CN115203355A - Target person grading method and system based on knowledge graph technology - Google Patents
Target person grading method and system based on knowledge graph technology Download PDFInfo
- Publication number
- CN115203355A CN115203355A CN202111533914.0A CN202111533914A CN115203355A CN 115203355 A CN115203355 A CN 115203355A CN 202111533914 A CN202111533914 A CN 202111533914A CN 115203355 A CN115203355 A CN 115203355A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge graph
- graph
- knowledge
- algorithm
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- 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
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the target person grading method and system based on the knowledge graph technology, relevant points and edges of the knowledge graph are stored in the RocksDB, a distributed structure is adopted for storage, billions of nodes and trillion of edges can be accessed, and meanwhile, a good disaster tolerance capability can be provided by utilizing a multiple redundancy architecture design. Compared with the small-level query of the traditional relational database, the query and traversal of the graph can reach the millisecond level, and the efficiency is remarkably improved in the node correlation query scene. The invention can quickly screen out the sub-graph network according to the correlation relationship, and simultaneously grades the nodes according to the sub-graph network structure, thereby helping the related personnel focus on the thread reconnaissance of the personnel and greatly saving the consumption of the related resources on the non-critical personnel.
Description
Technical Field
The invention relates to the field of data mining, in particular to a target person grading method and a target person grading system based on a knowledge graph technology.
Background
With the arrival of the big data era, the data volume required to be processed by security organs is in a situation of increasing in geometric progression, and a relational data model is urgently needed to perform linkage processing on various types of data. Most of the existing big data technologies focus on processing, converting and analyzing various structured and semi-structured data, the processing capability of the interrelation among different types of data is weak, and the calculation cost of the multilayer interrelation is high.
At present, various information platforms used by security organs generally have data barriers, the field types, data structures and storage modes of different platforms are different, and data cannot be effectively utilized in the case detection process to form an information isolated island. Meanwhile, a lot of data are not used in feasible and universal modes in different scenes, so that efficient study and judgment cannot be achieved, and accurate strategy is achieved.
The security personnel access mass data in the daily work of target personnel investigation, close contact person combing, anti-fraud informing propaganda and the like, but the existing big data technology obtains corresponding relations from different types of data and has difficulty in screening out personnel according to the relation intensity and the relation type. The problem of how to process different types of data in a linkage manner and identify personnel at the same time needs to be solved urgently.
Disclosure of Invention
In view of the above, the present invention has been developed to provide a method and system for targeted person ranking based on knowledge-graph technology that overcomes or at least partially solves the above problems.
In order to solve the technical problem, the embodiment of the application discloses the following technical scheme:
a target person grading method based on knowledge graph technology comprises the following steps:
s100, cleaning and converting data of different platforms and different formats, and importing the data into a big data platform;
s200, converting the data imported into the big data platform into the point and edge structures of the knowledge graph, and storing the point and edge structures;
s300, importing the stored point and edge structures into a knowledge map database, initializing corresponding attributes of the points and the edges, and setting corresponding permissions of users and user groups;
s400, acquiring corresponding side data according to the attributes of the target personnel, and converging and de-duplicating the acquired side data;
s500, converting the converged and de-duplicated data into a to-be-processed data format;
s600, processing the data to be processed by using a grading algorithm to obtain a target personnel grade;
and S700, storing the grade information of the target personnel into a database, and performing visual output.
Further, the data of different platforms and formats at least includes: the system comprises a personal information collection platform, a trip information collection platform, a communication information collection platform and a hotel management information platform.
Further, when the data imported into the big data platform are converted into the point and edge structures of the knowledge graph, the data are imported into the index server to serve as the index of the graph database, and a scheduling period is set for day increment data.
Further, the target person attributes include at least peer and economic commutes of the target person.
Further, the converged data is converted into a to-be-processed data format, and the to-be-processed data format is a tuple array format.
Further, the method for processing the data to be processed by using a grading algorithm to obtain the grade of the target person specifically comprises the following steps: the method comprises the steps of utilizing a Spark calculation engine, applying a PageRank algorithm to data to be processed, setting a damping coefficient, obtaining a Rank value of each node, setting nodes with empty Rank values as non-target personnel, filtering, and dividing all the Rank values into three clusters by using a KMeans algorithm, wherein the three clusters correspond to three levels of high-risk, medium-risk and low-risk respectively.
Further, the RANK value is calculated by using the edge-out attribute of the node, and the used algorithm formula is as follows:
wherein i and j respectively represent a certain node i and all nodes except i, N represents the total number of the nodes, L (j) represents the number of outgoing edges of a variable j point, q represents a damping coefficient, and the Rank value of each node is closely related to the number of the outgoing edges and the Rank values of the surrounding nodes.
Further, the calculation results are divided into three categories by using a Kmeans clustering algorithm, and the formula of the Kmeans clustering algorithm is as follows:
wherein, C i To divide into K clusters (C) according to the distance size between samples 1 ,C 2 ,.....，C i ，.....C k ) One of them, μ i Is a cluster C i E is the minimized square error.
The invention also discloses a target personnel grading system based on the knowledge graph technology, which comprises the following steps: the system comprises a knowledge graph data importing module, a knowledge graph constructing module, a knowledge graph database, a grading algorithm module and a knowledge graph application module; wherein:
the knowledge map data import module is used for gathering and cleaning and converting data dispersed in each platform and sending the data to the knowledge map construction module,
the knowledge graph building module is used for converting the data into corresponding point or edge structures, storing the corresponding graph data into the index server to improve the query efficiency, storing the converted entity and relationship data into a knowledge graph database and generating a corresponding knowledge graph;
the knowledge graph database is used for storing the entity and the relation data in the RocksDB and managing the query statement by utilizing the native DashBoard of the NebulaGraph;
the classification algorithm module is used for processing the screened target person attribute side data, processing the data to be processed by using a classification algorithm, calculating the Rank values of all nodes, dividing the Rank values into three sets, and returning the calculation result to the knowledge graph application module;
and the knowledge map application module is used for displaying the grading and related attributes of the target personnel to the user in a visual mode, and simultaneously providing screening and judging analysis functions, so that the user can flexibly process the information according to the actual service scene.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the target personnel grading method and system based on the knowledge graph technology, disclosed by the invention, store the relevant points and edges of the knowledge graph in the RocksDB, the storage adopts a distributed structure, so that billions of nodes and trillion edges can be accessed, and meanwhile, a good disaster tolerance capability can be provided by utilizing a multiple redundancy architecture design. Compared with the small-level query of the traditional relational database, the query and traversal of the graph can reach the millisecond level, and the efficiency is remarkably improved in the node correlation query scene. The invention can quickly screen out the sub-graph network according to the correlation relationship, and simultaneously grades the nodes according to the sub-graph network structure, thereby helping the case handling personnel focus on the thread reconnaissance of the personnel and greatly saving the consumption of the related resources on the non-critical personnel.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a target person classification method based on knowledge graph technology in embodiment 1 of the invention;
FIG. 2 shows a knowledge graph constructed based on data of relatives and co-residents and the like in embodiment 1 of the invention;
FIG. 3 shows a subgraph obtained by traversing a 2-level relationship based on Zhang-three of people in embodiment 1 of the invention;
FIG. 4 shows a relationship graph based on three allegedly-identical row relationships of persons at a maximum traversal depth of 2 in embodiment 1 of the invention;
FIG. 5 is a diagram showing a diagram of a judgment analysis based on Zhang III of people in example 1 of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to solve the problems in the prior art, the embodiment of the invention provides a target person classification method and system based on a knowledge graph technology.
Example 1
The embodiment discloses a target person classification method based on knowledge graph technology, as shown in fig. 1, including:
s100, cleaning and converting data of different platforms and different formats, and importing the data to a big data platform; in this embodiment, the data with different formats for different platforms at least includes: the system comprises a personal information collection platform, a trip information collection platform, a communication information collection platform and a hotel management information platform.
It can be understood that data of different platforms of the security system can be collected according to requirements. For example, the personal basic information of the target person, including at least age, native place, relationship, etc., can be obtained through the personal information collection platform; the information of the co-workers of the target personnel can be collected through the traffic travel information collection platform; the information of the target person communication personnel can be collected through the communication information collection platform; the information of the co-resident of the target person can be acquired through the hotel management information platform.
S200, converting the data imported into the big data platform into a point and edge structure of a knowledge graph, and storing the point and edge structure; in this embodiment, when data imported from a big data platform is converted into a point and edge structure of a knowledge graph, the data is imported into an index server as an index of a graph database, and a scheduling period is set for daily incremental data.
S300, importing the stored point and edge structures into a knowledge map database, initializing corresponding attributes of the points and the edges, and setting corresponding permissions of users and user groups;
s400, acquiring corresponding side data according to the attributes of the target personnel, and converging and de-duplicating the acquired side data; in this embodiment, the target person attributes at least include fellow persons and economic commutes of the target person.
S500, converting the gathered and de-duplicated data into a to-be-processed data format; in this embodiment, the aggregated data is converted into a to-be-processed data format, where the to-be-processed data format is a tuple array format. The format of the tuple array is similar to a data structure of List < (aid, (bid, cid, did)) > wherein aid, bid, cid and did represent unique identification numbers of nodes a, b, c and d respectively, and the structure shows that a node has three edges pointing to b, c and d, and how many edges of a node have node identification numbers in an internal set.
S600, processing the data to be processed by using a grading algorithm to obtain a target personnel grade; in this embodiment, the processing of the data to be processed by using a hierarchical algorithm to obtain the level of the target person specifically includes: the method comprises the steps of utilizing a Spark calculation engine, applying a PageRank algorithm to data to be processed, setting a damping coefficient, obtaining a Rank value of each node, setting nodes with empty Rank values as non-target persons, filtering out the nodes, and dividing all the Rank values into three clusters by using a KMeans algorithm, wherein the three clusters correspond to high-risk, medium-risk and low-risk levels respectively. Preferably, the damping coefficient is set to 0.83, the cluster center number is set to 3, the algorithm iteration number is set to 20, and the algorithm operation number is set to 5.
Specifically, the RANK value is calculated by using the edge-out attribute of the node, and the used algorithm formula is as follows:
wherein i and j respectively represent a certain node i and all nodes except i, N represents the total number of the nodes, L (j) represents the number of outgoing edges of a variable j point, q represents a damping coefficient, and the Rank value of each node is closely related to the number of the outgoing edges and the Rank values of the surrounding nodes.
Dividing the calculation results into three categories by using a Kmeans clustering algorithm, wherein the formula of the Kmeans clustering algorithm is as follows:
wherein, C i To divide into K clusters (C) according to the distance size between samples 1 ,C 2 ,.....，C i ，.....C k ) One of them, μ i Is a cluster C i E is the minimized square error.
And S700, storing the grade information of the target person into a database, and performing visual output.
In the embodiment of the present invention, a general knowledge graph may be constructed according to the steps S100 to S300, and in order to vividly describe the graph construction idea of the present invention, not all nodes are shown, but only a part of entities and their corresponding relations are drawn, as shown in fig. 2.
When setting the attribute of the start node, such as id number 420000199701017777 (zhang), and setting the attribute of the target node, such as id number 420000199502028888 (liq), and the maximum depth parameter N =2, the background finds the start node zhang within millisecond time by using the index, and then performs a loop traversal in a two-step relationship based on zhang, so as to obtain a sub-graph as shown in fig. 3.
Finding Zhang III according to the identity card number in the general graph, selecting the attributes of target personnel such as the same-living same-row, economic coming and going, and the like, and simultaneously setting the maximum depth parameter as 2, forming a corresponding sub-graph, and finally drawing a relation graph as shown in FIG. 4.
Based on the idea in fig. 4, the user can click the corresponding node on the front-end page to obtain the judgment analysis of the node. At this time, the background selects the corresponding target person attribute relationship edge by using the click node as an initial node, and draws a sub-graph within 5 of the maximum depth parameter, with the display effect as shown in fig. 5.
The embodiment also discloses a target person grading system based on the knowledge graph technology, which comprises the following steps: the system comprises a knowledge graph data importing module, a knowledge graph constructing module, a knowledge graph database, a grading algorithm module and a knowledge graph application module; wherein:
the knowledge map data import module is used for gathering and cleaning and converting data dispersed in each platform and sending the data to the knowledge map construction module,
the knowledge graph building module is used for converting the data into corresponding point or edge structures, storing the corresponding graph data into the index server to improve the query efficiency, storing the converted entity and relationship data into a knowledge graph database and generating a corresponding knowledge graph;
the knowledge graph database is used for storing the entity and the relation data in the RocksDB and managing the query statement by utilizing the native DashBoard of the NebulaGraph;
the classification algorithm module is used for processing the screened target person attribute side data, processing the data to be processed by using a classification algorithm, calculating the Rank values of all nodes, dividing the Rank values into three sets, and returning the calculation result to the knowledge graph application module;
and the knowledge map application module is used for displaying the grading and related attributes of the target personnel to the user in a visual mode, and simultaneously providing screening and judging analysis functions, so that the user can flexibly process the information according to the actual service scene.
According to the target person grading method and system based on the knowledge graph technology, relevant points and edges of the knowledge graph are stored in the RocksDB, a distributed structure is adopted for storage, billions of nodes and trillion of edges can be accessed, and meanwhile good disaster tolerance capacity can be provided by means of multiple redundancy architecture design. Compared with the small-level query of the traditional relational database, the query and traversal of the graph can reach the millisecond level, and the efficiency is remarkably improved in the node correlation query scene. The invention can quickly screen out the sub-graph network according to the relevant relation, and simultaneously grades the nodes according to the sub-graph network structure, thereby helping the case handling personnel focus on the thread reconnaissance of the personnel and greatly saving the consumption of the non-critical personnel of the relevant resources.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Claims (9)
1. A target person classification method based on knowledge graph technology is characterized by comprising the following steps:
s100, cleaning and converting data of different platforms and different formats, and importing the data to a big data platform;
s200, converting the data imported into the big data platform into a point and edge structure of a knowledge graph, and storing the point and edge structure;
s300, importing the stored point and edge structures into a knowledge graph database, initializing corresponding attributes of the points and the edges, and setting corresponding permissions of users and user groups;
s400, acquiring corresponding side data according to the attributes of the target personnel, and converging and de-duplicating the acquired side data;
s500, converting the converged and de-duplicated data into a to-be-processed data format;
s600, processing the data to be processed by using a grading algorithm to obtain a target personnel grade;
and S700, storing the grade information of the target personnel into a database, and performing visual output.
2. The method of claim 1, wherein the different formats of data for different platforms at least comprise: the system comprises a personal information collection platform, a traffic trip information collection platform, a communication information collection platform and a hotel management information platform.
3. The method for ranking target personnel based on knowledge-graph technology as claimed in claim 1, wherein when the data imported into the big data platform is converted into the point and edge structure of the knowledge-graph, the data is imported into the index server as the index of the graph database, and the scheduling period is set for the daily increment data.
4. The method of claim 1, wherein the target person attributes comprise at least peer and economic commuters of the target person.
5. The method of claim 1, wherein the aggregated data is converted into a to-be-processed data format, and the to-be-processed data format is a tuple array format.
6. The method for classifying target personnel based on knowledge-graph technology as claimed in claim 1, wherein the step of processing the data to be processed by using a classification algorithm to obtain the grade of the target personnel comprises the following steps: the method comprises the steps of utilizing a Spark calculation engine, applying a PageRank algorithm to data to be processed, setting a damping coefficient, obtaining a Rank value of each node, setting nodes with empty Rank values as non-target personnel, filtering, and dividing all the Rank values into three clusters by using a KMeans algorithm, wherein the three clusters correspond to three levels of high-risk, medium-risk and low-risk respectively.
7. The method of claim 6, wherein the RANK value is calculated using the edge attribute of the node, and the algorithm formula is:
wherein i and j respectively represent a certain node i and all nodes except i, N represents the total number of the nodes, L (j) represents the number of outgoing edges of a variable j point, q represents a damping coefficient, and the Rank value of each node is closely related to the number of the outgoing edges and the Rank values of the surrounding nodes.
8. The method of claim 6, wherein the results of the calculation are classified into three categories using a Kmeans clustering algorithm, the formula of the Kmeans clustering algorithm is:
wherein, C i To divide into K clusters (C) according to the distance size between samples 1 ,C 2 ,.....，C i ，.....C k ) One of (a), mu i Is a cluster C i E is the minimized square error.
9. A system for target person ranking based on knowledge-graph technology, comprising: the system comprises a knowledge graph data importing module, a knowledge graph constructing module, a knowledge graph database, a grading algorithm module and a knowledge graph application module; wherein:
the knowledge map data import module is used for gathering and cleaning and converting data dispersed in each platform and sending the data to the knowledge map construction module,
the knowledge graph building module is used for converting the data into corresponding point or edge structures, storing the corresponding graph data into the index server to improve the query efficiency, storing the converted entity and relationship data into a knowledge graph database and generating a corresponding knowledge graph;
the knowledge graph database is used for storing the entity and the relation data in the RocksDB and managing the query statement by utilizing the native DashBoard of the NebulaGraph;
the hierarchical algorithm module is used for processing the screened target person attribute edge data, processing the data to be processed by using a hierarchical algorithm, calculating the Rank values of all nodes, dividing the Rank values into three sets, and returning the calculation result to the knowledge graph application module;
and the knowledge map application module is used for displaying the grading and relevant attributes of the target personnel to the user in a visual mode, and simultaneously providing screening, judging and analyzing functions, so that the user can flexibly process the information according to the actual service scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111533914.0A CN115203355A (en) | 2021-12-15 | 2021-12-15 | Target person grading method and system based on knowledge graph technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111533914.0A CN115203355A (en) | 2021-12-15 | 2021-12-15 | Target person grading method and system based on knowledge graph technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115203355A true CN115203355A (en) | 2022-10-18 |
Family
ID=83574112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111533914.0A Pending CN115203355A (en) | 2021-12-15 | 2021-12-15 | Target person grading method and system based on knowledge graph technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115203355A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118051527A (en) * | 2024-04-16 | 2024-05-17 | 杭州悦数科技有限公司 | Method and device for realizing dynamic knowledge graph based on graph database |
-
2021
- 2021-12-15 CN CN202111533914.0A patent/CN115203355A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118051527A (en) * | 2024-04-16 | 2024-05-17 | 杭州悦数科技有限公司 | Method and device for realizing dynamic knowledge graph based on graph database |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hecht et al. | Automatic identification of building types based on topographic databases–a comparison of different data sources | |
| Gale et al. | Creating the 2011 area classification for output areas (2011 OAC) | |
| Disegna et al. | Copula-based fuzzy clustering of spatial time series | |
| Amini et al. | On density-based data streams clustering algorithms: A survey | |
| CN111666313A (en) | Correlation construction and multi-user data matching method based on multi-source heterogeneous remote sensing data | |
| Mu et al. | A scale-space clustering method: Mitigating the effect of scale in the analysis of zone-based data | |
| CN109493119B (en) | POI data-based urban business center identification method and system | |
| Wittich et al. | Recommending plant taxa for supporting on-site species identification | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| CN111738341B (en) | Distributed large-scale face clustering method and device | |
| CN111326236A (en) | Medical image automatic processing system | |
| CN116127190B (en) | Digital earth resource recommendation system and method | |
| Lin et al. | Extracting urban landmarks from geographical datasets using a random forests classifier | |
| Rabbi et al. | An Approximation For Monitoring The Efficiency Of Cooperative Across Diverse Network Aspects | |
| Renigier-Biłozor et al. | Modern challenges of property market analysis-homogeneous areas determination | |
| CN115203355A (en) | Target person grading method and system based on knowledge graph technology | |
| Runfola et al. | Deep learning fusion of satellite and social information to estimate human migratory flows | |
| US8849844B1 (en) | Image reacquisition | |
| CN111027771A (en) | Scenic spot passenger flow volume estimation method, system and device and storable medium | |
| Gubareva et al. | Literature Review on the Smart City Resources Analysis with Big Data Methodologies | |
| CN114398462B (en) | Destination recommendation method and system based on multi-source heterogeneous information network | |
| Li | Mapping urban land use by combining multi-source social sensing data and remote sensing images | |
| CN110633890A (en) | Land utilization efficiency judgment method and system | |
| CN116089448A (en) | Real-time population management system for establishing population portraits based on multidimensional perception | |
| CN112488236B (en) | Integrated unsupervised student behavior clustering method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |