keywords.
As an improvement of the above solution, the knowledge base establishing unit is further configured to: under the different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence; calculating the theme content relevance among the theme contents according to a preset theme content relevance formula, theme semantic similarity, index unit similarity and calculation method similarity; clustering the theme connotations according to an association clustering algorithm to obtain a theme group; the topic group comprises a plurality of topic vocabularies; and calculating the similarity between the subject vocabulary and the subject connotation according to a preset similarity calculation formula, and clustering the subject vocabulary and the subject connotation according to a preset classification threshold and the similarity to obtain a subject library.
As an improvement of the above, the classification induction unit is further configured to: acquiring a preset field category and a preset expert experience library; according to the expert experience base and the field categories, determining city physical examination body ranges corresponding to the field categories from the city physical examination knowledge; respectively extracting from the city physical examination knowledge range through a preset first high-frequency calculation method and a preset second high-frequency calculation method to correspondingly obtain a first key phrase and a second key phrase, and fusing and de-duplicating the first key phrase and the second key phrase to correspondingly obtain field concepts corresponding to all field categories; iteratively extracting to obtain the domain relation among the domain categories according to a preset second external knowledge base, a preset matching method and a preset scoring evaluation formula; and constructing a city physical examination ontology library according to the field concept and the field relation.
As an improvement of the above, the classification induction unit is further configured to: referring to a preset second external knowledge base, inducing and acquiring the relationship types among the entities, and storing the relationship types and the urban physical examination knowledge into an entity dictionary; matching the city physical examination knowledge with the relationship type by a boot-pulling method, and storing a matching result into a candidate word list; according to a preset scoring evaluation formula, evaluating and scoring the matching result in the candidate word list, and judging whether the evaluation scoring result is converged according to a preset iteration number and a preset convergence precision; and if the evaluation scoring result is converged, outputting the relationship type corresponding to the evaluation scoring result as the field relationship between the corresponding fields.
As an improvement of the above, the knowledge management apparatus further includes a supplementary feedback unit configured to: and reversely supplementing and perfecting the urban physical examination ontology base according to the urban physical examination knowledge base.
Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the method for knowledge management of urban physical examination knowledge as described above.
Another embodiment of the present invention provides a knowledge management system for urban physical examination knowledge, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the processor implements the knowledge management method for urban physical examination knowledge as described above.
Compared with the prior art, the technical scheme has the following beneficial effects:
the invention provides a knowledge management method, a knowledge management device, a computer readable storage medium and a knowledge management system for urban physical examination knowledge.
Further, the knowledge management method, the device, the computer readable storage medium and the system for the urban physical examination knowledge provided by the invention can timely perform reverse supplement and improvement on the urban physical examination ontology base according to the urban physical examination knowledge base, thereby improving the accuracy of the knowledge management of the urban physical examination knowledge.
Drawings
FIG. 1 is a flow chart of a knowledge management method for urban physical examination knowledge according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a knowledge management apparatus for urban physical examination knowledge according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Detailed description of the preferred embodiment
The embodiment of the invention firstly describes a knowledge management method of urban physical examination knowledge. Fig. 1 is a schematic flow chart of a knowledge management method of urban physical examination knowledge according to an embodiment of the present invention.
As shown in fig. 1, the knowledge management method includes:
and S1, acquiring urban physical examination data through the main body crawler data acquisition tool, and cleaning the urban physical examination data to acquire urban physical examination knowledge.
Specifically, a theme crawler data acquisition tool is adopted to extract the structural features of the webpage, and city physical examination knowledge is extracted from a website in the city physical examination field through data cleaning operation. The city physical examination data comprises a city physical examination historical report, city planning related data, city physical examination administrative leather data, industry data and an external city knowledge base.
And S2, classifying and summarizing the urban physical examination knowledge according to a preset field category and a preset expert experience base to obtain an urban physical examination ontology base.
Wherein the field categories include humanity, ecological environment, economy, and the like. Specifically, the method comprises the steps of firstly determining the urban physical examination ontology range according to three field knowledge of humanity, ecological environment and economy; then, a semantic-based concept and relation classification system is determined for the three types of domain knowledge.
In one embodiment, the method for obtaining the urban physical examination ontology library includes classifying and summarizing the urban physical examination knowledge according to a preset domain category and a preset expert experience library, and specifically includes: acquiring a preset field category and a preset expert experience library; according to the expert experience base and the field categories, determining city physical examination body ranges corresponding to the field categories from the city physical examination knowledge; respectively extracting from the city physical examination knowledge range through a preset first high-frequency calculation method and a preset second high-frequency calculation method to correspondingly obtain a first key phrase and a second key phrase, and fusing and de-duplicating the first key phrase and the second key phrase to correspondingly obtain field concepts corresponding to all field categories; iteratively extracting to obtain the domain relation among the domain categories according to a preset second external knowledge base, a preset matching method and a preset scoring evaluation formula; and constructing a city physical examination ontology library according to the field concept and the field relation.
In one embodiment, the preset second external knowledge base is external knowledge bases such as schema. The preset first high-frequency calculation method is a TF-IDF algorithm; the preset second high-frequency calculation method is a TextRank algorithm.
In one embodiment, the score evaluation formula is specifically:
wherein, N is the total number of candidate relations mined by the candidate word list P, and F is the number of relation entities which are already in the entity dictionary and are mined by the candidate word list P;indicating the accuracy, log, of the candidate vocabulary P 2 (F +1) indicates the recall capability of the candidate vocabulary P.
And S3, constructing an urban physical examination knowledge instance resource according to the preset first external knowledge base and the urban physical examination ontology base.
Specifically, the city physical examination knowledge in the city physical examination ontology base is subjected to word segmentation and word removal for stop, entities, attributes and relations in a preset first external knowledge base and the city physical examination ontology base are referred, part of speech tagging is carried out on the city physical examination domain knowledge, and a Bi-GRU model based on character-level attention and sentence-level attention is adopted for training and extracting Chinese entities and relations. And linking the extracted knowledge examples with external knowledge bases, such as the knowledge bases of Baidu encyclopedia, Wikipedia and the like, to form webpage version structured links of the knowledge examples and enrich knowledge example resources.
And S4, establishing an urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis evaluation index group, the urban physical examination knowledge instance resources and an associated clustering method from the aspects of theme, index and method.
By researching the requirements of relevant departments of the urban physical examination on knowledge, taking the urban physical examination evaluation as a core, the method for constructing the urban physical examination knowledge base which is oriented to the evaluation of a plurality of subjects, has multi-type index analysis and multi-method calculation is provided, and the hierarchical expression and information description of the subjects, the indexes and the methods are formed. And a multi-stage linkage operation closed loop is formed among the subject library, the index library and the method library.
In one embodiment, from three aspects of a theme, an index and a method, establishing an urban physical examination knowledge base according to a preset multi-department analysis evaluation index group, the urban physical examination knowledge instance resource and an associated clustering method, specifically includes: acquiring a preset multi-department analysis evaluation index group; calculating the analysis evaluation index by adopting a hidden Dirichlet distribution model to establish an index library; performing feature mining on the analysis evaluation index content to establish a method library; extracting the analysis evaluation index according to a correlation clustering method to obtain a theme group, and performing clustering analysis on the theme group to obtain a theme library; and establishing an urban physical examination knowledge base according to the index base, the method base and the subject base. The multi-department analysis and evaluation index group comprises analysis and evaluation indexes of different departments and corresponding analysis and evaluation index connotations.
In one embodiment, the calculating the analysis and evaluation index by using a hidden dirichlet distribution model to establish an index library specifically includes: establishing an analysis evaluation index set according to the analysis evaluation indexes; performing data preprocessing on the analysis evaluation index set to obtain a department analysis evaluation index set; the department analysis evaluation index set comprises a plurality of department analysis evaluation indexes; and calculating and confirming index keywords corresponding to the department analysis evaluation indexes according to a hidden Dirichlet distribution model and a preset target function corresponding to the keywords, and establishing an index library according to the entanglement degree, the department analysis evaluation indexes and the index keywords. The preprocessing process comprises word segmentation, word deactivation and the like.
In one embodiment, the preset target function corresponding to the keyword is specifically:
where α and β are iterable hyper-parameters. And according to the theta and the k, the probability distribution of each index keyword in the index and the probability distribution of each index keyword in the theme can be obtained. And converging the numerical value through iterative calculation, and obtaining an index keyword corresponding to the index through probability calculation.
The meaning of the index is a concrete representation of the meaning and how to calculate the index. The index connotations generally have the characteristic words "occupation", "proportion", "percentage", "average", "per", "total", "quantity", "rate", etc. In one embodiment, the feature mining is performed on the analysis and evaluation index connotations to establish a method library, which specifically includes: adding the characteristic words into a word segmentation word bank to ensure the word segmentation quality of professional vocabularies; mining the co-occurrence relation between index content words and feature words by using a TextRank algorithm, and selecting 2-8 feature words as variable parameters; and setting rule constraint to determine a logic operation relation R-operation through the position relation R-position of the variable parameter and the feature word, and combining the variable parameter V and the logic operation O into a calculation method ME.
For example, "the number of historical culture blocks where the maintenance and repair items were developed in the near 5 years in the city and county area as a percentage of the total amount of the historical culture blocks", and the TextRank algorithm is used to extract the variable parameters of "the city and county area", "the near 5 years", "the maintenance and repair items", "the number of the historical culture blocks", "the percentage of the total amount of the historical culture blocks", and "the percentage". The operation can be judged as division by the percentage, the variable parameter before occupation is numerator, and the variable parameter after occupation is denominator. In order to meet the requirement of the variable parameters for calling data from the knowledge examples, the variable parameters are further combined according to the knowledge examples to realize variable adaptation; then, establishing a calculation method word list MME of association indexes by a plurality of calculation method entities ME as { MME } 1 ,mme 2 ,...,mme i },i<170, setting positive and negative evaluation strategy S entity according to the evaluation intention of the index, and establishing an evaluation strategy interval table MS-MS 1 ,ms 2 ,...,ms 10 }; finally, the index library LI may invoke the calculation method and the evaluation strategy from the method library LM according to the matching of the index keywords and the feature words.
In one embodiment, the refining the analysis and evaluation index according to an association clustering method to obtain a topic group, and performing cluster analysis on the topic group to obtain a topic library specifically includes: under the different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence; calculating the theme content association degree among the theme contents according to a preset theme content association degree formula, theme semantic similarity, index unit similarity and calculation method similarity; clustering the theme connotations according to an association clustering algorithm to obtain a theme group; the topic group comprises a plurality of topic vocabularies; and calculating the similarity between the subject vocabulary and the subject connotation according to a preset similarity calculation formula, and clustering the subject vocabulary and the subject connotation according to a preset classification threshold and the similarity to obtain a subject library.
Under different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence, specifically calculating the similarity of the theme connotation indexes and the calculation methods by using the JS divergence from two angles of the index entities and the method entities. The probability distributions of entity e1 and entity e2 are P 1 And P 2 Then the similarity between the entities can be expressed as JS (P) 1 ||P 2 ):
Wherein D is KL (P 1 ||P 2 ) Represents P 1 And P 2 The KL divergence of (1), expressed as:
in one embodiment, the preset theme content association formula is specifically:
SC ═ a × topic semantic similarity + b × index semantic similarity + c × index unit similarity + d ×, and
calculating method similarity;
wherein SC is the theme connotation relevance degree; a, b, c, d are weighting factors, respectively, and a, b, c, d are belonged to (0, 1).
According to a preset classification threshold and the similarity, clustering the topic vocabulary and the topic connotation to obtain a topic library specifically comprises: and organizing the three levels of knowledge of indexes/methods, theme connotations and themes through bottom-to-top hierarchical clustering, and performing association extraction on the indexes based on the contents of the theme library to form an index library so as to realize response to the themes. The calculation method of the index library is obtained from the method library, and dynamic calculation and updating of the index are achieved. In one embodiment, the preset similarity calculation formula is specifically:
wherein S is a subject vocabulary; c is the theme connotation.
In one embodiment, the iteratively extracting to obtain the domain relationship between the domain categories according to a preset second external knowledge base, a preset matching method, and a preset score evaluation formula specifically includes: referring to a preset second external knowledge base, inducing and acquiring the relationship types among the entities, and storing the relationship types and the urban physical examination knowledge into an entity dictionary; matching the city physical examination knowledge with the relationship type by a boot-pulling method, and storing a matching result into a candidate word list; according to a preset scoring evaluation formula, evaluating and scoring the matching result in the candidate word list, and judging whether the evaluation scoring result is converged according to a preset iteration number and a preset convergence precision; and if the evaluation scoring result is converged, outputting the relationship type corresponding to the evaluation scoring result as the field relationship between the corresponding fields.
In one embodiment, the knowledge management method further comprises: and reversely supplementing and perfecting the urban physical examination body library according to the urban physical examination knowledge library.
The embodiment of the invention describes a knowledge management method of urban physical examination knowledge, which is characterized in that an urban physical examination knowledge base is established in a knowledge map form according to a preset multi-department analysis and evaluation index group, urban physical examination knowledge instance resources and an associated clustering method from the aspects of theme, index and method, so that a standardized frame is established based on different analysis and evaluation indexes, and further the universality and compatibility of knowledge management are realized, and the knowledge management method improves the knowledge management efficiency of the urban physical examination knowledge; further, the knowledge management method of the urban physical examination knowledge described in the embodiment of the invention also carries out reverse supplement and improvement on the urban physical examination ontology base in time according to the urban physical examination knowledge base, thereby improving the accuracy of the knowledge management of the urban physical examination knowledge.
Detailed description of the invention
Besides the method, the embodiment of the invention also discloses a knowledge management device for the urban physical examination knowledge. Fig. 2 is a schematic structural diagram of a knowledge management apparatus for urban physical examination knowledge according to an embodiment of the present invention.
As shown in fig. 2, the knowledge management device includes a data acquisition unit, a classification and induction unit, an instance construction unit, and a knowledge base establishment unit, wherein the data acquisition unit is configured to acquire city physical examination data through a main crawler data acquisition tool, and clean the city physical examination data to acquire city physical examination knowledge; the classification induction unit is used for classifying and inducing the urban physical examination knowledge according to a preset field category and a preset expert experience base to obtain an urban physical examination ontology base; the example construction unit is used for constructing an urban physical examination knowledge example resource according to a preset first external knowledge base and the urban physical examination ontology base; the knowledge base establishing unit is used for establishing the urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis and evaluation index group, the urban physical examination knowledge instance resources and an associated clustering method from the aspects of theme, indexes and methods.
In one embodiment, the knowledge base establishing unit is further configured to: acquiring a preset multi-department analysis evaluation index group; the multi-department analysis and evaluation index group comprises analysis and evaluation indexes and corresponding analysis and evaluation index connotations; calculating the analysis evaluation index by adopting a hidden Dirichlet distribution model to establish an index library; performing feature mining on the analysis evaluation index connotation to establish a method library; extracting the analysis evaluation index according to a correlation clustering method to obtain a theme group, and performing clustering analysis on the theme group to obtain a theme library; and establishing an urban physical examination knowledge base according to the index base, the method base and the subject base.
In one embodiment, the knowledge base establishing unit is further configured to: establishing an analysis evaluation index set according to the analysis evaluation indexes; performing data preprocessing on the analysis evaluation index set to obtain a department analysis evaluation index set; the department analysis evaluation index set comprises a plurality of department analysis evaluation indexes; and calculating and confirming index keywords corresponding to the department analysis and evaluation indexes according to a hidden Dirichlet distribution model and a preset target function corresponding to the keywords, and establishing an index library according to the entanglement degree, the department analysis and evaluation indexes and the index keywords.
In one embodiment, the knowledge base establishing unit is further configured to: under the different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence; calculating the theme content association degree among the theme contents according to a preset theme content association degree formula, theme semantic similarity, index unit similarity and calculation method similarity; clustering the theme connotations according to an association clustering algorithm to obtain a theme group; the topic group comprises a plurality of topic vocabularies; and calculating the similarity between the subject vocabulary and the subject connotation according to a preset similarity calculation formula, and clustering the subject vocabulary and the subject connotation according to a preset classification threshold and the similarity to obtain a subject library.
In one embodiment, the classification induction unit is further configured to: acquiring a preset field category and a preset expert experience library; according to the expert experience base and the field categories, determining city physical examination body ranges corresponding to the field categories from the city physical examination knowledge; respectively extracting from the urban physical examination knowledge range through a preset first high-frequency calculation method and a preset second high-frequency calculation method to correspondingly obtain a first keyword group and a second keyword group, and fusing and de-duplicating the first keyword group and the second keyword group to correspondingly obtain field concepts corresponding to all field categories; iteratively extracting to obtain the domain relation among the domain categories according to a preset second external knowledge base, a preset matching method and a preset scoring evaluation formula; and constructing a city physical examination ontology library according to the field concept and the field relation.
In one embodiment, the classification induction unit is further configured to: referring to a preset second external knowledge base, inducing and acquiring the relationship types among the entities, and storing the relationship types and the urban physical examination knowledge into an entity dictionary; matching the city physical examination knowledge with the relationship type by a boot-pulling method, and storing a matching result into a candidate word list; according to a preset scoring evaluation formula, evaluating and scoring the matching result in the candidate word list, and judging whether the evaluation scoring result is converged according to a preset iteration number and a preset convergence precision; and if the evaluation scoring result is converged, outputting the relationship type corresponding to the evaluation scoring result as the field relationship between the corresponding fields.
In one embodiment, the knowledge management apparatus further comprises a supplemental feedback unit to: and reversely supplementing and perfecting the urban physical examination ontology base according to the urban physical examination knowledge base.
Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the method for knowledge management of urban physical examination knowledge as described above.
Wherein, the integrated unit of the knowledge management device can be stored in a computer readable storage medium if the integrated unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and used by a processor to implement the steps of the above embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the units indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
The embodiment of the invention describes a knowledge management device and a computer readable storage medium for city physical examination knowledge, wherein a city physical examination knowledge base is established in a knowledge map form according to a preset multi-department analysis and evaluation index group, city physical examination knowledge instance resources and an associated clustering method from the aspects of theme, indexes and method, so that a standardized frame is established based on different analysis and evaluation indexes, and further the universality and compatibility of knowledge management are realized; further, the knowledge management device and the computer-readable storage medium for the urban physical examination knowledge described in the embodiments of the present invention also provide a method for reverse supplement and improvement of the urban physical examination ontology base in time according to the urban physical examination knowledge base, thereby improving the accuracy of the knowledge management of the urban physical examination knowledge.
Detailed description of the preferred embodiment
Besides the method and the device, the embodiment of the invention also describes a knowledge management system of the urban physical examination knowledge.
Specifically, the knowledge management system comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to realize the knowledge management method of the urban physical examination knowledge.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center for the device and that connects the various parts of the overall device using various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the apparatus by running or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The embodiment of the invention describes a knowledge management system of city physical examination knowledge, which establishes a city physical examination knowledge base in a knowledge map form according to a preset multi-department analysis and evaluation index group, city physical examination knowledge instance resources and an associated clustering method from the aspects of theme, index and method, thereby establishing a standardized frame based on different analysis and evaluation indexes, further realizing the universality and compatibility of knowledge management, and improving the knowledge management efficiency of the city physical examination knowledge; further, the knowledge management system of the urban physical examination knowledge described in the embodiment of the invention also supplements and perfects the urban physical examination ontology base in time in a reverse manner according to the urban physical examination knowledge base, thereby improving the accuracy of the knowledge management of the urban physical examination knowledge.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A knowledge management method for urban physical examination knowledge is characterized by comprising the following steps:
acquiring city physical examination data through a main crawler data acquisition tool, and cleaning the city physical examination data to acquire city physical examination knowledge;
classifying and summarizing the city physical examination knowledge according to a preset field category and a preset expert experience base to obtain a city physical examination ontology base;
constructing an urban physical examination knowledge instance resource according to a preset first external knowledge base and the urban physical examination ontology base;
and establishing an urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis evaluation index group, the urban physical examination knowledge instance resource and an associated clustering method from the aspects of theme, index and method.
2. The knowledge management method of urban physical examination knowledge as claimed in claim 1, wherein the establishing of the urban physical examination knowledge base according to a preset multi-department analysis evaluation index group, the urban physical examination knowledge instance resource and an association clustering method from three aspects of topic, index and method specifically comprises:
acquiring a preset multi-department analysis evaluation index group; the multi-department analysis and evaluation index group comprises analysis and evaluation indexes and corresponding analysis and evaluation index connotations;
calculating the analysis evaluation index by adopting a hidden Dirichlet distribution model to establish an index library;
performing feature mining on the analysis evaluation index content to establish a method library;
extracting the analysis evaluation index according to a correlation clustering method to obtain a theme group, and performing clustering analysis on the theme group to obtain a theme library;
and establishing an urban physical examination knowledge base according to the index base, the method base and the subject base.
3. The knowledge management method of urban physical examination knowledge according to claim 2, wherein the step of classifying and generalizing the urban physical examination knowledge according to a preset domain category and a preset expert experience library to obtain an urban physical examination ontology library specifically comprises:
acquiring a preset field category and a preset expert experience library;
according to the expert experience base and the field categories, determining city physical examination body ranges corresponding to the field categories from the city physical examination knowledge;
respectively extracting from the city physical examination knowledge range through a preset first high-frequency calculation method and a preset second high-frequency calculation method to correspondingly obtain a first key phrase and a second key phrase, and fusing and de-duplicating the first key phrase and the second key phrase to correspondingly obtain field concepts corresponding to all field categories;
iteratively extracting to obtain the domain relation among the domain categories according to a preset second external knowledge base, a preset matching method and a preset score evaluation formula;
and constructing an urban physical examination ontology library according to the field concept and the field relation.
4. The knowledge management method of urban physical examination knowledge according to claim 3, wherein the calculating the analysis evaluation index by using a hidden Dirichlet distribution model to establish an index library specifically comprises:
establishing an analysis evaluation index set according to the analysis evaluation indexes;
performing data preprocessing on the analysis evaluation index set to obtain a department analysis evaluation index set; the department analysis evaluation index set comprises a plurality of department analysis evaluation indexes;
and calculating and confirming index keywords corresponding to the department analysis evaluation indexes according to a hidden Dirichlet distribution model and a preset target function corresponding to the keywords, and establishing an index library according to the entanglement degree, the department analysis evaluation indexes and the index keywords.
5. The knowledge management method of urban physical examination knowledge according to claim 4, wherein the refining of the analysis evaluation index according to an association clustering method to obtain a topic group, and the performing of cluster analysis on the topic group to obtain a topic library specifically comprise:
under the different preset theme connotations, respectively calculating theme semantic similarity, index unit similarity and calculation method similarity according to the analysis and evaluation indexes through JS divergence;
calculating the theme content association degree among the theme contents according to a preset theme content association degree formula, theme semantic similarity, index unit similarity and calculation method similarity;
clustering the theme connotations according to an association clustering algorithm to obtain a theme group; the topic group comprises a plurality of topic vocabularies;
and calculating the similarity between the subject vocabulary and the subject connotation according to a preset similarity calculation formula, and clustering the subject vocabulary and the subject connotation according to a preset classification threshold and the similarity to obtain a subject library.
6. The knowledge management method of urban physical examination knowledge as claimed in claim 5, wherein the iterative extraction is performed according to a preset second external knowledge base, a preset matching method and a preset score evaluation formula to obtain the domain relationship among the domain categories, and specifically comprises:
referring to a preset second external knowledge base, inducing and acquiring the relationship types among the entities, and storing the relationship types and the urban physical examination knowledge into an entity dictionary;
matching the city physical examination knowledge with the relationship type by a boot-pulling method, and storing a matching result into a candidate word list;
according to a preset scoring evaluation formula, evaluating and scoring the matching result in the candidate word list, and judging whether the evaluation scoring result is converged according to a preset iteration number and a preset convergence precision;
and if the evaluation scoring result is converged, outputting the relationship type corresponding to the evaluation scoring result as the field relationship between the corresponding fields.
7. The knowledge management method of urban physical examination knowledge according to any one of claims 1 to 6, wherein the knowledge management method further comprises:
and reversely supplementing and perfecting the urban physical examination ontology base according to the urban physical examination knowledge base.
8. The knowledge management device of the urban physical examination knowledge is characterized by comprising a data acquisition unit, a classification and induction unit, an instance construction unit and a knowledge base establishment unit, wherein,
the data acquisition unit is used for acquiring city physical examination data through a main body crawler data acquisition tool and cleaning the city physical examination data to acquire city physical examination knowledge;
the classification induction unit is used for classifying and inducing the urban physical examination knowledge according to a preset field category and a preset expert experience base to obtain an urban physical examination ontology base;
the example construction unit is used for constructing an urban physical examination knowledge example resource according to a preset first external knowledge base and the urban physical examination ontology base;
the knowledge base establishing unit is used for establishing the urban physical examination knowledge base in a knowledge graph form according to a preset multi-department analysis and evaluation index group, the urban physical examination knowledge instance resources and an associated clustering method from the aspects of theme, indexes and methods.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method for knowledge management of urban medical examination knowledge according to any one of claims 1 to 7.
10. A knowledge management system of urban physical examination knowledge, the knowledge management system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the knowledge management method of urban physical examination knowledge according to any one of claims 1-7 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210647918.XA CN115048531A (en) | 2022-06-09 | 2022-06-09 | Knowledge management method, device and system for urban physical examination knowledge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210647918.XA CN115048531A (en) | 2022-06-09 | 2022-06-09 | Knowledge management method, device and system for urban physical examination knowledge |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115048531A true CN115048531A (en) | 2022-09-13 |
Family
ID=83162045
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210647918.XA Pending CN115048531A (en) | 2022-06-09 | 2022-06-09 | Knowledge management method, device and system for urban physical examination knowledge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115048531A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116307792A (en) * | 2022-10-12 | 2023-06-23 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
-
2022
- 2022-06-09 CN CN202210647918.XA patent/CN115048531A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116307792A (en) * | 2022-10-12 | 2023-06-23 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
CN116307792B (en) * | 2022-10-12 | 2024-03-12 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7930322B2 (en) | Text based schema discovery and information extraction | |
CN106844341B (en) | Artificial intelligence-based news abstract extraction method and device | |
CN116911312B (en) | Task type dialogue system and implementation method thereof | |
CN110297893A (en) | Natural language question-answering method, device, computer installation and storage medium | |
CN116701431A (en) | Data retrieval method and system based on large language model | |
CN103106262A (en) | Method and device of file classification and generation of support vector machine model | |
CN111797222A (en) | Course knowledge graph construction method, device, terminal and storage medium | |
CN110955766A (en) | Method and system for automatically expanding intelligent customer service standard problem pairs | |
CN111460145A (en) | Learning resource recommendation method, device and storage medium | |
CN112800213A (en) | Medical text information display method and device and electronic equipment | |
CN112907358A (en) | Loan user credit scoring method, loan user credit scoring device, computer equipment and storage medium | |
CN115048531A (en) | Knowledge management method, device and system for urban physical examination knowledge | |
Wei et al. | Online education recommendation model based on user behavior data analysis | |
CN116049376B (en) | Method, device and system for retrieving and replying information and creating knowledge | |
CN110888983B (en) | Positive and negative emotion analysis method, terminal equipment and storage medium | |
CN117216214A (en) | Question and answer extraction generation method, device, equipment and medium | |
CN114842982B (en) | Knowledge expression method, device and system for medical information system | |
CN114528378A (en) | Text classification method and device, electronic equipment and storage medium | |
CN113988878A (en) | Graph database technology-based anti-fraud method and system | |
Mahalakshmi et al. | Context based retrieval of scientific publications via reader lens | |
CN116595192B (en) | Technological front information acquisition method and device, electronic equipment and readable storage medium | |
CN117573956B (en) | Metadata management method, device, equipment and storage medium | |
CN114722163B (en) | Data query method and device, electronic equipment and storage medium | |
CN116910175B (en) | Method, device and storage medium for constructing fault level tree of automatic mobile equipment | |
CN112579841B (en) | Multi-mode database establishment method, retrieval method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |