CN112948595B - Urban group running state knowledge graph construction method, system and equipment - Google Patents
Urban group running state knowledge graph construction method, system and equipment Download PDFInfo
- Publication number
- CN112948595B CN112948595B CN202110337746.1A CN202110337746A CN112948595B CN 112948595 B CN112948595 B CN 112948595B CN 202110337746 A CN202110337746 A CN 202110337746A CN 112948595 B CN112948595 B CN 112948595B
- Authority
- CN
- China
- Prior art keywords
- index
- urban
- data
- city
- group operation
- 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
- 238000010276 construction Methods 0.000 title claims description 39
- 238000000605 extraction Methods 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 7
- 238000012351 Integrated analysis Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005065 mining Methods 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 abstract description 4
- 238000004445 quantitative analysis Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000005441 aurora Substances 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000019580 granularity Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of big data, in particular relates to a method, a system and equipment for constructing an urban group operation state knowledge graph, and aims to solve the problem that the existing method lacks comprehensive quantitative analysis on the urban group operation states in various fields and cannot meet the requirement of deep mining on the urban group operation rules. The invention comprises the following steps: and acquiring multi-source heterogeneous urban group operation data, converting the multi-source heterogeneous urban group operation data into an urban group operation space-time data set, dividing the urban group operation space-time data set into subsets, determining general urban group operation state indexes based on the space-time data subsets, calculating index weights based on the general urban group operation state indexes and combining urban characteristics, and constructing an urban group operation state index system to further construct an urban group operation state knowledge graph. The method realizes the extraction of potential relations among the operation elements in the urban mass and provides technical improvement for the deep mining of the urban mass operation rule.
Description
Technical Field
The invention belongs to the technical field of big data, and particularly relates to a method, a system and equipment for constructing an urban group operation state knowledge graph.
Background
Urban clusters are important development directions of urbanization, and construction and operation decisions of the urban clusters need to analyze multi-source heterogeneous data in various fields. With the rise of the internet of things, how to extract, organize, store, analyze and display mass data and to mine urban mass operation rules from the mass data is a problem to be solved. In the prior art, the running state of the urban mass is analyzed, namely, a specific field of the urban mass is usually selected for data mining analysis, or qualitative description is carried out on a plurality of fields, and the comprehensive quantitative analysis on the running state of each field of the urban mass is absent, so that the requirement of deep mining on the running rule of the urban mass cannot be met. In addition, with respect to analysis of urban mass operational states, there are often problems of neglecting synergy between cities and coupling across domains.
A knowledge graph is a knowledge base that uses a graph model to describe the relationships between knowledge and modeled things. In one aspect, knowledge maps can model and describe data of different sources, types, and structures using more canonical and standard conceptual models, ontology terms, and grammatical formats; on the other hand, the knowledge graph can enhance the association between data through semantic links, so that knowledge data is systemized and relational. The data with the expression specification and strong relevance can play an important role in improving the aspects of retrieval, data analysis, auxiliary decision making, supporting reasoning and the like. However, at present, in the field of smart city groups, no mature research on building a knowledge graph for the running state of the city group has yet occurred.
Disclosure of Invention
In order to solve the above problems in the prior art, namely that the prior art usually only performs data mining analysis on specific fields or performs qualitative description on a plurality of fields, and lacks comprehensive quantitative analysis on the running states of each field of the urban group, the requirement of deep mining on the running rule of the urban group cannot be met, and the problems of cooperation among cities, coupling across fields and the like are ignored, the invention provides a method for constructing a knowledge graph of the running states of the urban group, which comprises the following steps:
step S100, acquiring multi-source heterogeneous city group operation data;
step S200, converting the multi-source heterogeneous city group operation data into a city group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
step S300, constructing a general city group operation state index frame based on the space-time data subsets;
step S400, calculating index weight based on the general urban group operation state index frame and the space-time data subset and combining the urban group characteristics;
step S500, representing the running state of the urban mass based on a general urban mass running state index frame and each index weight of the urban mass running index system, and constructing the urban mass running state index system;
and step S600, performing entity extraction, entity relation extraction, entity attribute extraction and relation attribute extraction on the basis of the urban group operation state index system and the space-time data set, and constructing an urban group operation state knowledge graph.
In some preferred embodiments, the acquiring multi-source heterogeneous urban mass operational data further comprises padding, smoothing, merging, normalizing and checking consistency processing of the acquired data.
In some preferred embodiments, the city group operation status indicator includes q primary indicators, each primary indicator includes p secondary indicators, each secondary indicator sets a forward or reverse label, the forward label indicates that the larger the value is, the better the city group operation status is, the reverse label indicates that the larger the value is, the worse the city group operation status is, and p and q indicate natural numbers, and specific values are not particularly limited.
In some preferred embodiments, the specific steps of step S400 include:
step S410, carrying out standardization processing on different property data in the running state index system to obtain a standardized value of the index, wherein the method comprises the following steps:
wherein I is ab Representing the true value of the b-th indicator in the a-th city,
a normalized value representing the b index in the a-th city, e representing the base of the natural logarithm;
step S420, calculating contribution values of m cities in the city group to each index based on the standardized values of the indexes:
wherein P is ab Indicating the contribution degree of the a-th city to the b-th index;
step S430, calculating the total contribution amount of m cities in the group to all indexes based on the contribution values of m cities in the urban group to all indexes:
wherein S is b Representing the total contribution amount of m cities in the city group to the index b;
step S440, calculating each index weight of the city group operation index system based on the total contribution amount of the m cities to all indexes;
wherein W is b And (3) representing the weight of an index b in the urban group operation index system, wherein when the index is a forward index, the r value is 1, otherwise, the r value is-1, and z represents the total number of the urban operation indexes.
In some preferred embodiments, the city group operating state is expressed as:
wherein I' b A standardized value representing the running index b of the city group, and a numerical value I of the index b b Obtained after normalization treatment, the numerical value I of the index b b Is obtained by integrated analysis of city group operation data.
In some preferred embodiments, the building of the urban mass running state knowledge graph includes the specific steps of:
and determining each entity as a node, determining the entity relationship as a directed line segment, setting the attribute corresponding to the entity as a node attribute, and constructing a city group running state knowledge graph according to each node, the directed line segment and the node attribute.
In some preferred embodiments, the entity extraction comprises the specific steps of: writing an entity template by a method based on rules and a dictionary, and matching the corpus of the urban group operation index system by combining a heuristic algorithm to obtain an index entity;
the method comprises the steps of carrying out recognition of data entities based on a natural language model and artificial rules by a knowledge extraction method combining manual and automatic, and carrying out knowledge extraction on a time space data subset to obtain the data entities;
the entity relation extraction is carried out by a rule-based method based on the index entity and the data entity; the method comprises the steps of relation among entities, relation between index entities and data entities and relation among data entities; the relation between the upper and lower indexes is also included;
the entity attribute extraction and the relation attribute extraction are used for constructing an urban group operation entity attribute list and a relation attribute list, and comprise names, definitions, calculation methods, numerical values and forward and reverse directions.
In another aspect of the present invention, a system for constructing a knowledge graph of an urban mass running state is provided, the system comprising: the system comprises a data acquisition module, a space-time data dividing module, an index framework construction module, a weight calculation module, an operation state index system construction module and a knowledge graph construction module;
the data acquisition module is configured to acquire multi-source heterogeneous city group operation data;
the space-time data dividing module is configured to convert the multi-source heterogeneous urban group operation data into an urban group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
the index framework construction module is configured to determine a general city group operation state index based on the space-time data subset;
the weight calculation module is configured to calculate index weights based on the general city group running state indexes and combining city group characteristics;
the running state index system construction module is configured to represent the running state of a city based on the standardized value of the actual value of the index and each index weight of the running index system of the city group, and construct the running state index system of the city group;
the knowledge graph construction module is configured to construct a knowledge graph of the running state of the city group based on the running state index system of the city group and the space-time data subset, the extraction entity, the relation of the extraction entity and the attribute corresponding to the extraction entity.
A third aspect of the present invention provides an electronic device, including: at least one processor; and a memory communicatively coupled to at least one of the processors; the memory stores instructions executable by the processor, where the instructions are configured to be executed by the processor to implement the urban mass running state knowledge graph construction method described above.
In a fourth aspect of the present invention, a computer readable storage medium is provided, where the computer readable storage medium stores computer instructions, where the computer instructions are used to be executed by the computer to implement the above-mentioned urban mass running state knowledge graph construction method.
The invention has the beneficial effects that:
(1) The method for constructing the urban mass running state knowledge graph, which is disclosed by the invention, has the advantages that the constructed knowledge graph realizes the extraction of potential relations among all running elements in the urban mass, not only relates to the interaction of different service fields, but also comprises running rules such as inter-city competition, cooperation and the like which cannot be embodied by a common urban knowledge graph, so that technical improvement is provided for the deep mining of the running rules of the urban mass, and the problem of insufficient retrieval effect in the analysis of the big data of the urban mass is solved;
(2) According to the urban group operation state knowledge graph construction method, the weights of the indexes are obtained through the improved weight calculation method, so that an urban group operation state index system is constructed, and the operation state of an urban group is quantitatively evaluated in all directions.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings, in which:
FIG. 1 is a schematic flow chart of a method for constructing a knowledge graph of urban mass running state in an embodiment of the invention;
FIG. 2 is a schematic diagram of a general city group operation state index framework established by a city group operation state knowledge graph construction method in an embodiment of the invention;
fig. 3 is a schematic diagram of knowledge graph entities, relationships and attribute principles of a knowledge graph construction method for urban mass running state in an embodiment of the invention;
fig. 4 is a block diagram of a system for constructing an aurora state knowledge graph of an urban mass according to an embodiment of the invention.
Detailed Description
The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The invention provides a method for constructing a city group operation state knowledge graph, which comprises the following steps:
step S100, acquiring multi-source heterogeneous city group operation data;
step S200, converting the multi-source heterogeneous city group operation data into a city group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
step S300, constructing a general city group operation state index frame based on the space-time data subsets;
step S400, calculating index weight based on the general city group operation state index frame and combining city group characteristics;
step S500, representing the running state of the urban mass based on a general urban mass running state index frame and each index weight of the urban mass running index system, and constructing the urban mass running state index system;
and step S600, performing entity extraction, entity relation extraction, entity attribute extraction and relation attribute extraction based on the urban group operation state index system and the space-time data subsets, and constructing an urban group operation state knowledge graph.
The urban group operation state knowledge graph construction method constructs an index system of the urban group operation state, quantitatively evaluates the operation state of the urban group in an omnibearing manner, solves the problem of poor retrieval effect in urban group big data analysis, realizes extraction of potential relations among all operation elements in the urban group, and provides technical improvement for deep mining of the urban group operation rule.
In order to more clearly describe the method for constructing the urban mass running state knowledge graph of the present invention, each step in the embodiment of the present invention is described in detail below with reference to fig. 1.
The city group operation state knowledge graph construction method of the first embodiment of the invention comprises the steps S100-S600, and each step is described in detail as follows:
in this embodiment, the method further includes padding, smoothing, merging, normalizing and checking consistency processing on the collected data so as to obtain high-quality city group operation data.
Step S100, acquiring multi-source heterogeneous city group operation data;
in this embodiment, the heterogeneous city group operation data includes historical data and real-time data of at least two business fields. The data of the business fields include public data (such as social data and encyclopedic data) obtained through each data platform on the network, government service data (such as land utilization data and public transportation data), business data (such as map POI data and enterprise directory), such as business data of education, medical treatment, transportation, industry, finance, culture, ecology, population, land, social media and the like, and the business fields can also comprise other field definitions without being limited in particular.
Step S200, converting the multi-source heterogeneous city group operation data into a city group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
in this embodiment, the spatio-temporal data may refer to data having both time and space dimensions, and the urban mass running data mostly includes geographic location information and time information with different granularities. The spatiotemporal data format may be a tuple format comprising data entity information, a timestamp, spatial coordinates, for example, the spatiotemporal data format of population number may be expressed as { population number, timestamp, spatial coordinates }. The spatial coordinates include real world geospatial coordinates and also include network addresses of the network world, such as physical addresses of computer devices. Because the city group consists of relatively independent cities with definite geography and administrative boundaries, the city group operation data can be divided into data inside each city and data flowing mutually between cities; the city group operation spatiotemporal dataset may be divided into spatiotemporal data subsets. The above-mentioned city operation data converted by the space-time data format has time, space and domain attributes, and has subset labels after being divided into subsets, for example, the space-time label data format of traffic flow can be expressed as { traffic flow, time stamp, space coordinates } [ city inside/city between two cities inside the city group ].
In this embodiment, urban group operation service field data is divided into subsets by taking a city as a unit, and city labels are added to space-time data so as to construct a more perfect urban group operation state knowledge graph. By adopting the method, not only can effective technical improvement be provided for the running rule of the urban mass and the excavation of potential relations among cities, but also data support can be provided for the related application service of the smart urban mass, and meanwhile, convenience is provided for the maintenance and updating of the follow-up knowledge graph.
The set of spatio-temporal data and the subset of spatio-temporal data may be used to extract the city group operational data entity.
Step S300, constructing a general city group operation state index frame based on the space-time data subsets;
in this embodiment, the city group operation state index framework and the space-time data subset include q primary indexes, each primary index branch has p secondary indexes, each secondary index sets a forward or reverse label, the forward label indicates that the larger the numerical value is, the better the city group operation state is, the larger the numerical value is, the worse the city group operation state is, and p and q are natural numbers.
In this embodiment, as shown in fig. 2, the present application comprehensively considers each field of operation of the smart city group and the cooperative characteristics of the cross-city area, and the constructed city group operation state index system is composed of 8 primary index classifications and 46 secondary indexes according to the principles of scientificity, layering, relativity, definiteness and operability. Each secondary index has an index label of "forward direction" or "reverse direction", wherein the larger the corresponding index value is, the better the running state of the urban group is, and the worse the corresponding index value is, the larger the running state of the urban group is.
In particular, the primary index may be education, medical, traffic, cultural, ecological, economical, safe, virtual space.
The first-level index is classified into 5 second-level indexes, namely, high-quality educational resource coverage degree, per-person education investment amount, educational resource balanced allocation degree, per-person primary and secondary school teacher number and common high-school student number.
The first-level index is classified into 5 second-level indexes, which can be the number of hospital beds, the number of medical investments, the number of doctors in each department, the satisfaction of resident medical treatment and the ratio of medical treatment in different places.
The first-level index is classified into 7 second-level indexes, which can be expressway network density, average road area, one-hour traffic circle coverage area, high-speed railway station 20km radius coverage, cross-city public traffic mileage, highway passenger-cargo traffic volume and traffic jam index.
The primary index is classified into 8 secondary indexes under 'cultural' classification, namely the number of patents of people's average invention, the expenditure of R & D (Research and Development), the number of R & D personnel, the number of high-level scientific research papers, the book collection of people's average public library, the coverage and use rate of people's average entertainment facilities, the coverage and use rate of sports facilities and the number of points of people's tourism.
The primary index is classified into 7 secondary indexes under the 'ecological' classification, namely, the air quality index, the water consumption of a unit GDP (Gross Domestic Product), the urban domestic garbage treatment capacity, the urban domestic sewage treatment rate, the greening coverage rate of a built-up area, the cross-market environmental protection treatment rate and the product yield value of three wastes are comprehensively utilized.
The first-level index is classified into 6 second-level indexes under the 'economy' category, namely the difference degree of an industrial structure, the regional distribution quantity of industrial carriers, the space synergy degree of two industries and three industries, the average GDP of people, the average wages of workers and the investment quantity of crossing cities.
The first-level index is classified into 6 second-level indexes under the 'safety' classification, namely crime rate, emergency event processing efficiency, case setting rate across markets, natural disaster response efficiency, food and medicine safety accident rate and public facility integrity.
The first-level index is classified into a virtual space, and the virtual space is classified into 2 second-level indexes, namely network public opinion synergetic degree and network competitive index.
The universal city group operation state index system can be suitable for evaluating the operation states of most city groups at home and abroad, and can provide universal evaluation standards for construction and operation management effects of smart cities and smart city groups.
Step S400, calculating index weight based on the general city group operation state index frame and combining city group characteristics;
before the weight calculation of the urban group operation state index system is carried out, the urban group operation data is subjected to integrated analysis by using a big data integrated analysis method according to the general urban group operation index system so as to obtain index values.
The big data integrated analysis method can be statistical inference, visual analysis, classification and regression, naive Bayes, support vector machine, random forest, clustering and other methods.
The method comprises the following specific steps: step S410, carrying out standardization processing on different property data in the running state index system to obtain a standardized value of the index, wherein the method comprises the following steps:
wherein I is ab Representing the true value of the b-th indicator in the a-th city,
a normalized value representing the b-th index in the a-th city;
step S420, calculating contribution values of m cities in the city group to each index based on the standardized values of the indexes:
wherein P is ab Indicating the contribution degree of the a-th city to the b-th index;
step S430, calculating the total contribution amount of m cities in the group to all indexes based on the contribution values of the cities to the indexes:
wherein S is b Representing the total contribution amount of m cities in the city group to the index b;
step S440, calculating each index weight of the city group operation index system based on the total contribution amount of the m cities to all indexes;
wherein W is b And (3) representing the weight of an index b in the urban group operation index system, wherein when the index is a forward index, the r value is 1, otherwise, the r value is-1, and z represents the total number of the urban operation indexes.
Step S500, representing the running state of the urban mass based on a general urban mass running state index frame and each index weight of the urban mass running index system, and constructing the urban mass running state index system;
in this embodiment, the city group operation status is expressed as:
wherein I' b A standardized value representing the running index b of the city group, and a numerical value D of the index b b Obtained after standardized treatment, anThe value I of the index b b Is obtained by integrated analysis of city group operation data.
And step S600, performing entity extraction, entity relation extraction, entity attribute extraction and relation attribute extraction based on the urban group operation state index system and the space-time data subsets, and constructing an urban group operation state knowledge graph. The invention extracts knowledge from the index system, can directly show the coordination and competition relationship among cities, and can store the index value in the database, and can search and retrieve information at the same time.
In this embodiment, as shown in fig. 3, the extracting entity includes the specific steps of: writing an entity template by a method based on rules and the points, and matching the corpus of the urban group operation index system by combining a heuristic algorithm to obtain an index entity; for example, the primary index "traffic" and the secondary index "highway network density" in the city group operation index system can be extracted as index entities.
The method comprises the steps of carrying out recognition of data entities based on a natural language model and artificial rules by a knowledge extraction method combining manual and automatic, and carrying out knowledge extraction on a time space data subset to obtain the data entities; for example, traffic domain data of urban mass operation, such as railway network data, rail traffic operation data, etc., such as population data of urban mass operation, etc., are obtained in the data acquisition and format conversion stage, and may be extracted as data entities.
The urban group operation status field data is divided into data subsets, and each field data subset with different subset labels can also be extracted as data entities, for example, the population data of the urban group in the Guangdong, the Yue-hong, the Dawan, the Guangdong, the Shenzhen, the Buddha, the Zhuhe, the Huizhou, the Dongguan, the Zhongshan, the Jiangmen, the Zhaoqing, the hong Kong, the Australian, and the subsets of the urban group operation population data in the Yue-hong can be extracted as data entities.
The entity relation extraction is carried out by a rule-based method based on the index entity and the data entity; the method comprises the steps of relation among entities, relation between index entities and data entities and relation among data entities; the relation between the upper and lower indexes is also included;
specifically, the relationship between index entities may be a relationship between an upper level index and a lower level index, for example, the index entity "traffic" is an upper level index of the index entity "people average road area" and is a lower level index of the index entity "city group running state". The relationship between the index entity and the data entity has a use and used relationship, for example, the "population data" entity is used by the index entity "people average road area". The relationships between data entities are inclusive and inclusive, e.g., "Guangzhou demographic data subset" entities are included in "demographic data".
The entity attribute extraction and the relation attribute extraction are used for constructing an urban group operation entity attribute list and a relation attribute list, and comprise names, definitions, calculation methods, numerical values and forward and reverse directions. Attributes such as index entities include name, definition, calculation method, numerical value, forward and reverse, etc. The attribute of the index entity may be the name, definition, value, calculation method, etc. of the index. The attributes of the data entity may be the name, data content, storage format, source, purpose, subset tag, etc. of the item of data. The urban group operation state knowledge map entity attribute is mainly extracted from a semi-structured database and an unstructured database of urban annual certificates, government data open platforms, urban group operation related research documents and the like.
The city group knowledge graph construction provided by the invention is different from the conventional city knowledge graph construction in that: the city group is not an administrative division city, but rather the city is an administrative division;
the city group is a higher regional hierarchy than the city, and besides the independent information of a plurality of cities and the connection of indexes in the cities, the city group also comprises information rules such as business, collaboration, competition and collaboration among the cities, and the city group is regarded as a whole. And the urban knowledge graph only contains knowledge of different business fields (traffic, population, education, etc.).
In this embodiment, each entity is determined as a node, the entity relationship is determined as a directed line segment, the attribute corresponding to the entity is set as a node attribute, and a city group operation state knowledge graph is constructed according to each node, the directed line segment and the node attribute.
The system for constructing the urban mass running state knowledge graph according to the second embodiment of the invention, as shown in fig. 4, comprises: the system comprises a data acquisition module, a space-time data dividing module, an index framework construction module, a weight calculation module, an operation state index system construction module and a knowledge graph construction module;
the data acquisition module is configured to acquire multi-source heterogeneous city group operation data;
the space-time data dividing module is configured to convert the multi-source heterogeneous urban group operation data into an urban group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
the index framework construction module is configured to determine a general city group operation state index based on the space-time data subset;
the weight calculation module is configured to calculate index weights based on the general city group running state indexes and combining city group characteristics;
the running state index system construction module is configured to represent the running state of the city based on the standardized value of the actual value of the index and each index weight of the running index system of the city, and construct a running state index system of the city group;
the knowledge graph construction module is configured to construct a knowledge graph of the running state of the city group by extracting entities, extracting entity relations and attributes corresponding to the extracting entities based on the running state index system of the city group and the space-time data subsets
It will be clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the system described above and the related description may refer to the corresponding process in the foregoing method embodiment, which is not repeated here.
It should be noted that, in the system for constructing the urban mass running state knowledge graph provided in the foregoing embodiment, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the modules or steps in the foregoing embodiment of the present invention are further decomposed or combined, for example, the modules in the foregoing embodiment may be combined into one module, or may be further decomposed into a plurality of sub-modules, so as to complete all or part of the functions described above. The names of the modules and steps related to the embodiments of the present invention are merely for distinguishing the respective modules or steps, and are not to be construed as unduly limiting the present invention.
An electronic device according to a third embodiment of the present invention includes: at least one processor; and a memory communicatively coupled to at least one of the processors; the memory stores instructions executable by the processor, where the instructions are configured to be executed by the processor to implement the urban mass running state knowledge graph construction method described above.
A computer readable storage medium according to a fourth embodiment of the present invention is characterized in that the computer readable storage medium stores computer instructions for execution by the computer to implement the above-described urban mass running state knowledge graph construction method.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the storage device and the processing device described above and the related description may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The terms "first," "second," and the like, are used for distinguishing between similar objects and not for describing a particular sequential or chronological order.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus/apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus/apparatus.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
Claims (9)
1. The method for constructing the urban mass running state knowledge graph is characterized by comprising the following steps:
step S100, acquiring multi-source heterogeneous city group operation data;
step S200, converting the multi-source heterogeneous city group operation data into a city group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
step S300, constructing a general city group operation state index frame based on the space-time data subsets;
step S400, calculating each index weight of the urban group operation index system by combining the urban group characteristics based on the general urban group operation state index frame and the space-time data subsets;
step S500, representing the running state of the urban mass based on a general urban mass running state index frame and each index weight of the urban mass running index system, and constructing the urban mass running state index system;
step S600, based on the urban group operation state index system and the space-time data set, entity extraction, entity relation extraction, entity attribute extraction and relation attribute extraction are carried out, and an urban group operation state knowledge graph is constructed;
the entity extraction comprises the following specific steps: writing an entity template by a method based on rules and the points, and matching the corpus of the urban group operation index system by combining a heuristic algorithm to obtain an index entity;
the method comprises the steps of carrying out recognition of data entities based on a natural language model and artificial rules by a knowledge extraction method combining manual and automatic, and carrying out knowledge extraction on a time space data subset to obtain the data entities;
the entity relation extraction is based on the index entity and the data entity, and relation extraction is carried out by a rule-based method; the method comprises the steps of relation among entities, relation between index entities and data entities and relation among data entities; the relation between the upper and lower indexes is also included;
the entity attribute extraction and the relation attribute extraction are used for constructing an urban group operation entity attribute list and a relation attribute list, and comprise names, definitions, calculation methods, numerical values and forward and reverse directions.
2. The method for constructing a knowledge graph of urban mass operation state according to claim 1, wherein the obtaining multi-source heterogeneous urban mass operation data further comprises filling, smoothing, merging, normalizing and checking consistency of the collected data.
3. The method for constructing a city group operation state knowledge graph according to claim 1, wherein the city group operation state indexes comprise q primary indexes, each primary index branch has p secondary indexes, each secondary index is provided with a forward or reverse label, the forward label indicates that the larger the value is, the better the city group operation state is, the worse the reverse label indicates that the larger the value is, and p and q are natural numbers.
4. The urban mass transit state knowledge graph construction method according to claim 3, wherein the specific steps of step S400 include:
step S410, carrying out standardization processing on different property data in the running state index system to obtain a standardized value of the index, wherein the method comprises the following steps:
wherein I is ab Representing the true value of the b-th indicator in the a-th city,
a normalized value representing the b index in the a-th city, e representing the base of the natural logarithm;
step S420, calculating contribution values of m cities in the city group to each index based on the standardized values of the indexes:
wherein P is ab Indicating the contribution degree of the a-th city to the b-th index;
step S430, calculating the total contribution amount of m cities in the city group to each index based on the contribution values of the cities to the indexes:
wherein S is b Representing the total contribution amount of m cities in the city group to the index b;
step S440, calculating each index weight of the city group operation index system based on the total contribution amount of the m cities to all indexes;
wherein W is b And (3) representing the weight of an index b in the urban group operation index system, wherein when the index is a forward index, the r value is 1, otherwise, the r value is-1, and z represents the total number of the urban operation indexes.
5. The urban mass operation state knowledge graph construction method according to claim 4, wherein the urban mass operation state is expressed as:
wherein I' b A standardized value representing the running index b of the city group, and a numerical value I of the index b b Obtained after normalization treatment, the numerical value I of the index b b Is obtained by integrated analysis of city group operation data.
6. The urban mass transit state knowledge graph construction method according to claim 1, wherein the constructing the urban mass transit state knowledge graph comprises the specific steps of:
and determining each entity as a node, determining the entity relationship as a directed line segment, setting the attribute corresponding to the entity as a node attribute, and constructing a city group running state knowledge graph according to each node, the directed line segment and the node attribute.
7. A city group operational state knowledge graph construction system, the system comprising: the system comprises a data acquisition module, a space-time data dividing module, an index framework construction module, a weight calculation module, an operation state index system construction module and a knowledge graph construction module;
the data acquisition module is configured to acquire multi-source heterogeneous city group operation data;
the space-time data dividing module is configured to convert the multi-source heterogeneous urban group operation data into an urban group operation space-time data set; the city group operation space-time data set comprises a plurality of space-time data subsets;
wherein k=1, 2, …, n; n represents the number of urban group operation business fields; i=1, 2, …, m; j=1, 2, …, m; m represents the number of cities in the city group; when i is not equal to j,
representing a subset of the inter-flow data between city i and city j in the city group k domain data; when i=j, _j->
Representing a subset of the city i internal data in the city group k domain data;
the index framework construction module is configured to construct a general city group operation state index framework based on the space-time data subsets;
the weight calculation module is configured to calculate index weights based on the general city group operation state index frame and the space-time data subset and combining city group characteristics;
the running state index system construction module is configured to represent the running state of the urban group based on a general urban group running state index frame and each index weight of the urban group running index system, and construct the urban group running state index system;
the knowledge graph construction module is configured to construct a knowledge graph of the running state of the urban mass based on the running state index system of the urban mass and the space-time data subset, the extraction entity, the relation of the extraction entity and the attribute corresponding to the extraction entity;
the entity extraction comprises the following specific steps: writing an entity template by a method based on rules and the points, and matching the corpus of the urban group operation index system by combining a heuristic algorithm to obtain an index entity;
the method comprises the steps of carrying out recognition of data entities based on a natural language model and artificial rules by a knowledge extraction method combining manual and automatic, and carrying out knowledge extraction on a time space data subset to obtain the data entities;
the entity relation extraction is based on the index entity and the data entity, and relation extraction is carried out by a rule-based method; the method comprises the steps of relation among entities, relation between index entities and data entities and relation among data entities; the relation between the upper and lower indexes is also included;
the entity attribute extraction and the relation attribute extraction are used for constructing an urban group operation entity attribute list and a relation attribute list, and comprise names, definitions, calculation methods, numerical values and forward and reverse directions.
8. An electronic device, comprising: at least one processor; and a memory communicatively coupled to at least one of the processors; wherein the memory stores instructions executable by the processor for execution by the processor to implement the urban mass run state knowledge graph construction method of any one of claims 1-6.
9. A computer-readable storage medium storing computer instructions for execution by the computer to implement the urban mass run state knowledge graph construction method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110337746.1A CN112948595B (en) | 2021-03-30 | 2021-03-30 | Urban group running state knowledge graph construction method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110337746.1A CN112948595B (en) | 2021-03-30 | 2021-03-30 | Urban group running state knowledge graph construction method, system and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112948595A CN112948595A (en) | 2021-06-11 |
| CN112948595B true CN112948595B (en) | 2023-04-25 |
Family
ID=76227405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110337746.1A Active CN112948595B (en) | 2021-03-30 | 2021-03-30 | Urban group running state knowledge graph construction method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112948595B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657848B (en) * | 2021-07-19 | 2023-08-18 | 武汉理工大学 | Method, system, device and medium for shunting industrial three-waste treatment task |
| CN113901238B (en) * | 2021-12-07 | 2022-02-18 | 武大吉奥信息技术有限公司 | City physical examination index knowledge graph construction method and system |
| CN114925833B (en) * | 2022-04-20 | 2023-07-21 | 中国人民解放军91977部队 | Target state rule knowledge mining method based on capability data base graph |
| CN115099722B (en) * | 2022-08-24 | 2022-11-18 | 自然资源部第三航测遥感院 | Knowledge pedigree-based homeland space planning index model management and application method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112070304A (en) * | 2020-09-09 | 2020-12-11 | 深圳大学 | City group element interaction measuring method, equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9704104B2 (en) * | 2015-02-20 | 2017-07-11 | International Business Machines Corporation | Confidence weighting of complex relationships in unstructured data |
| US10664757B2 (en) * | 2015-09-16 | 2020-05-26 | International Business Machines Corporation | Cognitive operations based on empirically constructed knowledge graphs |
| CN106934032B (en) * | 2017-03-14 | 2019-10-18 | 北京软通智城科技有限公司 | A kind of city knowledge mapping construction method and device |
| CN110472066B (en) * | 2019-08-07 | 2022-03-25 | 北京大学 | Construction method of urban geographic semantic knowledge map |
| CN111191040A (en) * | 2019-11-13 | 2020-05-22 | 腾讯科技（深圳）有限公司 | City operation knowledge graph construction method and device and computer equipment |
| CN112131275B (en) * | 2020-09-23 | 2023-07-25 | 长三角信息智能创新研究院 | Enterprise portrait construction method of holographic city big data model and knowledge graph |
-
2021
- 2021-03-30 CN CN202110337746.1A patent/CN112948595B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112070304A (en) * | 2020-09-09 | 2020-12-11 | 深圳大学 | City group element interaction measuring method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112948595A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112948595B (en) | Urban group running state knowledge graph construction method, system and equipment | |
| CN107092680B (en) | Government affair information resource integration method based on geographic grids | |
| Janowicz et al. | Know, Know Where, KnowWhereGraph: A densely connected, cross-domain knowledge graph and geo-enrichment service stack for applications in environmental intelligence | |
| Wu et al. | Analyzing spatial heterogeneity of housing prices using large datasets | |
| Gude et al. | Rates and drivers of rural residential development in the Greater Yellowstone | |
| Zheng et al. | Guidelines on developing performance metrics for evaluating transportation sustainability | |
| Chen et al. | An ontology-based spatial data harmonisation for urban analytics | |
| CN108710625A (en) | A kind of special topic knowledge automatic mining system and method | |
| Chaudhry et al. | Automatic identification of urban settlement boundaries for multiple representation databases | |
| Dická et al. | Rural and non-rural municipalities in the Slovak Republic | |
| Klungboonkrong et al. | A microcomputer-based-system for multicriteria environmental impacts evaluation of urban road networks | |
| Dang et al. | Comparative study of city-level sustainability assessment standards in China and the United States | |
| CN115098696A (en) | Method and device for constructing urban physical examination knowledge graph and storage medium | |
| Kuznichenko et al. | Development of a multi-criteria model for making decisions on the location of solid waste landfills | |
| CN112508332A (en) | Gradual rural settlement renovation partitioning method considering multidimensional characteristics | |
| CN114819589A (en) | Urban space high-quality utilization determination method, system, computer equipment and terminal | |
| Pampoore-Thampi et al. | Mining GIS data to predict urban sprawl | |
| Xie et al. | Estimation of entity‐level land use and its application in urban sectoral land use footprint: A bottom‐up model with emerging geospatial data | |
| Vasconcelos et al. | The utility of open-access biodiversity information in representing anurans in the Brazilian Atlantic Forest and Cerrado | |
| Duan et al. | Urban flood vulnerability Knowledge-Graph based on remote sensing and textual bimodal data fusion | |
| Yu et al. | A comprehensive evaluation method for the site selection of new healthcare facilities in geological hazard-prone areas | |
| Colucci et al. | Minor historical centres ontology enrichment and population: An hamlet case study | |
| Krpan et al. | FUNCTIONAL-NODAL METHOD OF THE DEVELOPMENT OF STRATEGIC SPATIAL PLANNING DOCUMENTATION. | |
| Manso-Callejo et al. | Automatic metadata creation for supporting interoperability levels of spatial data infrastructures | |
| Kent et al. | Almost Automating the Planner: Florida Department of Transportation’s Approach to Understanding Places through Context Classification |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |