CN111159431A - Knowledge graph-based information visualization method, device, equipment and storage medium - Google Patents
Knowledge graph-based information visualization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111159431A CN111159431A CN201911424386.8A CN201911424386A CN111159431A CN 111159431 A CN111159431 A CN 111159431A CN 201911424386 A CN201911424386 A CN 201911424386A CN 111159431 A CN111159431 A CN 111159431A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge element
- entity
- element entity
- movie
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
Abstract
The invention belongs to the technical field of knowledge graphs, and discloses a method, a device, equipment and a storage medium for information visualization based on a knowledge graph. The method comprises the steps of determining an initial knowledge element entity according to knowledge element entity information input by a user; searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity; when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity; displaying the target and initial meta-knowledge entities through a current interface. By means of the method, the information of the user can be conveniently and quickly retrieved and checked when no specific target exists, the experience of the user in the aspect of resource retrieval is improved, and the technical problems that the information retrieval and checking are very inconvenient and the experience is poor when the user does not have the specific target in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of knowledge graphs, in particular to a method, a device, equipment and a storage medium for information visualization based on a knowledge graph.
Background
The knowledge graph technology is formally proposed by Google in 5 months 2012, and the original intention is to improve the capability of a search engine and enhance the search quality and experience of a user. At present, with the continuous development of intelligent information service application, the knowledge graph technology has been widely applied to the fields of intelligent search, intelligent question answering, personalized recommendation and the like. The data storage and use mode related to the knowledge map technology plays an important role in promoting machine understanding of the knowledge of the human world. The knowledge map technology displays the complex knowledge field through data mining, information processing, knowledge measurement and graph drawing, reveals the dynamic development rule of the knowledge field, and provides practical and valuable reference for subject research.
Knowledge-graph technology, which is generated from search engines, is also the most developed and applied in this field. At present, more application products consider information brought by knowledge graph technology, and optimize other information systems such as recommendation, intelligent question answering and the like. However, when the existing application products optimize recommendation and intelligently ask-answer by means of the knowledge graph technology, users are required to provide specific targeted information, so that information retrieval and viewing of the users are very inconvenient when the users do not have specific targets, and the experience of the users in the aspect of resource retrieval is poor.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a knowledge graph-based information visualization method, a knowledge graph-based information visualization device, knowledge graph-based information visualization equipment and a knowledge graph-based storage medium, and aims to solve the technical problems that in the prior art, a user is very inconvenient to retrieve and view information and poor in experience when the user does not have a specific target.
In order to achieve the above object, the present invention provides a method for visualizing information based on a knowledge graph, the method comprising the steps of:
determining an initial knowledge element entity according to knowledge element entity information input by a user;
searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity;
when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity;
displaying the target and initial meta-knowledge entities through a current interface.
Preferably, before the step of determining the initial knowledge element according to the knowledge element information input by the user, the method further includes:
obtaining corpus information of preset theme dimensionality;
inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities;
and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance.
Preferably, the step of searching for the associated principal knowledge entity corresponding to the initial principal knowledge entity in the preset knowledge graph and determining the graph distance between the associated principal knowledge entity and the initial principal knowledge entity specifically includes:
extracting a feature vector corresponding to the initial knowledge element entity from the preset knowledge graph according to the initial knowledge element entity;
searching for an associated knowledge element entity corresponding to the initial knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the preset knowledge map;
and determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
Preferably, after the steps of searching for the associated principal knowledge entity corresponding to the initial principal knowledge entity in the preset knowledge graph, and determining the graph distance between the associated principal knowledge entity and the initial principal knowledge entity, the method further includes:
sorting the map distances in size and obtaining a sorting result;
and selecting a preset number of target knowledge element entities from the associated knowledge element entities according to the sorting result.
Preferably, the step of displaying the target knowledgeable meta entity and the initial knowledgeable meta entity through the current interface specifically includes:
and taking the initial knowledge element entity as a display center, uniformly arranging the target knowledge element entity around the display center, and displaying an arrangement result through a current interface.
Preferably, after the step of displaying the target knowledgeable meta-entity and the initial knowledgeable meta-entity through the current interface, the method further comprises:
determining a skip knowledge element entity according to skip knowledge element entity information input by a user based on the current interface;
searching a projection matrix corresponding to the jumping knowledge element entity in a preset knowledge graph, and updating a preset graph distance between knowledge element entities in the preset knowledge graph according to the projection matrix to obtain a new knowledge graph;
searching a jump related knowledge element entity corresponding to the initial knowledge element entity in the new knowledge graph, and determining a jump graph distance between the jump related knowledge element entity and the initial knowledge element entity;
when the jump map distance belongs to the preset target distance range, taking a jump associated knowledge element entity corresponding to the jump map distance as a jump target knowledge element entity;
and displaying the initial knowledge element entity and the skip target knowledge element entity by taking the initial knowledge element entity as a center.
Preferably, after the step of displaying the target knowledgeable meta-entity and the initial knowledgeable meta-entity through the current interface, the method further comprises:
determining a mobile knowledge element entity according to mobile knowledge element entity information input by a user based on the current interface;
searching a mobile associated knowledge element entity corresponding to the mobile knowledge element entity in a preset knowledge graph, and determining the distance between the mobile associated knowledge element entity and the mobile knowledge element entity;
when the moving map distance belongs to the preset target distance range, taking a moving associated knowledge element entity corresponding to the moving map distance as a moving target knowledge element entity;
and displaying the moving target knowledge element entity and the moving knowledge element entity by taking the moving knowledge element entity as a center.
In addition, to achieve the above object, the present invention further provides an apparatus for visualizing information based on a knowledge graph, the apparatus comprising:
the input module is used for determining an initial knowledge element entity according to the knowledge element entity information input by a user;
the searching module is used for searching the associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge map and determining the map distance between the associated knowledge element entity and the initial knowledge element entity;
the target module is used for taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity when the map distance belongs to a preset target distance range;
and the display module is used for displaying the target knowledge element entity and the initial knowledge element entity through the current interface.
In addition, to achieve the above object, the present invention also provides an electronic device, including: a memory, a processor, and a knowledge-graph based information visualization program stored on the memory and executable on the processor, the knowledge-graph based information visualization program configured to implement the steps of the knowledge-graph based information visualization method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having a knowledge-graph based information visualization program stored thereon, wherein the knowledge-graph based information visualization program, when executed by a processor, implements the steps of the knowledge-graph based information visualization method as described above.
The method comprises the steps of determining an initial knowledge element entity according to knowledge element entity information input by a user; searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity; when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity; displaying the target and initial meta-knowledge entities through a current interface. By the aid of the method, the information of the user can be quickly retrieved and checked when the user does not have the specific target, the experience of the user in the aspect of resource retrieval is improved, and the technical problems that the information of the user is very inconvenient to retrieve and check when the user does not have the specific target and the experience is poor in the prior art are solved.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a knowledge-graph-based information visualization method according to the present invention;
FIG. 3 is a diagram illustrating a visualization of general dimension information according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a second embodiment of a knowledge-graph based information visualization method according to the present invention;
FIG. 5 is a flow chart of a third embodiment of the method for knowledge-graph-based information visualization according to the present invention;
FIG. 6 is a schematic diagram illustrating the visualization of jump dimension information according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating a fourth embodiment of a knowledge-graph based information visualization method according to the present invention;
fig. 8 is a schematic view illustrating visualization of mobile center information according to an embodiment of the present invention;
fig. 9 is a block diagram of a first embodiment of the knowledge-graph based information visualization apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a knowledge-graph-based information visualization program.
In the electronic apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the electronic device according to the present invention may be provided in the electronic device, and the electronic device calls the information visualization program based on the knowledge graph stored in the memory 1005 through the processor 1001 and executes the method for visualizing information based on the knowledge graph according to the embodiment of the present invention.
The embodiment of the invention provides a knowledge graph-based information visualization method, and referring to fig. 2, fig. 2 is a schematic flow diagram of a first embodiment of the knowledge graph-based information visualization method.
In this embodiment, the method for information visualization based on a knowledge graph includes the following steps:
step S10: and determining an initial knowledge element entity according to the knowledge element entity information input by the user.
In this embodiment, before the step of determining the initial knowledge element entity according to the knowledge element entity information input by the user, a preset knowledge graph needs to be constructed, where constructing the preset knowledge graph includes acquiring corpus information of a preset topic dimension; inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities; and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance. The corpus information is input into the TransR model corresponding to the preset topic dimension, and the preferred model in this embodiment is the TransR model, and other models may also be used to construct a knowledge graph, which is not limited in this embodiment.
It is easy to understand that, the initial knowledge element entity is determined according to the knowledge element entity information input by the user, for example, a preset knowledge map is constructed by taking a movie domain as an example, assuming that movie a is a movie that the user has viewed, when the user has no specific target, the user needs to perform quick information retrieval and viewing, the user decides to use movie a as a starting point of the search, and then the initial knowledge element entity is determined according to the knowledge element entity information input by the user, and at this time, the initial knowledge element entity can be regarded as movie a.
Step S20: searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity.
It should be noted that the step of searching for the associated principal knowledge entity corresponding to the initial principal knowledge entity in the preset knowledge graph, and determining the graph distance between the associated principal knowledge entity and the initial principal knowledge entity specifically includes: extracting a feature vector corresponding to the initial knowledge element entity from the preset knowledge graph according to the initial knowledge element entity; searching for an associated knowledge element entity corresponding to the initial knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the preset knowledge map; and determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
In a specific implementation, an initial knowledge element entity may be regarded as a movie a, a feature vector corresponding to the initial knowledge element entity, that is, the movie a, is extracted from a preset knowledge graph and may be recorded as H, and an associated knowledge element entity corresponding to the initial knowledge element entity is searched according to the feature vector H and a preset graph distance between knowledge element entities included in the preset knowledge graph, where the preset graph distance between knowledge element entities included in the preset knowledge graph is artificially defined when the preset knowledge graph is constructed according to a TransR model, and an expression form of the preset graph distance may be adjusted according to an actual requirement, which is not limited in this embodiment, and it is assumed that the associated knowledge element entity corresponding to the initial knowledge element entity, that is, the movie a, includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, And determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
Step S30: and when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity.
Specifically, when the graph distance belongs to a preset target distance range, the associated knowledge element entity corresponding to the graph distance is used as a target knowledge element entity. The preset target distance range is artificially defined, the size of the preset target distance range may be adjusted according to actual requirements, which is not limited in this embodiment, and it is assumed that the initial knowledge element entity, that is, the associated knowledge element entity corresponding to the movie a includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, a movie I, a movie J, and a movie K, where the map distance belongs to the preset target distance range and includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, and a movie I.
It is easy to understand that after the steps of searching the associated knowledgeable entity corresponding to the initial knowledgeable entity in the preset knowledge graph and determining the graph distance between the associated knowledgeable entity and the initial knowledgeable entity, the method further includes: sorting the map distances in size and obtaining a sorting result; and selecting a preset number of target knowledge element entities from the associated knowledge element entities according to the sorting result. The preset number is artificially defined, the preset number may be adjusted according to actual requirements, this embodiment is not limited to this, it is assumed that the initial intellectual element entity, that is, the associated intellectual element entity corresponding to the movie a, includes movie B, movie C, movie D, movie E, movie F, movie G, movie H, movie I, movie J, and movie K, where the preset number is 8, the graph distances of the associated intellectual element entities are sorted in size, and the obtained sorting result is movie B, movie C, movie D, movie E, movie F, movie G, movie H, movie I, movie J, and movie K, and the preset number of target intellectual element entities is selected from the associated intellectual element entities according to the sorting result, and the obtained target intellectual element entity is movie B, movie C, movie D, movie E, and movie K, Movie F, movie G, movie H, movie I.
Step S40: displaying the target and initial meta-knowledge entities through a current interface.
It should be noted that the step of displaying the target knowledgeable entity and the initial knowledgeable entity through the current interface specifically includes: and taking the initial knowledge element entity as a display center, uniformly arranging the target knowledge element entity around the display center, and displaying an arrangement result through a current interface. The display mode of the current interface may be defined manually, and may be adjusted according to actual requirements, which is not limited in this embodiment.
Specifically, the initial knowledge element entity movie a is used as a display center, the target knowledge element entities, namely, movie B, movie C, movie D, movie E, movie F, movie G, movie H, and movie I, are uniformly arranged around the display center, and the arrangement result is displayed through the current interface. As shown in fig. 3, fig. 3 is a schematic diagram of visualization of general dimension information according to an embodiment of the present invention; wherein, the initial knowledgeable meta-entity is movie a (as a in fig. 3), and the target knowledgeable meta-entity is movie B (as B in fig. 3), movie C (as C in fig. 3), movie D (as D in fig. 3), movie E (as E in fig. 3), movie F (as F in fig. 3), movie G (as G in fig. 3), movie H (as H in fig. 3), and movie I (as I in fig. 3) are uniformly arranged around the display center, that is, movie a (as a in fig. 3).
The embodiment determines an initial knowledge element entity according to the knowledge element entity information input by a user; searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity; when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity; displaying the target and initial meta-knowledge entities through a current interface. By the aid of the method, the information of the user can be quickly retrieved and checked when the user does not have the specific target, the experience of the user in the aspect of resource retrieval is improved, and the technical problems that the information of the user is very inconvenient to retrieve and check when the user does not have the specific target and the experience is poor in the prior art are solved.
Referring to fig. 4, fig. 4 is a flowchart illustrating a second embodiment of a method for knowledge-graph-based information visualization according to the present invention.
Based on the first embodiment, before the step S10, the method for visualizing information based on a knowledge-graph according to this embodiment further includes:
step S101: and obtaining corpus information of preset theme dimensionality.
It should be noted that, the corpus information of at least one field of the knowledge graph to be constructed is acquired, and the corpus information may include: a plurality of knowledge text content segments. The knowledge graph can be constructed by a knowledge graph construction system, which can be a hardware device such as a computer, a server, or the like, or software installed on the hardware device. Where a field may refer to a professional field, such as the "metallurgy" field, the "economic" field, the "medical" field, etc., a field may have a number of sub-fields, such as the "pediatric medicine" field below the "medical" field. The corpus information refers to knowledge text content segments, and the corpus information of the knowledge graph to be constructed in the embodiment may be a movie "chase dragon". A knowledge text content segment such as "the movie chases dragon was featured by liudeluxe".
Step S102: and inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, characteristic vectors of the knowledge element entities and preset map distances among the knowledge element entities.
It is easy to understand that, the corpus information is input into the TransR model corresponding to the preset topic dimension, the model in this embodiment is preferably a TransR model, and other models may also be used to construct a knowledge graph, which is not limited in this embodiment. For example, typical work of the domestic and foreign knowledge graph representation method mainly includes methods such as an embedded model TransE based on translation, an embedded model TransH based on a hyperplane, an embedded model TransR based on an entity relationship space, an embedded model CTRANsR based on a clustering and entity relationship space, and an embedded model TransD based on a dynamic mapping matrix, and the methods are collectively called a knowledge representation model based on translation. Each relation r is represented by establishing a mapping matrix Mr and a vector r, specifically, the head entity vector h and the tail entity vector t are mapped to the hierarchy of the relation vector r by the TransR through a matrix, so that Mrh + r Mrt is obtained, that is, the optimization target of the embedded model TransR based on the entity relation space.
Specifically, the corpus information is input into a transR model corresponding to the preset topic dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities. Inputting the corpus information into a TransR model, wherein the corpus information may include: the method comprises the steps that a plurality of knowledge text content segments are subjected to word segmentation and part-of-speech tagging, keywords in the knowledge text content segments are obtained, the keywords are matched with a domain ontology according to preset rules, and knowledge element examples, attributes of the knowledge element examples and incidence relations among the knowledge element examples in the knowledge text content segments are obtained; the domain ontology includes: the system comprises a domain theme, at least one model included in the domain theme, attributes of the models and incidence relations among the models; the model includes at least one instance of a knowledge element. The domain theme can refer to a professional domain or a sub-domain, the professional domain can have a plurality of sub-domains, each domain can have a plurality of models, each model can have own specific attributes, and the models can have various association relations. And translating the corpus information into corresponding knowledge element entities, characteristic vectors of the knowledge element entities and preset map distances among the knowledge element entities through a TransR model. Wherein, the preset map distance between the knowledge entity entities included in the preset knowledge map is artificially defined when the preset knowledge map is constructed according to the TransR model, the expression form of the preset map distance can be adjusted according to the actual requirement, which is not limited in this embodiment,
step S103: and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance.
The embodiment obtains corpus information of preset theme dimensions; inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities; and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance. By means of the method, the visual characteristic of the preset knowledge graph is used, the information retrieval of the non-specific target is provided for the user, the information of the user can be conveniently and quickly retrieved and checked when no specific target exists, and the experience of the user in the aspect of resource retrieval is improved.
Referring to fig. 5, fig. 5 is a flowchart illustrating a third embodiment of a method for knowledge-graph-based information visualization according to the present invention.
Based on the first embodiment, after the step S40, the method for visualizing information based on a knowledge-graph further includes:
step S51: and determining the skip knowledge element entity according to skip knowledge element entity information input by the user based on the current interface.
It is easy to understand that the target and initial meta-knowledge entities are displayed through the current interface. Specifically, the initial knowledge element entity movie a is used as a display center, the target knowledge element entities, namely, movie B, movie C, movie D, movie E, movie F, movie G, movie H, and movie I, are uniformly arranged around the display center, and the arrangement result is displayed through the current interface. And determining a jumping knowledge element entity according to jumping knowledge element entity information input by a user based on the current interface, specifically, if the user selects dimension jumping and needs to select jumping dimension, determining the jumping knowledge element entity by the user based on the jumping knowledge element entity information input by the current interface, and assuming that the jumping knowledge element entity is a 'leading role' relationship dimension.
Step S52: and searching a projection matrix corresponding to the jumping knowledge element entities in a preset knowledge graph, and updating preset graph distances among the knowledge element entities in the preset knowledge graph according to the projection matrix to obtain a new knowledge graph.
It should be noted that, if the user selects the dimension to jump, the user needs to select the dimension to jump, and the user determines the jumping knowledge entity based on the jumping knowledge entity information input by the current interface, and assumes that the jumping knowledge entity is the "leading" relationship dimension. And searching a corresponding projection matrix Mr when the jumping knowledge element entities are in a 'leading role' relation dimension in a preset knowledge graph, and updating preset graph distances among the knowledge element entities in the preset knowledge graph according to the projection matrix, namely, pre-multiplying the knowledge element entities in the preset knowledge graph by the projection matrix Mr to obtain a new knowledge graph.
Step S53: and searching a jump related knowledge element entity corresponding to the initial knowledge element entity in the new knowledge graph, and determining a jump graph distance between the jump related knowledge element entity and the initial knowledge element entity.
It should be noted that the step of searching the new knowledge graph for the jump related knowledge element entity corresponding to the initial knowledge element entity and determining the jump graph distance between the jump related knowledge element entity and the initial knowledge element entity specifically includes: extracting a feature vector corresponding to the initial knowledge element entity from the new knowledge graph according to the initial knowledge element entity; searching a skip associated knowledge element entity corresponding to the initial knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the new knowledge map; and determining the jump map distance between the jump associated knowledge element entity and the initial knowledge element entity according to the search result.
In a specific implementation, if a jumping knowledgeable entity is a "lead actor" relationship dimension, a corresponding projection matrix is marked as Mr when the jumping knowledgeable entity is the "lead actor" relationship dimension in a preset knowledgeable map, a preset map distance between knowledgeable entities in the preset knowledgeable map is updated according to the projection matrix, namely, each knowledgeable entity in the preset knowledgeable map is multiplied by the projection matrix Mr to obtain a new knowledgeable map, a feature vector corresponding to the initial knowledgeable entity is extracted from the new knowledgeable map and can be marked as h1, a jumping associated knowledgeable entity corresponding to the initial knowledgeable entity is found according to the feature vector h1 and the preset map distance between knowledgeable entities contained in the new knowledgeable map, and the jumping associated knowledgeable entity corresponding to the initial knowledgeable entity comprises a movie B, a movie playing, and a movie, And determining the jump map distance between the jump associated knowledge element entity and the initial knowledge element entity according to the search result.
Step S54: and when the jump map distance belongs to the preset target distance range, taking the jump associated knowledge element entity corresponding to the jump map distance as a jump target knowledge element entity.
Specifically, when the jump map distance belongs to a preset target distance range, the jump associated knowledge element entity corresponding to the jump map distance is used as a jump target knowledge element entity. The preset target distance range is artificially defined, the size of the preset target distance range may be adjusted according to actual requirements, this embodiment is not limited thereto, it is assumed that the jumping intellectual element entity is a "lead actor" relationship dimension, the jumping associated intellectual element entity corresponding to the initial intellectual element entity includes a movie B, a movie J, a movie M, a movie E, a movie K, a movie L, a movie H, a movie I, a movie X, and a movie Y, and the jumping map distance belongs to the preset target distance range and includes a movie B, a movie J, a movie M, a movie E, a movie K, a movie L, a movie H, and a movie I.
As will be readily appreciated, the method further comprises: sorting the jump map distances according to size, and acquiring a sorting result; and selecting a preset number of skip target knowledge element entities from the skip associated knowledge element entities according to the sequencing result. The preset number is artificially defined, the size of the preset number can be adjusted according to actual requirements, the embodiment is not limited thereto, it is assumed that the jumping intellectual element entity is a "lead actor" relationship dimension, the jumping associated intellectual element entity corresponding to the initial intellectual element entity includes movie B, movie J, movie M, movie E, movie K, movie L, movie H, movie I, movie X, and movie Y, wherein the preset number is 8, the jumping map distances of the jumping associated intellectual element entities are sorted in size, the jumping sorting result is obtained as movie B, movie J, movie M, movie E, movie K, movie L, movie H, movie I, movie X, and movie Y, the jumping target intellectual element entities with the preset number of 8 are selected from the jumping associated intellectual element entities according to the jumping sorting result, and the jumping target intellectual element entity is obtained as movie B, movie J, movie M, movie E, movie K, movie L, movie H, movie I, movie X, and movie Y, Movie J, movie M, movie E, movie K, movie L, movie H, movie I.
Step S55: and displaying the initial knowledge element entity and the skip target knowledge element entity by taking the initial knowledge element entity as a center.
It should be noted that the initial knowledgeable entity and the skip target knowledgeable entity are displayed through the current interface pair. The display mode of the current interface may be defined manually, and may be adjusted according to actual requirements, which is not limited in this embodiment.
Specifically, the initial knowledge element entity movie a is used as a display center, the jump target knowledge element entities, namely, movie B, movie J, movie M, movie E, movie K, movie L, movie H and movie I, are uniformly arranged around the display center, and the arrangement result is displayed through the current interface. As shown in fig. 6, fig. 6 is a schematic view illustrating the skip dimension information visualization according to the embodiment of the present invention; wherein, the initial knowledgeable meta-entity is movie a (as a in fig. 6), and the jumping target knowledgeable meta-entities are uniformly arranged around the display center, that is, movie a (as a in fig. 6), such as movie B (as B in fig. 6), movie J (as J in fig. 6), movie M (as M in fig. 6), movie E (as E in fig. 6), movie K (as K in fig. 6), movie L (as L in fig. 6), movie H (as H in fig. 6), and movie I (as I in fig. 6).
It is easy to understand that if two employees of a company are considered in reality, the graph distance between employee a and employee B, i.e. the correlation between employee a and employee B, if the correlation between employee a and employee B is considered in the relation dimension of work, the correlation between employee a and employee B may be high due to the same leadership, and if the graph distance between employee a and employee B, i.e. the correlation between employee a and employee B, is considered in the relation dimension of blood margin, the correlation between employee a and employee B may be low. But the kindred of employee a and the kindred of employee B are not listed because the dimension jumps to the relationship dimension of the kindred, and the consideration is still the atlas distance between employee a and employee B, i.e. the correlation between employee a and employee B. The leadership and kindred relatives of the employee A and the employee B are only mentioned to better understand the distance between the employee A and the employee B and the degree of correlation, and actually, when dimension skip is carried out, a skip knowledge element entity is determined according to skip knowledge element entity information input by a user based on the current interface; searching a projection matrix corresponding to the jumping knowledge element entity in a preset knowledge graph, and updating a preset graph distance between knowledge element entities in the preset knowledge graph according to the projection matrix to obtain a new knowledge graph; and in the new knowledge graph, computing the graph distance aiming at the employee A and the employee B.
It should be noted that, in order to improve the personalization capability when constructing the preset knowledge graph, attribute values such as user scores, user browsing volumes, user comment numbers and the like may be collected, taking the movie field as an example, the preset knowledge graph is constructed by using the attribute values such as the user scores, the user browsing volumes, the user comment numbers and the like, wherein each movie is still an entity, the user browsing volumes, the user scores, the user comment numbers and the like are new relations in the preset knowledge graph, each user is a new entity, the triple (h, r, t) array of the knowledge element entity may be analyzed as that the user α has watched the movie a once, and the corpus information of the preset theme dimension is obtained to construct the preset knowledge graph, so that the preset knowledge graph is updated, the projection matrix of the relation dimension of the feature vector and the behavior (such as the user scores, the user browsing volumes, the user comment numbers) of the user entity is increased, therefore, according to the steps S51 to S55, a target of skip operation may be added, which is called as a user dimension, and the user dimension represents the meaning of different product group application preferences corresponding to the actual physical internal physical relationship of the user.
The embodiment determines the jumping knowledge element entity according to the jumping knowledge element entity information input by the user based on the current interface; searching a projection matrix corresponding to the jumping knowledge element entity in a preset knowledge graph, and updating a preset graph distance between knowledge element entities in the preset knowledge graph according to the projection matrix to obtain a new knowledge graph; searching a jump related knowledge element entity corresponding to the initial knowledge element entity in the new knowledge graph, and determining a jump graph distance between the jump related knowledge element entity and the initial knowledge element entity; when the jump map distance belongs to the preset target distance range, taking a jump associated knowledge element entity corresponding to the jump map distance as a jump target knowledge element entity; and displaying the initial knowledge element entity and the skip target knowledge element entity by taking the initial knowledge element entity as a center. The dimension jumping is carried out in the mode, and the technical problems that information retrieval and viewing are very inconvenient and experience is poor when a user does not have a specific target in the prior art are solved.
Referring to fig. 7, fig. 7 is a flowchart illustrating a method for knowledge-graph-based information visualization according to a fourth embodiment of the present invention.
Based on the first embodiment, after the step S40, the method for visualizing information based on a knowledge-graph further includes:
step S61: and determining the mobile knowledge element entity according to the mobile knowledge element entity information input by the user based on the current interface.
It is easy to understand that the target and initial meta-knowledge entities are displayed through the current interface. Specifically, the initial knowledge element entity movie a is used as a display center, the target knowledge element entities, namely, movie B, movie C, movie D, movie E, movie F, movie G, movie H, and movie I, are uniformly arranged around the display center, and the arrangement result is displayed through the current interface. And determining the mobile knowledge meta-entity according to the mobile knowledge meta-entity information input by the user based on the current interface, specifically, if the user selects the center to move and needs to reselect the knowledge meta-entity of the center, determining the mobile knowledge meta-entity by the user based on the mobile knowledge meta-entity information input by the current interface, and assuming that the mobile knowledge meta-entity is movie B.
Step S62: and searching a mobile associated knowledge element entity corresponding to the mobile knowledge element entity in a preset knowledge graph, and determining the distance between the mobile associated knowledge element entity and the mobile knowledge element entity.
It should be noted that the step of searching for the mobile associated intellectual element entity corresponding to the mobile intellectual element entity in the preset knowledge graph and determining the mobile graph distance between the mobile associated intellectual element entity and the mobile intellectual element entity specifically includes: extracting a feature vector corresponding to the mobile knowledge element entity from a preset knowledge map according to the mobile knowledge element entity; searching a mobile associated knowledge element entity corresponding to the mobile knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the preset knowledge map; and determining the mobile map distance between the mobile associated knowledge element entity and the mobile knowledge element entity according to the search result.
In a specific implementation, the mobile knowledgeable entity may be regarded as a movie B, a feature vector corresponding to the mobile knowledgeable entity, that is, the movie B, is extracted from a preset knowledge graph and may be recorded as h2, and a mobile associated knowledgeable entity corresponding to the mobile knowledgeable entity is searched according to the feature vector h2 and a preset graph distance between the knowledgeable entities included in the preset knowledge graph, where the preset graph distance between the knowledgeable entities included in the preset knowledge graph is artificially defined when the preset knowledge graph is constructed according to a TransR model, and a representation form of the preset graph distance may be adjusted according to an actual requirement, which is not limited in this embodiment, and it is assumed that the mobile knowledgeable entity, that is, the mobile associated knowledgeable entity corresponding to the movie B, includes a movie D, a movie J, a movie P, a movie E, a movie Q, a movie O, a movie B, and a movie B, And determining the moving map distance between the moving associated knowledge element entity and the moving knowledge element entity according to the search result.
Step S63: and when the moving map distance belongs to the preset target distance range, taking the moving associated knowledge element entity corresponding to the moving map distance as a moving target knowledge element entity.
Specifically, when the mobile map distance belongs to a preset target distance range, the mobile associated knowledge element entity corresponding to the mobile map distance is used as a mobile target knowledge element entity. The preset target distance range is artificially defined, the size of the preset target distance range may be adjusted according to actual requirements, which is not limited in this embodiment, and it is assumed that the mobile knowledgeable entity, that is, the mobile associated knowledgeable entity corresponding to the movie B, includes movie D, movie J, movie P, movie E, movie Q, movie O, movie N, movie a, movie Z, and movie V, where the mobile map distance belongs to the preset target distance range and includes movie D, movie J, movie P, movie E, movie Q, movie O, movie N, and movie a.
As will be readily appreciated, the method further comprises: sorting the distances of the mobile atlas according to the size, and acquiring a mobile sorting result; and selecting a preset number of moving target knowledge element entities from the moving associated knowledge element entities according to the moving sequencing result. The preset number is artificially defined, the size of the preset number may be adjusted according to actual requirements, this embodiment is not limited thereto, and assuming that the mobile knowledgeable entity, that is, the mobile associated knowledgeable entity corresponding to the movie B, includes movie D, movie J, movie P, movie E, movie Q, movie O, movie N, movie a, movie Z, and movie V, where the preset number is 8, the mobile atlas distances of the mobile associated knowledgeable entities are sorted in size, and a mobile sorting result of movie D, movie J, movie P, movie E, movie Q, movie O, movie N, movie a, movie Z, and movie V is obtained, a preset number of 8 mobile target knowledgeable entities are selected from the mobile associated knowledgeable entities according to the mobile sorting result, and the mobile target knowledgeable entity is obtained as movie D, movie Z, movie V, or movie V, Movie J, movie P, movie E, movie Q, movie O, movie N, movie a.
Step S64: and displaying the moving target knowledge element entity and the moving knowledge element entity by taking the moving knowledge element entity as a center.
It should be noted that the moving target knowledge entity and the moving knowledge entity are displayed through the current interface. The method specifically comprises the following steps: and taking the mobile knowledge element entity as a display center, uniformly arranging the mobile target knowledge element entity around the display center, and displaying an arrangement result through a current interface. The display mode of the current interface may be defined manually, and may be adjusted according to actual requirements, which is not limited in this embodiment.
Specifically, the moving target intellectual element entities, namely, the movie D, the movie J, the movie P, the movie E, the movie Q, the movie O, the movie N, and the movie a, are uniformly arranged around the display center with the moving intellectual element entity movie B as the display center, and the arrangement result is displayed through the current interface. As shown in fig. 8, fig. 8 is a schematic diagram illustrating visualization of mobile center information according to an embodiment of the present invention; wherein, the moving knowledgeable meta-entity is movie B, and the moving target knowledgeable meta-entities are, for example, movie D (e.g., D in fig. 8), movie J (e.g., J in fig. 8), movie P (e.g., P in fig. 8), movie E (E in fig. 8), movie Q (e.g., Q in fig. 8), movie O (e.g., O in fig. 8), movie N (e.g., N in fig. 8), and movie a (e.g., a in fig. 8) are uniformly arranged around the display center, that is, movie B (e.g., B in fig. 8).
It should be noted that the user can perform the move and jump mixing operation any number of times. And theoretically, the user can reach any one of the knowledge meta-entities through two operations of moving and jumping. The user can intuitively know various conditions from multiple angles through two operation modes of moving and jumping, and can more conveniently retrieve the result which is in line with the imagination of the user but is inconvenient to express as the search word by characters or language according to the existing cognition of the user.
For example, the user α selects 10 movies from the user browsing amount as the central point, extracts the intellectual entity vectors of the 10 movies, calculates the mean value of the intellectual entity vectors of the 10 movies as the central intellectual entity selected by the user α, and also requests the user to provide the weighted mean value of the 10 movies as the central intellectual entity selected by the user α. the central intellectual entity selected by the user α is used as the display center, and the central intellectual entity is used as the initial intellectual entity, which can be displayed according to steps S10-S40 in the flow diagram of the first embodiment of the knowledge graph-based information visualization method of the present invention, and in addition, the user α can perform any number of mixed operations of jumping dimension and movement, see the flow diagrams of the third embodiment and the fourth embodiment of the knowledge graph-based information visualization method of the present invention, or can reselect the central intellectual entity for retrieval.
The embodiment determines the mobile knowledge element entity according to the mobile knowledge element entity information input by the user based on the current interface; searching a mobile associated knowledge element entity corresponding to the mobile knowledge element entity in a preset knowledge graph, and determining the distance between the mobile associated knowledge element entity and the mobile knowledge element entity; when the moving map distance belongs to the preset target distance range, taking a moving associated knowledge element entity corresponding to the moving map distance as a moving target knowledge element entity; and displaying the moving target knowledge element entity and the moving knowledge element entity by taking the moving knowledge element entity as a center. The center is moved in the mode, and the technical problems that information retrieval and viewing are very inconvenient and experience is poor when a user does not have a specific target in the prior art are solved.
Furthermore, an embodiment of the present invention further provides a storage medium, on which a knowledge-graph based information visualization program is stored, which when executed by a processor implements the steps of the knowledge-graph based information visualization method as described above.
Referring to fig. 9, fig. 9 is a block diagram illustrating a first embodiment of a knowledge-graph-based information visualization apparatus according to the present invention.
As shown in fig. 9, the apparatus for visualizing information based on a knowledge-graph according to an embodiment of the present invention includes:
an input module 10, configured to determine an initial knowledge element entity according to the knowledge element entity information input by the user.
In this embodiment, before the step of determining the initial knowledge element entity according to the knowledge element entity information input by the user, a preset knowledge graph needs to be constructed, where constructing the preset knowledge graph includes acquiring corpus information of a preset topic dimension; inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities; and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance. The corpus information is input into the TransR model corresponding to the preset topic dimension, and the preferred model in this embodiment is the TransR model, and other models may also be used to construct a knowledge graph, which is not limited in this embodiment.
It is easy to understand that, the initial knowledge element entity is determined according to the knowledge element entity information input by the user, for example, a preset knowledge map is constructed by taking a movie domain as an example, assuming that movie a is a movie that the user has viewed, when the user has no specific target, the user needs to perform quick information retrieval and viewing, the user decides to use movie a as a starting point of the search, and then the initial knowledge element entity is determined according to the knowledge element entity information input by the user, and at this time, the initial knowledge element entity can be regarded as movie a.
The searching module 20 is configured to search for an associated principal knowledge entity corresponding to the initial principal knowledge entity in a preset knowledge graph, and determine a graph distance between the associated principal knowledge entity and the initial principal knowledge entity.
It should be noted that the step of searching for the associated principal knowledge entity corresponding to the initial principal knowledge entity in the preset knowledge graph, and determining the graph distance between the associated principal knowledge entity and the initial principal knowledge entity specifically includes: extracting a feature vector corresponding to the initial knowledge element entity from the preset knowledge graph according to the initial knowledge element entity; searching for an associated knowledge element entity corresponding to the initial knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the preset knowledge map; and determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
In a specific implementation, an initial knowledge element entity may be regarded as a movie a, a feature vector corresponding to the initial knowledge element entity, that is, the movie a, is extracted from a preset knowledge graph and may be recorded as H, and an associated knowledge element entity corresponding to the initial knowledge element entity is searched according to the feature vector H and a preset graph distance between knowledge element entities included in the preset knowledge graph, where the preset graph distance between knowledge element entities included in the preset knowledge graph is artificially defined when the preset knowledge graph is constructed according to a TransR model, and an expression form of the preset graph distance may be adjusted according to an actual requirement, which is not limited in this embodiment, and it is assumed that the associated knowledge element entity corresponding to the initial knowledge element entity, that is, the movie a, includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, And determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
And the target module 30 is configured to take the associated principal as a target principal corresponding to the graph distance when the graph distance belongs to a preset target distance range.
Specifically, when the graph distance belongs to a preset target distance range, the associated knowledge element entity corresponding to the graph distance is used as a target knowledge element entity. The preset target distance range is artificially defined, the size of the preset target distance range may be adjusted according to actual requirements, which is not limited in this embodiment, and it is assumed that the initial knowledge element entity, that is, the associated knowledge element entity corresponding to the movie a includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, a movie I, a movie J, and a movie K, where the map distance belongs to the preset target distance range and includes a movie B, a movie C, a movie D, a movie E, a movie F, a movie G, a movie H, and a movie I.
It is easy to understand that after the steps of searching the associated knowledgeable entity corresponding to the initial knowledgeable entity in the preset knowledge graph and determining the graph distance between the associated knowledgeable entity and the initial knowledgeable entity, the method further includes: sorting the map distances in size and obtaining a sorting result; and selecting a preset number of target knowledge element entities from the associated knowledge element entities according to the sorting result. The preset number is artificially defined, the preset number may be adjusted according to actual requirements, this embodiment is not limited to this, it is assumed that the initial intellectual element entity, that is, the associated intellectual element entity corresponding to the movie a, includes movie B, movie C, movie D, movie E, movie F, movie G, movie H, movie I, movie J, and movie K, where the preset number is 8, the graph distances of the associated intellectual element entities are sorted in size, and the obtained sorting result is movie B, movie C, movie D, movie E, movie F, movie G, movie H, movie I, movie J, and movie K, and the preset number of target intellectual element entities is selected from the associated intellectual element entities according to the sorting result, and the obtained target intellectual element entity is movie B, movie C, movie D, movie E, and movie K, Movie F, movie G, movie H, movie I.
A display module 40, configured to display the target knowledgeable entity and the initial knowledgeable entity through the current interface.
It should be noted that the step of displaying the target knowledgeable entity and the initial knowledgeable entity through the current interface specifically includes: and taking the initial knowledge element entity as a display center, uniformly arranging the target knowledge element entity around the display center, and displaying an arrangement result through a current interface. The display mode of the current interface may be defined manually, and may be adjusted according to actual requirements, which is not limited in this embodiment.
Specifically, the initial knowledge element entity movie a is used as a display center, the target knowledge element entities, namely, movie B, movie C, movie D, movie E, movie F, movie G, movie H, and movie I, are uniformly arranged around the display center, and the arrangement result is displayed through the current interface. As shown in fig. 3, fig. 3 is a schematic diagram of visualization of general dimension information according to an embodiment of the present invention; wherein, the initial knowledgeable meta-entity is movie a (as a in fig. 3), and the target knowledgeable meta-entity is movie B (as B in fig. 3), movie C (as C in fig. 3), movie D (as D in fig. 3), movie E (as E in fig. 3), movie F (as F in fig. 3), movie G (as G in fig. 3), movie H (as H in fig. 3), and movie I (as I in fig. 3) are uniformly arranged around the display center, that is, movie a (as a in fig. 3).
The embodiment is used for determining an initial knowledge element entity according to knowledge element entity information input by a user through an input module 10; the searching module 20 is configured to search a preset knowledge graph for an associated principal knowledge entity corresponding to the initial principal knowledge entity, and determine a graph distance between the associated principal knowledge entity and the initial principal knowledge entity; the target module 30 is configured to, when the graph distance belongs to a preset target distance range, use the associated principal as a target principal corresponding to the graph distance; a display module 40, configured to display the target knowledgeable entity and the initial knowledgeable entity through the current interface. By the aid of the method, the information of the user can be quickly retrieved and checked when the user does not have the specific target, the experience of the user in the aspect of resource retrieval is improved, and the technical problems that the information of the user is very inconvenient to retrieve and check when the user does not have the specific target and the experience is poor in the prior art are solved.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the method for visualizing information based on a knowledge graph provided in any embodiment of the present invention, and are not described herein again.
Further, it is to 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 system 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 system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for knowledge-graph-based information visualization, the method comprising:
determining an initial knowledge element entity according to knowledge element entity information input by a user;
searching for an associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge graph, and determining a graph distance between the associated knowledge element entity and the initial knowledge element entity;
when the map distance belongs to a preset target distance range, taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity;
displaying the target and initial meta-knowledge entities through a current interface.
2. The method of claim 1, wherein the step of determining an initial knowledgeable meta-entity based on user-entered knowledgeable entity information is preceded by the step of:
obtaining corpus information of preset theme dimensionality;
inputting the corpus information into a TransR model corresponding to the preset theme dimension to obtain corresponding knowledge element entities, feature vectors of the knowledge element entities and preset map distances among the knowledge element entities;
and constructing a preset knowledge graph according to the knowledge element entity, the characteristic vector of the knowledge element entity and the preset graph distance.
3. The method according to claim 2, wherein the step of searching for the associated intellectual entity corresponding to the initial intellectual entity in the preset knowledge graph and determining the graph distance between the associated intellectual entity and the initial intellectual entity specifically comprises:
extracting a feature vector corresponding to the initial knowledge element entity from the preset knowledge graph according to the initial knowledge element entity;
searching for an associated knowledge element entity corresponding to the initial knowledge element entity according to the feature vector and a preset map distance between knowledge element entities contained in the preset knowledge map;
and determining the map distance between the associated knowledge element entity and the initial knowledge element entity according to the search result.
4. The method of claim 3, wherein after the steps of finding the associated knowledgeable entity corresponding to the initial knowledgeable entity in the preset knowledgegraph and determining the graph distance between the associated knowledgeable entity and the initial knowledgeable entity, the method further comprises:
sorting the map distances in size and obtaining a sorting result;
and selecting a preset number of target knowledge element entities from the associated knowledge element entities according to the sorting result.
5. The method of claim 4, wherein the step of displaying the target and initial meta-knowledge entities via the current interface comprises:
and taking the initial knowledge element entity as a display center, uniformly arranging the target knowledge element entity around the display center, and displaying an arrangement result through a current interface.
6. The method of claim 2, wherein after the step of displaying the target and initial meta-knowledge entities via the current interface, further comprising:
determining a skip knowledge element entity according to skip knowledge element entity information input by a user based on the current interface;
searching a projection matrix corresponding to the jumping knowledge element entity in a preset knowledge graph, and updating a preset graph distance between knowledge element entities in the preset knowledge graph according to the projection matrix to obtain a new knowledge graph;
searching a jump related knowledge element entity corresponding to the initial knowledge element entity in the new knowledge graph, and determining a jump graph distance between the jump related knowledge element entity and the initial knowledge element entity;
when the jump map distance belongs to the preset target distance range, taking a jump associated knowledge element entity corresponding to the jump map distance as a jump target knowledge element entity;
and displaying the initial knowledge element entity and the skip target knowledge element entity by taking the initial knowledge element entity as a center.
7. The method of claim 2, wherein after the step of displaying the target and initial meta-knowledge entities via the current interface, further comprising:
determining a mobile knowledge element entity according to mobile knowledge element entity information input by a user based on the current interface;
searching a mobile associated knowledge element entity corresponding to the mobile knowledge element entity in a preset knowledge graph, and determining the distance between the mobile associated knowledge element entity and the mobile knowledge element entity;
when the moving map distance belongs to the preset target distance range, taking a moving associated knowledge element entity corresponding to the moving map distance as a moving target knowledge element entity;
and displaying the moving target knowledge element entity and the moving knowledge element entity by taking the moving knowledge element entity as a center.
8. An apparatus for knowledge-graph based information visualization, the apparatus comprising:
the input module is used for determining an initial knowledge element entity according to the knowledge element entity information input by a user;
the searching module is used for searching the associated knowledge element entity corresponding to the initial knowledge element entity in a preset knowledge map and determining the map distance between the associated knowledge element entity and the initial knowledge element entity;
the target module is used for taking the associated knowledge element entity corresponding to the map distance as a target knowledge element entity when the map distance belongs to a preset target distance range;
and the display module is used for displaying the target knowledge element entity and the initial knowledge element entity through the current interface.
9. An electronic device, characterized in that the device comprises: a memory, a processor, and a knowledge-graph based information visualization program stored on the memory and executable on the processor, the knowledge-graph based information visualization program configured to implement the steps of the knowledge-graph based information visualization method of any one of claims 1 to 7.
10. A storage medium having stored thereon a knowledgegraph-based information visualization program that, when executed by a processor, performs the steps of the method of any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424386.8A CN111159431A (en) | 2019-12-30 | 2019-12-30 | Knowledge graph-based information visualization method, device, equipment and storage medium |
| PCT/CN2020/111114 WO2021135290A1 (en) | 2019-12-30 | 2020-08-25 | Information visualization method, apparatus and device based on knowledge graph, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424386.8A CN111159431A (en) | 2019-12-30 | 2019-12-30 | Knowledge graph-based information visualization method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111159431A true CN111159431A (en) | 2020-05-15 |
Family
ID=70560774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911424386.8A Pending CN111159431A (en) | 2019-12-30 | 2019-12-30 | Knowledge graph-based information visualization method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111159431A (en) |
| WO (1) | WO2021135290A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858784A (en) * | 2020-07-21 | 2020-10-30 | 广东科杰通信息科技有限公司 | Personnel relativity prediction method based on transH |
| CN112395506A (en) * | 2020-12-04 | 2021-02-23 | 上海帜讯信息技术股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN112464627A (en) * | 2020-11-05 | 2021-03-09 | 北京科技大学 | Manual text labeling tool and method for coreference relationship |
| WO2021135290A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳Tcl新技术有限公司 | Information visualization method, apparatus and device based on knowledge graph, and storage medium |
| WO2021139105A1 (en) * | 2020-05-29 | 2021-07-15 | 平安科技（深圳）有限公司 | Data map-based search method, smart terminal, and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460083A (en) * | 2018-01-16 | 2018-08-28 | 浙江大学 | A kind of knowledge mapping visual query tool |
| CN108694177A (en) * | 2017-04-06 | 2018-10-23 | 北大方正集团有限公司 | Knowledge mapping construction method and system |
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109992673A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | A kind of knowledge mapping generation method, device, equipment and readable storage medium storing program for executing |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345399B (en) * | 2018-10-23 | 2024-03-26 | 平安科技（深圳）有限公司 | Method, device, computer equipment and storage medium for evaluating risk of claim settlement |
| CN110334219B (en) * | 2019-07-12 | 2023-05-09 | 电子科技大学 | Knowledge graph representation learning method based on attention mechanism integrated with text semantic features |
| CN111159431A (en) * | 2019-12-30 | 2020-05-15 | 深圳Tcl新技术有限公司 | Knowledge graph-based information visualization method, device, equipment and storage medium |
-
2019
- 2019-12-30 CN CN201911424386.8A patent/CN111159431A/en active Pending
-
2020
- 2020-08-25 WO PCT/CN2020/111114 patent/WO2021135290A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694177A (en) * | 2017-04-06 | 2018-10-23 | 北大方正集团有限公司 | Knowledge mapping construction method and system |
| CN108460083A (en) * | 2018-01-16 | 2018-08-28 | 浙江大学 | A kind of knowledge mapping visual query tool |
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109992673A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | A kind of knowledge mapping generation method, device, equipment and readable storage medium storing program for executing |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021135290A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳Tcl新技术有限公司 | Information visualization method, apparatus and device based on knowledge graph, and storage medium |
| WO2021139105A1 (en) * | 2020-05-29 | 2021-07-15 | 平安科技（深圳）有限公司 | Data map-based search method, smart terminal, and readable storage medium |
| CN111858784A (en) * | 2020-07-21 | 2020-10-30 | 广东科杰通信息科技有限公司 | Personnel relativity prediction method based on transH |
| CN112464627A (en) * | 2020-11-05 | 2021-03-09 | 北京科技大学 | Manual text labeling tool and method for coreference relationship |
| CN112464627B (en) * | 2020-11-05 | 2021-12-03 | 北京科技大学 | Manual text labeling tool and method for coreference relationship |
| CN112395506A (en) * | 2020-12-04 | 2021-02-23 | 上海帜讯信息技术股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021135290A1 (en) | 2021-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111159431A (en) | Knowledge graph-based information visualization method, device, equipment and storage medium | |
| US10698956B2 (en) | Active knowledge guidance based on deep document analysis | |
| US9569541B2 (en) | Evaluating preferences of content on a webpage | |
| US7769771B2 (en) | Searching a document using relevance feedback | |
| JP2019507417A (en) | User interface for multivariable search | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| CN109906450A (en) | For the method and apparatus by similitude association to electronic information ranking | |
| US11010360B2 (en) | Extending tags for information resources | |
| CN107315833A (en) | Method and apparatus of the retrieval with downloading based on application program | |
| JP2018504686A (en) | Method and apparatus for processing search data | |
| JP2007528531A (en) | Search service system and method for providing input order of keywords by category | |
| CN110008396B (en) | Object information pushing method, device, equipment and computer readable storage medium | |
| US9152698B1 (en) | Substitute term identification based on over-represented terms identification | |
| JP2000222418A (en) | Method and device for retrieving data base | |
| CN112231554A (en) | Search recommendation word generation method and device, storage medium and computer equipment | |
| CN111602129B (en) | Smart search for notes and ink | |
| JP6163143B2 (en) | Information providing apparatus, information providing method, and information providing program | |
| CN107577388B (en) | Input interface control method and device | |
| JP2007233752A (en) | Retrieval device, computer program and recording medium | |
| CN113076395A (en) | Semantic model training, search and display method, device, equipment and storage medium | |
| JP2009199164A (en) | Document management device, document management method and recording medium | |
| JP2017072964A (en) | Information analyzing apparatus and information analyzing method | |
| JP2010015394A (en) | Link destination presentation device and computer program | |
| CN111797257B (en) | Picture recommendation method and related equipment based on word vector | |
| JP7323484B2 (en) | Information processing device, information processing method, and program |
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 |