CN116662528B - Map self-adaptive recommendation method based on knowledge graph and related equipment - Google Patents
Map self-adaptive recommendation method based on knowledge graph and related equipment Download PDFInfo
- Publication number
- CN116662528B CN116662528B CN202310504997.3A CN202310504997A CN116662528B CN 116662528 B CN116662528 B CN 116662528B CN 202310504997 A CN202310504997 A CN 202310504997A CN 116662528 B CN116662528 B CN 116662528B
- Authority
- CN
- China
- Prior art keywords
- map
- similarity
- recommendation
- data
- knowledge
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000000007 visual effect Effects 0.000 claims abstract description 81
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 230000003044 adaptive effect Effects 0.000 claims description 39
- 238000012800 visualization Methods 0.000 claims description 28
- 238000013507 mapping Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002123 temporal effect Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000009897 systematic effect Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003068 static effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a map self-adaptive recommendation method and related equipment based on a knowledge graph, wherein the method comprises the following steps: collecting a plurality of types of map cases, and establishing a map case instance library; analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model; based on a map recommendation ontology model, analyzing map features of map examples in the map case example library, and establishing a map expression feature library; based on the map recommendation ontology model and the map feature analysis result, constructing a map knowledge graph according to a preset mode; calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user; and calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result. The invention improves the drawing efficiency and provides effective support for map diversification and personalized popularization and application.
Description
Technical Field
The invention relates to the technical field of map visualization, in particular to a map self-adaptive recommendation method, system, terminal and computer readable storage medium based on a knowledge graph.
Background
With the development of information communication technology, the visual form of the map is more and more abundant, and besides the traditional map such as layered color map, contour map, shaded map and the like, a large number of class maps which are different from the traditional map in terms of objectivity, intuitiveness, scalability, list and the like of spatial information expression, such as Whisper map, krikogram map, cholermatic map, micro map and the like are also developed.
Under the traditional digital map making, the production of the thematic map needs to firstly have professional drawing knowledge or seek drawing expert assistance so as to meet the expression requirement of thematic content. However, on one hand, the constraint of the priori knowledge limits the popularization and development of the map to a certain extent, and the popular lovers lacking the professional drawing theory knowledge easily enter various drawing traps which violate the general knowledge of map expression by mistake; on the other hand, in the internet environment, higher requirements are put on timeliness of map information transfer and richness of information interaction.
In the face of the individuation and diversification demands of the ICT era map, how to internalize basic rules, visual features and knowledge of map making into a map selection process, so that the map type works suitable for non-professional cartoons are recommended, and the important problem that attention is needed for current map making and use is solved.
Accordingly, the prior art is still in need of improvement and development.
Disclosure of Invention
The invention mainly aims to provide a map self-adaptive recommending method, a system, a terminal and a computer readable storage medium based on a knowledge graph, and aims to solve the problems that in the prior art, a non-professional diagramming staff cannot quickly acquire an optimal map type from a large number of charts and the diagramming efficiency is low.
In order to achieve the above object, the present invention provides a map adaptive recommendation method based on a knowledge graph, the map adaptive recommendation method based on a knowledge graph includes the following steps:
collecting a plurality of types of map cases, and establishing a map case instance library;
analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model;
based on a map recommendation ontology model, analyzing map features of map examples in the map case example library, and establishing a map expression feature library;
based on the map recommendation ontology model and the map feature analysis result, constructing a map knowledge graph according to a preset mode;
calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user;
and calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result.
Optionally, the knowledge-graph-based map adaptive recommendation method includes collecting a plurality of types of map cases, and establishing a map case instance library, including:
retrieving a plurality of types of map cases from a plurality of channels;
and classifying and storing all the retrieved map cases to establish the map case instance library.
Optionally, the knowledge-graph-based map adaptive recommendation method, wherein the data features include: temporal features, spatial features, and attribute features;
the visualization dimensions include: time dimension, space dimension, attribute dimension, and user dimension;
the application fields include: application fields facing to human use and application fields facing to object use;
the visualization form comprises: standard maps, ideographic maps, and pictorial maps.
Optionally, the method for adaptively recommending a map based on a knowledge graph, wherein the method for adaptively recommending a map based on a map recommendation ontology model analyzes map features of map instances in the map case instance library, and establishes a map expression feature library, specifically includes:
acquiring map cases to be identified in the map case instance library, and performing systematic deconstructment on data features, expression dimensions, application fields and visual types of various map cases according to characteristics of the map cases to be identified and by combining the map recommendation ontology model;
analyzing time, space and attribute characteristics of data under the map type, expressing the specific expression of the related time, space, attribute and user visual dimension, applying the application scene to which the map is applicable, and classifying the visual form to which the map belongs, and constructing the map expression characteristic library oriented to multiple subjects, multiple types and multiple users.
Optionally, the map self-adaptive recommendation method based on the knowledge graph, wherein the map self-recommendation ontology model and the map feature analysis result are based on the map, and the map knowledge graph is built according to a preset mode, specifically includes:
constructing formal description of a map recommendation body;
mapping the instance to a corresponding class, mapping the attribute to a corresponding attribute keyword, mapping the relationship to a corresponding relationship predicate, and realizing formal description of map expression knowledge based on the mapping relationship;
and (3) storing knowledge in the forms of spatial data, expression dimension, application field and visualization based on the Neo4J map database, and constructing a map knowledge graph according to the mode of entity-relation-entity or entity-attribute values.
Optionally, in the knowledge-graph-based map adaptive recommendation method, the calculating the similarity values of the map data, the expression preference and the application purpose according to the data features, the visual dimension preference and the application purpose input by the user specifically includes:
the method comprises the steps of performing knowledge embedding on data characteristics and visual dimensions of space data by adopting single-hot coding, taking entity nodes representing data information as states, and coding N states by using N-bit state registers, wherein each state register is mutually independent;
performing knowledge embedding on the spatial data information in the map knowledge graph by using the independent thermal coding, and converting the map knowledge graph into a feature vector;
wherein,representing a feature vector matrix obtained after the map knowledge graph is subjected to single-heat coding, m represents the number of spatial data strips, n represents the number of feature states, and a ij Representing the ith row and the jth column in the eigenvector matrix;
calculating the feature similarity of the spatial data:
calculating visual dimension similarity:
calculating the similarity of application fields:
wherein D is 1 ，D 2 Representing spatial data features, d 1 ,d 2 Representing a data feature set, the card representing a potential or cardinality of the data feature set;
wherein V is 1 ，V 2 Representing the comprehensive similarity result under all visual dimension comparison, A, B representing visual dimension feature vectors, a i ，b i Representing the visualization dimensions, z representing the total number of visualization dimensions;
wherein T is 1 ，T 2 The application field of the map is represented, k represents the application field similarity degree, k epsilon (0, 1), and sim represents the element similarity.
Optionally, in the map self-adaptive recommendation method based on a knowledge graph, the calculating the comprehensive value of the similarity of the map types, analyzing the map type with the highest similarity to obtain a final map recommendation result specifically includes:
and comprehensively calculating a map type similarity result, wherein the overall similarity is calculated as follows:
wherein similarity represents overall similarity, ω represents weight, ω∈ (0, 1), ω 1 +ω 2 +ω 3 ＝1；
Based on the map knowledge graph, determining the map type with the highest similarity according to the space data, the visual dimension and the similarity comprehensive calculation result of the application field, and recommending a corresponding map result for the user.
In addition, in order to achieve the above object, the present invention further provides a map adaptive recommendation system based on a knowledge graph, wherein the map adaptive recommendation system based on a knowledge graph includes:
the map case instance library establishing module is used for collecting a plurality of types of map cases and establishing a map case instance library;
the map recommendation ontology model construction module is used for analyzing the data characteristics, the visual dimension, the application field and the visual form of the map and constructing a map recommendation ontology model;
the map expression feature library establishing module is used for analyzing map features of map examples in the map case example library based on the map recommendation ontology model and establishing a map expression feature library;
the map knowledge graph construction module is used for constructing a map knowledge graph according to a preset mode based on the map recommendation ontology model and the map feature analysis result;
the similarity evaluation module is used for calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user;
and the map type self-adaptive recommendation module is used for calculating the comprehensive value of the similarity of the map types, analyzing the map type with the highest similarity and obtaining a final map recommendation result.
In addition, to achieve the above object, the present invention also provides a terminal, wherein the terminal includes: the system comprises a memory, a processor and a map-based adaptive recommendation program which is stored in the memory and can be run on the processor, wherein the map-based adaptive recommendation program realizes the steps of the map-based adaptive recommendation method based on the knowledge map when being executed by the processor.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium storing a map-based adaptive recommendation program based on a knowledge graph, which when executed by a processor, implements the steps of the map-based adaptive recommendation method based on a knowledge graph as described above.
In the invention, a plurality of types of map cases are collected, and a map case instance library is established; analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model; based on a map recommendation ontology model, analyzing map features of map examples in the map case example library, and establishing a map expression feature library; based on the map recommendation ontology model and the map feature analysis result, constructing a map knowledge graph according to a preset mode; calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user; and calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result. The invention builds the map visual information knowledge base under different application scenes by using the knowledge map as the basis and through the map case-knowledge map-similarity matching-map type building flow, and carries out self-adaptive map recommendation according to the user drawing requirements, thereby assisting the drawing staff to quickly acquire the most suitable map type from the mass charts, improving the drawing efficiency and providing effective support for map diversification and personalized popularization and application.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the knowledge-based map adaptive recommendation method of the present invention;
FIG. 2 is a schematic diagram of a map recommendation ontology model in a preferred embodiment of the knowledge-based map adaptive recommendation method of the present invention;
FIG. 3 is a schematic diagram of a map recommendation knowledge graph structure in a preferred embodiment of the knowledge graph-based map adaptive recommendation method of the present invention;
FIG. 4 is a diagram illustrating knowledge embedding of a single thermal encoding in a preferred embodiment of a knowledge-based map adaptive recommendation method of the present invention;
FIG. 5 is a schematic diagram of a knowledge graph of a recommendation result in a preferred embodiment of the map adaptive recommendation method based on knowledge graph of the present invention;
FIG. 6 is a schematic diagram of a preferred embodiment of the knowledge-based map adaptive recommendation system of the present invention;
FIG. 7 is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear and clear, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a map self-adaptive recommendation method based on a knowledge graph due to the demands of users on the diversification of map visualization forms and more scientific and reasonable drawing in an application scene. The knowledge graph is an important method for mining, analyzing and constructing structural relations among knowledge, and is widely applied to the fields of intelligent semantic search, intelligent question-answering, personalized recommendation and the like. The invention builds the map visual information knowledge base under different application scenes by the construction flow of map case-knowledge map-similarity matching-map type based on the knowledge map, and carries out self-adaptive map recommendation according to the user drawing demands, thereby assisting drawing staff to quickly acquire the most suitable map type from a large number of charts and improving drawing efficiency.
The invention comprises the following steps: firstly, collecting map cases and establishing a map case instance library; secondly, analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model; thirdly, based on the map recommendation ontology model, analyzing map features of the map instance, and establishing a map expression feature library; fourth, based on the map recommendation ontology model and the map feature analysis result, constructing a knowledge graph according to an entity-relation-entity or entity-attribute value mode; fifthly, calculating similarity values of map data, expression preference, application purpose and the like according to the data characteristics, the visual dimension preference and the application purpose input by a user; and finally, calculating the comprehensive value of the map type similarity to obtain a final map recommendation result. The invention effectively solves the problems of difficult and even wrong selection of map types by non-professional cartoonists, and can provide effective support for map diversification and personalized popularization and application.
The knowledge-graph-based map self-adaptive recommendation method according to the preferred embodiment of the present invention, as shown in fig. 1, comprises the following steps:
step S10, collecting a plurality of types of map cases, and establishing a map case instance library.
Specifically, retrieving multiple types of map cases from multiple channels, for example, retrieving map type cases from multiple sources of internet, atlas, home and abroad literature, etc., includes: and classifying and storing all retrieved map cases to establish the map case example library according to traditional maps such as administrative division maps, contour maps, shading maps, punctiform distribution maps and the like, and class maps such as Cartogram maps, schematic subway maps, krikograms maps, whisper maps, choramic maps and the like.
And S20, analyzing the data characteristics, the visual dimension, the application field and the visual form of the map, and constructing a map recommendation ontology model.
Wherein the data characteristic comprises: temporal features, spatial features, and attribute features; the visualization dimensions include: time dimension, space dimension, attribute dimension, and user dimension; the application fields include: application fields facing to human use and application fields facing to object use; the visualization form comprises: standard maps, ideographic maps, and pictorial maps.
Specifically, an ontology is a collection of concepts, and a knowledge-graph ontology layer is essentially a variety of concepts and their relationships. As shown in fig. 2, the map recommendation ontology model is constructed according to the data features, the visual dimensions, the application fields and the visual forms related to the map expression. On the data features, the map data features are divided into: temporal features (e.g., duration features, interval time features, discrete time features, cycle time features, and static features), spatial features (e.g., punctiform, linear, planar, volumetric, and field-like), attribute features (e.g., qualitative features including sequential features including rank order, degree order, and side-by-side order, and quantitative features including numerical quantity, interval quantity, and ratio quantity), and class features including single class, compound class, and multiple class; the visualization dimensions are divided into: object states (e.g., static and dynamic), temporal structures (e.g., linear, branched, and cyclic structures), etc., spatial dimensions (e.g., 1-dimensional, 2-dimensional, 2.5-dimensional, 3-dimensional, and multidimensional), geometric logic (e.g., euclidean geometry and topological relationships), spatial organization (e.g., vectors, grids, and hybrids), spatial reference planes (e.g., planes and surfaces), carrier media (e.g., physical and electronic), etc., abstract, avatar, style, etc., attribute dimensions, and express dimensions (e.g., single-scale, multi-scale, and variable-scale), person perspective (e.g., first person perspective, and third person perspective), etc., user dimensions; the application fields comprise application fields facing to 'people' such as topography, geology, topography, traffic, politics, culture, history and the like, and application fields facing to 'things' such as automatic driving, industrial automation and the like; the visual form is divided into: standard maps (e.g., punctuation, line, range, base, contour, hierarchical statistics, partition statistics), ideographic maps (e.g., cartogram, schematic subway, krikograms, metaphor), pictorial maps (e.g., video, 2.5-dimensional, and live-action three-dimensional maps), and the like.
And step S30, analyzing map features of map examples in the map case example library based on the map recommendation ontology model, and establishing a map expression feature library.
Specifically, map cases to be identified in the map case instance library are obtained, according to the characteristics of the map cases to be identified, meanwhile, the map recommendation ontology model is combined, system deconstructing is carried out on the data features, the expression dimension, the application field and the visualization types of the map cases of various types, the time, the space and the attribute features of the data under the map types are analyzed, the specific expression of the related time, space, attribute and user visualization dimension is expressed, the application scene to which the map is applicable, and the classification to which the visualization forms belong are constructed, and the map expression feature library facing multiple subjects, multiple types and multiple users is constructed.
And S40, constructing a map knowledge graph according to a preset mode based on the map recommendation ontology model and the map feature analysis result.
Specifically, the ontology OWL description language is utilized to describe data characteristics, expression dimensions, application fields, concept definition of map forms, association relations, attribute structures, rule methods and organization forms. Starting from 5 parts of concept (C), relation (R), attribute (P), rule (RU), instance (I) and the like related to map recommendation, a formal description of a map recommendation body is constructed, namely: o= < C, R, P, RU, I >. Wherein, O is a map form body, C is a set of a series of element concepts such as space data, expression dimension, application field, etc., R is an element relation set such as "applicable", "owned", "used", "having", etc., P is an object element attribute set, RU is an expression rule set, and I is a series of map expression instance sets. And mapping the instance to the corresponding class, mapping the attribute to the corresponding attribute keyword, mapping the relationship to the corresponding relationship predicate, and realizing formal description of map expression knowledge based on the mapping relationship. The knowledge storage of spatial data, expression dimension, application field, visual form and the like related to map recommendation is carried out through a Neo4J map database, a map knowledge map is established, as shown in fig. 3, a spatial data entity comprises forest coverage, a data feature entity comprises planar, single-category, degree sequence features, no-time features and interval number features, a visual dimension entity comprises static, euclidean geometry, vectors, no-space deformation, planes, single-scale, figures, two-dimensional and no-time structures, a visual form entity comprises a hierarchical statistical map, and an application field entity comprises forest resources.
Step S50, calculating similarity values of map data, expression preference and application purpose according to the data characteristics, the visual dimension preference and the application purpose input by the user.
Specifically, a one-hot encoding (one-hot) is adopted to embed knowledge of data characteristics and visual dimensions of space data, as shown in fig. 4, entity nodes representing data information are regarded as states, N states are encoded by using N-bit state registers, and each state register is independent from the other; the process of embedding knowledge of spatial data information in a map knowledge graph by using independent thermal coding and converting the map knowledge graph into feature vectors is shown in fig. 4.
Wherein,representing a feature vector matrix obtained after the map knowledge graph is subjected to single-heat coding, m represents the number of spatial data strips, n represents the number of feature states, and a ij Representing the ith row and the jth column in the eigenvector matrix.
The similarity comprises three parts of spatial data characteristics, visual dimensions and application fields, wherein each part is calculated through a corresponding similarity model, and the similarity calculation is shown in formulas (1) - (3).
Calculating the feature similarity of the spatial data:
wherein D is 1 ，D 2 Representing spatial data features, D 1 D is a feature of the known spatial data in the knowledge base 2 For the characteristics of the spatial data input by the user, performing similarity calculation on the two data characteristics, and determining a similar result; d, d 1 ,d 2 Representing the data feature set and the card representing the potential or cardinality of the data feature set.
Calculating visual dimension similarity:
wherein V is 1 ，V 2 Representing the comprehensive similarity result under all visual dimension comparison, A, B representing visual dimension feature vectors, a i ，b i Representing a visualization dimension, a i B, for map visualization dimensions known in the knowledge base i A visualization dimension representing a user's propensity to apply; z represents the total number of visualization dimensions, and as can be seen in fig. 2, there are 12 dimensions in time, space, attributes, and several user dimensions, each of which may have a different value.
Calculating the similarity of application fields:
wherein T is 1 ，T 2 Representing the application field of a map, T 1 T is a known field of application 2 The application field is expressed for the map which the user tends to; k represents application domain similarity, k epsilon (0, 1), sim represents element similarity.
And S60, calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result.
Specifically, the map type similarity results are comprehensively calculated, and the overall similarity is calculated as follows:
wherein similarity represents overall similarity, ω represents weight, ω∈ (0, 1), ω 1 +ω 2 +ω 3 =1; the three kinds of visual element similarity are mutually independent and jointly influence the overall similarity, and when any similarity value is 0, the overall similarity value is also 0.
Based on the map knowledge graph, determining the map type with the highest similarity according to the space data, the visual dimension and the similarity comprehensive calculation result of the application field, and recommending a corresponding map result for the user.
Table 1: experimental data recommendation results
Table 1 shows the visual recommendation results corresponding to the three groups of experimental data, and the recommendation results have high accuracy, taking the production total value data, the subway line data and the living facility density data as examples. When experimental data information is input, geometric logic and space deformation dimension requirements are set, and the recommendation effect of the knowledge recommendation method on the map is checked.
Fig. 5 shows data characteristics, visualization dimensions, application fields and visualization forms of experimental data characteristic information corresponding to highly similar data nodes. Spatial data entities include financial revenue growth rate, stock exchange amount, living facility density distribution, industrial park density distribution, green road density, road network distribution, subway lines, rail transit networks, and production total values, data feature entities include parallel order, no order feature, hierarchical order, degree order, multi-category, single category, coincidence category, planar, linear, interval number feature, numerical number feature, countless number feature, discrete time feature, and no time feature, visual dimension entities include no time structure, static, vector, two-dimensional, abstract, discrete, continuity, no space deformation, topological relation, euclidean geometry, elephant, planar, and single scale, visual form entities include a Cartogram map, a linear symbol map, a schematic subway map, a hierarchical statistical map, and a network density map, and application field entities include financial finance, urban green road, urban traffic, advanced manufacturing, urban facilities, and comprehensive economy; the similarity value of the securities trade amount distribution data and the production total value data is 0.9, and the corresponding visual form is a Cartogram map; the similarity value of the rail transit network data and the subway line data is 0.92, and the corresponding visual form is a schematic subway map; the similarity value of the living facility density distribution data and the green road density distribution is 0.88, and the corresponding visual form is a hierarchical statistical map. The recommendation visual form can meet the visual expression requirement of the user, has higher rationality, and a diagraph can select the most suitable visual form from recommendation results.
The method is oriented to map self-adaptive visualization, the knowledge graph construction method is adopted, intelligent recommendation of the optimal map type can be achieved on the premise of defining map data, application scenes and user preferences, and the result is more scientific. The invention provides a map recommendation ontology model, which identifies the optimal map form from different data characteristics, expression preference and practical application angles.
Further, as shown in fig. 6, the present invention further provides a map adaptive recommendation system based on a knowledge graph, based on the map adaptive recommendation method based on a knowledge graph, where the map adaptive recommendation system based on a knowledge graph includes:
the map case instance library establishing module 51 is used for collecting a plurality of types of map cases and establishing a map case instance library;
the map recommendation ontology model construction module 52 is used for analyzing the data characteristics, the visual dimension, the application field and the visual form of the map and constructing a map recommendation ontology model;
the map expression feature library establishing module 53 is configured to analyze map features of map instances in the map case instance library based on a map recommendation ontology model, and establish a map expression feature library;
the map knowledge graph construction module 54 is configured to construct a map knowledge graph according to a preset mode based on the map recommendation ontology model and the map feature analysis result;
a similarity evaluation module 55 for calculating similarity values of map data, expression preference and application destination according to the data characteristics, visual dimension preference and application destination input by the user;
the map type self-adaptive recommendation module 56 is used for calculating the comprehensive value of the similarity of the map types, analyzing the map type with the highest similarity, and obtaining the final map recommendation result.
Further, as shown in fig. 7, the present invention further provides a terminal based on the map-based map adaptive recommendation method and system, and the terminal includes a processor 10, a memory 20 and a display 30. Fig. 7 shows only some of the components of the terminal, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may alternatively be implemented.
The memory 20 may in some embodiments be an internal storage unit of the terminal, such as a hard disk or a memory of the terminal. The memory 20 may in other embodiments also be an external storage device of the terminal, such as a plug-in hard disk provided on the terminal, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard) or the like. Further, the memory 20 may also include both an internal storage unit and an external storage device of the terminal. The memory 20 is used for storing application software installed in the terminal and various data, such as program codes of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In an embodiment, the memory 20 stores a map adaptive recommendation program 40 based on a knowledge map, and the map adaptive recommendation program 40 based on the knowledge map is executable by the processor 10, so as to implement the map adaptive recommendation method based on the knowledge map in the present application.
The processor 10 may be, in some embodiments, a Central processing unit (Central ProcessingUnit, CPU), microprocessor or other data processing chip for executing program codes or processing data stored in the memory 20, for example, performing the map-based map adaptive recommendation method, etc.
The display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (organic light-emitting diode) touch, or the like in some embodiments. The display 30 is used for displaying information at the terminal and for displaying a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.
In an embodiment, the steps of the knowledge-based map adaptive recommendation method described above are implemented when the processor 10 executes the knowledge-based map adaptive recommendation program 40 in the memory 20.
The present invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a map adaptive recommendation program based on a knowledge graph, and the map adaptive recommendation program based on the knowledge graph realizes the steps of the map adaptive recommendation method based on the knowledge graph when being executed by a processor.
In summary, the present invention provides a map adaptive recommendation method and related devices based on a knowledge graph, where the method includes: collecting a plurality of types of map cases, and establishing a map case instance library; analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model; based on a map recommendation ontology model, analyzing map features of map examples in the map case example library, and establishing a map expression feature library; based on the map recommendation ontology model and the map feature analysis result, constructing a map knowledge graph according to a preset mode; calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user; and calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result. The invention builds the map visual information knowledge base under different application scenes by using the knowledge map as the basis and through the map case-knowledge map-similarity matching-map type building flow, and carries out self-adaptive map recommendation according to the user drawing requirements, thereby assisting the drawing staff to quickly acquire the most suitable map type from the mass charts, improving the drawing efficiency and providing effective support for map diversification and personalized popularization and application.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal 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 terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal comprising the element.
Of course, those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by a computer program for instructing relevant hardware (e.g., processor, controller, etc.), the program may be stored on a computer readable storage medium, and the program may include the above described methods when executed. The computer readable storage medium may be a memory, a magnetic disk, an optical disk, etc.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (8)
1. The map self-adaptive recommendation method based on the knowledge graph is characterized by comprising the following steps of:
collecting a plurality of types of map cases, and establishing a map case instance library;
analyzing data characteristics, visual dimensions, application fields and visual forms of the map, and constructing a map recommendation ontology model;
based on a map recommendation ontology model, analyzing map features of map examples in the map case example library, and establishing a map expression feature library;
based on the map recommendation ontology model and the map feature analysis result, constructing a map knowledge graph according to a preset mode;
the map knowledge graph is constructed according to a preset mode based on the map recommendation ontology model and the map feature analysis result, and specifically comprises the following steps:
constructing formal description of a map recommendation body;
mapping the instance to a corresponding class, mapping the attribute to a corresponding attribute keyword, mapping the relationship to a corresponding relationship predicate, and realizing formal description of map expression knowledge based on the mapping relationship;
knowledge storage in the forms of space data, expression dimension, application field and visualization is carried out based on a Neo4J map database, and a map knowledge map is constructed according to a mode of entity-relation-entity or entity-attribute value;
calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user;
the calculating the similarity values of the map data, the expression preference and the application purpose according to the data characteristics, the visual dimension preference and the application purpose input by the user specifically comprises the following steps:
the method comprises the steps of performing knowledge embedding on data characteristics and visual dimensions of space data by adopting single-hot coding, taking entity nodes representing data information as states, and coding N states by using N-bit state registers, wherein each state register is mutually independent;
performing knowledge embedding on the spatial data information in the map knowledge graph by using the independent thermal coding, and converting the map knowledge graph into a feature vector;
wherein,representing a feature vector matrix obtained after the map knowledge graph is subjected to single-heat coding, m represents the number of spatial data strips, n represents the number of feature states, and a ij Representing the ith row and the jth column in the eigenvector matrix;
calculating the feature similarity of the spatial data:
calculating visual dimension similarity:
calculating the similarity of application fields:
wherein D is 1 ，D 2 Representing spatial data features, d 1 ,d 2 Representing a data feature set, the card representing a potential or cardinality of the data feature set;
wherein V is 1 ，V 2 Representing the comprehensive similarity result under all visual dimension comparison, A, B representing visual dimension feature vectors, a i ，b i Representing the visualization dimensions, z representing the total number of visualization dimensions;
wherein T is 1 ，T 2 Representing the application field of the map, k represents the application field similarity, k epsilon (0, 1), sim represents the element similarity;
and calculating the comprehensive value of the similarity of the map types, and analyzing the map type with the highest similarity to obtain a final map recommendation result.
2. The knowledge-based map adaptive recommendation method according to claim 1, wherein the gathering of a plurality of types of map cases and the establishment of a map case instance library specifically comprises:
retrieving a plurality of types of map cases from a plurality of channels;
and classifying and storing all the retrieved map cases to establish the map case instance library.
3. The knowledge-based map adaptive recommendation method of claim 1, wherein the data features comprise: temporal features, spatial features, and attribute features;
the visualization dimensions include: time dimension, space dimension, attribute dimension, and user dimension;
the application fields include: application fields facing to human use and application fields facing to object use;
the visualization form comprises: standard maps, ideographic maps, and pictorial maps.
4. The knowledge-graph-based map adaptive recommendation method according to claim 1, wherein the map-based recommendation ontology model analyzes map features of map instances in the map case instance library, and establishes a map expression feature library, and specifically comprises:
acquiring map cases to be identified in the map case instance library, and performing systematic deconstructment on data features, expression dimensions, application fields and visual types of various map cases according to characteristics of the map cases to be identified and by combining the map recommendation ontology model;
analyzing time, space and attribute characteristics of data under the map type, expressing the specific expression of the related time, space, attribute and user visual dimension, applying the application scene to which the map is applicable, and classifying the visual form to which the map belongs, and constructing the map expression characteristic library oriented to multiple subjects, multiple types and multiple users.
5. The knowledge-graph-based map self-adaptive recommendation method according to claim 1, wherein the calculating the comprehensive value of the map type similarity, analyzing the map type with the highest similarity, and obtaining the final map recommendation result comprises the following steps:
and comprehensively calculating a map type similarity result, wherein the overall similarity is calculated as follows:
wherein similarity represents overall similarity, ω represents weight, ω∈ (0, 1), ω 1 +ω 2 +ω 3 ＝1；
Based on the map knowledge graph, determining the map type with the highest similarity according to the space data, the visual dimension and the similarity comprehensive calculation result of the application field, and recommending a corresponding map result for the user.
6. The map self-adaptive recommendation system based on the knowledge graph is characterized by comprising:
the map case instance library establishing module is used for collecting a plurality of types of map cases and establishing a map case instance library;
the map recommendation ontology model construction module is used for analyzing the data characteristics, the visual dimension, the application field and the visual form of the map and constructing a map recommendation ontology model;
the map expression feature library establishing module is used for analyzing map features of map examples in the map case example library based on the map recommendation ontology model and establishing a map expression feature library;
the map knowledge graph construction module is used for constructing a map knowledge graph according to a preset mode based on the map recommendation ontology model and the map feature analysis result;
the map knowledge graph is constructed according to a preset mode based on the map recommendation ontology model and the map feature analysis result, and specifically comprises the following steps:
constructing formal description of a map recommendation body;
mapping the instance to a corresponding class, mapping the attribute to a corresponding attribute keyword, mapping the relationship to a corresponding relationship predicate, and realizing formal description of map expression knowledge based on the mapping relationship;
knowledge storage in the forms of space data, expression dimension, application field and visualization is carried out based on a Neo4J map database, and a map knowledge map is constructed according to a mode of entity-relation-entity or entity-attribute value;
the similarity evaluation module is used for calculating similarity values of map data, expression preference and application destination according to the data characteristics, the visual dimension preference and the application destination input by the user;
the calculating the similarity values of the map data, the expression preference and the application purpose according to the data characteristics, the visual dimension preference and the application purpose input by the user specifically comprises the following steps:
the method comprises the steps of performing knowledge embedding on data characteristics and visual dimensions of space data by adopting single-hot coding, taking entity nodes representing data information as states, and coding N states by using N-bit state registers, wherein each state register is mutually independent;
performing knowledge embedding on the spatial data information in the map knowledge graph by using the independent thermal coding, and converting the map knowledge graph into a feature vector;
wherein,representing a feature vector matrix obtained after the map knowledge graph is subjected to single-heat coding, m represents the number of spatial data strips, n represents the number of feature states, and a ij Representing the ith row and the jth column in the eigenvector matrix;
calculating the feature similarity of the spatial data:
calculating visual dimension similarity:
calculating the similarity of application fields:
wherein D is 1 ，D 2 Representing spatial data features, d 1 ,d 2 Representing a data feature set, the card representing a potential or cardinality of the data feature set;
wherein V is 1 ，V 2 Representing the comprehensive similarity result under all visual dimension comparison, A, B representing visual dimension feature vectors, a i ，b i Representing the visualization dimensions, z representing the total number of visualization dimensions;
wherein T is 1 ，T 2 Representing the application field of the map, k represents the application field similarity, k epsilon (0, 1), sim represents the element similarity;
and the map type self-adaptive recommendation module is used for calculating the comprehensive value of the similarity of the map types, analyzing the map type with the highest similarity and obtaining a final map recommendation result.
7. A terminal, the terminal comprising: a memory, a processor and a knowledge-based map adaptive recommendation program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the knowledge-based map adaptive recommendation method according to any of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a knowledge-graph based map adaptive recommendation program, which when executed by a processor, implements the steps of the knowledge-graph based map adaptive recommendation method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504997.3A CN116662528B (en) | 2023-05-06 | 2023-05-06 | Map self-adaptive recommendation method based on knowledge graph and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504997.3A CN116662528B (en) | 2023-05-06 | 2023-05-06 | Map self-adaptive recommendation method based on knowledge graph and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116662528A CN116662528A (en) | 2023-08-29 |
| CN116662528B true CN116662528B (en) | 2024-02-02 |
Family
ID=87710881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310504997.3A Active CN116662528B (en) | 2023-05-06 | 2023-05-06 | Map self-adaptive recommendation method based on knowledge graph and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116662528B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245204A (en) * | 2019-06-12 | 2019-09-17 | 桂林电子科技大学 | A kind of intelligent recommendation method based on positioning and knowledge mapping |
| CN114970547A (en) * | 2022-06-09 | 2022-08-30 | 深圳大学 | Multi-level and multi-type planning content difference identification and conflict elimination method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112000700A (en) * | 2020-07-14 | 2020-11-27 | 北京百度网讯科技有限公司 | Map information display method and device, electronic equipment and storage medium |
-
2023
- 2023-05-06 CN CN202310504997.3A patent/CN116662528B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245204A (en) * | 2019-06-12 | 2019-09-17 | 桂林电子科技大学 | A kind of intelligent recommendation method based on positioning and knowledge mapping |
| CN114970547A (en) * | 2022-06-09 | 2022-08-30 | 深圳大学 | Multi-level and multi-type planning content difference identification and conflict elimination method |
Non-Patent Citations (2)
| Title |
|---|
| Actual Image Data Generation and Application via Generative Adversarial Network;Ruiming Li等;《 2020 2nd International Conference on Applied Machine Learning (ICAML)》;329-332 * |
| 三元空间下的泛地图可视化维度;郭仁忠 等;武汉大学学报(信息科学版);第43卷(第11期);1603-1610 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116662528A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bartolini et al. | Recommending multimedia visiting paths in cultural heritage applications | |
| CN107193967A (en) | A kind of multi-source heterogeneous industry field big data handles full link solution | |
| Mackenzie | More parts than elements: how databases multiply | |
| CA2906232A1 (en) | Domain-specific syntax tagging in a functional information system | |
| Ma et al. | Large-scale graph visualization and analytics | |
| CN111291191B (en) | Broadcast television knowledge graph construction method and device | |
| CN107563407A (en) | A kind of character representation learning system of the multi-modal big data in network-oriented space | |
| Zoraghein et al. | Data-enriched interpolation for temporally consistent population compositions | |
| CN116108194A (en) | Knowledge graph-based search engine method, system, storage medium and electronic equipment | |
| CN116010722A (en) | Query method of dynamic multi-objective space-time problem based on grid space-time knowledge graph | |
| Liu et al. | Visual exploration of urban functional zones based on augmented nonnegative tensor factorization | |
| Dong et al. | Browsing behavior modeling and browsing interest extraction in the trajectories on web map service platforms | |
| CN117312680A (en) | Resource recommendation method based on user-entity sub-graph comparison learning | |
| CN116662528B (en) | Map self-adaptive recommendation method based on knowledge graph and related equipment | |
| CN115577519A (en) | Double-level multiple space-time coupling modeling method based on ontology and knowledge graph | |
| Xu et al. | Tourist Attraction Recommendation Method and Data Management Based on Big Data Analysis | |
| Lin et al. | The application of deep generative models in urban form generation based on topology: a review | |
| Qin et al. | Statistical System of Cultural Heritage Tourism Information Based on Image Feature Extraction Technology | |
| Courtat | Promenade dans les cartes de villes-phénoménologie mathématique et physique de la ville-une approche géométrique | |
| Kehrer | Interactive visual analysis of multi-faceted scientific data | |
| Deng et al. | MVCV-Traffic: multiview road traffic state estimation via cross-view learning | |
| Pokorny et al. | Big graph storage, processing and visualization | |
| CN103500219B (en) | The control method that a kind of label is adaptively precisely matched | |
| Aigner et al. | Visualization aspects | |
| Ma et al. | Learning resource recommendation via knowledge graphs and learning style clustering |
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 |