CN114528443A - Knowledge graph-based information mining method and related equipment thereof - Google Patents
Knowledge graph-based information mining method and related equipment thereof Download PDFInfo
- Publication number
- CN114528443A CN114528443A CN202210168429.6A CN202210168429A CN114528443A CN 114528443 A CN114528443 A CN 114528443A CN 202210168429 A CN202210168429 A CN 202210168429A CN 114528443 A CN114528443 A CN 114528443A
- Authority
- CN
- China
- Prior art keywords
- industry
- knowledge
- network
- key
- centrality
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application belongs to the technical field of big data, and relates to a knowledge graph-based information mining method and related equipment thereof, wherein the method comprises the steps of obtaining supply and demand data of different industries, and constructing a plurality of sub-knowledge graphs corresponding to the different industries according to the supply and demand data; dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing a total knowledge map according to the industry networks and the enterprise information; calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry. In addition, the present application relates to blockchain techniques, where an overall knowledge map can be stored. The method and the system realize efficient and accurate excavation of key enterprises.
Description
Technical Field
The application relates to the technical field of big data, in particular to an information mining method based on a knowledge graph and related equipment thereof.
Background
The inter-industry relationships are divided into a support relationship and a drive relationship. The supporting relationship is mainly embodied in that the industrial department providing guarantee and support for the main industrial chain is mainly a production element department, such as land, facilities, equipment, raw materials, energy, fund, technology, talents, information, intermediary services and the like. Without these supporting industries or without them, the production process of the subject product or service either cannot begin or cannot continue. Therefore, the industrial departments of certain products or services cannot exist independently, and must establish life-to-death dependence with the industrial departments of guarantee and support. When the market environment changes, each link of the industrial chain changes. The driving relationship is mainly embodied in the connection relationship between the main industry and the driven industry formed by driving and influencing the development of other products or service industries due to the existence and development of certain products or service industries.
In the process, industrial chain rings are buckled, one link is blocked, and upstream and downstream enterprises cannot operate. However, how to efficiently and accurately mine information for a huge industry network while considering external environmental influence factors is a great challenge to determine the industry and enterprises which dominate the network.
Disclosure of Invention
The embodiment of the application aims to provide an information mining method based on a knowledge graph and related equipment thereof so as to solve the technical problem of low industry information mining accuracy.
In order to solve the above technical problem, an embodiment of the present application provides an information mining method based on a knowledge graph, which adopts the following technical scheme:
acquiring supply and demand data of different industries, and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing a total knowledge map according to the industry networks and the enterprise information;
calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
Further, the step of constructing a plurality of sub-knowledge maps corresponding to different industries according to the supply and demand data includes:
selecting one industry from all the industries as a target industry, and acquiring an associated industry having a supply and demand relationship with the target industry according to the supply and demand data;
calculating the proportion of the transaction amount of the target industry supplied or required by the associated industry to the total amount of the target industry according to the supply and demand data;
establishing a data relation table of the target industry and the associated industry according to the proportion and the supply and demand relation;
and importing the data relation table to a database system to obtain the sub-knowledge graph of the target industry.
Further, the step of constructing a total knowledge graph according to the industry network and the enterprise information includes:
determining a target industry which has an incidence relation with the enterprise in the industry network according to the enterprise information;
and completing the sub-knowledge graph based on the incidence relation between the enterprise and the target industry to obtain the total knowledge graph.
Further, the step of determining a target industry in the industry network having an association relationship with the enterprise according to the enterprise information includes:
acquiring a preset evaluation algorithm and a reference enterprise, and performing similarity calculation on the enterprise information and the reference enterprise according to the evaluation algorithm to obtain a correlation score corresponding to the enterprise information;
and determining the industry corresponding to the reference enterprise with the highest correlation score as the target industry.
Further, the step of calculating the centrality of each industry in the industry network and determining the key industry of the industry network according to the centrality comprises:
acquiring the number of nodes in the industry network, and normalizing the centrality of the degree according to the number of the nodes to obtain the centrality of the standard degree;
and determining the industry with the highest standard degree centrality as a key industry in all the industry networks.
Further, the step of determining key industries of the industry network according to the centrality further comprises:
calculating the centrality of each industry in the industry network;
and calculating the influence score of each different industry in the industry network according to the mesocentrality and the centrality, and determining the industry with the largest influence score as a key industry in the industry network.
Further, the step of calculating the centrality of each industry in the industry network comprises:
determining a shortest path between any two industries in the industry network;
and calculating the coincidence rate of the industries in all the shortest paths, and taking the coincidence rate as the mesocentrality of the industries in the industry network.
In order to solve the above technical problem, an embodiment of the present application further provides an information mining apparatus based on a knowledge graph, which adopts the following technical scheme:
the first construction module is used for acquiring supply and demand data of different industries and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
the second construction module is used for dividing the sub-knowledge maps to obtain the industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing to obtain a total knowledge map according to the industry networks and the enterprise information;
the confirming module is used for calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
acquiring supply and demand data of different industries, and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing a total knowledge map according to the industry networks and the enterprise information;
calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
In order to solve the foregoing technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
acquiring supply and demand data of different industries, and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing a total knowledge map according to the industry networks and the enterprise information;
calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
According to the method, the supply and demand data of different industries are obtained, a plurality of sub-knowledge maps corresponding to the different industries are constructed according to the supply and demand data, and key industries can be accurately obtained through the sub-knowledge maps; then, the sub-knowledge maps are divided to obtain the industry networks corresponding to the sub-knowledge maps, enterprise information of different enterprises is obtained, and a total knowledge map is constructed according to the industry networks and the enterprise information, so that unified and standardized arrangement of the enterprises is realized, and the obtaining efficiency and accuracy of key enterprises are further improved; and then, calculating the degree centrality of each industry in the industry network, determining the key industry of the industry network according to the degree centrality, searching the key enterprises of the key industry in the total knowledge graph based on the key industry, and finally, realizing efficient and accurate mining of the key industry, further searching the key enterprises with larger influence in the total knowledge graph according to the key industry, further realizing accurate adjustment of resources, and improving the utilization rate of the resources.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a knowledge-graph based information mining method according to the present application;
FIG. 3 is an industry shortest path diagram;
FIG. 4 is a schematic block diagram of one embodiment of a knowledge-graph based information mining apparatus according to the present application;
FIG. 5 is a schematic block diagram of one embodiment of a computer device according to the present application.
Reference numerals: a knowledge-graph-based information mining apparatus 400, a first building module 401, a second building module 402, and a validation module 403.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the method for mining information based on a knowledge graph provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the apparatus for mining information based on a knowledge graph is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a method of knowledge-graph based information mining in accordance with the present application is shown. The information mining method based on the knowledge graph comprises the following steps:
step S201, acquiring supply and demand data of different industries, and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
in this embodiment, the supply and demand data is the output scale of each industry and the supply and demand data between every two industries, and the supply and demand data of each industry every month can be obtained through downloading by a crawler or a wind client. For example, the supply and demand data for the wholesale and retail industry is acquired at 10 trillions, the supply and demand data for the construction industry is acquired at 5 trillions, and the wholesale and retail industry offers 2 trillions to the construction industry. And when the supply and demand data are obtained, constructing and obtaining the sub-knowledge graph of the corresponding industry according to the supply and demand data. Specifically, when the supply and demand data is obtained, the supply and demand relationship between two different industries is determined according to the supply and demand data, the industry-supply and demand relationship-industry triple is constructed based on the supply and demand relationship, the triple construction is input into a map construction tool (such as a Neo4j map database system), and the sub-knowledge maps corresponding to the different industries are constructed based on the map construction tool. One industry corresponds to one sub-knowledge graph.
Step S202, dividing the sub-knowledge graph to obtain an industry network corresponding to the sub-knowledge graph, acquiring enterprise information of different enterprises, and constructing according to the industry network and the enterprise information to obtain a total knowledge graph;
in this embodiment, when the sub-knowledge graph is obtained, a preset division standard is obtained, where the division standard may be a division standard of an industry specification, for example, the industry may be divided into categories, large categories, middle categories, and small categories according to the division standard of the industry specification, where the categories include agriculture, forestry, animal husbandry, fishery, collection industry, manufacturing industry, and the like, each category includes a plurality of large categories, the large categories include a plurality of middle categories, and the middle categories include a plurality of small categories. Therefore, the sub-knowledge maps corresponding to each industry are divided into industry networks with different sizes according to the division standard, such as an industry middle class network and an industry subclass network, wherein the industry networks are networks consisting of a plurality of industries, and one industry network consists of a plurality of sub-knowledge maps according to the division standard. And then acquiring enterprise information of the enterprise, wherein the enterprise information comprises information such as production information and product information of the enterprise, and the enterprise information can be acquired through public websites such as official websites of the enterprise. And constructing triplets of different industry networks and enterprises according to the enterprise information and the industry networks, and constructing a total knowledge graph based on the triplets. Wherein, the total knowledge graph comprises a plurality of sub knowledge graphs.
It is emphasized that the global knowledge graph may also be stored in a node of a blockchain in order to further ensure the privacy and security of the global knowledge graph.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Step S203, calculating the degree centrality of each industry in the industry network, determining the key industry of the industry network according to the degree centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
In this embodiment, after the industry networks are obtained, the degree-centrality of each different industry in its corresponding industry network is calculated. The degree centrality is the degree of influence of each industry on other industries in the industry network, and the higher the degree centrality is, the higher the degree centrality of the industry is. Specifically, in most industry networks, the degrees of the industry nodes follow a power law distribution, the number of nodes with large degrees (i.e., industries) only accounts for a small part of the total number of nodes in one industry network, and the number of nodes with small degrees (i.e., industries) often accounts for the majority. Therefore, the number of connections between each industry and other industries in the industry network is calculated, and the centrality of each industry is determined according to the number of connections, and a calculation formula of the centrality is specifically as follows:
wherein di is the centrality of each industry, i represents the current industry number, j is the total number of industries in the industry network, and A is the number of connections. When the centrality of the industry in the industry network is obtained, the industry with the highest centrality in the current industry network is determined as the key industry in the industry network. And then, searching the enterprise closest to the key industry in the total knowledge graph according to the key industry, and determining the enterprise closest to the key industry as the key enterprise of the current key industry. The closer the distance to the key industry in the total knowledge graph represents that the contribution degree of the enterprise in the key industry is larger, and the farther the distance from the key industry represents that the contribution degree of the enterprise in the key industry is smaller; the contribution degree can be obtained by comprehensively calculating information such as the share of the enterprise in the key industry.
According to the method and the system, efficient and accurate excavation of the key industry is realized, the key enterprises with large influence are further searched in the total knowledge graph according to the key industry, accurate adjustment of resources is further realized, and the utilization rate of the resources is improved.
In some optional implementation manners of this embodiment, the step of constructing a plurality of sub-knowledge graphs corresponding to different industries according to the supply and demand data includes:
selecting one industry from all the industry categories as a target industry, and acquiring an associated industry having a supply and demand relationship with the target industry according to the supply and demand data;
calculating the proportion of the transaction amount of the target industry supplied or required by the associated industry to the total amount of the target industry according to the supply and demand data;
establishing a data relation table of the target industry and the associated industry according to the proportion and the supply and demand relation;
and importing the data relation table to a database system to obtain the sub-knowledge graph of the target industry.
In this embodiment, when constructing sub-knowledge graphs of different industries, one industry is selected from all the obtained industries as a target industry, and an associated industry having a supply and demand relationship with the target industry is obtained. The supply and demand relationship can be determined by whether the supply and demand data of the target industry and other industries is zero or not; if the supply and demand data of the target industry and other industries are not zero, determining that the supply and demand relation exists between the target industry and other industries, wherein the other industries are related industries; and if the supply and demand data of the target industry and other industries is zero, determining that the supply and demand relation does not exist between the target industry and other industries.
And when the associated industry is obtained, calculating the proportion of the transaction amount of the associated industry for supplying or requiring the target industry to the total amount of the target industry according to the supply and demand data. For example, wholesale and retail industry supplies (20.1%) to the construction industry and construction industry demands (12.6%) to the financial industry. Constructing a data relation table of the target industry and the associated industry according to the proportion and the supply and demand relation, namely, taking the proportion and the supply and demand relation as field contents of the target industry and the associated industry, taking the name of the target industry and the associated industry as field identification, and constructing and obtaining the data relation table based on the field contents and the field identification; and then importing the data relation table into a database system (such as Neo4j) to generate a sub-knowledge graph of the target industry.
According to the embodiment, the sub-knowledge maps are generated through the supply-demand relationship and the proportion between the target industry and the associated industry, so that the sub-knowledge maps of different industries are accurately constructed, and the key industry can be further accurately acquired through the sub-knowledge maps.
In some optional implementation manners of this embodiment, the step of constructing a total knowledge graph according to the industry network and the enterprise information includes:
determining a target industry which has an incidence relation with the enterprise in the industry network according to the enterprise information;
and completing the sub-knowledge graph based on the incidence relation between the enterprise and the target industry to obtain the total knowledge graph.
In this embodiment, when the enterprise information is obtained, a target industry associated with the industry in the industry network is determined according to the enterprise information. The target industry is the industry which is most closely related to the enterprise in the industry network, and the target industry corresponding to the enterprise can be determined according to the production products or the matching field of the enterprise. And when target industries respectively corresponding to different enterprises are obtained, completing the sub-knowledge graph based on the association relation between the enterprises and the target industries to obtain the total knowledge graph. Specifically, when target industries corresponding to different enterprises are obtained, triples of the enterprises, the association relations and the target industries are constructed according to the association relations of the enterprises and the target industries, and the total knowledge graph is obtained by processing through a graph database system (such as Neo4j) based on the triples and the sub knowledge graphs.
According to the embodiment, the sub-knowledge graph is completed through the enterprise and the target industry to obtain the total knowledge graph, so that the key enterprise in the key industry can be accurately obtained through the total knowledge graph.
In some optional implementation manners of this embodiment, the step of determining, according to the enterprise information, a target industry in the industry network that has an association relationship with the enterprise includes:
acquiring a preset evaluation algorithm and a reference enterprise, and performing similarity calculation on the enterprise information and the reference enterprise according to the evaluation algorithm to obtain a correlation score corresponding to the enterprise information;
and determining the industry corresponding to the reference enterprise with the highest correlation score as the target industry.
In this embodiment, the evaluation algorithm may adopt a classification algorithm such as a logistic regression algorithm, a decision tree algorithm, a random forest, and the like, and the current enterprise information is classified through the classification algorithm to obtain an industry corresponding to the enterprise information. In addition, the evaluation algorithm can also adopt a collaborative filtering algorithm, specifically, a plurality of groups of reference enterprises and industry labels corresponding to the reference enterprises are collected, the similarity between the reference enterprises and the enterprise information is calculated according to the collaborative filtering model, and the similarity is used as the association score of the enterprise information; and determining the industry label of the reference enterprise with the largest correlation score as a target label of the enterprise information, wherein the industry corresponding to the target label is the target industry corresponding to the current enterprise information.
According to the embodiment, the association score corresponding to each enterprise information is calculated, so that the industry to which the enterprise belongs is accurately identified, and the accuracy of the total knowledge graph construction is further improved.
In some optional implementations of this embodiment, the calculating a centrality of each industry in the industry network includes:
acquiring the number of nodes in the industry network, and normalizing the centrality of the degree according to the number of the nodes to obtain the centrality of the standard degree;
and determining the industry with the highest standard degree centrality as a key industry in all the industry networks.
In this embodiment, in addition to determining the key industries of different industries in the same industry network according to the centrality, the centrality of the degree of the industries of different industry networks may be normalized, and the final key industry is determined from all the different industry networks. Specifically, when the centrality of each industry in the industry network is obtained, the number of nodes in each industry network is obtained, and the number of the nodes is the total number of the industries in each industry network. Normalizing the centrality of the degree of each industry according to the number of the nodes to obtain the centrality of the standard degree, wherein a calculation formula of the centrality of the standard degree is as follows:
wherein N is the number of nodes of the industry network to which the nodes belong, and di is the centrality of each industry. And when the standard degree centrality corresponding to each industry is obtained, sequencing the standard degree centrality of the industries in all the industry networks, and determining the industry with the maximum standard degree centrality as a key industry.
According to the embodiment, the industries in all the industry networks are uniformly measured by normalizing the centrality of the degree, and the accuracy of obtaining the key industries is further improved.
In some optional implementations of this embodiment, the step of determining the key industry of the industry network according to the centrality further includes:
calculating the centrality of each industry in the industry network;
and calculating the influence score of each different industry in the industry network according to the mesocentrality and the mesocentrality, and determining the industry with the largest influence score as a key industry in the industry network.
In the embodiment, the importance of the network in the industry cannot be measured by the centrality for some industries. Therefore, after the centrality of each industry in the corresponding industry network is calculated, the centrality of each industry in the industry network can be calculated; and further determining the industry with the largest influence in the industry network according to the centrality and the centrality, and taking the industry as a key industry.
Specifically, the betweenness of a node indicates the number of shortest paths passing through the node in one network, and the larger the betweenness of the node in one network is, the more the node plays a role in communication between the nodes. Calculating all shortest paths of any two nodes (industries) in each industry network, and determining the coincidence rate of the nodes in the shortest paths, wherein the coincidence rate is the mesocentricity of the nodes. When the centrality and the centrality of degree of different nodes are obtained, calculating the influence score of each industry in the industry network according to the centrality and the centrality of degree; the influence score can be calculated by weighted summation of the betweenness and the degree-centrality. Then, the node (industry) with the largest influence score is determined as a key industry in the industry network.
According to the method, the key industry is determined through the mesocentrality and the centrocentrality, and the accuracy of the key industry is further improved.
In some optional implementations of this embodiment, the step of calculating the centrality of each industry in the industry network includes:
determining a shortest path between any two industries in the industry network;
and calculating the coincidence rate of the industries in all the shortest paths, and taking the coincidence rate as the mesocentrality of the industries in the industry network.
In this embodiment, there is only one shortest path between one industry and a different other industry, and different nodes (industries) may be passed through in the shortest path. As shown in fig. 3 below, fig. 3 is a schematic diagram of shortest paths of industries, and a shortest path from industry a to industry B and a shortest path from industry B to industry C both pass through industry H, which is a coincident industry in the shortest paths. When the coincidence rate of the industry H is calculated, the corresponding coincidence rate can be determined by calculating the number of shortest paths passing through the industry H. Specifically, the shortest path between any two industries in the industry network is determined, and the shortest path of the industry is the path which needs to pass through the least nodes (industries) between the two industries; determining the coincidence rate of industries in all shortest paths in the industry network, wherein the coincidence rate is the ratio of the shortest paths passing through the industries (nodes) to the total number of the shortest paths, and taking the ratio as the mesocentrality of the industries in the industry network.
In the embodiment, the centrality of the industry in the industry network is determined by calculating the coincidence rate of the industry, so that the industry can be further accurately evaluated through the centrality.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an information mining apparatus based on a knowledge graph, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.
As shown in fig. 4, the knowledge-graph-based information mining apparatus 400 according to the present embodiment includes: a first building block 401, a second building block 402, and a validation block 403. Wherein:
the first construction module 401 is configured to obtain supply and demand data of different industries, and construct a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
in some optional implementations of this embodiment, the first building block 401 includes:
the acquisition unit is used for selecting one industry from all the industries as a target industry and acquiring an associated industry having a supply and demand relationship with the target industry according to the supply and demand data;
the first calculating unit is used for calculating the proportion of the transaction amount of the target industry supplied or required by the associated industry to the total amount of the target industry according to the supply and demand data;
the construction unit is used for constructing a data relation table of the target industry and the associated industry according to the proportion and the supply and demand relation;
and the importing unit is used for importing the data relation table to a database system to obtain the sub-knowledge graph of the target industry.
In this embodiment, the supply and demand data is the output scale of each industry and the supply and demand data between every two industries, and the supply and demand data of each industry every month can be obtained through downloading by a crawler or a wind client. For example, the supply and demand data for the wholesale and retail industry is acquired at 10 trillions, the supply and demand data for the construction industry is acquired at 5 trillions, and the wholesale and retail industry offers 2 trillions to the construction industry. And when the supply and demand data are obtained, constructing and obtaining the sub-knowledge graph of the corresponding industry according to the supply and demand data. Specifically, when the supply and demand data is obtained, the supply and demand relationship between two different industries is determined according to the supply and demand data, the industry-supply and demand relationship-industry triple is constructed based on the supply and demand relationship, the triple construction is input into a map construction tool (such as a Neo4j map database system), and the sub-knowledge maps corresponding to the different industries are constructed based on the map construction tool. One industry corresponds to one sub-knowledge graph.
A second construction module 402, configured to divide the sub-knowledge graph to obtain an industry network corresponding to the sub-knowledge graph, obtain enterprise information of different enterprises, and construct a total knowledge graph according to the industry network and the enterprise information;
in some optional implementations of this embodiment, the second building block 402 includes:
the first confirming unit is used for determining a target industry which has an incidence relation with the enterprise in the industry network according to the enterprise information;
and the completion unit is used for completing the sub-knowledge graphs based on the incidence relation between the enterprise and the target industry to obtain the total knowledge graph.
In some optional implementations of this embodiment, the confirming unit includes:
the second calculation unit is used for acquiring a preset evaluation algorithm and a reference enterprise, and performing similarity calculation on the enterprise information and the reference enterprise according to the evaluation algorithm to obtain a correlation score corresponding to the enterprise information;
and the second confirmation unit is used for determining the industry corresponding to the reference enterprise with the highest association score as the target industry.
In this embodiment, when the sub-knowledge graph is obtained, a preset division standard is obtained, where the division standard may be a division standard of an industry specification, for example, the industry may be divided into categories, large categories, middle categories, and small categories according to the division standard of the industry specification, where the categories include agriculture, forestry, animal husbandry, fishery, collection industry, manufacturing industry, and the like, each category includes a plurality of large categories, the large categories include a plurality of middle categories, and the middle categories include a plurality of small categories. Therefore, the sub-knowledge maps corresponding to each industry are divided into industry networks with different sizes according to the division standard, such as an industry middle class network and an industry subclass network, wherein the industry networks are networks consisting of a plurality of industries, and one industry network consists of a plurality of sub-knowledge maps according to the division standard. And then acquiring enterprise information of the enterprise, wherein the enterprise information comprises information such as production information and product information of the enterprise, and the enterprise information can be acquired through public websites such as official websites of the enterprise. And constructing and obtaining triples of different industry networks and enterprises according to the enterprise information and the industry networks, and constructing and obtaining the total knowledge graph based on the triples. Wherein, the total knowledge graph comprises a plurality of sub knowledge graphs.
It is emphasized that the global knowledge graph may also be stored in a node of a blockchain in order to further ensure the privacy and security of the global knowledge graph.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The confirming module 403 is configured to calculate a centrality of each industry in the industry network, determine a key industry of the industry network according to the centrality, and find a key enterprise of the key industry in the total knowledge graph based on the key industry.
In this embodiment, after the industry networks are obtained, the degree-centrality of each different industry in its corresponding industry network is calculated. The degree centrality is the degree of influence of each industry on other industries in the industry network, and the higher the degree centrality is, the higher the degree centrality of the industry is. Specifically, in most industry networks, the degrees of the industry nodes follow a power law distribution, the number of nodes with large degrees (i.e., industries) only accounts for a small part of the total number of nodes in one industry network, and the number of nodes with small degrees (i.e., industries) often accounts for the majority. Therefore, the number of connections between each industry and other industries in the industry network is calculated, and the centrality of each industry is determined according to the number of connections, and a calculation formula of the centrality is specifically as follows:
wherein di is the centrality of each industry, i represents the current industry number, j is the total number of industries in the industry network, and A is the number of connections. When the centrality of the industry in the industry network is obtained, the industry with the highest centrality in the current industry network is determined as the key industry in the industry network. And then, searching the enterprise closest to the key industry in the total knowledge graph according to the key industry, and determining the enterprise closest to the key industry as the key enterprise of the current key industry. The closer the distance to the key industry in the total knowledge graph represents that the contribution degree of the enterprise in the key industry is larger, and the farther the distance from the key industry represents that the contribution degree of the enterprise in the key industry is smaller; the contribution degree can be obtained by comprehensively calculating information such as the share of the enterprise in the key industry.
In some optional implementations of this embodiment, the confirming module 403 includes:
the normalization unit is used for acquiring the number of nodes in the industry network and normalizing the degree centrality according to the number of the nodes to obtain the standard degree centrality;
and the third confirming unit is used for confirming that the industry with the largest standard degree centrality is a key industry in all the industry networks.
In this embodiment, in addition to determining the key industries of different industries in the same industry network according to the centrality, the centrality of the degree of the industries of different industry networks may be normalized, and the final key industry is determined from all the different industry networks. Specifically, when the centrality of each industry in the industry network is obtained, the number of nodes in each industry network is obtained, and the number of the nodes is the total number of the industries in each industry network. Normalizing the centrality of the degree of each industry according to the number of the nodes to obtain the centrality of the standard degree, wherein a calculation formula of the centrality of the standard degree is as follows:
wherein N is the number of nodes of the industry network to which the nodes belong, and di is the centrality of each industry. And when the standard degree centrality corresponding to each industry is obtained, sequencing the standard degree centrality of the industries in all the industry networks, and determining the industry with the maximum standard degree centrality as a key industry.
In some optional implementations of this embodiment, the determining module 403 further includes:
the third calculation unit is used for calculating the centrality of each industry in the industry network;
and the fourth calculating unit is used for calculating the influence score of each different industry in the industry network according to the centrality and the centrality, and determining the industry with the largest influence score as the key industry in the industry network.
In some optional implementations of this embodiment, the third computing unit includes:
the confirming subunit is used for confirming the shortest path between any two industries in the industry network;
and the calculating subunit is used for calculating the coincidence rate of the industries in all the shortest paths, and the coincidence rate is the mesocentrality of the industries in the industry network.
In the embodiment, the importance of the network in the industry cannot be measured by the centrality for some industries. Therefore, after the centrality of each industry in the corresponding industry network is calculated, the centrality of each industry in the industry network can be calculated; and further determining the industry with the largest influence in the industry network according to the centrality and the centrality, and taking the industry as a key industry.
Specifically, the betweenness of a node indicates the number of shortest paths passing through the node in one network, and the larger the betweenness of the node in one network is, the more the node plays a role in communication between the nodes. Calculating all shortest paths of any two nodes (industries) in each industry network, and determining the coincidence rate of the nodes in the shortest paths, wherein the coincidence rate is the mesocentrality of the nodes. When the centrality and the centrality of degree of different nodes are obtained, calculating the influence score of each industry in the industry network according to the centrality and the centrality of degree; the influence score can be calculated by weighted summation of the betweenness and the degree-centrality. Then, the node (industry) with the largest influence score is determined as a key industry in the industry network.
The knowledge graph-based information mining device provided by the embodiment realizes efficient and accurate mining of key industries, further searches key enterprises with large influence in the total knowledge graph according to the key industries, further realizes accurate adjustment of resources, and improves the utilization rate of the resources.
In order to solve the technical problem, the embodiment of the application further provides computer equipment. Referring to fig. 5, fig. 5 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only a computer device 6 having components 61-63 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 61 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal storage unit of the computer device 6 and an external storage device thereof. In this embodiment, the memory 61 is generally used for storing an operating system installed in the computer device 6 and various types of application software, such as computer readable instructions of a knowledge-graph-based information mining method. Further, the memory 61 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 62 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute computer readable instructions stored in the memory 61 or to process data, such as computer readable instructions for executing the knowledge-graph based information mining method.
The network interface 63 may comprise a wireless network interface or a wired network interface, and the network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.
The computer equipment provided by the embodiment realizes efficient and accurate mining of the key industry, further searches the key enterprises with larger influence in the total knowledge graph according to the key industry, further realizes accurate adjustment of resources, and improves the utilization rate of the resources.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the knowledge-graph based information mining method as described above.
The computer-readable storage medium provided by the embodiment realizes efficient and accurate mining of key industries, further searches for key enterprises with large influence in the total knowledge graph according to the key industries, further realizes accurate adjustment of resources, and improves the utilization rate of the resources.
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 solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A knowledge graph-based information mining method is characterized by comprising the following steps:
acquiring supply and demand data of different industries, and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing a total knowledge map according to the industry networks and the enterprise information;
calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
2. The knowledge-graph-based information mining method according to claim 1, wherein the step of constructing a plurality of sub knowledge graphs corresponding to different industries according to the supply and demand data comprises:
selecting one industry from all the industries as a target industry, and acquiring an associated industry having a supply and demand relationship with the target industry according to the supply and demand data;
calculating the proportion of the transaction amount of the target industry supplied or required by the associated industry to the total amount of the target industry according to the supply and demand data;
establishing a data relation table of the target industry and the associated industry according to the proportion and the supply and demand relation;
and importing the data relation table to a database system to obtain the sub-knowledge graph of the target industry.
3. The method of knowledge-graph-based information mining of claim 1, wherein the step of constructing a master knowledge graph from the industry network and the enterprise information comprises:
determining a target industry which has an incidence relation with the enterprise in the industry network according to the enterprise information;
and completing the sub-knowledge graph based on the incidence relation between the enterprise and the target industry to obtain the total knowledge graph.
4. The method of knowledge-graph-based information mining according to claim 3, wherein the step of determining a target industry in the industry network having an association relationship with the enterprise according to the enterprise information comprises:
acquiring a preset evaluation algorithm and a reference enterprise, and performing similarity calculation on the enterprise information and the reference enterprise according to the evaluation algorithm to obtain a correlation score corresponding to the enterprise information;
and determining the industry corresponding to the reference enterprise with the highest correlation score as the target industry.
5. The method of knowledge-graph-based information mining of claim 1, wherein the step of calculating a centrality of each of the industries in the industry network from which to determine key industries of the industry network comprises:
acquiring the number of nodes in the industry network, and normalizing the centrality of the degree according to the number of the nodes to obtain the centrality of the standard degree;
and determining the industry with the highest standard degree centrality as a key industry in all the industry networks.
6. The method of knowledge-graph-based information mining of claim 1, wherein the step of determining key industries of the industry network based on the centrality further comprises:
calculating the mesocentricity of each industry in the industry network;
and calculating the influence score of each different industry in the industry network according to the mesocentrality and the centrality, and determining the industry with the largest influence score as a key industry in the industry network.
7. The method of knowledge-graph-based information mining of claim 6, wherein the step of calculating the centrality of each industry in the industry network comprises:
determining a shortest path between any two industries in the industry network;
and calculating the coincidence rate of the industries in all the shortest paths, and taking the coincidence rate as the mesocentrality of the industries in the industry network.
8. An apparatus for information mining based on knowledge-graph, comprising:
the first construction module is used for acquiring supply and demand data of different industries and constructing a plurality of sub-knowledge maps corresponding to the different industries according to the supply and demand data;
the second construction module is used for dividing the sub-knowledge maps to obtain industry networks corresponding to the sub-knowledge maps, acquiring enterprise information of different enterprises, and constructing and obtaining a total knowledge map according to the industry networks and the enterprise information;
and the confirmation module is used for calculating the centrality of each industry in the industry network, determining the key industry of the industry network according to the centrality, and searching the key enterprises of the key industry in the total knowledge graph based on the key industry.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the knowledge-graph based information mining method of any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the knowledge-graph based information mining method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210168429.6A CN114528443A (en) | 2022-02-23 | 2022-02-23 | Knowledge graph-based information mining method and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210168429.6A CN114528443A (en) | 2022-02-23 | 2022-02-23 | Knowledge graph-based information mining method and related equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114528443A true CN114528443A (en) | 2022-05-24 |
Family
ID=81624874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210168429.6A Pending CN114528443A (en) | 2022-02-23 | 2022-02-23 | Knowledge graph-based information mining method and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114528443A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996507A (en) * | 2022-06-10 | 2022-09-02 | 北京达佳互联信息技术有限公司 | Video recommendation method and device |
-
2022
- 2022-02-23 CN CN202210168429.6A patent/CN114528443A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996507A (en) * | 2022-06-10 | 2022-09-02 | 北京达佳互联信息技术有限公司 | Video recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN110119413B (en) | Data fusion method and device | |
| CN112365202B (en) | Method for screening evaluation factors of multi-target object and related equipment thereof | |
| CN113836131A (en) | Big data cleaning method and device, computer equipment and storage medium | |
| CN114398477A (en) | Policy recommendation method based on knowledge graph and related equipment thereof | |
| CN114493255A (en) | Enterprise abnormity monitoring method based on knowledge graph and related equipment thereof | |
| CN112860662A (en) | Data blood relationship establishing method and device, computer equipment and storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN116860856A (en) | Financial data processing method and device, computer equipment and storage medium | |
| CN113283222B (en) | Automatic report generation method and device, computer equipment and storage medium | |
| CN111639360A (en) | Intelligent data desensitization method and device, computer equipment and storage medium | |
| CN114265835A (en) | Data analysis method and device based on graph mining and related equipment | |
| CN114528443A (en) | Knowledge graph-based information mining method and related equipment thereof | |
| CN116956326A (en) | Authority data processing method and device, computer equipment and storage medium | |
| CN114549053B (en) | Data analysis method, device, computer equipment and storage medium | |
| CN115099875A (en) | Data classification method based on decision tree model and related equipment | |
| CN112084408A (en) | List data screening method and device, computer equipment and storage medium | |
| CN112529718B (en) | Product demonstration method and device based on multiple scenes, computer equipment and medium | |
| CN112328960B (en) | Optimization method and device for data operation, electronic equipment and storage medium | |
| CN114545328B (en) | Tracking method and system for optical cable inspection equipment, computer equipment and storage medium | |
| CN114912818B (en) | Asset index analysis method, device, equipment and storage medium | |
| CN112258195A (en) | Transaction data processing method and device, computer equipment and storage medium | |
| CN116932697A (en) | Service data processing method based on rule engine optimization and related equipment | |
| US10922416B1 (en) | System, device, and method for transient event detection | |
| CN117933699A (en) | Task analysis method, device, computer equipment and storage medium |
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 |