CN117973520B - Method for constructing intelligent community knowledge graph based on big data visualization - Google Patents
Method for constructing intelligent community knowledge graph based on big data visualization Download PDFInfo
- Publication number
- CN117973520B CN117973520B CN202410370767.7A CN202410370767A CN117973520B CN 117973520 B CN117973520 B CN 117973520B CN 202410370767 A CN202410370767 A CN 202410370767A CN 117973520 B CN117973520 B CN 117973520B
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge graph
- information
- representation
- association
- 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 16
- 238000013079 data visualisation Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 109
- 230000014509 gene expression Effects 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 22
- 238000010276 construction Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to big data processing technology, and discloses a method for constructing a knowledge graph of an intelligent community based on big data visualization, which comprises the following steps: and processing the structured data acquired by the intelligent community by utilizing the knowledge graph to obtain a structural set of the structured data, and representing unstructured data and semi-structured data by taking the structural set of the structured data as a basis, so that the whole expression is consistent. And under the condition that the knowledge graph model supports the upper limit of the data processing capacity, and the upper limit of the data processing capacity of the knowledge graph model is lower than the storage capacity of any one storage unit, sending a data loading request to at least one storage unit with the same mark, and transmitting data information by at least one storage unit according to the data loading request in a capacity supporting the upper limit of the data processing capacity of the knowledge graph model, so that the knowledge graph model can extract and fuse the data information under full load.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a method for constructing an intelligent community knowledge graph based on big data visualization.
Background
The data generated by the intelligent community is diversified, from structured data and semi-structured data to unstructured data, when the data are uniformly processed, the semi-structured data and the unstructured data are expressed as structured data, and the knowledge graph of the intelligent community can be uniformly constructed, in the prior art, as disclosed in the publication number of CN112883201A, a knowledge graph construction method based on large data of the intelligent community is disclosed, and comprises S1) acquiring data; s2) knowledge extraction is carried out on the semi-structured data and the unstructured data to form second structured data; s3) data integration is carried out on the first structured data, and a preliminary intelligent community knowledge graph is formed; s4) knowledge representation: knowledge representation is carried out on the second structured data and the first structured data; s5) knowledge fusion: entity linking and knowledge merging are carried out on the entities, the relations and the attributes of the entities in the second structured data; s6) resolving conflicts in the construction process of the intelligent community map; s7) updating the intelligent community knowledge graph: updating of the data pattern layer and updating of the data layer. Aiming at multiple types of data, multiple persons, multiple types of behavior characteristics and multiple samples, the invention constructs the intelligent community big data knowledge graph, and provides important support for intelligent city service. In the technology, knowledge extraction is actually performed on semi-structured data and unstructured data to form structured data, and because the semi-structured data and unstructured data are subjected to knowledge extraction, a chain word (seed word) is constructed, when the constructed chain word does not accord with the expression of the structural data in a corresponding intelligent community, the obtained structural data actually deviate, and in addition, a plurality of computers are required to perform synchronous processing for a large amount of data processing, so that the construction of a real representation large model cannot be realized.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method for constructing a knowledge graph of an intelligent community based on big data visualization.
The main technical scheme is as follows:
The method for constructing the intelligent community knowledge graph based on big data visualization comprises the following steps:
And acquiring deployment line information and equipment information of all acquisition ends of the intelligent community, and connecting the acquisition ends with the same equipment information on the same deployment line to the same equipment node.
The equipment nodes are encoded, so that the equipment nodes of the acquisition end for converging the same equipment information have the same codes, corresponding transmission paths are respectively set for the equipment nodes with the same codes on different deployment lines, and the transmission paths corresponding to the equipment nodes with the same codes are configured to the same storage unit.
And marking the storage units according to the types of the storage data in the storage units, so that the storage units with the same data structure are configured to have the same mark, and setting independent loading paths for the storage units according to the mark.
And configuring a knowledge graph model, and when the upper limit of the knowledge graph model supporting data processing capacity is lower than the storage capacity of any one storage unit, sending a data loading request to at least one storage unit with the same mark, and transmitting data information by at least one storage unit according to the data loading request so as to enable the knowledge graph model to extract and fuse the data information under full load under the condition that the upper limit of the knowledge graph model supporting data processing capacity is supported.
Preferably, a knowledge graph model is configured, when the knowledge graph model supports the upper limit of the data processing capability, and the upper limit of the data processing capability of the knowledge graph model is larger than the sum of storage capacities of any one of a plurality of storage units with the same mark, a data loading request is sent to a task management module, according to the data loading request, the task management module configures a plurality of storage units with different marks according to the upper limit of the data processing capability of the knowledge graph model, and establishes data information transmission with the knowledge graph model by the configured storage units with different marks, so that the knowledge graph model can extract and fuse data information under full load.
Preferably, the task management module and the plurality of storage units are respectively associated according to marks, wherein a detection unit and a task allocation unit are arranged in the task management module, wherein the detection unit is used for acquiring the storage capacity of data in each storage unit, and configuring the storage capacity detected by each storage unit into the task allocation unit.
The task allocation unit configures a plurality of storage units with different marks according to the upper limit of the data processing capability supported by the knowledge graph model, and establishes data information transmission with the knowledge graph model by the configured storage units with different marks so as to enable the knowledge graph model to extract and fuse data information under full load.
Preferably, the knowledge graph model has:
the data structure identification module is provided with a plurality of identification units, and the identification units are connected with the accessed storage units in a one-to-one correspondence manner and are used for acquiring the data structure of the data information transmitted by each accessed storage unit.
The first processing unit is connected with the data structure identification module and used for accessing data information of which the data structure is structured data, performing entity extraction, semantic extraction and relation extraction on the data information of the structured data to obtain a first entity representation information set, a first semantic representation information set and a first relation representation information set, and forming an intelligent community knowledge graph set by the obtained first entity representation information set, the first semantic representation information set and the first relation representation information set.
The second processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of which the data structure is semi-structured data, the data information of the semi-structured data is represented by taking the intelligent community knowledge graph set as a basis of data representation in the second processing unit, a second entity representation information set, a second semantic representation information set and a second relation representation information set corresponding to the data information of the semi-structured data are obtained, and the second entity representation information set, the second semantic representation information set and the second relation representation information set are fused to the intelligent community knowledge graph set.
The third processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of unstructured data, the data information of semi-structured data is represented by taking the intelligent community knowledge graph set as a basis of data representation in the third processing unit, a third entity representation information set, a third semantic representation information set and a third relation representation information set corresponding to the data information of unstructured data are obtained, and the third entity representation information set, the third semantic representation information set and the third relation representation information set are fused to the intelligent community knowledge graph set.
Preferably, the data structure identification module is provided with a priority configuration unit, and the priority configuration unit is used for correspondingly configuring priorities of the first processing unit, the second processing unit and the third processing unit according to the data structure identified by the identification unit.
The first processing unit is used for processing the structured data, the second processing unit is used for processing the semi-structured data, and the third processing unit is used for processing the unstructured data.
And the priority of the first processing unit > the priority of the second processing unit > the priority of the third processing unit.
Preferably, the second processing unit uses the intelligent community knowledge graph set as a basis of the data representation, which means that a basic configuration of the data representation is obtained from the intelligent community knowledge graph set, and a first set of entity representations, a second set of semantic representations and a third set of relation representations of data information of the semi-structured data are obtained based on the basic configuration.
Executing a first fusion instruction, and fusing a third set which is provided with a first set related to entity representation and expressed by a relation as an association tie to form a second entity representation information set; and recording the corresponding association relation to form a first association set.
Executing a second fusion instruction, and fusing a third set which is expressed by a relation with the second set of semantic expressions as an association tie to form a second semantic expression information set; and recording the corresponding association relation to form a second association set.
And executing a third fusion instruction, and fusing the first association set, the second association set and the third set of relationship representation to obtain a second relationship representation information set.
Preferably, the third processing unit uses the intelligent community knowledge graph set as a basis of the data representation, which means that a basic configuration of the data representation is obtained from the intelligent community knowledge graph set, and a fourth set of entity representations, a fifth set of semantic representations and a sixth set of relation representations of data information of unstructured data are obtained based on the basic configuration.
Executing a fourth fusion instruction, and fusing a sixth set which is related to entity representation and is represented by a relation with a fourth set as an association tie to form a third entity representation information set; and recording the corresponding association relation to form a third association set.
Executing a fifth fusion instruction, and fusing a sixth set which is expressed by a relation with a third set of semantic expressions as an association tie to form a third semantic expression information set; and recording the corresponding association relation to form a fourth association set.
And executing a sixth fusion instruction, and fusing the third association set, the fourth association set and the sixth set of relation representation to obtain a third relation representation information set.
Preferably, executing a third fusion instruction, firstly comparing the first association set, the second association set and the third set of relationship representation one by one, eliminating the coincident association relationship, and then fusing to obtain the second relationship representation information set.
Preferably, executing a sixth fusion instruction, firstly comparing the third association set, the fourth association set and the sixth association set represented by the relationship one by one, eliminating the coincident association relationship, and then fusing to obtain a third relationship representation information set.
According to the invention, a knowledge graph model is formed by using historical data collected by the intelligent community, then the structured data collected by the intelligent community is processed by using the knowledge graph to obtain the structure set of the structured data, meanwhile, the structured data is processed firstly by setting priority, and then the unstructured data and the semi-structured data are represented by taking the structure set of the structured data as a basis, so that the whole expression is consistent. Meanwhile, when data processing is carried out, data information is transmitted by adopting the capacity supporting the upper limit of the data processing capacity of the knowledge graph model, so that the knowledge graph model is known to extract and fuse the data information under full load, and the processing efficiency of the knowledge graph model is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method provided by the invention.
Fig. 2 is a schematic diagram of a knowledge graph model provided by the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings.
In the smart community, some collected community personnel information, face data, vehicle information, participation information, age structure information and the like are typical structured data, different information structures with human subjects can be obtained through relation extraction, association relation is obtained through association of the information structures, such as sex, age, community property information, vehicle information, working information, participation information and the like of a person, all association information of the person in the community can be obtained, and association relation based on the person is formed. Similarly, the object may be a reference, such as vehicle information, corresponding payment information of vehicles in a community, vehicle in-out information, and the like, and when these data are correlated, diversified structure data may be formed.
The application utilizes the historical data collected in the intelligent community to carry out entity extraction, semantic extraction and relation extraction to obtain a structured data set, constructs a primary knowledge graph model through the structured data set, and sets the knowledge graph model to ensure that the knowledge graph model has the function of identifying a data structure and the function of respectively processing structured data, semi-structured data and unstructured data, and the semi-structured data and the unstructured data are represented by taking the structure set obtained by the structured data as a basis, wherein the structure set comprises: entity representation information set, semantic representation information set, and relationship representation information set.
The invention provides a method for constructing a knowledge graph of an intelligent community based on big data visualization, which comprises the following steps: acquiring deployment line information and equipment information of all acquisition ends of the intelligent community, and connecting the acquisition ends with the same equipment information on the same deployment line to the same equipment node; encoding the equipment nodes so that the equipment nodes of the acquisition end for converging the same equipment information have the same codes, respectively setting corresponding transmission paths for the equipment nodes with the same codes on different deployment lines, and configuring the transmission paths corresponding to the equipment nodes with the same codes to the same storage unit; marking the storage units according to the storage data types in the storage units, so that the storage units with the same data structure are configured to have the same mark, and setting independent loading paths for the storage units according to the mark; and configuring a knowledge graph model, and when the upper limit of the knowledge graph model supporting data processing capacity is lower than the storage capacity of any one storage unit, sending a data loading request to at least one storage unit with the same mark, and transmitting data information by at least one storage unit according to the data loading request so as to enable the knowledge graph model to extract and fuse the data information under full load under the condition that the upper limit of the knowledge graph model supporting data processing capacity is supported.
In the application, the deployment of the acquisition end is carried out according to the corresponding electric circuit topology, and the acquisition end comprises various sensors (voltage, current, temperature sensors and the like, and also comprises face recognition, infrared induction, monitoring equipment, gate control equipment and the like). In the above, the same acquisition end and the same deployment line have the same code, corresponding transmission paths are respectively set for the equipment nodes with the same code on different deployment lines, and the transmission paths corresponding to the equipment nodes with the same code are configured to the same storage unit; therefore, the data information acquired by the same acquisition end is stored in the fixed storage unit, and the structure types of the acquired data are consistent because the equipment information of the acquisition end is consistent, so that the data structure is not required to be reclassified, and the setting of data classification is reduced.
The knowledge graph model processing capability can be configured according to the use conditions of different communities, and for general communities, background processing can be constructed, peak staggering processing can be also performed, for example, the data volume collected by the communities in the daytime is relatively large, at the moment, the processing is not performed, or only structured data processing is performed, and at night, semi-structured and unstructured data are processed.
In one embodiment, when the upper limit of the data processing capability of the knowledge graph model is lower than the storage capacity of any one of the storage units, a data loading request is sent to at least one storage unit with the same label, and the at least one storage unit transmits data information according to the data loading request in a capacity supporting the upper limit of the data processing capability of the knowledge graph model, so that the knowledge graph model can extract and fuse the data information under full load.
In another embodiment, a knowledge graph model is configured, when the knowledge graph model supports the upper limit of the data processing capability, and the upper limit of the data processing capability of the knowledge graph model is larger than the sum of storage capacities of any one of a plurality of storage units with the same mark, a data loading request is sent to a task management module, according to the data loading request, the task management module configures a plurality of storage units with different marks according to the upper limit of the data processing capability of the knowledge graph model, and establishes data information transmission with the knowledge graph model by the configured storage units with different marks, so that the knowledge graph model is known to extract and fuse data information under full load.
In order to match the implementation of the above embodiment, the task management module and the plurality of storage units are respectively associated according to marks, wherein a detection unit and a task allocation unit are arranged in the task management module, the detection unit is used for acquiring the storage capacity of the data in each storage unit, and the storage capacity detected by each storage unit is configured in the task allocation unit; the task allocation unit configures a plurality of storage units with different marks according to the upper limit of the data processing capability supported by the knowledge graph model, and establishes data information transmission with the knowledge graph model by the configured storage units with different marks so as to enable the knowledge graph model to extract and fuse data information under full load.
In the application, when the configuration of the knowledge graph model is carried out, the knowledge graph model is specifically divided according to the following functions, wherein the knowledge graph model comprises: the data structure identification module is provided with a plurality of identification units, and the identification units are in one-to-one correspondence connection with the accessed storage units and are used for acquiring the data structure of the data information transmitted by each accessed storage unit; the first processing unit is connected with the data structure identification module and used for accessing data information of which the data structure is structured data, performing entity extraction, semantic extraction and relation extraction on the data information of the structured data to obtain a first entity representation information set, a first semantic representation information set and a first relation representation information set, and forming an intelligent community knowledge graph set by the obtained first entity representation information set, the first semantic representation information set and the first relation representation information set; the second processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of which the data structure is semi-structured data, the data information of the semi-structured data is represented by taking the intelligent community knowledge graph set as a basis of data representation in the second processing unit, a second entity representation information set, a second semantic representation information set and a second relation representation information set corresponding to the data information of the semi-structured data are obtained, and the second entity representation information set, the second semantic representation information set and the second relation representation information set are fused to the intelligent community knowledge graph set; the third processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of unstructured data, the data information of semi-structured data is represented by taking the intelligent community knowledge graph set as a basis of data representation in the third processing unit, a third entity representation information set, a third semantic representation information set and a third relation representation information set corresponding to the data information of unstructured data are obtained, and the third entity representation information set, the third semantic representation information set and the third relation representation information set are fused to the intelligent community knowledge graph set.
In order to enable the knowledge graph model to represent semi-structured data and unstructured data based on structured data, priorities of a first processing unit, a second processing unit and a third processing unit are required to be set, wherein a priority configuration unit is arranged in the data structure identification module and is used for correspondingly configuring priorities of the first processing unit, the second processing unit and the third processing unit according to the data structure identified by the identification unit; the first processing unit is used for processing the structured data, the second processing unit is used for processing the semi-structured data, and the third processing unit is used for processing the unstructured data; and the priority of the first processing unit > the priority of the second processing unit > the priority of the third processing unit. The corresponding processing orders are different under the set priority, and the processing is sequentially performed according to the size of the priority.
In the foregoing, the second processing unit uses the smart community knowledge graph set as a basis of the data representation, which means that a basic configuration of the data representation is obtained from the smart community knowledge graph set, and a first set of entity representations, a second set of semantic representations and a third set of relational representations of data information of the semi-structured data are obtained based on the basic configuration; executing a first fusion instruction, and fusing a third set which is provided with a first set related to entity representation and expressed by a relation as an association tie to form a second entity representation information set; recording corresponding association relations to form a first association set; executing a second fusion instruction, and fusing a third set which is expressed by a relation with the second set of semantic expressions as an association tie to form a second semantic expression information set; recording corresponding association relations to form a second association set; and executing a third fusion instruction, and fusing the first association set, the second association set and the third set of relationship representation to obtain a second relationship representation information set.
In the foregoing, the third processing unit uses the smart community knowledge graph set as a basis of the data representation, which means that a basic configuration of the data representation is obtained from the smart community knowledge graph set, and a fourth set of entity representations, a fifth set of semantic representations and a sixth set of relational representations of data information of unstructured data are obtained based on the basic configuration; executing a fourth fusion instruction, and fusing a sixth set which is related to entity representation and is represented by a relation with a fourth set as an association tie to form a third entity representation information set; recording corresponding association relations to form a third association set; executing a fifth fusion instruction, and fusing a sixth set which is expressed by a relation with a third set of semantic expressions as an association tie to form a third semantic expression information set; recording corresponding association relations to form a fourth association set; and executing a sixth fusion instruction, and fusing the third association set, the fourth association set and the sixth set of relation representation to obtain a third relation representation information set.
Preferably, executing a third fusion instruction, firstly comparing the first association set, the second association set and the third set of relationship representation one by one, eliminating the coincident association relationship, and then fusing to obtain the second relationship representation information set. Executing a sixth fusion instruction, firstly comparing the third association set, the fourth association set and the sixth set of relation representation one by one, eliminating the coincident association relation, and then fusing to obtain a third relation representation information set.
According to the invention, a knowledge graph model is formed by using historical data collected by the intelligent community, then the structured data collected by the intelligent community is processed by using the knowledge graph to obtain the structure set of the structured data, meanwhile, the structured data is processed firstly by setting priority, and then the unstructured data and the semi-structured data are represented by taking the structure set of the structured data as a basis, so that the whole expression is consistent. Meanwhile, when data processing is carried out, data information is transmitted by adopting the capacity supporting the upper limit of the data processing capacity of the knowledge graph model, so that the knowledge graph model is known to extract and fuse the data information under full load, and the processing efficiency of the knowledge graph model is improved.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (7)
1. The method for constructing the intelligent community knowledge graph based on big data visualization is characterized by comprising the following steps of:
acquiring deployment line information and equipment information of all acquisition ends of the intelligent community, and connecting the acquisition ends with the same equipment information on the same deployment line to the same equipment node;
Encoding the equipment nodes so that the equipment nodes of the acquisition end for converging the same equipment information have the same codes, respectively setting corresponding transmission paths for the equipment nodes with the same codes on different deployment lines, and configuring the transmission paths corresponding to the equipment nodes with the same codes to the same storage unit;
marking the storage units according to the storage data types in the storage units, so that the storage units with the same data structure are configured to have the same mark, and setting independent loading paths for the storage units according to the mark;
Configuring a knowledge graph model, when the knowledge graph model supports the upper limit of the data processing capacity and the upper limit of the data processing capacity of the knowledge graph model is lower than the storage capacity of any one storage unit, sending a data loading request to at least one storage unit with the same mark, and enabling at least one storage unit to transmit data information according to the data loading request by the capacity of supporting the upper limit of the data processing capacity of the knowledge graph model so as to enable the knowledge graph model to extract and fuse the data information under full load;
The knowledge graph model has:
The data structure identification module is provided with a plurality of identification units, and the identification units are in one-to-one correspondence connection with the accessed storage units and are used for acquiring the data structure of the data information transmitted by each accessed storage unit;
The first processing unit is connected with the data structure identification module and used for accessing data information of which the data structure is structured data, performing entity extraction, semantic extraction and relation extraction on the data information of the structured data to obtain a first entity representation information set, a first semantic representation information set and a first relation representation information set, and forming an intelligent community knowledge graph set by the obtained first entity representation information set, the first semantic representation information set and the first relation representation information set;
The second processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of which the data structure is semi-structured data, the data information of the semi-structured data is represented by taking the intelligent community knowledge graph set as a basis of data representation in the second processing unit, a second entity representation information set, a second semantic representation information set and a second relation representation information set corresponding to the data information of the semi-structured data are obtained, and the second entity representation information set, the second semantic representation information set and the second relation representation information set are fused to the intelligent community knowledge graph set;
The third processing unit is connected with the data structure identification module and the first processing unit and is used for accessing data information of unstructured data with a data structure, the data information of the unstructured data is represented by taking the intelligent community knowledge graph set as a data representation basis in the third processing unit, a third entity representation information set, a third semantic representation information set and a third relation representation information set corresponding to the data information of the unstructured data are obtained, and the third entity representation information set, the third semantic representation information set and the third relation representation information set are fused to the intelligent community knowledge graph set;
The data structure identification module is provided with a priority configuration unit which is used for correspondingly configuring the priorities of the first processing unit, the second processing unit and the third processing unit according to the data structure identified by the identification unit;
The first processing unit is used for processing the structured data, the second processing unit is used for processing the semi-structured data, and the third processing unit is used for processing the unstructured data;
and the priority of the first processing unit > the priority of the second processing unit > the priority of the third processing unit.
2. The method for constructing the intelligent community knowledge graph based on big data visualization according to claim 1, wherein a knowledge graph model is configured, when the knowledge graph model supports the upper limit of the data processing capability and the upper limit of the data processing capability of the knowledge graph model is larger than the sum of storage capacities of any one of a plurality of storage units with the same mark, a data loading request is sent to a task management module, the task management module configures a plurality of storage units with different marks according to the data loading request by using the upper limit of the data processing capability of the knowledge graph model, and data information transmission is established between the configured storage units with different marks and the knowledge graph model, so that the knowledge graph model can extract and fuse data information under full load.
3. The method for constructing the intelligent community knowledge graph based on big data visualization according to claim 2, wherein,
The task management module is respectively associated with the plurality of storage units according to marks, wherein a detection unit and a task allocation unit are arranged in the task management module, the detection unit is used for acquiring the storage capacity of data in each storage unit, and the storage capacity detected by each storage unit is configured in the task allocation unit;
The task allocation unit configures a plurality of storage units with different marks according to the upper limit of the data processing capability supported by the knowledge graph model, and establishes data information transmission with the knowledge graph model by the configured storage units with different marks so as to enable the knowledge graph model to extract and fuse data information under full load.
4. The method for constructing a smart community knowledge graph based on big data visualization according to claim 1, wherein the second processing unit uses a smart community knowledge graph set as a basis of data representation, which means that a basic configuration of the data representation is obtained from the smart community knowledge graph set, and a first set of entity representations, a second set of semantic representations and a third set of relational representations of data information of semi-structured data are obtained based on the basic configuration;
Executing a first fusion instruction, and fusing a third set which is provided with a first set related to entity representation and expressed by a relation as an association tie to form a second entity representation information set; recording corresponding association relations to form a first association set;
Executing a second fusion instruction, and fusing a third set which is expressed by a relation with the second set of semantic expressions as an association tie to form a second semantic expression information set; recording corresponding association relations to form a second association set;
And executing a third fusion instruction, and fusing the first association set, the second association set and the third set of relationship representation to obtain a second relationship representation information set.
5. The method for constructing a smart community knowledge graph based on big data visualization according to claim 1, wherein the third processing unit uses a smart community knowledge graph set as a basis of data representation, which means that a basic configuration of the data representation is obtained from the smart community knowledge graph set, and a fourth set of entity representations, a fifth set of semantic representations and a sixth set of relational representations of data information of unstructured data are obtained based on the basic configuration;
Executing a fourth fusion instruction, and fusing a sixth set which is related to entity representation and is represented by a relation with a fourth set as an association tie to form a third entity representation information set; recording corresponding association relations to form a third association set;
Executing a fifth fusion instruction, and fusing a sixth set which is expressed by a relation with a third set of semantic expressions as an association tie to form a third semantic expression information set; recording corresponding association relations to form a fourth association set;
And executing a sixth fusion instruction, and fusing the third association set, the fourth association set and the sixth set of relation representation to obtain a third relation representation information set.
6. The method for constructing the intelligent community knowledge graph based on big data visualization according to claim 4, wherein a third fusion instruction is executed, the first association set, the second association set and the third set of relationship representation are compared one by one, the coincident association relationship is removed, and then the second relationship representation information set is obtained through fusion.
7. The method for constructing the intelligent community knowledge graph based on big data visualization according to claim 5, wherein a sixth fusion instruction is executed, the third association set, the fourth association set and the sixth set of relationship representation are firstly compared one by one, the coincident association relationship is removed, and then the third relationship representation information set is obtained through fusion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410370767.7A CN117973520B (en) | 2024-03-29 | 2024-03-29 | Method for constructing intelligent community knowledge graph based on big data visualization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410370767.7A CN117973520B (en) | 2024-03-29 | 2024-03-29 | Method for constructing intelligent community knowledge graph based on big data visualization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117973520A CN117973520A (en) | 2024-05-03 |
CN117973520B true CN117973520B (en) | 2024-06-07 |
Family
ID=90858443
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410370767.7A Active CN117973520B (en) | 2024-03-29 | 2024-03-29 | Method for constructing intelligent community knowledge graph based on big data visualization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117973520B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019050968A1 (en) * | 2017-09-05 | 2019-03-14 | Forgeai, Inc. | Methods, apparatus, and systems for transforming unstructured natural language information into structured computer- processable data |
CN112883201A (en) * | 2021-03-23 | 2021-06-01 | 西安电子科技大学昆山创新研究院 | Knowledge graph construction method based on big data of smart community |
WO2021196520A1 (en) * | 2020-03-30 | 2021-10-07 | 西安交通大学 | Tax field-oriented knowledge map construction method and system |
CN115525768A (en) * | 2022-09-21 | 2022-12-27 | 中国电子科技集团公司第十四研究所 | Visual construction method and device for domain knowledge graph |
CN117216293A (en) * | 2023-09-15 | 2023-12-12 | 南京瑞拷得智慧信息科技有限公司 | Multi-mode inquiry college archive knowledge graph construction method and management platform |
-
2024
- 2024-03-29 CN CN202410370767.7A patent/CN117973520B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019050968A1 (en) * | 2017-09-05 | 2019-03-14 | Forgeai, Inc. | Methods, apparatus, and systems for transforming unstructured natural language information into structured computer- processable data |
WO2021196520A1 (en) * | 2020-03-30 | 2021-10-07 | 西安交通大学 | Tax field-oriented knowledge map construction method and system |
CN112883201A (en) * | 2021-03-23 | 2021-06-01 | 西安电子科技大学昆山创新研究院 | Knowledge graph construction method based on big data of smart community |
CN115525768A (en) * | 2022-09-21 | 2022-12-27 | 中国电子科技集团公司第十四研究所 | Visual construction method and device for domain knowledge graph |
CN117216293A (en) * | 2023-09-15 | 2023-12-12 | 南京瑞拷得智慧信息科技有限公司 | Multi-mode inquiry college archive knowledge graph construction method and management platform |
Non-Patent Citations (1)
Title |
---|
中文在线医疗社区问答内容知识图谱构建研究;席运江;图书情报工作;20240220;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117973520A (en) | 2024-05-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11586992B2 (en) | Travel plan recommendation method, apparatus, device and computer readable storage medium | |
CN107909512A (en) | A kind of equipment operating data matching of combination power system operating mode and extended method | |
CN111651474B (en) | Method and system for converting natural language into structured query language | |
CN102968430A (en) | Method and apparatus for automatically generating and managing groups in address book | |
CN112182007A (en) | Cloud computing data processing method based on artificial intelligence and artificial intelligence platform | |
CN105208622A (en) | High-efficiency dynamic automatic-maintenance routing list structure and routing list management method | |
CN113935390A (en) | Data processing method, system, device and storage medium | |
CN117973520B (en) | Method for constructing intelligent community knowledge graph based on big data visualization | |
CN115345093A (en) | SCD model-based intelligent substation secondary equipment loop information correlation mapping method | |
CN104301435A (en) | Data cluster marshalling method and system for distributed cluster sensors | |
CN103929499A (en) | Internet of things heterogeneous identification recognition method and system | |
CN106290772A (en) | A kind of sewage monitoring system | |
US11310353B2 (en) | Data transmission method for creating data structure facilitating data transmission and reception | |
CN112215197A (en) | Underground cable fault early warning method and system based on artificial intelligence | |
CN112491468B (en) | FBG sensing network node fault positioning method based on twin node auxiliary sensing | |
CN113344638B (en) | Power grid user group portrait construction method and device based on hypergraph | |
CN106412073B (en) | A kind of network system for detection of building fire equipment | |
CN111444254A (en) | SK L system file format conversion method and system | |
CN116186613B (en) | Intelligent acquisition processing method and system for industrial Internet data | |
CN111104994A (en) | Intelligent infrastructure management system and method based on radio frequency identification technology | |
CN112085099A (en) | Distributed student clustering integration method and system | |
CN111062633A (en) | Power transmission and transformation line and equipment state evaluation system based on multi-source heterogeneous data | |
CN105321211A (en) | Real-time train capacity query method and system | |
CN113569904B (en) | Bus wiring type identification method, system, storage medium and computing device | |
CN111587426B (en) | Session control device, session control 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 | ||
GR01 | Patent grant |