CN111435367A

CN111435367A - Knowledge graph construction method, system, equipment and storage medium

Info

Publication number: CN111435367A
Application number: CN201910035977.XA
Authority: CN
Inventors: 王剑; 张雅婷; 曾杰梁; 孙常龙; 刘晓钟
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-01-15
Filing date: 2019-01-15
Publication date: 2020-07-21

Abstract

The embodiment of the application provides a method, a system, equipment and a storage medium for constructing a knowledge graph. In the embodiment of the application, the method comprises the steps of receiving a knowledge point of a knowledge graph, wherein the knowledge point comprises a node and an edge of the knowledge graph, obtaining a first structured knowledge graph according to the knowledge point, receiving at least one first correction result aiming at the first structured knowledge graph, and correcting the first structured knowledge graph by using the received at least one first correction result; and extracting each node in the corrected first structured knowledge graph and edges among the nodes to obtain a second structured knowledge graph, thereby providing the latest structured knowledge graph for corresponding services, automatically completing the construction of the knowledge graph and the iterative modification and updating of the knowledge graph, reducing the labor cost and improving the construction speed.

Description

Knowledge graph construction method, system, equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, a system, a device, and a storage medium for constructing a knowledge graph.

Background

With the development of computers and the internet, the total amount of global data shows an exponential growth situation, and a big data era comes along, wherein the big data is a data set with a huge number of data structures with complex structures and numerous types, and the data in the data set reflects objective world information, so that a large amount of useful information can be obtained from the big data through analysis of the big data. In order to extract useful information from massive data, so that the big data can be fully utilized, advanced data analysis technologies such as artificial intelligence and the like are also increasingly innovated, wherein the artificial intelligence is to connect data which are not connected originally and integrate discrete data together, so that more valuable decision support is provided, and the basis of the artificial intelligence is to construct a knowledge graph.

Disclosure of Invention

Aspects of the present application provide a method, system, device and storage medium for constructing a knowledge graph, so as to efficiently and automatically construct a relatively accurate knowledge graph, and reduce labor costs.

The embodiment of the application provides a method for constructing a knowledge graph, which comprises the following steps: receiving key points of a knowledge graph, wherein the key points comprise nodes and edges of the knowledge graph, and obtaining a first structured knowledge graph according to the key points, wherein the edges represent the relationship between the two nodes; receiving at least one first correction result for the first structured knowledge-graph, correcting the first structured knowledge-graph using the received at least one first correction result; and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

The embodiment of the application further provides a method for constructing the knowledge graph, which comprises the following steps: responding to the construction operation of the knowledge graph, generating the key points of the knowledge graph, and sending the key points of the knowledge graph to a server; and when a first verification result sent by the server is received, executing the steps of generating the key points of the knowledge graph and sending the key points of the knowledge graph to the server according to the first verification result.

The embodiment of the application further provides a method for constructing the knowledge graph, which comprises the following steps: receiving a first structured knowledge graph sent by the server; and responding to a first correction operation, performing first correction on the first structured knowledge graph, and returning a first correction result to the server.

The embodiment of the present application further provides a system for constructing a knowledge graph, including: a server; the server is used for receiving the key points of knowledge graph, the key points of knowledge graph comprise nodes and edges of the knowledge graph, a first structured knowledge graph is obtained according to the key points of knowledge graph, and the edges represent the relation between the two nodes; receiving at least one first correction result for the first structured knowledge-graph, correcting the first structured knowledge-graph using the received at least one first correction result; and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

The embodiment of the application also provides a server, which comprises a memory, a processor and a communication component; the memory for storing a computer program; the communication component is used for receiving the key points of knowledge graph, the key points of knowledge graph comprise nodes and edges of the knowledge graph, a first structured knowledge graph is obtained according to the key points of knowledge graph, and the edges represent the relation between the two nodes; receiving at least one first revised result for the first structured knowledge-graph; the processor to execute the computer program to: modifying the first structured knowledge-graph using the received at least one first modification; and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, causes the one or more processors to implement the steps of the above method.

The embodiment of the application also provides a terminal, which comprises a memory, a processor and a communication component; the memory for storing a computer program; the processor to execute the computer program to: responding to the construction operation of the knowledge graph, and generating the key points of the knowledge graph; when a first checking result sent by the server is received, executing the step of generating the key points of knowledge graph according to the first checking result, and sending the key points of knowledge graph to the server through a communication component; and the communication component is used for sending the knowledge points of the knowledge graph to a server.

The embodiment of the application also provides a terminal, which comprises a memory, a processor and a communication component; the memory for storing a computer program; the communication component to: receiving a first structured knowledge graph sent by the server; returning a first correction result to the server; the processor to execute the computer program to: in response to a first revising operation, a first revision is made to the first structured knowledge-graph.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, causes the one or more processors to implement the steps in the above.

In the embodiment of the application, the method comprises the steps of receiving a knowledge point of a knowledge graph, wherein the knowledge point comprises a node and an edge of the knowledge graph, obtaining a first structured knowledge graph according to the knowledge point, receiving at least one first correction result aiming at the first structured knowledge graph, and correcting the first structured knowledge graph by using the received at least one first correction result; and extracting each node in the corrected first structured knowledge graph and edges among the nodes to obtain a second structured knowledge graph, thereby providing the latest structured knowledge graph for corresponding services, automatically completing the construction of the knowledge graph and the iterative modification and updating of the knowledge graph, reducing the labor cost and improving the construction speed.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a schematic diagram of an exemplary knowledge graph construction system of the present application;

FIG. 2 is a schematic flow chart diagram of a method for constructing a knowledge graph according to another exemplary embodiment of the present application;

FIG. 3 is a schematic illustration of an editing interface provided in accordance with yet another exemplary embodiment of the present application;

FIG. 4 is a schematic flow chart diagram illustrating a method for constructing another knowledge-graph according to another exemplary embodiment of the present application;

FIG. 5 is a schematic flow chart diagram illustrating a method for constructing a knowledge-graph according to another exemplary embodiment of the present application;

FIG. 6 is a schematic structural diagram of an apparatus for constructing a knowledge-graph according to another exemplary embodiment of the present application;

FIG. 7 is a schematic diagram of an apparatus for constructing a knowledge-graph according to another exemplary embodiment of the present application;

FIG. 8 is a schematic structural diagram of another knowledge-graph constructing apparatus according to another exemplary embodiment of the present application;

fig. 9 is a schematic structural diagram of a server according to another exemplary embodiment of the present application;

fig. 10 is a schematic structural diagram of a terminal according to another exemplary embodiment of the present application;

fig. 11 is a schematic structural diagram of a terminal according to another exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The knowledge graph is also called as a scientific knowledge graph, and is a series of different graphs displaying the relation between the knowledge development process and the structure, the knowledge resource and the carrier thereof are described by using a visual technology, and the knowledge is mined, analyzed, constructed, drawn and displayed, and the mutual relation among the knowledge and the knowledge is among the knowledge graph types, but the knowledge graph is deficient in various judicial applications, and the two reasons are two, namely 1) the establishment of the knowledge graph depends on strong algorithm capability support, and the actual application effect of the knowledge graph is determined by the related technologies of Natural language Processing N L P (Natural L and Natural language Processing), such as entity identification, knowledge extraction, semantic understanding and the like, except for the graph construction capability, 2) the knowledge graph of a specific industry cannot be established only by the algorithm expert, and the accurate and universal knowledge graph can be generated only by the cooperation of a plurality of experts in the industry due to the deviation of the individual understanding.

In some embodiments of the present application, a key knowledge point of a knowledge-graph is received, the key knowledge point comprising nodes and edges of the knowledge-graph, a first structured knowledge-graph is obtained according to the key knowledge point, at least one first correction result for the first structured knowledge-graph is received, and the first structured knowledge-graph is corrected using the received at least one first correction result; and extracting each node in the corrected first structured knowledge graph and edges among the nodes to obtain a second structured knowledge graph, thereby providing the latest structured knowledge graph for corresponding services, automatically completing the construction of the knowledge graph and the iterative modification and updating of the knowledge graph, reducing the labor cost and improving the construction speed.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of a system for constructing a knowledge graph according to an exemplary embodiment of the present application. As shown in fig. 1, the building system 100 includes: a first terminal 101, a server 102, and a second terminal 103.

The first terminal 101 may be any device with certain computing capability, for example, a smart phone, a notebook, a pc (personal computer) computer, etc. The basic structure of the first terminal 101 includes: at least one processor. The number of processors depends on the configuration and type of the first terminal 101. The first terminal 101 may also include a Memory, which may be volatile, such as RAM, or non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or may include both types. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. Besides the processing unit and the memory, the first terminal 101 further includes some basic configurations, such as a network card chip, an IO bus, a camera, and an audio/video component. Optionally, the first terminal 101 may also include some peripheral devices, such as a keyboard, a mouse, a stylus, a printer, etc. Other peripheral devices are well known in the art and will not be described in detail herein.

The server 102 refers to a server capable of performing information construction in a network virtual environment, and generally refers to a server capable of performing a knowledge graph construction operation based on the internet. In physical implementation, the server 102 may be any device capable of providing computing services, responding to service requests, and performing processing, and may be, for example, a conventional server, a cloud host, a virtual center, and the like. The server mainly comprises a processor, a hard disk, a memory, a system bus and the like, and is similar to a general computer framework.

The second terminal 103 may be any device with certain computing capability, for example, a smart phone, a notebook, a pc (personal computer) computer, etc. The basic structure of the second terminal 103 includes: at least one processor. The number of processors depends on the configuration and type of the second terminal 103. The second terminal 103 may also include a Memory, which may be volatile, such as RAM, or non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or may include both types. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. In addition to the processing unit and the memory, the second terminal 103 also includes some basic configurations, such as a network card chip, an IO bus, and audio/video components. Optionally, the second terminal 103 may also include some peripheral devices, such as a keyboard, a mouse, a stylus, a printer, etc. Other peripheral devices are well known in the art and will not be described in detail herein.

In the embodiment, the server 102 receives the key points of knowledge graph, the key points of knowledge graph comprise nodes and edges of knowledge graph, a first structured knowledge graph is obtained according to the key points of knowledge graph, and the edges represent the relationship between the two nodes; receiving at least one first correction result for the first structured knowledge-graph, and correcting the first structured knowledge-graph using the received at least one first correction result; and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

In some examples, the first terminal 101 generates a key point of knowledge graph in response to a construction operation of the knowledge graph, and transmits the key point of knowledge graph to the server 102; when a first verification result sent by the server 102 is received, the steps of generating the key points of the knowledge graph and sending the key points of the knowledge graph to the server 102 are executed according to the first verification result.

In some examples, the second terminal 103 receives the first structured knowledge-graph sent by the server 102; in response to the first correction operation, a first correction is performed on the first structured knowledge-graph and a first correction result is returned to the server 102.

In this embodiment, the first terminal 101 is connected to the server 102 through a network, and the server 102 is connected to the second terminal 103 through a network, the first terminal 101 may be connected to the server 102 through a wireless or wired network, and the second terminal 103 may be connected to the server 102 through a wireless or wired network, if the first terminal 101 is connected to the server 102 through a mobile network, and the second terminal 103 is connected to the server 102 through a mobile network, the network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (L TE), 4G + (L TE +), WiMax, and the like.

The process of the server 102 building the knowledge graph is described in detail below in connection with method embodiments.

Fig. 2 is a flowchart illustrating a method for constructing a knowledge graph according to another exemplary embodiment of the present application. The method 200 provided by the embodiment of the present application is executed by a server, and the method 200 includes the following steps:

201: and receiving the key points of knowledge of the knowledge graph, wherein the key points of knowledge comprise nodes and edges of the knowledge graph, and the first structured knowledge graph is obtained according to the key points of knowledge, and the edges represent the relationship between the two nodes.

202: at least one first modification result for the first structured knowledge-graph is received, and the first structured knowledge-graph is modified using the received at least one first modification result.

203: and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

The following is a detailed explanation of the above steps:

Optionally, the knowledge-graph comprises a knowledge-graph corresponding to a type of domain of knowledge, e.g., a judicial knowledge-graph of a folk debt case.

The knowledge map is also called scientific knowledge map, is known as knowledge domain visualization or knowledge domain mapping map in the book intelligence world, is a series of different graphs for displaying the relation between the knowledge development process and the structure, describes knowledge resources and carriers thereof by using visualization technology, and excavates, analyzes, constructs, draws and displays knowledge and the mutual relation between the knowledge resources and the carriers.

The judicial knowledge map is an important basis for accurately providing legal knowledge question and answer, class case pushing, risk point confirmation and judgment, judgment results and literary production.

In some examples, prior to deriving the first structured knowledge-graph from the point of knowledge, the method 200 further comprises: performing first verification on the key points, returning a first verification result to the first terminal when the first verification result is unqualified, repeatedly performing the steps of receiving the key points of the knowledge map and performing the first verification on the key points until the first verification result is qualified; wherein, obtain first structural knowledge map according to the knowledge point, include: and when the first verification result is qualified, taking the key points of knowledge as a first structured knowledge graph.

It should be noted that, no matter the server receives the information sent by the first terminal or the second terminal, the server needs to check the information first (the first check may be performed, or the second check may be performed), so as to ensure that the information conforms to the construction rule or the construction logic of the knowledge graph. It should be understood that the information herein may refer to the key points of knowledge of the knowledge graph, and may also be the first correction result, the second correction result, the third correction result, and so on.

The construction rules or the construction logic refer to application rules for describing the use rules of each node and the association relation between the nodes in the knowledge graph in the construction process of the knowledge graph. For example, a label 1 node cannot use a label 2 connection relationship to connect a label 3 node, a person-type entity node uses a blue triangle control, an advertised entity node is an entity node with a connection relationship, and so on.

For example, according to the foregoing, after receiving the key points of the initial judicial knowledge graph of the folk debt sent by the first terminal, the server first performs the first verification on the construction rules and the construction logic of the key points of the initial judicial knowledge graph of the folk debt. And when the first verification result is qualified or successful, storing the key points of the initial judicial knowledge map so as to generate a first structured knowledge map, and sending the key points of the initial judicial knowledge map to at least one second terminal. And when the first checking result is unqualified or unsuccessful, sending the first checking result to the first terminal so that the first terminal modifies the knowledge key points according to the first checking result and returns the modified knowledge key points, and repeating the steps until the received first checking result of the knowledge key points sent by the first terminal is qualified.

When the first verification result is unqualified, the first verification result comprises a description of the reason of the verification failure.

For example, as described above, when the server fails to verify the initial judicial knowledge graph of the inter-folk debt, the reason of the verification failure is described through log records, for example, the node 1 can not use the connection relation of the node 2 to connect the node 3, the server sends the log recording the reason of the verification failure to the first terminal, the first terminal receives the log and displays the log to the user, the user modifies the key points of the initial judicial knowledge graph of the inter-folk debt according to the reason recorded in the log, and returns the modified key points of the initial judicial knowledge graph of the inter-folk debt to the server again until the verification of the server is successful and stores the modified key points, so as to generate the first structured knowledge graph, and it should be understood that the first structured knowledge graph can be represented and stored by using a relational database and is expressed as a two-dimensional knowledge graph, such as triple text and tables of information.

The first end-user may view the locally cached key points of knowledge and select some of the information that is useful to perform the initial construction or updating of other types of judicial knowledge maps.

It should be noted that, the first terminal is used to construct the key points of the initial knowledge graph corresponding to one type in one knowledge field at the initial stage, and send the key points of the initial knowledge graph to the server, so that the server generates the key points of the initial knowledge graph to be processed and sends the key points to the second terminal. The user to which the first terminal is directed may be a judicial expert.

202: at least one first correction result for the first structured knowledge-graph is received, and the first structured knowledge-graph is corrected using the received at least one first correction result.

In some examples, the method 200 further comprises: sending the obtained first structured knowledge graph to a second terminal; and when at least one first correction result aiming at the obtained first structured knowledge graph and sent by the second terminal is received, executing the step of correcting the first structured knowledge graph by using the received at least one first correction result.

In some examples, the method 200 further comprises: and performing second check on the at least one first correction result, returning the second check result to the second terminal when the second check result is unqualified, receiving the at least one first correction result aiming at the first structural knowledge graph, performing the step of performing second check on the at least one first correction result until the second check result is qualified, and performing the step of correcting the first structural knowledge graph by using the received at least one first correction result.

For example, according to the foregoing, after the server successfully verifies the first verification of the "key points of the initial judicial knowledge graph of the debt between people" sent by the first terminal, the server may send the first structured knowledge graph to at least one second terminal in the form of a message, the second terminal displays the message after receiving the message of the first structured knowledge graph, and responds to the click operation of the message, pull the first structured knowledge graph according to the address carried in the message, each second terminal displays the first structured knowledge graph "key points of the initial judicial knowledge graph of the debt between people" after receiving the first structured knowledge graph, the judge user views the displayed key points and modifies the displayed key points according to the part of his own responsible knowledge, the second terminal modifies the key points of the initial judicial knowledge graph of the debt between people in response to the modification operation, and responding to the submission operation, and sending the modified knowledge points of the initial judicial knowledge graph of the inter-folk debt to the server as a first correction result. Fig. 3 shows an interface 300 for the second terminal to modify the key points of knowledge graph, and the received key points of knowledge graph are displayed in the interface 300, and the received key points of knowledge graph are modified through a toolbar in the interface 300. When the server receives the knowledge main points of the modified initial judicial knowledge maps of the inter-folk debts sent by the second terminals, performing second check on the initial judicial knowledge maps of the inter-folk debts, and after a second check result is qualified, comparing the knowledge main points of the initial judicial knowledge maps of the inter-folk debts with the knowledge main points of the initial judicial knowledge maps of the inter-folk debts, determining and acquiring a modified part of the knowledge main points of the initial judicial knowledge maps of the inter-folk debts, merging the modified part with the knowledge main points of the initial judicial knowledge maps of the inter-folk debts, generating the knowledge main points of the initial judicial knowledge maps of the modified inter-folk debts, and storing the knowledge main points in the local server to obtain a modified first structured knowledge map; when the second check result is not qualified, the server sends the second check result to the second terminal, and the second terminal modifies the first correction result according to the second check result. And revising the first structured knowledge graph by using the received at least one first revising result until the second checking result is qualified.

In some examples, extracting each node and edges between nodes in the modified first structured knowledge-graph to obtain a second structured knowledge-graph includes: acquiring a first identifier corresponding to each entity node and a second identifier corresponding to edges between the entity nodes; determining attribute information of the corresponding entity node according to the first identifier, and determining structured data of the entity node according to the first identifier of the entity node and the attribute information; and determining the type of the corresponding edge according to the second identifier, and determining the structured data of the edge between the entity nodes according to the type of the edge and the first identifier corresponding to the entity nodes connected with the edge.

The entity node refers to a specific entity in the knowledge graph and can be represented by a graphic control element. The connection relation refers to an incidence relation between the entity nodes and can be represented by a line control element.

Structured data refers to data that can be represented and stored using a relational database in a two-dimensional form, such as a triple text and information table.

Alternatively, the first identifier and the second identifier may be IDs. The attribute information may include a name, a type, an action, etc. of the entity node, where the type may be evidence, a person, a thing, etc.

Optionally, the type of the connection relationship refers to a type of an association relationship between the entity node and the entity node, and may be a debit relationship or the like.

For example, as described above, after generating the modified first structural knowledge graph, the server acquires IDs corresponding to the entity nodes and the control elements corresponding to the connection relationships in the modified first structural knowledge graph, acquires names, types, and actions of the entity nodes according to the IDs, and acquires types of the connection relationships according to the IDs. And generating an information table of the entity node according to the identification, the name, the type, the action and the like of each entity node. And determining the node relation of the triple text according to the identification (or name) of the entity node with the connection relation and the type of the connection relation, such as (node 1: connection relation 1: node 2).

It should be noted that the server sets in advance the ID, name, type, control element, action, and the like of each entity node, and may also set in advance the ID, type, control element, and the like of the connection relationship, so after generating the second to-be-processed association information, each entity node and the connection relationship may be determined according to information in the second to-be-processed association information. It should be noted that the second structured knowledge graph may be the same as the first structured knowledge graph in the generation process, and the first structured knowledge graph is not described again, and in addition, for the first structured knowledge graph, usually, it needs to be modified, so the first structured knowledge graph here may also be understood as a knowledge graph only having a certain storage form, and determination of structured data is not performed, and may be different from the second structured knowledge graph.

In some examples, the method 200 further comprises: determining the content of the edge node according to the acquired first identifier of the edge node; and determining the structured data of the edges between the entity nodes according to the content of the edge nodes and the corresponding entity nodes connected with the edge nodes.

The connection relation node is a node used for representing a connection relation, can be used for representing a graphic control element, and takes a node name as a type of the connection relation.

For example, according to the foregoing, the connection relationship node and the content of the connection relationship node are determined according to the ID of each node, such as the debt relationship, and according to the content of the connection relationship node: debit relationship and entity node connected to the node: the method comprises the steps that an announced A (or a node 1) and an original announcement B (or a node 2) are determined, the fact that the announced A (or the node 1) and the original announcement B (or the node 2) belong to a debit relationship is determined, and the node relationship of a triple text is determined, such as (the node 1: the debit relationship: the node 2).

In some examples, the method 200 further comprises: and sending the corrected first structured knowledge graph to the first terminal, and correcting the second structured knowledge graph according to a second correction result if the second correction result sent by the first terminal is received.

For example, according to the foregoing, after the server successfully verifies the modified first structural knowledge graph and generates the second structural knowledge graph, the server may send a message to the first terminal, the first terminal displays the message after receiving the message, and responds to a click operation of the message, pulls the modified first structural knowledge graph to the first terminal according to the address carried in the message, the first terminal displays the modified first structural knowledge graph after receiving the modified first structural knowledge graph, the judicial expert user modifies the modified first structural knowledge graph after seeing the modified first structural knowledge graph, modifies the modified first structural knowledge graph in response to a modification operation, and sends the modified first structural knowledge graph to the server in response to a submission operation, after the server receives the modified first structured knowledge graph, the server updates the second structured knowledge graph again according to the process of generating the second structured knowledge graph already discussed in the foregoing, so as to form an iterative modification process, which is not repeated here.

In some examples, the method 200 further comprises: and sending the first structured knowledge graph corresponding to the corrected second structured knowledge graph to the second terminal, and correcting the corrected second structured knowledge graph according to a third correction result if the third correction result sent by the second terminal is received.

It should be noted that this example is the same as the foregoing specific implementation of sending the modified first structured knowledge graph to the first terminal, and is not described here again, so as to form the process of iterative modification or updating.

It should be noted that, for better understanding by the user, the first structured knowledge graph or the modified first structured knowledge graph is sent to the corresponding terminal, and the second structured knowledge graph is the available stored data extracted from the first structured knowledge graph.

It should be noted that no matter which terminal sends the information, the server needs to perform verification first, because the server receives the information sent by the corresponding terminal, and then responds to the information, verifies the information, and sends the corresponding verification result (including the log of successful verification or failed verification) to the corresponding terminal, that is, the first terminal or the corresponding second terminal, at this time, the user of the first terminal or the corresponding second terminal will wait for the verification result after submitting the information, and the server responds quickly, at this time, the interface of the corresponding terminal still shows that the information is, if the verification fails, the corresponding user can immediately modify the information according to the information of failed verification, until the verification passes, and the user can close the information on the interface. It should be understood that the information herein may refer to the key points of knowledge of the knowledge graph, and may also be the first correction result, the second correction result, the third correction result, and so on.

And no matter which corresponding terminal receives the information sent by the server, the server corrects or updates the local corresponding information according to whether the current server locally stores the corresponding information or not, generates a second structured knowledge graph, then verifies the corrected information, sends the corrected information to another corresponding terminal for modification after the verification result is qualified, directly provides the current second structured knowledge graph for the service if no modification exists, repeats the process if no modification exists, continues to modify the information until no modification exists, extracts the latest information to generate the latest second structured knowledge graph, and provides the latest second structured knowledge graph for the service.

In addition, the server sends the key points of the current knowledge graph to at least one second terminal, and the second terminal is used for modifying or supplementing part of information in the key points of the current knowledge graph, so that the part of information is modified, and the modified key points of the current knowledge graph are sent to the server.

Optionally, the manner in which the server issues the key points of knowledge of the current knowledge graph to the at least one second terminal may be: and sending the same key points of the current knowledge graph to each second terminal, modifying part of information of the key points of the current knowledge graph by the second terminals according to the modification operation of the user, and then sending the modified key points of the current knowledge graph to the server by at least one second terminal.

When any second terminal does not modify the knowledge points of the current knowledge graph, the information does not need to be sent to the server.

Optionally, the manner in which the server issues the key points of knowledge of the current knowledge graph to the at least one second terminal may also be: the server splits the key points of knowledge of the current knowledge graph into a plurality of pieces of partial information, and respectively sends the partial information to the corresponding second terminals.

Meanwhile, the second terminal also has the functions of the first terminal, and a user of the second terminal can also check the knowledge points of the modified knowledge graph cached locally at the second terminal and select useful part of information to modify the knowledge points of other types of judicial knowledge graphs.

In addition, the first terminal or the second terminal can also directly acquire the key points of the current knowledge graph from the server, and the acquisition mode can be that the server receives the acquisition request, the server acquires the corresponding second structured knowledge graph according to the identification of the key points of the current knowledge graph carried in the acquisition request, reversely determines the key points of the current knowledge graph by reading and identifying the content in the second structured knowledge graph, and transmits the key points of the current knowledge graph to the first terminal or the second terminal, and if the server stores the corresponding key points of the current knowledge graph, the key points of the corresponding knowledge graph are directly transmitted to the first terminal or the second terminal.

It should be noted that, in the embodiment of the present application, the second to-be-processed associated information is continuously modified in an iterative modification manner until no modifiable information exists, and corresponding structured data is generated according to each node in the current second to-be-processed associated information and a connection relationship between the nodes, so that other services can directly obtain data, for example, a judicial inquiry service can obtain the structured data, and a judicial judgment template of a corresponding type is generated, so that a user and a judge consulting a judicial can inquire the judgment result according to the judicial template.

Fig. 4 is a flowchart illustrating a method for constructing a knowledge graph according to another exemplary embodiment of the present application. The method 400 provided by the embodiment of the present application is executed by a first terminal, and the method 400 includes the following steps:

401: and responding to the construction operation of the knowledge graph, generating the knowledge points of the knowledge graph, and sending the knowledge points of the knowledge graph to the server.

402: and when a first verification result sent by the server is received, executing the steps of generating the key points of the knowledge graph according to the first verification result and sending the key points of the knowledge graph to the server.

It should be noted that, since the steps of the method 400 have been described in detail in the foregoing, no further description is provided herein.

Fig. 5 is a flowchart illustrating a method for constructing a knowledge graph according to another exemplary embodiment of the present application. The method 500 provided by the embodiment of the present application is executed by the second terminal, and the method 500 includes the following steps:

501: and receiving the first structured knowledge graph sent by the server.

502: and responding to the first correction operation, performing first correction on the first structured knowledge graph, and returning a first correction result to the server.

It should be noted that, since the steps of the method 500 have been described in detail in the foregoing, no further description is provided herein.

The following describes the technical solution of the present application in detail with reference to several exemplary application scenarios:

scene 1: the first terminal responds to the construction operation of a judicial expert to construct the key points of the initial judicial knowledge map of the inter-folk debt, responds to the submission operation, sends the key points of the initial judicial knowledge map of the inter-folk debt to the server, verifies the key points of the initial judicial knowledge map of the inter-folk debt after the server receives the key points of the initial judicial knowledge map of the inter-folk debt, and stores the key points of the initial judicial knowledge map of the inter-folk debt to the local server after the verification is successful.

The server can obtain the ID of each entity node and the connection relation ID from the knowledge points of the initial judicial knowledge graph of the folk debt at this time, obtain the name, the type, the action and the like of the corresponding entity node according to each entity node ID, determine the information table (the entity node ID, the entity node name, the entity node type, the entity node action and the like) of each entity node, and obtain the type of the corresponding connection relation according to the connection relation ID. And determining a triple text (node ID '2': connection relation 'borrow relation': node ID '2') according to the entity nodes connected by each connection relation in the knowledge points of the initial judicial knowledge graph of the folk borrow. The server stores the information table and the triple text of each entity node, the triple text is used for judicial judgment of the folk debt cases in the judicial industry, and a judicial judgment template of the folk debt cases is generated for user query and judge query results. The user can select the folk debt cases in the provided query interface, input the query conditions according to the query condition input box provided by the template, perform query and receive the query result.

The server respectively issues the key points of the initial judicial knowledge map of the inter-folk debt to 10 second terminals, the second terminals display the key points after receiving the key points of the initial judicial knowledge map of the inter-folk debt, respond to the modification operation of a judge, modify the key points of the initial judicial knowledge map of the inter-folk debt, respond to the submission operation, the second terminals send the modified key points of the initial judicial knowledge map of the inter-folk debt to the server, the server receives the modified key points of the initial judicial knowledge map of the inter-folk debt sent by 9 second terminals, when the server verifies the received key points of the initial judicial knowledge map of each modified key point of the inter-folk debt, and when the verification is successful, the key points of the initial judicial knowledge map of each modified inter-folk debt are compared with the key points of the initial judicial knowledge map of the inter-folk debt, acquiring updated information in the key points of the initial judicial knowledge map of each modified inter-folk debit, combining the 9 pieces of modified information with the key points of the initial judicial knowledge map of the inter-folk debit to generate the key points of the initial judicial knowledge map of the new inter-folk debit or the key points of the initial judicial knowledge map of the modified inter-folk debit, verifying the key points of the initial judicial knowledge map of the new inter-folk debit or the key points of the initial judicial knowledge map of the modified inter-folk debit by the server, and storing the modified initial judicial knowledge map of the inter-folk debit to the local server after the verification is successful.

The server can obtain the ID of each entity node and the connection relationship ID from the knowledge point of the modified initial judicial knowledge graph of the inter-folk debt, obtain the name, type, action and the like of the corresponding entity node according to each entity node ID, determine the information table (entity node ID, entity node name, entity node type, entity node action and the like) of each entity node, and obtain the type of the corresponding connection relationship according to the connection relationship ID. And determining a triple text (node ID '2': connection relation 'borrow relation': node ID '2') according to the entity nodes connected by each connection relation in the modified initial judicial knowledge graph of the folk borrow. The server stores the information table and the triple text of each entity node, the triple text is used for judicial judgment of the folk debt cases in the judicial industry, and a judicial judgment template of the folk debt cases is generated for user query and judge query results. The user can select the folk debt cases in the provided query interface, input the query conditions according to the query condition input box provided by the template, perform query and receive the query result.

The iteration circulation is carried out, after the server generates the knowledge key points of the initial judicial knowledge map of the new folk debt, the corresponding structured data are generated to be directly obtained by the corresponding judicial judging service, and the structured data can be continuously updated until the updating is stopped, so that the structured data can be more and more accurate, a large amount of manpower iteration work can be reduced, the labor cost is saved, different types of cases in each judicial can be obtained by the embodiment of the application, and the application effect is good.

Fig. 6 is a schematic structural framework diagram of an apparatus for constructing a knowledge graph according to another exemplary embodiment of the present application. The apparatus 600 may be applied to a server, and the apparatus 600 includes an obtaining module 601, a modifying module 602, and an extracting module 603, and the functions of the modules are described in detail below:

the obtaining module 601 is configured to receive a key point of knowledge graph, where the key point of knowledge graph includes a node and an edge of the knowledge graph, and obtain a first structured knowledge graph according to the key point of knowledge, and the edge represents a relationship between the two nodes.

A modification module 602 configured to receive at least one first modification result for the first structured knowledge-graph, and modify the first structured knowledge-graph using the received at least one first modification result.

An extracting module 603, configured to extract each node and edges between nodes in the modified first structured knowledge graph to obtain a second structured knowledge graph.

In some examples, the apparatus 600 further comprises: the first checking module is used for carrying out first checking on the key points of knowledge, returning a first checking result to the first terminal when the first checking result is unqualified, repeatedly executing the steps of receiving the key points of knowledge maps and carrying out first checking on the key points of knowledge until the first checking result is qualified; and when the first verification result is qualified, taking the key points of knowledge as a first structured knowledge graph.

In some examples, the apparatus 600 further comprises: the sending module is used for sending the obtained first structured knowledge graph to a second terminal; and when at least one first correction result aiming at the obtained first structured knowledge graph and sent by the second terminal is received, executing the step of correcting the first structured knowledge graph by using the received at least one first correction result.

In some examples, the apparatus 600 further comprises: and the first checking module is used for performing second checking on at least one first correction result, returning the second checking result to the second terminal when the second checking result is unqualified, receiving at least one first correction result aiming at the first structural knowledge graph, performing second checking on at least one first correction result until the second checking result is qualified, and performing the step of correcting the first structural knowledge graph by using the received at least one first correction result.

In some examples, the extraction module 603 includes: the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first identifier corresponding to each entity node and a second identifier corresponding to edges between the entity nodes; the first determining unit is used for determining the attribute information of the corresponding entity node according to the first identifier and determining the structured data of the entity node according to the first identifier and the attribute information of the entity node; and the second determining unit is used for determining the type of the corresponding edge according to the second identifier and determining the structured data of the edge between the entity nodes according to the type of the edge and the first identifier corresponding to the entity nodes connected with the edge.

In some examples, the apparatus 600 further comprises: the determining module is used for determining the content of the edge node according to the acquired first identifier of the edge node; and determining the structured data of the edges between the entity nodes according to the content of the edge nodes and the corresponding entity nodes connected with the edge nodes.

In some examples, the modification module 602 is configured to send the modified first structural knowledge-graph to the first terminal, and if a second modification result sent by the first terminal is received, modify the second structural knowledge-graph according to the second modification result.

In some examples, the modifying module 602 is configured to send the first structured knowledge graph corresponding to the modified second structured knowledge graph to the second terminal, and if a third modification result sent by the second terminal is received, modify the modified second structured knowledge graph according to the third modification result.

Fig. 7 is a schematic structural framework diagram of another apparatus for constructing a knowledge graph according to another exemplary embodiment of the present application. The apparatus 700 may be applied to a terminal, and the apparatus 700 includes: a generating module 701 and an executing module 702, the functions of which are described in detail below:

the generating module 701 is configured to generate a key point of knowledge of the knowledge graph in response to a construction operation of the knowledge graph, and send the key point of knowledge of the knowledge graph to the server.

The executing module 702 is configured to, when receiving a first verification result sent by the server, execute the steps of generating the key points of the knowledge graph according to the first verification result, and sending the key points of the knowledge graph to the server.

FIG. 8 is a schematic structural framework diagram of another knowledge-graph building apparatus according to another exemplary embodiment of the present application. The apparatus 800 may be applied to a terminal, and the apparatus 800 includes: the receiving module 801 and the modifying module 802 are described in detail below with respect to functions of the respective modules:

a receiving module 801, configured to receive the first structured knowledge graph sent by the server.

The modification module 802 is configured to perform a first modification on the first structured knowledge graph in response to the first modification operation, and return a first modification result to the server.

Having described the internal functions and structure of the building apparatus 600 shown in fig. 6, in one possible design, the structure of the building apparatus 600 shown in fig. 6 may be implemented as a server, as shown in fig. 9, and the server 900 may include: memory 901, processor 902, and communications component 903;

a memory 901 for storing a computer program;

a processor 902 for executing a computer program for:

modifying the first structured knowledge-graph using the received at least one first modification;

extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph;

a communication component 903, configured to receive a key point of knowledge of the knowledge graph, where the key point of knowledge includes a node and an edge of the knowledge graph, and obtain a first structured knowledge graph according to the key point of knowledge, and the edge represents a relationship between the two nodes; at least one first correction result for the first structured knowledge-graph is received.

In some examples, the processor 902 is further configured to: a first check is performed on the knowledge point, and when the first check result is not qualified, the communication component 903 is configured to return the first check result to the first terminal, and the processor 902 is further configured to: repeatedly executing the steps of receiving the key points of knowledge graph and carrying out first verification on the key points of knowledge until the first verification result is qualified; and when the first verification result is qualified, taking the key points of knowledge as a first structured knowledge graph.

In some examples, the communication component 903 is further configured to: sending the obtained first structured knowledge graph to a second terminal; the processor 902 is further configured to: and when at least one first correction result aiming at the obtained first structured knowledge graph and sent by the second terminal is received, executing the step of correcting the first structured knowledge graph by using the received at least one first correction result.

In some examples, the processor 902 is further configured to: a second check is performed on the at least one first modification result, and when the second check result is not qualified, the communication component 903 is further configured to: returning the second check result to the second terminal, the processor 902 is further configured to: the steps of receiving at least one first correction result for the first structured knowledge-graph, performing a second check on the at least one first correction result until the second check result is qualified, and performing the step of correcting the first structured knowledge-graph using the received at least one first correction result.

In some examples, the processor 902 is specifically configured to: acquiring a first identifier corresponding to each entity node and a second identifier corresponding to edges between the entity nodes; determining attribute information of the corresponding entity node according to the first identifier, and determining structured data of the entity node according to the first identifier of the entity node and the attribute information; and determining the type of the corresponding edge according to the second identifier, and determining the structured data of the edge between the entity nodes according to the type of the edge and the first identifier corresponding to the entity nodes connected with the edge.

In some examples, the processor 902 is further configured to: determining the content of the edge node according to the acquired first identifier of the edge node; and determining the structured data of the edges between the entity nodes according to the content of the edge nodes and the corresponding entity nodes connected with the edge nodes.

In some examples, the processor 902 is specifically configured to: and sending the corrected first structured knowledge graph to the first terminal, and correcting the second structured knowledge graph according to a second correction result if the second correction result sent by the first terminal is received.

In some examples, the communication component 903 is further configured to: the first structured knowledge graph corresponding to the modified second structured knowledge graph is sent to the second terminal, and if a third modification result sent by the second terminal is received, the processor 902 is further configured to: and correcting the corrected second structured knowledge graph according to a third correction result.

In addition, embodiments of the present invention provide a computer storage medium, and the computer program, when executed by one or more processors, causes the one or more processors to implement the steps of the method for constructing a knowledge graph in the method embodiment of fig. 2.

Having described the internal functions and structure of the construction apparatus 700 shown in fig. 7, in one possible design, the structure of the construction apparatus 700 shown in fig. 7 may be implemented as a terminal, as shown in fig. 10, and the first terminal 1000 may include: memory 1001, processor 1002, and communications component 1003;

a memory 1001 for storing a computer program;

a processor 1002 for executing a computer program for: responding to the construction operation of the knowledge graph, and generating the key points of the knowledge graph; when a first verification result sent by the server is received, executing a step of generating key points of the knowledge graph according to the first verification result, and sending the key points of the knowledge graph to the server through the communication assembly;

a communication component 1003 for sending the knowledge points of the knowledge graph to the server.

In addition, embodiments of the present invention provide a computer storage medium, and the computer program, when executed by one or more processors, causes the one or more processors to implement the steps of the method for constructing a knowledge graph in the method embodiment of fig. 4.

Having described the internal functions and structure of the construction apparatus 800 shown in fig. 8, in one possible design, the structure of the construction apparatus 800 shown in fig. 8 may be implemented as a terminal, as shown in fig. 11, and the second terminal 1100 may include: memory 1101, processor 1102, and communications component 1103;

a memory 1101 for storing a computer program;

a communication component 1103 for receiving the first structured knowledge-graph sent by the server; returning the first correction result to the server;

a processor 1102 for executing a computer program for: in response to the first revising operation, a first revision is made to the first structured knowledge-graph.

In addition, embodiments of the present invention provide a computer storage medium, and the computer program, when executed by one or more processors, causes the one or more processors to implement the steps of the method for constructing a knowledge graph in the embodiment of the method of fig. 5.

In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 201, 202, 203, etc., are merely used for distinguishing different operations, and the sequence numbers themselves do not represent any execution order. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described aspects and portions of the present technology which contribute substantially or in part to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including without limitation disk storage, CD-ROM, optical storage, and the like.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable multimedia data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable multimedia data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable multimedia data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable multimedia data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A construction method of a knowledge graph comprises the following steps:

receiving key points of a knowledge graph, wherein the key points comprise nodes and edges of the knowledge graph, and obtaining a first structured knowledge graph according to the key points, wherein the edges represent the relationship between the two nodes;

receiving at least one first correction result for the first structured knowledge-graph, correcting the first structured knowledge-graph using the received at least one first correction result;

and extracting each node and edges among the nodes in the corrected first structured knowledge graph to obtain a second structured knowledge graph.

2. The method of claim 1, prior to said deriving a first structured knowledge-graph from said points of knowledge, further comprising:

performing first verification on the key points, returning a first verification result to the first terminal when the first verification result is unqualified, repeatedly performing the steps of receiving the key points of the knowledge map and performing first verification on the key points until the first verification result is qualified;

wherein, obtaining a first structured knowledge graph according to the key points of knowledge comprises: and when the first verification result is qualified, taking the key points of knowledge as a first structured knowledge graph.

3. The method of claim 1, further comprising:

sending the obtained first structured knowledge graph to a second terminal;

and when at least one first correction result aiming at the obtained first structured knowledge graph and sent by the second terminal is received, executing the step of correcting the first structured knowledge graph by using the received at least one first correction result.

4. The method of claim 3, further comprising:

and performing second check on the at least one first correction result, returning the second check result to the second terminal when the second check result is unqualified, performing the step of receiving the at least one first correction result aiming at the first structured knowledge graph, performing the second check on the at least one first correction result until the second check result is qualified, and performing the step of correcting the first structured knowledge graph by using the received at least one first correction result.

5. The method of claim 1, wherein extracting nodes and edges between nodes in the modified first structured knowledge-graph to obtain a second structured knowledge-graph comprises:

acquiring a first identifier corresponding to each entity node and a second identifier corresponding to edges between the entity nodes;

determining attribute information of a corresponding entity node according to the first identifier, and determining structured data of the entity node according to the first identifier of the entity node and the attribute information;

and determining the type of the corresponding edge according to the second identifier, and determining the structured data of the edge between the entity nodes according to the type of the edge and the first identifier corresponding to the entity nodes connected with the edge.

6. The method of claim 5, further comprising:

determining the content of the edge node according to the acquired first identifier of the edge node;

and determining the structured data of the edges between the entity nodes according to the content of the edge nodes and the corresponding entity nodes connected with the edge nodes.

7. The method of claim 1, further comprising:

and sending the corrected first structured knowledge graph to a first terminal, and correcting a second structured knowledge graph according to a second correction result if the second correction result sent by the first terminal is received.

8. The method of claim 7, further comprising:

and sending the first structured knowledge graph corresponding to the corrected second structured knowledge graph to the second terminal, and correcting the corrected second structured knowledge graph according to a third correction result if the third correction result sent by the second terminal is received.

9. A construction method of a knowledge graph comprises the following steps:

responding to the construction operation of the knowledge graph, generating the key points of the knowledge graph, and sending the key points of the knowledge graph to a server;

and when a first verification result sent by the server is received, executing the steps of generating the key points of the knowledge graph and sending the key points of the knowledge graph to the server according to the first verification result.

10. A construction method of a knowledge graph comprises the following steps:

receiving a first structured knowledge graph sent by a server;

and responding to a first correction operation, performing first correction on the first structured knowledge graph, and returning a first correction result to the server.

11. A system for constructing a knowledge graph, comprising: a server;

the server is used for receiving the key points of knowledge graph, the key points of knowledge graph comprise nodes and edges of the knowledge graph, a first structured knowledge graph is obtained according to the key points of knowledge graph, and the edges represent the relation between the two nodes;

12. The system of claim 11, further comprising: a first terminal and at least one second terminal;

the first terminal is used for responding to the construction operation of the knowledge graph, generating the key points of the knowledge graph and sending the key points of the knowledge graph to the server; when a first verification result sent by the server is received, executing the key points of the generated knowledge graph according to the first verification result, and sending the key points of the knowledge graph to the server;

the at least one second terminal is used for receiving the first structured knowledge graph sent by the server; and responding to a first correction operation, performing first correction on the first structured knowledge graph, and returning a first correction result to the server.

13. A server comprising a memory, a processor, and a communication component;

the memory for storing a computer program;

the communication component is used for receiving the key points of knowledge graph, the key points of knowledge graph comprise nodes and edges of the knowledge graph, a first structured knowledge graph is obtained according to the key points of knowledge graph, and the edges represent the relation between the two nodes; receiving at least one first revised result for the first structured knowledge-graph;

the processor to execute the computer program to:

14. A computer readable storage medium storing a computer program which, when executed by one or more processors, causes the one or more processors to carry out the steps in the method of any one of claims 1 to 8.

15. A terminal comprising a memory, a processor, and a communication component;

the memory for storing a computer program;

the processor to execute the computer program to:

responding to the construction operation of the knowledge graph, and generating the key points of the knowledge graph;

when a first checking result sent by the server is received, executing the step of generating the key points of knowledge graph according to the first checking result, and sending the key points of knowledge graph to the server through a communication component;

and the communication component is used for sending the knowledge points of the knowledge graph to a server.

16. A computer readable storage medium having a computer program stored thereon, which, when executed by one or more processors, causes the one or more processors to carry out the steps of the method of claim 9.

17. A terminal comprising a memory, a processor, and a communication component;

the memory for storing a computer program;

the communication component is used for receiving a first structured knowledge graph sent by the server; returning a first correction result to the server;

the processor to execute the computer program to: in response to a first revising operation, a first revision is made to the first structured knowledge-graph.

18. A computer readable storage medium having a computer program stored thereon, which, when executed by one or more processors, causes the one or more processors to carry out the steps of the method of claim 10.