CN114896425A - City knowledge archive construction method and system based on city brain - Google Patents
City knowledge archive construction method and system based on city brain Download PDFInfo
- Publication number
- CN114896425A CN114896425A CN202210822068.2A CN202210822068A CN114896425A CN 114896425 A CN114896425 A CN 114896425A CN 202210822068 A CN202210822068 A CN 202210822068A CN 114896425 A CN114896425 A CN 114896425A
- Authority
- CN
- China
- Prior art keywords
- node
- attribute
- importance
- archive
- information
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a city knowledge archive construction method and system based on a city brain, which are applied to the technical field of data processing, and the method comprises the following steps: the method comprises the steps of acquiring and collecting archive information of different areas by acquiring urban areas. And constructing an archive knowledge base according to the acquired archive information, wherein the archive knowledge base has a knowledge map topological structure. And traversing the topological structure of the knowledge graph to obtain the node cluster. And traversing the node clusters to evaluate the importance degree to obtain an importance degree set. And carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result. And adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base. The method solves the technical problem that in the prior art, data of all dimensions are simply collected, sorted and stored, and the preprocessing mode is simple classification, so that the reference value of the data serving as the urban knowledge archive is low.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a city knowledge file construction method and system based on a city brain.
Background
The urban brain is an open intelligent operation platform which is constructed based on new-generation information technologies such as cloud computing, big data, Internet of things and artificial intelligence and supports economic, social and government digital transformation. The city file records some characters, images, sounds and other information which have recording value to the country and the society in the activities of politics, military, economy, science, technology, culture, religion and the like in a city within a certain historical period.
However, in the prior art, the construction of the city archive only simply collects, arranges and stores data of each dimension, calls the data when necessary, and does not preprocess the data of each dimension, so that the reference value of the city archive is low.
Therefore, in the prior art, data of each dimension is simply collected, sorted and stored, and the preprocessing mode is simply classification, so that the technical problem that the sorted data is used as a reference value of the urban knowledge archive and is low exists.
Disclosure of Invention
The application provides a city knowledge archive construction method and system based on a city brain, which are used for solving the technical problem that in the prior art, only data of each dimension is simply collected, sorted and stored, and the sorted data is used as a reference value of a city knowledge archive due to the fact that a preprocessing mode is only simple classification, so that the sorted data is low.
In view of the above problems, the present application provides a city knowledge archive construction method and system based on a city brain.
In a first aspect of the application, a city knowledge record construction method based on a city brain is provided, the method comprises: performing hierarchical clustering analysis on a preset city to obtain a regional clustering tree; traversing the regional clustering tree and collecting archive information; constructing an archive knowledge base according to the archive information, wherein the archive knowledge base has a knowledge graph topological structure; traversing the topological structure of the knowledge graph to obtain a node cluster; traversing the node cluster to evaluate the importance degree to obtain an importance degree set; carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result; and adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base.
In a second aspect of the present application, there is provided a city knowledge archive construction system based on a city brain, the system comprising: the hierarchical clustering module is used for carrying out hierarchical clustering analysis on the preset city to obtain a regional clustering tree; the file acquisition module is used for acquiring file information for traversing the regional clustering tree; the knowledge base building module is used for building an archive knowledge base according to the archive information, wherein the archive knowledge base has a knowledge map topological structure; the node extraction module is used for traversing the topological structure of the knowledge graph to obtain a node cluster; the importance evaluation module is used for evaluating the importance of traversing the node cluster to obtain an importance set; the weight distribution module is used for carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result; and the knowledge base adjusting module is used for adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the method provided by the application acquires the archive information of different areas by acquiring the urban areas. And constructing an archive knowledge base according to the acquired archive information, wherein the archive knowledge base has a knowledge map topological structure. And traversing the topological structure of the knowledge graph to obtain the node cluster. And traversing the node clusters to evaluate the importance degree to obtain an importance degree set. And carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result. And adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base. The method solves the technical problem that in the prior art, only data of each dimension is simply collected, sorted and stored, and the preprocessing mode is only simple classification, so that the sorted data is used as a reference value of the urban knowledge archive and is low. The intelligent classification, extraction and arrangement of various types of data are realized, the weight of the knowledge base is adjusted according to the importance degree of the node records, and the technical effect of improving the reference value of the archive knowledge base is achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart of a city knowledge record construction method based on a city brain according to the present application;
FIG. 2 is a schematic diagram of a process for acquiring archive information in a city knowledge archive construction method based on a city brain according to the present application;
FIG. 3 is a schematic flow chart of acquisition of an archive knowledge base in a city knowledge archive construction method based on a city brain according to the present application;
FIG. 4 is a schematic structural diagram of a city knowledge archive construction system based on a city brain.
Description of reference numerals: the system comprises a hierarchical clustering module 11, a file acquisition module 12, a knowledge base building module 13, a node extraction module 14, an importance evaluation module 15, a weight distribution module 16 and a knowledge base adjusting module 17.
Detailed Description
The application provides a city knowledge archive construction method and system based on a city brain, which are used for solving the technical problem that the prior art only simply collects, arranges and stores data of all dimensions, and the preprocessing mode is simple classification, so that the arranged data is used as a low reference value of a city knowledge archive.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
according to the method provided by the embodiment of the application, the urban areas of the preset city are obtained by performing hierarchical clustering analysis on the preset city, and the archive information of different areas is collected. And constructing an archive knowledge base according to the acquired archive information, wherein the archive knowledge base has a knowledge map topological structure. And traversing the topological structure of the knowledge graph to obtain the node cluster. And traversing the node clusters to evaluate the importance degree to obtain an importance degree set. And acquiring a weight distribution result of each node according to the importance evaluation result, and then adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base. The method solves the technical problem that in the prior art, only data of each dimension is simply collected, sorted and stored, and the preprocessing mode is only simple classification, so that the sorted data is used as a reference value of the urban knowledge archive and is low.
Having described the basic principles of the present application, further description of the present application will be made with reference to the accompanying drawings and examples. The embodiments described are only a part of the disclosure that can be realized by the present application, and not the entire disclosure of the present application.
Example one
As shown in fig. 1, the present application provides a city knowledge archive construction method based on a city brain, including:
s100: performing hierarchical clustering analysis on a preset city to obtain a regional clustering tree;
specifically, the urban brain is an open intelligent operation platform which is constructed based on new-generation information technologies such as cloud computing, big data, internet of things and artificial intelligence and supports economic, social and government digital transformation. The city file records some characters, images, sounds and other information which have recording value to the country and the society in the activities of politics, military, economy, science, technology, culture, religion and the like in a city within a certain historical period. Firstly, hierarchical clustering analysis is carried out on a preset city, wherein the preset city is a city of a city file to be constructed. When the hierarchical clustering analysis is performed on the city of the city archive to be constructed, the regional information of the city can be acquired, for example, the regional clustering can be performed through a specific administrative level, for example, a certain city can be divided into a plurality of regions, more specific division exists under each region, such as information of villages, towns, streets and the like divided under the region, and all region components of a preset city are acquired according to layer-by-layer division. And constructing an area cluster tree according to the area constitution of the city, wherein the lower part of the area cluster tree is divided into specific streets or villages and the upper part is the area constitution of the city, namely, the area cluster tree is in an inclusive relationship from the lower area to the upper area, and the upper area comprises the lower area.
S200: traversing the regional clustering tree and collecting archive information;
specifically, the region clustering tree is traversed to obtain all regions recorded from bottom to top in the clustering tree. Acquiring the acquisition dimension according to the acquired recording area, acquiring the preset archive acquisition dimension in the area, and setting the information in the aspects of historical dimension, geographical dimension, humanistic dimension, physical dimension and the like of the city as the preset city archive acquisition dimension. And searching in a database according to the collection dimension, wherein the database can be an electronic library of the area or other databases with information of the area, and the record archives of the dimension in the database, namely archive information, are obtained.
S300: constructing an archive knowledge base according to the archive information, wherein the archive knowledge base has a knowledge graph topological structure;
specifically, the entity information recorded in the archive information is acquired, the attribute information recorded in the entity information, the association relationship between the entity and the attribute, and the recorded information of the entity are extracted to construct an archive knowledge base, the record of each entity, various attribute characteristics of the entity, and the association relationship between the attribute characteristics and the recorded entity are recorded in the archive knowledge base, and the construction of the archive knowledge base is realized by the information. The archive knowledge base is provided with a knowledge graph topological structure, wherein the knowledge graph topological structure is a semantic network and consists of data nodes and relationship edges for expressing the data nodes, in the embodiment, the data nodes are entity records and entity attributes, and the relationship edges among the data nodes are incidence relationship information between the entity records and the entity attributes.
S400: traversing the topological structure of the knowledge graph to obtain a node cluster;
s500: traversing the node cluster to evaluate the importance degree to obtain an importance degree set;
specifically, the method includes traversing a knowledge-graph topological structure, obtaining all node information in the knowledge-graph topological structure, wherein the node information includes entity record information obtained through archive information and entity attribute information obtained according to the entity record, and obtaining a node cluster through obtaining the node information in the knowledge-graph topological structure, and the node cluster is a set of the node information in the knowledge-graph topological structure. And evaluating the importance of the set of node information in the topological structure of the knowledge graph to obtain an importance set. And when the importance degree is evaluated, the node information is input into the importance degree evaluation channel for the importance degree evaluation, and the final importance degree evaluation results of all the nodes are obtained to form an importance degree set.
S600: carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result;
s700: and adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base.
Specifically, according to the obtained importance evaluation results of all the nodes, namely an importance set, weight distribution is carried out on the node cluster according to the importance, the weight proportion of the nodes with higher importance in an archive knowledge base is improved, the weight proportion of the nodes with lower importance in the archive knowledge base is reduced, wherein weight determination can be carried out according to the size of data in the finally obtained importance set during weight distribution. And adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base. The weight adjustment of the knowledge base is realized according to the importance degree of the node records, and the reference value of the archive knowledge base is further improved.
As shown in fig. 2, the method step S200 provided in the embodiment of the present application includes:
s210: acquiring a preset city file acquisition dimension, wherein the preset city file acquisition dimension is a preset city file acquisition dimension;
s220: performing region extraction on the region clustering tree from the bottom to the top to obtain a region set;
s230: and traversing the area set according to the preset city archive acquisition dimension to acquire data, and acquiring archive information.
Specifically, the preset city of the city archive to be constructed is subjected to acquisition dimension analysis, the preset city archive acquisition dimension is acquired, if the information in the aspects of the history dimension, the geographical dimension, the humanistic dimension, the physical and physical product dimension and the like of the city can be set as the preset city archive acquisition dimension, and the preset city archive acquisition dimension is constructed according to the preset city archive acquisition dimension. And then, extracting regions from bottom to top according to the region clustering tree, acquiring all regions in a preset city to form a region set, acquiring data in the region set according to the acquired preset city file acquisition dimension, and acquiring a file, namely file information, recording the dimension of the region. The data acquisition can be carried out in a multi-level acquisition mode when the data acquisition is carried out according to preset city archive acquisition dimensions, for example, when the material and product dimensions are acquired, the material and product dimensions can be divided into embodied levels of mineral products, vegetation products, other material products and the like, then the material and product dimensions are further divided into more specific levels according to the embodied levels, for example, the vegetation products can be further divided into specific plant varieties or plant categories and the like, the data extraction efficiency is further improved through the data extraction mode, and the speed of acquiring archive information is improved.
As shown in fig. 3, step S300 of the method provided in the embodiment of the present application includes:
s310: performing entity extraction on the archive information to obtain knowledge graph entity information;
s320: traversing the knowledge graph entity information according to the archive information to extract attributes, and acquiring knowledge graph attribute information;
s330: traversing the knowledge graph entity information according to the archive information to extract the relation, and acquiring knowledge graph relation information;
s340: and constructing the topological structure of the knowledge graph according to the entity information of the knowledge graph, the attribute information of the knowledge graph and the relation information of the knowledge graph, and generating the archive knowledge base.
Specifically, the obtained archive information is subjected to entity extraction, wherein the entity extraction is to extract real record information of a corresponding hierarchical division result recorded in the archive information, and the real record information is obtained, namely knowledge graph entity information. And traversing knowledge graph entity information according to the archive information to extract attribute information in the entity information, wherein the attribute information in the acquired knowledge graph entity information comprises specific categories of the entities and attribute information capable of more specifically expressing the entities, for example, a plant contained in the region is a tree, and the attribute information is the attribute information capable of expressing the entities in multiple directions according to the distribution range, the specific categories, the growth period and the like of the tree recorded in the knowledge graph entity information. And traversing knowledge graph entity information according to the archive information to extract the relation, wherein the relation information is the relation between the entity in the knowledge graph entity information and knowledge graph attribute information. If the entity object is a willow, the attribute information of the entity object is obtained by distributing a large amount of attribute information at a certain position in a certain area, wherein the relationship between the entity and the attribute is used for expressing the distribution position of the entity, and if the entity object is searched, the attribute information of the entity can be obtained by inquiring the relationship of the entity. And then, according to the knowledge map entity information, the knowledge map attribute information and the knowledge map relation information, constructing a knowledge map topological structure, wherein the knowledge map topological structure comprises the recorded entity information, the entity attribute information and the related relation information for acquiring the entity and the attribute information, and generating an archive knowledge base according to the knowledge map topological structure, so that the construction of the archive knowledge base in the region is realized.
The method provided by the embodiment of the application comprises the following steps of S500:
s510: acquiring a node memory intensity attribute and a node influence intensity attribute;
s520: traversing the node cluster to extract information according to the node memory strength attribute and the node influence strength attribute to obtain a node memory strength attribute value set and a node influence strength attribute value set;
s530: and sequentially inputting the node memory intensity attribute value set and the node influence intensity attribute value set into an importance degree evaluation channel to obtain an importance degree set, wherein the importance degrees are in one-to-one correspondence with the nodes.
Specifically, the node information in the acquired knowledge graph topological structure is evaluated, and a node memory strength attribute and a node influence strength attribute are acquired. The node memory strength attribute is used for evaluating the memory strength of the node, namely recording duration information of the node and recording quantity information of the node, when the recording duration of the node is longer, the traceability of the recording information of the node is higher, and when the recording quantity information is higher, the recording of the recording information is more comprehensive, and because the information recording time is long and the recording quantity is more, the recording information is more important information. The node influence strength attribute represents the node influence strength, namely the record popularity of the node is recorded, and when the record popularity of the node is higher, the record information of the node is more reliable, which is known by the public. Acquiring all node information in the node cluster, acquiring the node memory strength attribute and the node influence strength attribute of the corresponding node, and acquiring the node memory strength attribute value set and the node influence strength attribute value set. The node memory strength attribute value set and the node influence strength attribute value set are input into an importance degree evaluation channel, an importance degree evaluation set, namely an importance degree set, of each node is obtained, wherein the importance degree sets correspond to all nodes in the node cluster one to one, evaluation can be carried out in an expert scoring mode when the evaluation attributes are obtained, and the results can be embodied by setting evaluation levels when the evaluation is carried out. The real importance of each node is obtained by evaluating the importance of each node, so that the archive knowledge base is adjusted according to the importance of the nodes.
The method provided by the embodiment of the application comprises the following steps of S520:
s521: disassembling the memory intensity attribute of the node to obtain a history propagation duration attribute and a history recorded quantity;
s522: disassembling the node influence strength attribute to obtain a cultural popularity attribute, a political popularity attribute and a military popularity attribute;
s523: according to the history inheritance duration attribute and the history record number, information extraction is carried out on the node cluster, and the node memory strength attribute value set is obtained;
s524: and extracting information of the node cluster according to the cultural awareness attribute, the political awareness attribute and the military awareness attribute to obtain the node influence strength attribute value set.
Specifically, the memory strength attribute of the node is disassembled to obtain a history propagation duration attribute and history record quantity, wherein the history propagation duration attribute represents history propagation duration, and the history propagation duration is record duration information of the node. The history quantity represents history record quantity, namely quantity information of the node recorded in each literature record. The node influence strength attribute is disassembled to obtain a cultural awareness attribute, a political awareness attribute and a military awareness attribute, wherein the cultural awareness attribute represents cultural awareness, the political awareness attribute represents political awareness, and the military awareness attribute represents military awareness, the evaluation attribute can be evaluated in an expert scoring mode when the evaluation attribute is obtained, and the result can be embodied by setting an evaluation grade when the evaluation is carried out. And obtaining the history propagation time length attribute and history record quantity evaluation of all node information in the node cluster to form a final node memory strength attribute value set. And obtaining the cultural popularity attribute, the political popularity attribute and the military popularity attribute evaluation of all the node information in the node cluster to form a final node influence strength attribute value set. By further dividing the evaluation attribute values, the acquisition accuracy of the evaluation attribute values is further improved.
The method provided by the embodiment of the present application further includes step S520:
s525: according to the importance evaluation channel, a node memory strength attribute importance evaluation module, a node influence strength attribute importance evaluation module and an importance fusion module are obtained;
s526: inputting the node memory strength attribute value set into the node memory strength attribute importance evaluation module to obtain the node memory strength attribute importance;
s527: inputting the node influence strength attribute value set into the node influence strength attribute importance evaluation module to obtain the node influence strength attribute importance;
s528: and inputting the importance of the node memory strength attribute and the importance of the node influence strength attribute into the importance fusion module to obtain the importance set.
Specifically, the importance evaluation channel is a channel for generating a final importance score according to the node memory strength attribute and the node influence strength attribute, and the importance evaluation channel comprises a node memory strength attribute importance evaluation module, a node influence strength attribute importance evaluation module and an importance fusion module. When the importance of the node memory strength attribute is obtained, the node memory strength attribute importance is obtained by inputting the node memory strength attribute value set into the node memory strength attribute importance evaluation module. And when the importance of the node influence strength attribute is obtained, the importance of the node influence strength attribute is obtained by inputting the node influence strength attribute value set into the node influence strength attribute importance evaluation module. Namely, the node memory strength attribute importance evaluation module is used for generating a corresponding importance score according to the node memory strength attribute, and the node influence strength attribute importance evaluation module is used for generating a corresponding importance score according to the first evaluation attribute. And for the importance fusion module, a final importance set is generated according to the importance of the node memory strength attribute and the importance of the node influence strength attribute, and the importance evaluation is performed on the node memory strength attribute and the node influence strength attribute through an importance evaluation channel, so that the acquired importance set is acquired more accurately.
The method provided by the embodiment of the application comprises the following steps of S525:
s525-1: constructing a first coordinate axis according to the history propagation duration attribute, and constructing a second coordinate axis according to the history recording quantity;
s525-2: generating a primary two-dimensional coordinate system according to the first coordinate axis and the second coordinate axis;
s525-3: a third coordinate axis is constructed according to the cultural popularity attribute, a fourth coordinate axis is constructed according to the political popularity attribute, and a fifth coordinate axis is constructed according to the military popularity attribute;
s525-4: generating a primary three-dimensional coordinate system according to the third coordinate axis, the fourth coordinate axis and the fifth coordinate axis;
s525-5: constructing a sixth coordinate axis according to the importance of the node memory intensity attribute, and constructing a seventh coordinate axis according to the importance of the node influence intensity attribute;
s525-6: generating a secondary coordinate system according to the sixth coordinate axis and the seventh coordinate axis;
s525-7: setting the primary two-dimensional coordinate system as the node memory strength attribute importance evaluation module, setting the primary three-dimensional coordinate system as the node influence strength attribute importance evaluation module, and setting the secondary coordinate system as the importance fusion module.
Specifically, a first coordinate axis is established through the history inheritance duration attribute, a second coordinate axis is established through the history number of records of the history inheritance duration attribute, a first-level two-dimensional coordinate system is generated through the first coordinate axis and the second coordinate axis, the coordinate system is used for obtaining the importance degree of the node memory strength attribute through a KNN algorithm according to the history inheritance duration attribute grading level and the history number of records of the history number of records grading level, the KNN algorithm is a common classification algorithm, the principle is that when new value-added prediction is conducted in the coordinate system, new value-added prediction is conducted through the distance between points close to the new value-added prediction, and the predicted new value-added is the importance degree of the node memory strength attribute. And a third coordinate axis is constructed according to the cultural popularity attribute, a fourth coordinate axis is constructed according to the political popularity attribute, and a fifth coordinate axis is constructed according to the military popularity attribute. And generating a primary three-dimensional coordinate system according to the third coordinate axis, the fourth coordinate axis and the fifth coordinate axis, wherein the primary three-dimensional coordinate system is used for acquiring the importance of the node influence strength attribute through a KNN algorithm according to the cultural popularity attribute grading level, the political popularity attribute grading level and the military popularity attribute grading level. And finally, constructing a sixth coordinate axis according to the importance of the node memory strength attribute, constructing a seventh coordinate axis according to the importance of the node influence strength attribute, and generating a secondary coordinate system, wherein the secondary coordinate system is an importance fusion module and is used for acquiring a final importance evaluation result through a KNN algorithm according to the acquired importance of the node memory strength attribute and the importance of the node influence strength attribute. Through the attribute importance evaluation module obtained in the mode, the importance evaluation result is more accurately obtained.
In summary, the method provided by the embodiment of the present application obtains the city area of the preset city by performing hierarchical clustering analysis on the preset city, and collects archive information of different areas. And constructing an archive knowledge base according to the acquired archive information, wherein the archive knowledge base has a knowledge map topological structure. And traversing the topological structure of the knowledge graph to obtain the node cluster. And traversing the node clusters to evaluate the importance degree to obtain an importance degree set. And carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result. And adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base. The method solves the technical problem that in the prior art, only data of each dimension is simply collected, sorted and stored, and the preprocessing mode is only simple classification, so that the sorted data is used as a reference value of the urban knowledge archive and is low. The intelligent classification, extraction and arrangement of various types of data are realized, the weight of the knowledge base is adjusted according to the importance degree of the node records, and the technical effect of improving the reference value of the archive knowledge base is achieved.
Example two
Based on the same inventive concept as the city knowledge archive construction method based on the city brain in the foregoing embodiment, as shown in fig. 4, the present application provides a city knowledge archive construction system based on the city brain, including:
the hierarchical clustering module 11 is used for performing hierarchical clustering analysis on a preset city to obtain a regional clustering tree;
the file acquisition module 12 is used for acquiring file information for traversing the regional clustering tree;
a knowledge base construction module 13, configured to construct an archive knowledge base according to the archive information, where the archive knowledge base has a knowledge graph topology structure;
a node extraction module 14, configured to traverse the knowledge-graph topology structure to obtain a node cluster;
the importance evaluation module 15 is configured to evaluate the importance of traversing the node cluster to obtain an importance set;
the weight distribution module 16 is configured to perform weight distribution on the node cluster according to the importance set to obtain a weight distribution result;
and the knowledge base adjusting module 17 is configured to adjust the archive knowledge base according to the weight distribution result to obtain an adjusted archive knowledge base.
Further, the archive collection module is further configured to:
acquiring a preset city file acquisition dimension, wherein the preset city file acquisition dimension is a preset city file acquisition dimension;
performing region extraction on the region clustering tree from the bottom to the top to obtain a region set;
and traversing the area set according to the preset city archive acquisition dimension to acquire data, and acquiring archive information.
Further, the knowledge base building module is further configured to:
performing entity extraction on the archive information to obtain knowledge graph entity information;
traversing the knowledge graph entity information according to the archive information to extract attributes, and acquiring knowledge graph attribute information;
traversing the knowledge graph entity information according to the archive information to extract the relation, and acquiring knowledge graph relation information;
and constructing the topological structure of the knowledge graph according to the entity information of the knowledge graph, the attribute information of the knowledge graph and the relation information of the knowledge graph, and generating the archive knowledge base.
Further, the importance evaluation module is further configured to:
acquiring a node memory intensity attribute and a node influence intensity attribute;
traversing the node cluster to extract information according to the node memory strength attribute and the node influence strength attribute to obtain a node memory strength attribute value set and a node influence strength attribute value set;
and sequentially inputting the node memory intensity attribute value set and the node influence intensity attribute value set into an importance degree evaluation channel to obtain an importance degree set, wherein the importance degrees are in one-to-one correspondence with the nodes.
Further, the importance evaluation module is further configured to:
the traversing the node cluster for information extraction according to the node memory strength attribute and the node influence strength attribute to obtain a node memory strength attribute value set and a node influence strength attribute value set includes:
disassembling the memory intensity attribute of the node to obtain a history propagation duration attribute and a history recorded quantity;
disassembling the node influence strength attribute to obtain a cultural popularity attribute, a political popularity attribute and a military popularity attribute;
according to the history inheritance duration attribute and the history record number, information extraction is carried out on the node cluster, and the node memory strength attribute value set is obtained;
and extracting information of the node cluster according to the cultural awareness attribute, the political awareness attribute and the military awareness attribute to obtain the node influence strength attribute value set.
Further, the importance evaluation module is further configured to:
according to the importance evaluation channel, a node memory strength attribute importance evaluation module, a node influence strength attribute importance evaluation module and an importance fusion module are obtained;
inputting the node memory strength attribute value set into the node memory strength attribute importance evaluation module to obtain the node memory strength attribute importance;
inputting the node influence strength attribute value set into the node influence strength attribute importance evaluation module to obtain the node influence strength attribute importance;
and inputting the importance of the node memory strength attribute and the importance of the node influence strength attribute into the importance fusion module to obtain the importance set.
Further, the importance evaluation module is further configured to:
constructing a first coordinate axis according to the history propagation duration attribute, and constructing a second coordinate axis according to the history recording quantity;
generating a primary two-dimensional coordinate system according to the first coordinate axis and the second coordinate axis;
a third coordinate axis is constructed according to the cultural popularity attribute, a fourth coordinate axis is constructed according to the political popularity attribute, and a fifth coordinate axis is constructed according to the military popularity attribute;
generating a primary three-dimensional coordinate system according to the third coordinate axis, the fourth coordinate axis and the fifth coordinate axis;
constructing a sixth coordinate axis according to the importance of the node memory intensity attribute, and constructing a seventh coordinate axis according to the importance of the node influence intensity attribute;
generating a secondary coordinate system according to the sixth coordinate axis and the seventh coordinate axis;
setting the primary two-dimensional coordinate system as the node memory strength attribute importance evaluation module, setting the primary three-dimensional coordinate system as the node influence strength attribute importance evaluation module, and setting the secondary coordinate system as the importance fusion module.
The second embodiment is used for executing the method as in the first embodiment, and both the execution principle and the execution basis can be obtained through the content recorded in the first embodiment, which is not described herein again. Although the present application has been described in connection with particular features and embodiments thereof, the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application, and what is obtained in this way also belongs to the protection scope of the present application.
Claims (8)
1. A city knowledge file construction method based on a city brain is characterized by comprising the following steps:
performing hierarchical clustering analysis on a preset city to obtain a regional clustering tree;
traversing the regional clustering tree and collecting archive information;
constructing an archive knowledge base according to the archive information, wherein the archive knowledge base has a knowledge graph topological structure;
traversing the topological structure of the knowledge graph to obtain a node cluster;
traversing the node cluster to evaluate the importance degree to obtain an importance degree set;
carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result;
and adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base.
2. The method of claim 1, wherein traversing the region cluster tree, collecting archival information, comprises:
acquiring a preset city file acquisition dimension, wherein the preset city file acquisition dimension is a preset city file acquisition dimension;
performing region extraction on the region clustering tree from the bottom to the top to obtain a region set;
and traversing the area set according to the preset city archive acquisition dimension to acquire data, and acquiring archive information.
3. The method of claim 1, wherein said building an archive knowledge base from said archive information comprises:
performing entity extraction on the archive information to obtain knowledge graph entity information;
traversing the knowledge graph entity information according to the archive information to extract attributes, and acquiring knowledge graph attribute information;
traversing the knowledge graph entity information according to the archive information to extract the relation, and acquiring knowledge graph relation information;
and constructing the topological structure of the knowledge graph according to the entity information of the knowledge graph, the attribute information of the knowledge graph and the relation information of the knowledge graph, and generating the archive knowledge base.
4. The method of claim 1, wherein traversing the cluster of nodes for importance evaluation to obtain a set of importance comprises:
acquiring a node memory intensity attribute and a node influence intensity attribute;
traversing the node cluster to extract information according to the node memory strength attribute and the node influence strength attribute to obtain a node memory strength attribute value set and a node influence strength attribute value set;
and sequentially inputting the node memory intensity attribute value set and the node influence intensity attribute value set into an importance degree evaluation channel to obtain an importance degree set, wherein the importance degrees are in one-to-one correspondence with the nodes.
5. The method of claim 4, wherein said traversing the node cluster for information extraction based on the node memory strength attribute and the node impact strength attribute, obtaining a node memory strength attribute value set and a node impact strength attribute value set, comprises:
disassembling the memory intensity attribute of the node to obtain a history propagation duration attribute and a history recorded quantity;
disassembling the node influence strength attribute to obtain a cultural popularity attribute, a political popularity attribute and a military popularity attribute;
according to the history inheritance duration attribute and the history record number, information extraction is carried out on the node cluster, and the node memory strength attribute value set is obtained;
and extracting information of the node cluster according to the cultural awareness attribute, the political awareness attribute and the military awareness attribute to obtain the node influence strength attribute value set.
6. The method of claim 5, wherein said sequentially inputting said node memory strength attribute value set and said node impact strength attribute value set to a importance evaluation channel to obtain an importance set comprises:
according to the importance evaluation channel, a node memory strength attribute importance evaluation module, a node influence strength attribute importance evaluation module and an importance fusion module are obtained;
inputting the node memory strength attribute value set into the node memory strength attribute importance evaluation module to obtain the node memory strength attribute importance;
inputting the node influence strength attribute value set into the node influence strength attribute importance evaluation module to obtain the node influence strength attribute importance;
and inputting the importance of the node memory strength attribute and the importance of the node influence strength attribute into the importance fusion module to obtain the importance set.
7. The method of claim 6, wherein the method comprises:
constructing a first coordinate axis according to the history propagation duration attribute, and constructing a second coordinate axis according to the history recording quantity;
generating a primary two-dimensional coordinate system according to the first coordinate axis and the second coordinate axis;
a third coordinate axis is constructed according to the cultural popularity attribute, a fourth coordinate axis is constructed according to the political popularity attribute, and a fifth coordinate axis is constructed according to the military popularity attribute;
generating a primary three-dimensional coordinate system according to the third coordinate axis, the fourth coordinate axis and the fifth coordinate axis;
constructing a sixth coordinate axis according to the importance of the node memory intensity attribute, and constructing a seventh coordinate axis according to the importance of the node influence intensity attribute;
generating a secondary coordinate system according to the sixth coordinate axis and the seventh coordinate axis;
setting the primary two-dimensional coordinate system as the node memory strength attribute importance evaluation module, setting the primary three-dimensional coordinate system as the node influence strength attribute importance evaluation module, and setting the secondary coordinate system as the importance fusion module.
8. A city knowledge file construction system based on a city brain is characterized by comprising:
the hierarchical clustering module is used for carrying out hierarchical clustering analysis on the preset city to obtain a regional clustering tree;
the file acquisition module is used for acquiring file information for traversing the regional clustering tree;
the knowledge base building module is used for building an archive knowledge base according to the archive information, wherein the archive knowledge base has a knowledge map topological structure;
the node extraction module is used for traversing the topological structure of the knowledge graph to obtain a node cluster;
the importance evaluation module is used for evaluating the importance of traversing the node cluster to obtain an importance set;
the weight distribution module is used for carrying out weight distribution on the node cluster according to the importance set to obtain a weight distribution result;
and the knowledge base adjusting module is used for adjusting the archive knowledge base according to the weight distribution result to obtain the adjusted archive knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210822068.2A CN114896425A (en) | 2022-07-13 | 2022-07-13 | City knowledge archive construction method and system based on city brain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210822068.2A CN114896425A (en) | 2022-07-13 | 2022-07-13 | City knowledge archive construction method and system based on city brain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114896425A true CN114896425A (en) | 2022-08-12 |
Family
ID=82729426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210822068.2A Pending CN114896425A (en) | 2022-07-13 | 2022-07-13 | City knowledge archive construction method and system based on city brain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114896425A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309963A (en) * | 2022-08-13 | 2022-11-08 | 佩齐睿鸿文化科技(武汉)有限公司 | Intelligent archive management method, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104519A (en) * | 2019-10-29 | 2020-05-05 | 北京海致星图科技有限公司 | Method for constructing full-scale administrative region knowledge base |
| CN112084341A (en) * | 2020-08-26 | 2020-12-15 | 哈尔滨工业大学（深圳） | Knowledge graph completion method based on triple importance |
| WO2021254457A1 (en) * | 2020-06-17 | 2021-12-23 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph, computer device, and storage medium |
| CN113886596A (en) * | 2021-09-23 | 2022-01-04 | 同济大学 | Method for constructing flexible city knowledge graph based on city element and multi-disaster fusion |
| CN114372125A (en) * | 2021-12-03 | 2022-04-19 | 北京北明数科信息技术有限公司 | Government affair knowledge base construction method, system, equipment and medium based on knowledge graph |
-
2022
- 2022-07-13 CN CN202210822068.2A patent/CN114896425A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104519A (en) * | 2019-10-29 | 2020-05-05 | 北京海致星图科技有限公司 | Method for constructing full-scale administrative region knowledge base |
| WO2021254457A1 (en) * | 2020-06-17 | 2021-12-23 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph, computer device, and storage medium |
| CN112084341A (en) * | 2020-08-26 | 2020-12-15 | 哈尔滨工业大学（深圳） | Knowledge graph completion method based on triple importance |
| CN113886596A (en) * | 2021-09-23 | 2022-01-04 | 同济大学 | Method for constructing flexible city knowledge graph based on city element and multi-disaster fusion |
| CN114372125A (en) * | 2021-12-03 | 2022-04-19 | 北京北明数科信息技术有限公司 | Government affair knowledge base construction method, system, equipment and medium based on knowledge graph |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309963A (en) * | 2022-08-13 | 2022-11-08 | 佩齐睿鸿文化科技(武汉)有限公司 | Intelligent archive management method, system and storage medium |
| CN115309963B (en) * | 2022-08-13 | 2023-09-12 | 晶品科技股份有限公司 | Intelligent archive management method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577688B (en) | Original article influence analysis system based on media information acquisition | |
| Abraham et al. | Survey of spatio-temporal databases | |
| CN110334391B (en) | Automatic planning method for collecting circuit of multi-dimensional constraint wind power plant | |
| CN108595414B (en) | Soil heavy metal enterprise pollution source identification method based on source-sink space variable reasoning | |
| CN108710625A (en) | A kind of special topic knowledge automatic mining system and method | |
| CN105468677A (en) | Log clustering method based on graph structure | |
| CN106790468A (en) | A kind of distributed implementation method for analyzing user's WiFi event trace rules | |
| CN101196905A (en) | Intelligent pattern searching method | |
| CN106599915A (en) | Vehicle-mounted laser point cloud classification method | |
| CN113779169B (en) | Space-time data stream model self-enhancement method | |
| CN115934990B (en) | Remote sensing image recommendation method based on content understanding | |
| CN113157800A (en) | Identification method for discovering dynamic target in air in real time | |
| CN116129262A (en) | Cultivated land suitability evaluation method and system for suitable mechanized transformation | |
| CN114896425A (en) | City knowledge archive construction method and system based on city brain | |
| CN114819589A (en) | Urban space high-quality utilization determination method, system, computer equipment and terminal | |
| Isaj et al. | Multi-source spatial entity linkage | |
| CN107798357A (en) | A kind of village land used reclamation planning analogy method based on KNN | |
| Xue et al. | An improved random forest model applied to point cloud classification | |
| CN116883026A (en) | Agricultural product origin tracing method and system based on big data | |
| CN115619275B (en) | Ecological restoration decision method and device for railway engineering | |
| CN116011564A (en) | Entity relationship completion method, system and application for power equipment | |
| Ramzan et al. | A comprehensive review on data stream mining techniques for data classification; and future trends | |
| CN112818923A (en) | Urban mass living space construction time identification method | |
| CN106168982A (en) | Data retrieval method for particular topic | |
| CN106294652A (en) | Web page information search method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220812 |
|
| RJ01 | Rejection of invention patent application after publication |