Knowledge graph creation method and device, electronic equipment, storage medium and program

Abstract

The embodiment of the invention discloses a knowledge graph creation method and device, electronic equipment, a storage medium and a program.The method comprises the steps that in response to a triggering operation of a target knowledge graph element, a configuration interface area of the target knowledge graph element is displayed in a target area in a knowledge graph editing interface; wherein the target knowledge graph elements comprise entity nodes or connecting lines; obtaining element configuration data input based on a configuration interface area of the target knowledge graph element, and determining graph attribute data of the target knowledge graph element according to the element configuration data; and generating the knowledge graph of the target knowledge domain according to each knowledge graph element in the knowledge graph editing interface and the graph attribute data of each knowledge graph element. According to the technical scheme, the flexibility and interactivity of the knowledge graph creating process can be improved, and then the user interaction experience is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of knowledge graph technology, and in particular, to a knowledge graph creation method, device, electronic device, storage medium and program. Background Art

[0002] Knowledge graph is a structured knowledge representation method that expresses entities and the relationships between entities in the form of graphics. It is widely used in technical fields such as knowledge extraction, business query, and fault reasoning.

[0003] The construction of knowledge graphs requires a large amount of data information. Currently, the construction of knowledge graphs mainly relies on extracting entities, attributes and relationships from massive data and adding this information to the data layer of the knowledge graph. Then, the knowledge graph compiler can use the pre-set nodes to build the knowledge graph based on the information in the data layer. However, due to the wide variety of data and the complex relationships between entities, it is often difficult to sort out and understand the corresponding relationships between data.

[0004] In the process of implementing the present invention, the inventors found that the prior art has the following defects: users cannot modify node attributes in real time in the knowledge graph editing interface, which limits the dynamic update and real-time interaction capabilities of the knowledge graph. Summary of the invention

[0005] Embodiments of the present invention provide a knowledge graph creation method, device, electronic device, storage medium and program, which can improve the flexibility and interactivity of the knowledge graph creation process, thereby enhancing the user interaction experience.

[0006] According to one aspect of the present invention, a knowledge graph creation method is provided, which is applied to a knowledge graph compiler, comprising:

[0007] In response to a triggering operation of a target knowledge graph element, a configuration interface area of ​​the target knowledge graph element is displayed in a target area in a knowledge graph editing interface; wherein the target knowledge graph element includes an entity node or a connection line;

[0008] Obtaining element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element, and determining graph attribute data of the target knowledge graph element according to the element configuration data;

[0009] Generate a knowledge graph of the target knowledge domain based on each knowledge graph element in the knowledge graph editing interface and the graph attribute data of each knowledge graph element.

[0010] According to another aspect of the present invention, a knowledge graph creation device is provided, which is configured in a knowledge graph compiler and includes:

[0011] A configuration interface display module, for displaying the configuration interface area of ​​the target knowledge graph element in the target area of ​​the knowledge graph editing interface in response to a trigger operation of the target knowledge graph element; wherein the target knowledge graph element includes an entity node or a connection line;

[0012] A graph attribute data acquisition module, used to acquire element configuration data input based on the configuration interface area of ​​the target knowledge graph element, and determine the graph attribute data of the target knowledge graph element according to the element configuration data;

[0013] The knowledge graph creation module is used to generate a knowledge graph of the target knowledge field based on the knowledge graph elements in the knowledge graph editing interface and the graph attribute data of each knowledge graph element.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the knowledge graph creation method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the knowledge graph creation method described in any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the knowledge graph creation method described in any embodiment of the present invention.

[0020] The embodiments of the present invention respond to the triggering operation of the entity node or the connection line to display the configuration interface area of ​​the entity node or the connection line in the target area in the knowledge graph editing interface, and further obtain the element configuration data input based on the configuration interface area of ​​the entity node or the connection line, and determine the graph attribute data of the entity node or the connection line according to the element configuration data, so as to generate a knowledge graph of the target knowledge field according to each entity node or connection line in the knowledge graph editing interface and the graph attribute data of each entity node or connection line, thereby solving the problem of insufficient dynamic update and real-time interaction capabilities of the existing knowledge graph, and being able to improve the flexibility and interactivity of the knowledge graph creation process, thereby enhancing the user interaction experience.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 It is a flowchart of a knowledge graph creation method provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a schematic diagram of a knowledge graph structure in the field of fault reasoning provided by the second embodiment of the present invention;

[0025] Figure 3 It is a flowchart of a knowledge graph creation method provided in Embodiment 2 of the present invention;

[0026] Figure 4 This is a schematic diagram of a knowledge graph in the field of fault reasoning provided by the second embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of a knowledge graph structured data format conversion provided by Embodiment 2 of the present invention;

[0028] Figure 6 It is a schematic diagram of a knowledge graph creation device provided in Embodiment 3 of the present invention;

[0029] Figure 7 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the term "target" and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 This is a flowchart of a knowledge graph creation method provided in the first embodiment of the present invention. This embodiment is applicable to the case where the attribute data of the knowledge graph is configured in real time by the knowledge graph compiler to flexibly create the knowledge graph. The method can be executed by a knowledge graph creation device, which can be implemented by software and / or hardware, and can generally be integrated in an electronic device. The electronic device can be a terminal device or a server device. As long as it can run the knowledge graph compiler to execute the knowledge graph creation method, the embodiment of the present invention does not limit the specific device type of the electronic device. Accordingly, Figure 1 As shown, the method includes the following operations:

[0034] S110. In response to a triggering operation of a target knowledge graph element, a configuration interface area of ​​the target knowledge graph element is displayed in a target area in a knowledge graph editing interface; wherein the target knowledge graph element includes an entity node or a connecting line.

[0035] Among them, the knowledge graph compiler can be a tool for creating a knowledge graph by dragging components and configuring the relationships and constraints between the components. Optionally, the knowledge graph compiler can support the creation of knowledge graphs in multiple different fields. The target knowledge graph element can be an element that needs to be included in the knowledge graph. Exemplarily, the target knowledge graph element can include entity nodes or connecting lines used to constitute the knowledge graph. The knowledge graph editing interface can be a tool interface for creating, editing and managing knowledge graphs in the knowledge graph compiler. In the knowledge graph editing interface, users can perform operations such as dragging and editing configurations on the target knowledge graph elements in a graphical manner. The target area can be a specific location in the knowledge graph editing interface for displaying the target knowledge graph element configuration interface area. Exemplarily, the target area can be the right edge area of ​​the knowledge graph editing interface. The configuration interface area can be an area in the knowledge graph editing interface for configuring and managing the target knowledge graph elements.

[0036] In an embodiment of the present invention, a graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. Exemplarily, the graph element library can be displayed in the left menu bar of the knowledge graph editing interface. Optionally, the graph element library can be used to store a variety of knowledge graph elements that constitute the knowledge graph, for example, entity nodes and various types of connections. It should be noted that the knowledge graph elements stored in the graph element library can be understood as a template, which does not have any attribute data and configuration data. Correspondingly, the user can select one of the graph elements as the target knowledge graph element by clicking or dragging the graph element library of the knowledge graph editing interface. When the target knowledge graph element is triggered, the knowledge graph compiler can respond to the triggering operation of the target knowledge graph element, and display the configuration interface area of ​​the target knowledge graph element in the target area of ​​the knowledge graph editing interface, and further configure the target knowledge graph element through the configuration interface area of ​​the target knowledge graph element, thereby realizing the online configuration of the target knowledge graph element.

[0037] In a specific example, when a user clicks on an element of an entity node in the graph element library on the left side of the knowledge graph editing interface, an entity node to be configured can be displayed at a certain position in the knowledge graph editing interface, and the configuration interface of the entity node can be displayed on the right side of the knowledge graph editing interface. The user can configure the graph attribute data and other configurations of the entity node in real time through the configuration interface of the entity node. Alternatively, the user can also select an element of an entity node from the graph element library on the left side of the knowledge graph editing interface and drag it to a specified position in the knowledge graph editing interface. The knowledge graph compiler can then display an entity node to be configured based on the user's specified position, and display the configuration interface of the entity node on the right side of the knowledge graph editing interface. The user can configure the attributes and other configurations of the entity node in real time through the configuration interface of the entity node.

[0038] S120. Obtain element configuration data input based on the configuration interface area of ​​the target knowledge graph element, and determine graph attribute data of the target knowledge graph element according to the element configuration data.

[0039] The element configuration data may be the relevant configuration data of the target knowledge graph element input through the configuration interface area of ​​the target knowledge graph element. The graph attribute data may be the attribute data of the target knowledge graph element.

[0040] Correspondingly, after the knowledge graph compiler displays the configuration interface area of ​​the target knowledge graph element in the target area of ​​the knowledge graph editing interface, the user can configure the attribute data of the target knowledge graph element based on the configuration interface area of ​​the target knowledge graph element. Furthermore, the knowledge graph compiler can determine the graph attribute data of the target knowledge graph element based on the element configuration data input by the user based on the configuration interface area of ​​the target knowledge graph element, thereby realizing the online real-time configuration of the graph attribute data of the target knowledge graph element.

[0041] In an embodiment of the present invention, after determining the graph attribute data of the target knowledge graph element according to the element configuration data, it may also include: performing a compliance check on the graph attribute data of the target knowledge graph element; when it is determined that the graph attribute data of the target knowledge graph element has not passed the compliance check, displaying a prompt message that the graph attribute data is non-compliant to indicate that the element configuration data input based on the configuration interface area of ​​the target knowledge graph element should be re-obtained.

[0042] Specifically, after completing the configuration of the graph attribute data of the target knowledge graph element, the knowledge graph compiler can start the built-in verification rules to perform compliance verification on the graph attribute data of the target knowledge graph element. If the knowledge graph compiler determines that the graph attribute data of the target knowledge graph element passes the compliance verification, for example, a certain type of entity node must have at least two states, and the sum of the prior probabilities is 1, then the target knowledge graph element can be displayed normally at the relevant position in the knowledge graph editing interface. If the knowledge graph compiler determines that the graph attribute data of the target knowledge graph element does not pass the compliance verification, for example, a certain entity node requires output, but the output item is not configured in the knowledge graph editing interface, then a prompt message indicating that the graph attribute data of the target knowledge graph element is non-compliant can be displayed. Accordingly, the user can re-enter reasonable element configuration data in the configuration interface area of ​​the target knowledge graph element according to the non-compliant prompt information until the graph attribute data of the target knowledge graph element passes the compliance verification.

[0043] S130. Generate a knowledge graph of the target knowledge domain according to each knowledge graph element in the knowledge graph editing interface and graph attribute data of each knowledge graph element.

[0044] The target knowledge domain may be a knowledge domain for which a knowledge graph needs to be constructed. For example, the target knowledge domain may include, but is not limited to, the fault reasoning domain, the search engine domain, and the medical domain, etc. The embodiment of the present invention does not limit the specific type of the target knowledge domain.

[0045] Specifically, when it is necessary to create a knowledge graph for a certain knowledge field, the knowledge field can be determined as the target knowledge field. After determining the target knowledge field, the user can select the corresponding target knowledge graph element in the knowledge graph editing interface according to specific needs, and configure its graph attribute data through the configuration interface area of ​​these elements. Furthermore, the knowledge graph of the target knowledge field can be created based on the relationship between the target knowledge graph elements in the knowledge graph editing interface and the graph attribute data of each knowledge graph element. For example, the entity nodes are connected by connecting lines in the knowledge graph editing interface, and the knowledge graph of the target knowledge field is created based on the description data of the entity nodes and the constraints of the connecting lines.

[0046] The embodiments of the present invention respond to the triggering operation of the entity node or the connection line to display the configuration interface area of ​​the entity node or the connection line in the target area in the knowledge graph editing interface, and further obtain the element configuration data input based on the configuration interface area of ​​the entity node or the connection line, and determine the graph attribute data of the entity node or the connection line according to the element configuration data, so as to generate a knowledge graph of the target knowledge field according to each entity node or connection line in the knowledge graph editing interface and the graph attribute data of each entity node or connection line, thereby solving the problem of insufficient dynamic update and real-time interaction capabilities of the existing knowledge graph, and being able to improve the flexibility and interactivity of the knowledge graph creation process, thereby enhancing the user interaction experience.

[0047] Embodiment 2

[0048] In the embodiment of the present invention, optionally, the target knowledge domain may include a field of fault reasoning technology; the entity nodes may include a fault cause node, a fault symptom node, and a logic gate node; and the connecting lines may include solid lines and dotted lines.

[0049] Among them, the fault cause node can be a physical node representing the fault cause, which is used to describe and analyze the cause of the fault phenomenon. The fault symptom node can be a physical node representing the fault symptom, which is used to indicate a potential fault. The logic gate node can be a physical node representing a logical operation relationship, and the logical relationship between different fault symptom nodes can be represented by performing a logical operation. Exemplarily, the logical operation can include but is not limited to AND, OR, NOT and NAND operations, etc. The embodiment of the present invention does not limit the specific operations included in the logical operation.

[0050] Figure 2 is a schematic diagram of a knowledge graph structure in the field of fault reasoning provided by the second embodiment of the present invention. In a specific example, Figure 2 As shown in FIG. 1 , when the target knowledge domain is the field of fault reasoning technology, the entity nodes may include fault cause nodes, fault symptom nodes, and logic gate nodes; and the connecting lines may include solid lines and dotted lines. It should be noted that in the knowledge graph of the fault reasoning field, there is at least one fault cause node and one fault symptom node.

[0051] Figure 3 This is a flow chart of a knowledge graph creation method provided by the second embodiment of the present invention. This embodiment is specific based on the above embodiment. In this embodiment, the field of fault reasoning technology is used as a specific application scenario, and multiple specific optional implementation methods of configuring entity nodes and connection line graph attribute data of knowledge graphs in the field of fault reasoning technology are provided. Figure 3 As shown, the method of this embodiment may include:

[0052] S211. In response to a triggering operation of a fault cause node, a configuration interface area of ​​the fault cause node is displayed in a target area in a knowledge graph editing interface.

[0053] In an embodiment of the present invention, a knowledge graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. When the fault cause node is triggered, the knowledge graph compiler can respond to the triggering operation of the fault cause node and display the configuration interface area of ​​the fault cause node in the target area of ​​the knowledge graph editing interface. The fault cause node can be further configured through the configuration interface area of ​​the fault cause node, thereby realizing the online configuration of the fault cause node.

[0054] In an optional embodiment of the present invention, the graph attribute data of the fault cause node may include a fault cause description, status and prior probability; the configuration interface area of ​​the fault cause node may include a fault cause configuration interface area, and the fault cause configuration interface area is connected to an interface of a fault cause database to provide fault cause associated configuration data.

[0055] Among them, the fault cause description may be a description of the cause of the fault. Exemplarily, in the field of industrial cooling, the system pressure drop may be caused by the low water level of the closed-circuit cooling water tank, so the fault cause description in the graph attribute data of the system pressure drop fault cause may be the low water level of the closed-circuit cooling water tank. The state of the fault cause node may be the state corresponding to the current fault cause description. Exemplarily, the state may include at least two states such as normal and abnormal. The prior probability may be an estimated value of the probability of occurrence of various states of the fault cause based on historical fault experience. It should be noted that the fault cause node includes at least one output entity node, the state of the fault cause node includes at least two states, and the sum of the prior probabilities corresponding to each state is 1. When the configuration information of the graph attribute data of the fault cause node does not comply with the above rules, the knowledge graph compiler will display a prompt message that the graph attribute data is not compliant. The fault cause configuration interface area may be an interface area for configuring the graph attribute data of the fault cause node in the knowledge graph editing interface. The fault cause database may be a database for storing and managing fault cause association information. It is understandable that the fault cause database can be pre-established based on historical fault experience. The fault cause-related configuration data may be a series of configuration parameters and data related to the fault cause in the fault diagnosis and management system.

[0056] Specifically, the configuration interface area of ​​the fault cause node may be a fault cause configuration interface area, and the fault cause configuration interface area may be connected to a fault cause database through an interface to obtain fault cause associated configuration data through the fault cause database. A user may configure the fault cause description, state, and prior probability of the fault cause node through the fault cause configuration area in conjunction with the fault cause database.

[0057] S212: In response to a triggering operation of a target fault cause description in the fault cause configuration interface area, determine a fault cause description of the fault cause node.

[0058] The target fault cause description may be the fault cause description of the selected fault cause node.

[0059] Specifically, after selecting a fault cause node, the user can click on the target fault cause description option in the fault cause configuration interface area. Furthermore, the fault cause associated configuration data can be obtained from the fault cause database through the interface, so that the required fault cause description can be selected from the acquired fault cause associated configuration data as the target fault cause description to configure the fault cause description of the fault cause node.

[0060] S213: In response to a triggering operation of a target state in the fault cause configuration interface area, determine a state of the fault cause node.

[0061] The target state in the fault cause configuration interface area may be the state of the selected fault cause node.

[0062] Specifically, after selecting the fault cause node, the user can also click the state option in the fault cause configuration interface area, select the corresponding state as the target state from the drop-down menu, and complete the configuration of the state of the fault cause node. Exemplarily, in the field of fault reasoning technology, the state of the fault cause node may include but is not limited to a normal state and an abnormal state.

[0063] S214: In response to the editing configuration operation of the prior probability in the fault cause configuration interface area, determine the prior probability of the fault cause node.

[0064] Specifically, after selecting a fault cause node, the user can also configure the prior probability of the fault cause node in the fault cause configuration interface area, such as editing the prior probability of the configuration target state, etc., thereby completing the configuration of the fault cause node graph attribute data.

[0065] S221. In response to a triggering operation of a fault symptom node, a configuration interface area of ​​the fault symptom node is displayed in a target area in a knowledge graph editing interface.

[0066] In an embodiment of the present invention, a graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. When a fault symptom node is triggered, the knowledge graph compiler can respond to the triggering operation of the fault symptom node and display the configuration interface area of ​​the fault symptom node in the target area of ​​the knowledge graph editing interface, and further configure the fault symptom node through the configuration interface area of ​​the fault symptom node, thereby realizing the online configuration of the fault symptom node.

[0067] In an optional embodiment of the present invention, the graph attribute data of the fault symptom node may include a fault symptom description and status; the configuration interface area of ​​the fault symptom node may include a fault symptom configuration interface area, and the fault symptom configuration interface area is connected to an interface of a fault symptom database to provide fault symptom associated configuration data.

[0068] Among them, the fault symptom description may be a series of signals or signs that appear before the system or device fails. Exemplarily, the fault symptom description may be the device or system temperature, response time or energy consumption, etc., and the embodiment of the present invention does not limit the specific content included in the fault symptom description. The state of the fault symptom node may be state data corresponding to the fault symptom description. Exemplarily, the state of the fault symptom node may include the device or system temperature being lower than 20 degrees Celsius, the response time being extended by 5 minutes, or the energy consumption being greatly increased, etc., and the embodiment of the present invention does not limit the specific content included in the state of the fault symptom node. It should be noted that the fault symptom node must contain an input node, and the fault symptom node contains at least one state, that is, the fault cause node in the knowledge graph contains at least one input. When the fault cause node has no input, the knowledge graph compiler will display a prompt message that the graph attribute data is not compliant. The fault symptom configuration interface area may be an interface area in the knowledge graph editing interface for configuring the graph attribute data of the fault symptom node. The fault symptom database may be a database for storing and managing fault symptom related information. It is understandable that the fault symptom database can be pre-established based on historical fault experience. The fault symptom associated configuration data can be a series of signals or signs that appear before a device or system fails. By monitoring and analyzing the fault symptom management configuration data, preventive and maintenance measures can be taken to avoid or reduce the occurrence of failures and ensure the reliability and safety of the device or system.

[0069] Specifically, the configuration interface area of ​​the fault symptom node may be a fault symptom configuration interface area, and the fault symptom configuration interface area may be connected to a fault symptom database through an interface to obtain fault symptom-related configuration data through the fault symptom database. A user may configure the fault symptom description and status of the fault symptom node through the fault symptom configuration area in conjunction with the fault symptom database.

[0070] S222: In response to a triggering operation of a target fault symptom description in the fault symptom configuration interface area, determine a fault symptom description of the fault symptom node.

[0071] The target fault symptom description may be a fault symptom description of a selected fault symptom node.

[0072] Specifically, after selecting a fault symptom node, the user can click on the target fault symptom description option in the fault symptom configuration interface area. Furthermore, the fault cause associated configuration data can be obtained from the fault symptom database through the interface, so that the required fault symptom description can be selected from the obtained fault symptom associated configuration data as the target fault symptom description to configure the fault symptom description of the fault symptom node.

[0073] S223: In response to an edit configuration operation of a target state in the fault symptom configuration interface area, determine a state of the fault symptom node.

[0074] The target state in the fault symptom configuration interface area may be the state of the selected fault symptom node.

[0075] Specifically, after selecting a fault symptom node, the user can also configure the state of the fault symptom node in the fault symptom configuration interface area as the target state in the fault symptom configuration interface area, such as editing and configuring the state of the fault symptom description, thereby completing the configuration of the fault symptom node graph attribute data. For example, assuming that the fault symptom description is system temperature, the state of the fault symptom description can be that the temperature is lower than 10 degrees Celsius.

[0076] S231. In response to the triggering operation of the logic gate node, the configuration interface area of ​​the logic gate node is displayed in the target area in the knowledge graph editing interface.

[0077] In an embodiment of the present invention, a graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. When a logic gate node is triggered, the knowledge graph compiler can respond to the triggering operation of the logic gate node and display the configuration interface area of ​​the logic gate node in the target area of ​​the knowledge graph editing interface. The logic gate node can be further configured through the configuration interface area of ​​the logic gate node, thereby realizing the online configuration of the logic gate node.

[0078] In an optional embodiment of the present invention, the graph attribute data of the logic gate node may include a logic condition; and the configuration interface area of ​​the logic gate node may include a logic gate configuration interface area.

[0079] Among them, the logical condition may be a rule or condition that defines the behavior of a logic gate node. Exemplarily, the logical condition may include AND, NAND, or XOR operations, etc. The embodiment of the present invention does not limit the specific operations included in the logical condition. It should be noted that since the graph attribute data of the logic gate node includes the logical condition, the logic gate node includes at least one logical condition, and the logic gate node includes at least two input entity nodes and one output entity node. When the graph attribute data configuration of the logic gate node does not comply with the above rules, the knowledge graph compiler will display a prompt message that the graph attribute data is not compliant.

[0080] Specifically, in the knowledge graph editing interface, the configuration interface area of ​​the logic gate node can be a logic gate configuration interface area. After the user selects the logic gate node, the user can configure the logical conditions of the logic gate node through the logic gate configuration interface area.

[0081] S232: In response to the edit configuration operation of the target logic condition in the logic gate configuration interface area, determine the logic condition of the logic gate node.

[0082] The target logic condition may be a logic condition of a selected logic gate node.

[0083] Specifically, after the user selects a logic gate node in the knowledge graph compiler, he can click the target logic condition option in the logic gate configuration interface area to configure the logic condition of the logic gate node. For example, assuming that entity node A and entity node B are the input of logic gate node 1, and entity node C is the output of logic gate node 1, the target logic condition can be configured as A+B as the logic condition of the logic gate node. By configuring the logic conditions of the logic gate node, complex logical analysis and accurate diagnosis of faults can be achieved.

[0084] S241. In response to the triggering operation of the solid line, the configuration interface area of ​​the solid line is displayed in the target area in the knowledge graph editing interface.

[0085] In an embodiment of the present invention, a graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. When a solid line is triggered, the knowledge graph compiler can respond to the triggering operation of the solid line, display the configuration interface area of ​​the solid line in the target area of ​​the knowledge graph editing interface, and further configure the solid line through the configuration interface area of ​​the solid line, thereby realizing the online configuration of the solid line.

[0086] In an optional embodiment of the present invention, the graph attribute data of the solid line may include a weight and state probability matrix; the configuration interface area of ​​the solid line may include a solid line configuration interface area.

[0087] The weight of the solid line can be the amount of data in the knowledge graph that measures the strength of the relationship between entities. The larger the weight, the stronger the relationship between the two entities. The state probability matrix of the solid line can be the correlation between the states of the nodes at both ends of the solid line, that is, the probability of occurrence. The solid line configuration interface area can be the interface area for configuring the graph attribute data of the solid line in the knowledge graph editing interface.

[0088] Specifically, in the knowledge graph editing interface, the solid line configuration interface area may be a solid line configuration interface area, and the user may configure the graph attribute data of the solid line through the solid line configuration interface area.

[0089] S242: In response to an edit configuration operation of a target weight in the solid line configuration interface area, determine a weight of the solid line.

[0090] The target weight in the solid line configuration interface area may be the weight of the selected solid line.

[0091] Specifically, after selecting a solid line, the user can click the edit configuration option of the target weight in the solid line configuration interface area, and enter the weight value corresponding to the solid line as the target weight in the solid line configuration interface area to configure the weight of the solid line.

[0092] S243. In response to the edit configuration operation of the target state probability matrix in the solid line configuration interface area, determine the state probability matrix of the solid line.

[0093] The target state probability matrix in the solid line configuration interface area may be the state probability matrix of the selected solid line.

[0094] Specifically, after selecting a solid line, the user can also configure the state probability matrix of the solid line as the target state probability matrix in the solid line configuration interface area by clicking the edit configuration option of the target state probability matrix in the solid line configuration interface area to configure the state probability matrix of the solid line.

[0095] S251. In response to the triggering operation of the dotted line, the configuration interface area of ​​the dotted line is displayed in the target area in the knowledge graph editing interface.

[0096] In an embodiment of the present invention, a graph element library can be configured in the knowledge graph editing interface of the knowledge graph compiler. When a dotted line is triggered, the knowledge graph compiler can respond to the triggering operation of the dotted line and display the configuration interface area of ​​the dotted line in the target area of ​​the knowledge graph editing interface. The dotted line can be further configured through the configuration interface area of ​​the dotted line, thereby realizing the online configuration of the dotted line.

[0097] In an optional embodiment of the present invention, the dotted line graph attribute data may include conditions, weights and state probability matrices; the dotted line configuration interface area may include a dotted line configuration interface area.

[0098] Among them, the condition of the dotted line can represent that the connection relationship in the knowledge graph is established only under specific conditions. That is, the dotted line has the same effect as the solid line when the condition is met, and the connection relationship is not established when the condition is not met. Exemplarily, the condition of the dotted line can be that when the input entity node of a certain entity node is true, the connection relationship between the input entity node and the entity node is established. That is, when the condition is met, the meaning of the graph attribute data weight and state probability matrix of the dotted line is the same as the meaning of the graph attribute data weight and state probability matrix of the solid line. In the knowledge graph, by setting the conditions of the dotted line, the complex relationship between nodes can be expressed more flexibly and accurately. The dotted line configuration interface area can be the interface area for configuring the graph attribute data of the dotted line in the knowledge graph editing interface. It should be noted that the connecting lines are all with arrows, the end of the connecting line without an arrow is used as the output of the previous node, and the end of the connecting line with an arrow is used as the input of the next node.

[0099] Specifically, in the knowledge graph editing interface, the dotted line configuration interface area may be a dotted line configuration interface area, and the user may configure the dotted line graph attribute data through the dotted line configuration interface area.

[0100] S252: In response to an edit configuration operation of a target condition in the dotted line configuration interface area, determine a condition of the dotted line.

[0101] The target condition may be the condition of the selected dotted line.

[0102] Specifically, after selecting a dotted line, the user can click the edit configuration option of the target condition in the dotted line configuration interface area, and input the condition for the connection relationship between the entity nodes as the condition of the dotted line to configure the condition of the dotted line.

[0103] S253: In response to the edit configuration operation of the target weight in the dotted line configuration interface area, determine the weight of the dotted line.

[0104] The target weight in the dashed line configuration interface area may be the weight of the selected dashed line.

[0105] Specifically, after selecting the dotted line, the user can also enter the weight value corresponding to the dotted line as the target weight in the dotted line configuration interface area when clicking the edit configuration option of the target weight in the dotted line configuration interface area to configure the target weight in the dotted line configuration interface area.

[0106] S254: In response to the edit configuration operation of the target state probability matrix in the dotted line configuration interface area, determine the state probability matrix of the dotted line.

[0107] The target state probability matrix in the dashed line configuration interface area may be the state probability matrix of the selected dashed line.

[0108] Specifically, after selecting the dotted line, the user can also click the edit configuration option of the target state probability matrix in the dotted line configuration interface area, and enter the state probability matrix of the dotted line as the target state probability matrix in the dotted line configuration interface area to configure the state probability matrix of the dotted line.

[0109] It should be noted that the weights of solid and dashed lines must be greater than 0 and less than or equal to 1; the sum of each column in the state probability matrix of solid and dashed lines is 1; a condition must be set for each dashed connecting line. When the graph attribute data configuration of the connecting line does not comply with the above rules, the knowledge graph compiler will display a prompt message that the graph attribute data is not compliant.

[0110] S260. Generate a knowledge graph of the target knowledge domain according to each knowledge graph element in the knowledge graph editing interface and graph attribute data of each knowledge graph element.

[0111] In an embodiment of the present invention, in the field of fault reasoning, after the user determines the entity nodes and connection lines of the knowledge graph and completes the configuration of the graph attribute data of the entity nodes and connection lines, the knowledge graph compiler can generate a knowledge graph in the field of fault reasoning according to the entity nodes and connection lines determined by the user and the graph attribute data of each entity node and connection line. The construction of the knowledge graph in the field of fault reasoning can realize the visualization of a large amount of fault knowledge data relationships, thereby improving the accuracy of fault reasoning.

[0112] Figure 4 Schematic diagram of a knowledge graph in the field of fault reasoning provided by the second embodiment of the present invention. Figure 4 As shown, according to the above-mentioned knowledge graph construction method, a knowledge graph in the field of fault reasoning including multiple fault cause nodes, fault symptom nodes and logic gate nodes can be obtained, and the description of the entity nodes in the knowledge graph editing interface is concise, which can improve the readability of the knowledge graph. Among them, the fault cause node can include B69, etc., the fault symptom node can include X151-X153, X118-X121 and X251-X257, etc., and the logic gate node can include G1-G4, etc.

[0113] Optionally, after generating the knowledge graph of the target knowledge domain, the knowledge graph compiler can also automatically convert the created knowledge graph into a structured data format that can be directly called by the algorithm through a program.

[0114] Figure 5 is a schematic diagram of a knowledge graph structured data format conversion provided by the second embodiment of the present invention. In a specific example, Figure 5 As shown in the figure, the knowledge graph compiler can convert the nodes of the created knowledge graph into nodes, where nodes can have attributes such as id, name, type, states, probabilities, parents and gate; the knowledge graph compiler can also convert the connections of the knowledge graph into flows, where flows have attributes such as id, type, sourceRef, targetRef and expressionRef; in addition, all state probability matrices in the knowledge graph are stored in matrix, and all conditional expressions are stored in expression.

[0115] The embodiments of the present invention respond to the triggering or editing configuration operations of fault cause nodes, fault symptom nodes, logic gate nodes, solid lines or dotted lines, and display the input configuration interface area of ​​entity nodes or connecting lines in the target area in the knowledge graph editing interface. Furthermore, element configuration data of the configuration interface area based on the entity nodes or connecting lines is obtained, and the graph attribute data of the entity nodes or connecting lines is determined according to the element configuration data, so as to generate a knowledge graph of the target knowledge field according to each entity node or connecting line in the knowledge graph editing interface and the graph attribute data of each entity node or connecting line, thereby solving the problem of insufficient dynamic update and real-time interaction capabilities of existing knowledge graphs, and improving the flexibility and interactivity of the knowledge graph creation process, thereby enhancing the user interaction experience.

[0116] Embodiment 3

[0117] Figure 6 is a schematic diagram of a knowledge graph creation device provided in Embodiment 3 of the present invention, such as Figure 6 As shown, the device includes: a configuration interface display module 310, a graph attribute data acquisition module 320 and a knowledge graph creation module 330, wherein:

[0118] A configuration interface display module 310 is used to display the configuration interface area of ​​the target knowledge graph element in the target area of ​​the knowledge graph editing interface in response to the triggering operation of the target knowledge graph element; wherein the target knowledge graph element includes an entity node or a connection line;

[0119] A graph attribute data acquisition module 320, used to acquire element configuration data input based on the configuration interface area of ​​the target knowledge graph element, and determine the graph attribute data of the target knowledge graph element according to the element configuration data;

[0120] The knowledge graph creation module 330 is used to generate a knowledge graph of the target knowledge domain based on the knowledge graph elements in the knowledge graph editing interface and the graph attribute data of each knowledge graph element.

[0121] The embodiments of the present invention respond to the triggering operation of the entity node or the connection line to display the configuration interface area of ​​the entity node or the connection line in the target area in the knowledge graph editing interface, and further obtain the element configuration data input based on the configuration interface area of ​​the entity node or the connection line, and determine the graph attribute data of the entity node or the connection line according to the element configuration data, so as to generate a knowledge graph of the target knowledge field according to each entity node or connection line in the knowledge graph editing interface and the graph attribute data of each entity node or connection line, thereby solving the problem of insufficient dynamic update and real-time interaction capabilities of the existing knowledge graph, and being able to improve the flexibility and interactivity of the knowledge graph creation process, thereby enhancing the user interaction experience.

[0122] In an optional embodiment of the present invention, the target knowledge domain includes the field of fault reasoning technology; the entity nodes include fault cause nodes, fault symptom nodes and logic gate nodes; and the connection lines include solid lines and dotted lines.

[0123] In an optional embodiment of the present invention, the graph attribute data of the fault cause node includes a fault cause description, a state, and a priori probability; the configuration interface area of ​​the fault cause node includes a fault cause configuration interface area, and the interface of the fault cause configuration interface area connected to the fault cause database provides fault cause associated configuration data. The graph attribute data acquisition module 320 is also used to: determine the fault cause description of the fault cause node in response to a trigger operation of a target fault cause description in the fault cause configuration interface area; determine the state of the fault cause node in response to a trigger operation of a target state in the fault cause configuration interface area; and determine the prior probability of the fault cause node in response to an edit configuration operation of a priori probability in the fault cause configuration interface area.

[0124] In an optional embodiment of the present invention, the graph attribute data of the fault symptom node includes a fault symptom description and a state; the configuration interface area of ​​the fault symptom node includes a fault symptom configuration interface area, and the interface of the fault symptom configuration interface area connected to the fault symptom database provides fault symptom-related configuration data. The graph attribute data acquisition module 320 is also used to: determine the fault symptom description of the fault symptom node in response to a trigger operation of a target fault symptom description in the fault symptom configuration interface area; determine the state of the fault symptom node in response to an edit configuration operation of a target state in the fault symptom configuration interface area.

[0125] In an optional embodiment of the present invention, the graph attribute data of the logic gate node includes a logic condition; the configuration interface area of ​​the logic gate node includes a logic gate configuration interface area. The graph attribute data acquisition module 320 is further used to: determine the logic condition of the logic gate node in response to an edit configuration operation of a target logic condition in the logic gate configuration interface area.

[0126] In an optional embodiment of the present invention, the graph attribute data of the solid line includes weights and state probability matrices; the configuration interface area of ​​the solid line includes a solid line configuration interface area; the graph attribute data of the dotted line includes conditions, weights and state probability matrices; the configuration interface area of ​​the dotted line includes a dotted line configuration interface area. The graph attribute data acquisition module 320 is also used to: determine the weight of the solid line in response to an edit configuration operation of a target weight in the solid line configuration interface area; determine the state probability matrix of the solid line in response to an edit configuration operation of a target state probability matrix in the solid line configuration interface area; determine the condition of the dotted line in response to an edit configuration operation of a target condition in the dotted line configuration interface area; determine the weight of the dotted line in response to an edit configuration operation of a target weight in the dotted line configuration interface area; determine the state probability matrix of the dotted line in response to an edit configuration operation of a target state probability matrix in the dotted line configuration interface area.

[0127] In an optional embodiment of the present invention, the above-mentioned device may also include a verification module, which is used to: perform compliance verification on the graph attribute data of the target knowledge graph element; when it is determined that the graph attribute data of the target knowledge graph element has not passed the compliance verification, display a prompt message that the graph attribute data is non-compliant to indicate the need to re-acquire the element configuration data input in the configuration interface area based on the target knowledge graph element.

[0128] The above-mentioned knowledge graph creation device can execute the knowledge graph creation method provided by any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the knowledge graph creation method provided by any embodiment of the present invention.

[0129] Since the knowledge graph creation device introduced above is a device that can execute the knowledge graph creation method in the embodiment of the present invention, based on the knowledge graph creation method introduced in the embodiment of the present invention, the technical personnel in this field can understand the specific implementation method of the knowledge graph creation device of this embodiment and its various variations, so how the knowledge graph creation device implements the knowledge graph creation method in the embodiment of the present invention will not be introduced in detail here. As long as the technical personnel in this field implement the device used by the knowledge graph creation method in the embodiment of the present invention, it belongs to the scope of protection of this application.

[0130] Embodiment 4

[0131] Figure 7 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0132] like Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0133] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0134] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the knowledge graph creation method.

[0135] In some embodiments, the knowledge graph creation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the knowledge graph creation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the knowledge graph creation method in any other appropriate manner (e.g., by means of firmware).

[0136] Optionally, the knowledge graph creation method may include: in response to a trigger operation of a target knowledge graph element, displaying a configuration interface area of ​​the target knowledge graph element in a target area in a knowledge graph editing interface; wherein the target knowledge graph element includes entity nodes or connecting lines; obtaining element configuration data input based on the configuration interface area of ​​the target knowledge graph element, and determining graph attribute data of the target knowledge graph element based on the element configuration data; and generating a knowledge graph of the target knowledge domain based on each knowledge graph element in the knowledge graph editing interface and the graph attribute data of each knowledge graph element.

[0137] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0144] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A knowledge graph creation method, characterized in that: Applied to knowledge graph compiler, including: In response to a triggering operation of a target knowledge graph element, a configuration interface area of ​​the target knowledge graph element is displayed in a target area in a knowledge graph editing interface; wherein the target knowledge graph element includes an entity node or a connection line; Obtaining element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element, and determining graph attribute data of the target knowledge graph element according to the element configuration data; Generate a knowledge graph of the target knowledge domain based on each knowledge graph element in the knowledge graph editing interface and the graph attribute data of each knowledge graph element.

2. The method according to claim 1, characterized in that The target knowledge domain includes the field of fault reasoning technology; the entity nodes include fault cause nodes, fault symptom nodes and logic gate nodes; and the connection lines include solid lines and dotted lines.

3. The method according to claim 2, characterized in that The graph attribute data of the fault cause node includes a fault cause description, a state and a priori probability; the configuration interface area of ​​the fault cause node includes a fault cause configuration interface area, and the fault cause configuration interface area is connected to an interface of a fault cause database to provide fault cause associated configuration data; The obtaining of element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element includes: In response to a triggering operation of a target fault cause description in the fault cause configuration interface area, determining a fault cause description of the fault cause node; In response to a trigger operation of a target state in the fault cause configuration interface area, determining a state of the fault cause node; In response to the editing configuration operation of the prior probability in the fault cause configuration interface area, the prior probability of the fault cause node is determined.

4. The method according to claim 2, characterized in that: The graph attribute data of the fault symptom node includes a fault symptom description and a state; the configuration interface area of ​​the fault symptom node includes a fault symptom configuration interface area, and the fault symptom configuration interface area is connected to an interface of a fault symptom database to provide fault symptom associated configuration data; The obtaining of element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element includes: In response to a triggering operation of a target fault symptom description in the fault symptom configuration interface area, determining a fault symptom description of the fault symptom node; In response to an edit configuration operation of a target state in the fault symptom configuration interface area, a state of the fault symptom node is determined.

5. The method according to claim 2, characterized in that: The graph attribute data of the logic gate node includes a logic condition; the configuration interface area of ​​the logic gate node includes a logic gate configuration interface area; The obtaining of element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element includes: In response to an edit configuration operation of a target logic condition in the logic gate configuration interface area, a logic condition of the logic gate node is determined.

6. The method according to claim 2, characterized in that The graph attribute data of the solid line includes weights and state probability matrices; the configuration interface area of ​​the solid line includes a solid line configuration interface area; the graph attribute data of the dotted line includes conditions, weights and state probability matrices; the configuration interface area of ​​the dotted line includes a dotted line configuration interface area; The obtaining of element configuration data inputted based on the configuration interface area of ​​the target knowledge graph element includes: In response to an edit configuration operation of a target weight in the solid line configuration interface area, determining a weight of the solid line; In response to an edit configuration operation of a target state probability matrix in the solid line configuration interface area, determining a state probability matrix of the solid line; In response to an edit configuration operation of a target condition in the dashed line configuration interface area, determining a condition of the dashed line; In response to an edit configuration operation of a target weight in the dashed line configuration interface area, determining a weight of the dashed line; In response to an edit configuration operation of a target state probability matrix in the dashed line configuration interface area, a state probability matrix of the dashed line is determined.

7. The method according to any one of claims 1 to 6, characterized in that: After determining the graph attribute data of the target knowledge graph element according to the element configuration data, the method further includes: Performing compliance check on the graph attribute data of the target knowledge graph element; When it is determined that the graph attribute data of the target knowledge graph element has not passed the compliance check, a prompt message indicating that the graph attribute data is non-compliant is displayed to instruct the re-acquisition of the element configuration data input in the configuration interface area based on the target knowledge graph element.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the knowledge graph creation method described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the knowledge graph creation method described in any one of claims 1-7 when executed.

10. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the knowledge graph creation method described in any one of claims 1-7 is implemented.

Images