Event reasoning method and system based on visual programming

Abstract

The application discloses an event reasoning method and system based on visual arrangement, which is based on a generalized data template, utilizes a graphic element to generate a generalized event reasoning logic flow, and is based on a preset synonym dictionary to standardize the attributes of signals of each measuring point of a main station; when the matching degree is greater than a set threshold, instance data obtained by combining the standardized attributes with typical generalized data is utilized to instantiate the generalized event reasoning logic flow, so that a specific event reasoning logic flow is obtained; the specific event reasoning logic flow is compiled into a rule file; based on a reasoning model, the validity of the rule file is verified according to historical data; when it is determined that the rule file is valid, event reasoning is performed based on the reasoning model according to system real-time data, a preset operation time and automatic operation conditions; and the event diagnosis and fault identification capability of the power system protection main station is improved by taking into account the simplicity of graphical operation, the flexibility of low-code expansion and the intelligence of the reasoning mechanism.

Description

Technical Field

[0001] This invention belongs to the field of power system automation and relay protection technology. Specifically, it relates to a low-code event reasoning method and system based on visual graphical arrangement applied to a relay protection master station system. Background Technology

[0002] With the rapid development of power systems, the scale of substation equipment is constantly expanding, and the amount of data collected is growing rapidly. The daily alarm volume at a single substation can reach thousands, significantly increasing the pressure on the main station monitoring panel. During power system faults, secondary systems generate a large number of alarm signals. This massive volume of signals in a short period can easily lead to on-duty personnel missing critical alarms, and delays in manual decision-making may amplify the impact of the fault. Currently, the main station lacks logical combination analysis of alarms and measurements, and cannot promptly transform problems or accumulated knowledge from maintenance into auxiliary decision-making functions for the main station system. It also lacks effective reasoning methods, which may lead to the failure to detect anomalies in a timely manner and cause power accidents.

[0003] Currently, the main problems faced by the main station system in intelligent operation and maintenance include: difficulty in quickly locating core fault signals from massive amounts of data; the current intelligent alarm function relies on a rule base that is solidified by expert experience, which has poor flexibility and cannot adapt to scenarios outside the rules; and the lack of event-based reasoning based on spatiotemporal correlation makes it difficult to support accurate fault diagnosis. Existing master station systems have significant limitations in advanced data processing applications, including: a hard-coded development model and poor flexibility: Existing diagnostic logic is mostly implemented by software developers through coding (such as C++, Java, and SQL). This model has long development cycles and high maintenance costs. When the power grid structure changes, protection principles are updated, or new diagnostic requirements are added, programmers must modify the source code and redeploy the system, making it difficult to quickly respond to business changes and adapt to the agility requirements of intelligent operation and maintenance. High professional barriers and difficulty in knowledge accumulation: Field operation and maintenance personnel and experts cannot effectively and continuously transform their experience into system functions, i.e., digitize and software-ize valuable experience, resulting in the ineffective accumulation and reuse of knowledge. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an event reasoning method and system based on visual orchestration for power system protection master stations. This method balances the ease of graphical operation, the flexibility of low-code expansion, and the intelligence of the reasoning mechanism, thereby improving the event diagnosis and fault identification capabilities of power system protection master stations.

[0005] The present invention adopts the following technical solution.

[0006] This invention proposes an event reasoning method based on visual orchestration for power system protection master stations, comprising: Step 1: Based on the generalized data template, generate a generalized event reasoning logic flow using primitives; Step 2: Obtain typical generalized data from the database and assign it to each primitive in the generalized event reasoning logic flow; based on a preset synonym dictionary, normalize the attributes of the signals at each measurement point of the main station; based on a preset keyword dictionary, determine the number of high-priority keywords, low-priority keywords, and keyword order matching numbers that match the normalized attributes, and calculate the matching degree; when the matching degree is greater than a set threshold, use the instance data obtained by combining the normalized attributes and typical generalized data to instantiate the generalized event reasoning logic flow, and obtain the specific event reasoning logic flow. Step 3: Compile the specific event reasoning logic flow into a rule file; based on the reasoning model and historical data, verify the validity of the rule file; when the rule file is determined to be valid, execute event reasoning based on the reasoning model, real-time system data, preset running time, and automatic commissioning conditions.

[0007] The typical generalized data assigned to graphic elements is the generalized data stored in the keyword dictionary based on relay protection business data.

[0008] The typical generalized data assigned to graphic elements is the generalized data stored in the keyword dictionary based on relay protection business data.

[0009] The attributes of the measurement point signal include: substation, voltage level, interval, equipment, and signal.

[0010] The priority of keywords is determined based on the priority of various protections in different scenarios, specifically as follows: 1) Scenario 1: Line Protection The main protection has the highest priority and includes: longitudinal differential protection, high frequency protection, and fiber optic current differential protection; the backup protection has the second highest priority and includes: distance protection and zero-sequence current protection; the abnormal alarm has the lowest priority and includes: overload alarm and TV / TA disconnection detection. 2) Scenario 2: Transformer Protection Differential protection and heavy gas protection have the highest priority; backup protection has the second priority, including: composite voltage blocking overcurrent protection and zero-sequence current and voltage protection; abnormal operation protection has the third priority, including: overload protection and light gas protection. 3) Scenario 3: Busbar Protection Busbar differential protection and circuit breaker failure protection have the highest priority; the remaining protections have the second highest priority. Keywords covered by the highest and second-highest priority protection are designated as high-priority keywords, while keywords covered by the third-highest priority protection are designated as low-priority keywords.

[0011] The matching degree is calculated as the weighted sum of the ratios of the number of high-priority keywords to the number of high-priority keywords in typical generalized data, the ratio of the number of low-priority keywords to the number of low-priority keywords in typical generalized data, and the ratio of the number of keyword order matches to the number of keywords in typical generalized data, as shown in the following formula:

[0012] In the formula, For matching degree; , , All are weighting coefficients, and + + =1; , , These are the number of high-priority keywords, the number of low-priority keywords, and the number of keywords matched in sequence. , , These represent the number of high-priority keywords, low-priority keywords, and the total number of keywords in typical generalized data, respectively. = + .

[0013] If typical generalized data exists that matches multiple normalized attributes and all of them have a matching degree greater than a set threshold, then the normalized attribute with the highest matching degree is combined with the typical generalized data to obtain instance data.

[0014] The signals from each measuring point at the main station include the analog quantities and status quantities of the device. Based on keywords that match the standardized attributes, the interval is located in the plant. After traversing the equipment under the interval to determine the characteristic quantities, the device is located. The analog quantities and status quantities of the device are segmented and the attributes of the measuring point signals are optimized.

[0015] This invention also proposes an event reasoning system based on visual orchestration for power system protection master stations, comprising: The generalized event flow generation module is used to generate generalized event reasoning logic flow based on generalized data templates and using primitives. The specific event flow generation module is used to retrieve typical generalized data from the database and assign it to each element in the generalized event reasoning logic flow; based on a preset synonym dictionary, it performs normalization processing on the attributes of the signals of each measurement point of the main station; based on a preset keyword dictionary, it determines the number of high-priority keywords, low-priority keywords, and keyword order matching that match the normalized attributes, in order to calculate the matching degree; when the matching degree is greater than a set threshold, it uses the instance data obtained by combining the normalized attributes and typical generalized data to instantiate the generalized event reasoning logic flow, thus obtaining the specific event reasoning logic flow. The event reasoning module is used to compile the specific event reasoning logic flow into a rule file; based on the reasoning model and historical data, it verifies the validity of the rule file; when the rule file is determined to be valid, it executes event reasoning based on the reasoning model, real-time system data, preset running time, and automatic commissioning conditions.

[0016] The present invention is also a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method.

[0017] The present invention is also a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method.

[0018] The beneficial effects of this invention are as follows, compared with the prior art, at least including: users can quickly build logical processes in a visual way without the need for in-depth programming experience, thus lowering the user threshold; a large number of alarms are combined into events, greatly reducing the number of alarms monitored; the reasoning mechanism combines typical feature rules with real-time data to accurately generate feature events, reducing false alarms and missed alarms; feature events record the rule triggering conditions and data sources, supporting backtracking of the diagnostic process and making the results interpretable. Attached Figure Description

[0019] Figure 1 This is a flowchart of the event reasoning method based on visual orchestration proposed in this invention; Figure 2 This is the generalized event reasoning logic flow generated using primitives in this embodiment of the invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0021] This invention proposes an event reasoning method based on visual orchestration for power system protection master stations, such as... Figure 1 As shown, the method includes: Step 1: Based on the generalized data template, generate a generalized event reasoning logic flow using primitives.

[0022] Specifically, the system provides users with generalized data templates, allowing users to add, delete, and modify graphical elements in a visual graphical interface. The graphical elements in the generalized data templates that are related to the event reasoning logic flow include, but are not limited to: input graphical elements, output graphical elements, logical relationship graphical elements, and text graphical elements. Among them, input graphical elements are classified according to voltage level and equipment type, and text graphical elements are used to edit keywords and add necessary explanations to enhance readability. In the embodiments, such as Figure 2 As shown, users can drag and drop graphical elements in the graphical interface to connect them. Responding to user drag-and-drop operations, various graphical elements are added and connected, forming a closed, generalized event reasoning logic flow. This includes: the logical relationship between the input graphical element "Total Station Accident = 1" and the input graphical element "XX Interval Accident Signal = 1" is OR "|", resulting in the first signal; the logical relationship between the input graphical element "XX Line Protection Output = 1" and the input graphical element "XX Line Protection C Phase Trip Output = 1" is OR "|". Since "XX Line Protection Output" involves signals from multiple protection systems, the text graphical element "First Protection" is added. The keywords "Second Set of Protection" and "Second Set of Protection" are used, and priorities are set according to the keywords. The logical relationship between the text elements "First Set of Protection" and "Second Set of Protection" is ANDed with "&", resulting in the second signal. The logical relationship between the input elements "XX Line Protection Reclosing Action=1" and "XX Line Protection Reclosing Action=1" is ORed with "|", resulting in the third signal. The logical relationship between the input elements "XX Switch C Phase Position=0" and "XX Switch C Phase Position=1" is implied with "→", resulting in the fourth signal. The four signals are ANDed with "&" to obtain the output element "500kV XX Line XX Circuit Breaker C Tripped C Closed, Reclosing Successful".

[0023] This invention enables the intuitive construction of logical processes through visual orchestration; the established generalized data templates support users to write C / C++ functions, support access to real-time library interfaces, and retain the flexibility of extending programming through low-code methods.

[0024] Step 2: Obtain typical generalized data from the database and assign it to each primitive in the generalized event reasoning logic flow; based on a preset thesaurus, normalize the attributes of the signals at each measurement point of the main station; based on a preset keyword dictionary, determine the number of high-priority keywords, low-priority keywords, and keyword order matching that match the normalized attributes, and calculate the matching degree; when the matching degree is greater than a set threshold, use the instance data obtained by combining the normalized attributes and typical generalized data to instantiate the generalized event reasoning logic flow, and obtain the specific event reasoning logic flow.

[0025] Specifically, step 2 includes: Step 2.1: Obtain typical generalized data from the database and assign it to each graphic element; In this embodiment, the typical generalized data assigned to the graphic elements is generalized data stored in a keyword dictionary based on relay protection business data, and is categorized and organized according to equipment, data source, data type, etc. The keyword dictionary has been stored in the generalized data template.

[0026] Step 2.2: Obtain the attributes of the signals at each measuring point of the main station, including: substation, voltage level, interval, equipment, and signal; and standardize the attributes of the signals at each measuring point based on a preset thesaurus. In the embodiment, a thesaurus is established, such as "trip" = "outlet" = "action"; to look up the thesaurus, the data expression needs to be converted into synonyms first, including Roman numeral conversion (e.g., Ⅲ=III) and phrase conversion (e.g., first set = A set | a set | I set | the I set | auxiliary A | protection 1 | protection one | protection I | one protection | I protection | I protection | protection A | A protection | main one | main 1). In the embodiment, the attributes of the measuring point signals are hierarchically divided according to "substation / voltage level / interval / equipment / signal", such as "Shuicheng Station / 500kV / Shuisu II Line / First PCS931 Protection / A Phase Adjustment Outlet".

[0027] Step 2.3: Based on the preset keyword dictionary, determine the number of high-priority keywords, low-priority keywords, and keyword order matching keywords that match the normalized attributes; The priority of keywords is determined based on the priority of various protections in different scenarios, specifically as follows: 1) Scenario 1: Line Protection The main protection has the highest priority and includes: longitudinal differential protection, high frequency protection, and fiber optic current differential protection; the backup protection has the second highest priority and includes: distance protection and zero-sequence current protection; the abnormal alarm has the lowest priority and includes: overload alarm and TV / TA disconnection detection. 2) Scenario 2: Transformer Protection Differential protection and heavy gas protection have the highest priority; backup protection has the second priority, including: composite voltage blocking overcurrent protection and zero-sequence current and voltage protection; abnormal operation protection has the third priority, including: overload protection and light gas protection. 3) Scenario 3: Busbar Protection Busbar differential protection and circuit breaker failure protection have the highest priority; the remaining protections have the second highest priority. Keywords covered by the highest and second-highest priority protection are designated as high-priority keywords, while keywords covered by the third-highest priority protection are designated as low-priority keywords.

[0028] Furthermore, the signals from each measuring point at the main station include the analog quantities and status quantities of the devices. Based on keywords that match the standardized attributes, the intervals are located in the plant. After traversing the equipment under the intervals to determine the characteristic quantities, the devices are located. The analog quantities and status quantities of the devices are segmented to optimize the attributes of the measuring point signals.

[0029] Step 2.4: The matching degree is calculated as the weighted sum of the ratios of the number of high-priority keywords to the number of high-priority keywords in the typical generalized data, the ratio of the number of low-priority keywords to the number of low-priority keywords in the typical generalized data, and the ratio of the number of keyword order matches to the number of keywords in the typical generalized data, as shown in the following formula:

[0030] In the formula, For matching degree; , , All are weighting coefficients, and + + =1; , , These are the number of high-priority keywords, the number of low-priority keywords, and the number of keywords matched in sequence. , , These represent the number of high-priority keywords, low-priority keywords, and the total number of keywords in typical generalized data, respectively. = + ; In the embodiments, The value is 0.8. The value is 0.15. The value is 0.05.

[0031] Step 2.5: When the matching degree is greater than the set threshold, the normalized attributes and typical generalized data are combined to obtain instance data; based on the generalized event reasoning logic flow, the specific event reasoning logic flow is obtained according to the instance data. In the embodiment, the threshold value is set to 0.7; in actual application, there are typical generalized data that match multiple normalized attributes and the matching degree is greater than the set threshold. Then, the normalized attribute with the highest matching degree is combined with the typical generalized data to obtain instance data. In the embodiment, the normalized attributes include "Shuicheng Substation" + "500kV" + "Shuisu II Line", and the typical generalized data includes "First Set" + "Phase A" + "Protection Trip" + "Output". The instance data obtained by combining the normalized attributes and the typical generalized data is "Shuicheng Substation / 500kV / Shuisu II Line / First Set PCS931 Protection / Phase A Trip Output". Based on the generalized event reasoning logic flow, according to the instance data, the specific event reasoning logic flow is "Shuicheng Substation.500kV.Shuisu II Line.Protection Trip Output".

[0032] This invention not only uses typical generalized data to filter normalized attributes, but also uses typical generalized data and normalized attributes to form instance data. This enables the inference mechanism proposed in this invention to combine typical feature rules with real-time data, thereby accurately generating feature events and reducing false positives and false negatives.

[0033] The method proposed in this invention does not require modification of the underlying code. It only requires defining or adjusting the generalized data template, which enables the system to adapt to new business scenarios or event types. Moreover, when necessary, it can extend complex data processing logic in a low-code manner, perform reasoning based on rule files and real-time data, generate feature events, and thus provide accurate and interpretable anomaly diagnosis and fault identification results.

[0034] Step 3: Compile the specific event reasoning logic flow into a rule file; based on the reasoning model and historical data, verify the validity of the rule file; when the rule file is determined to be valid, execute event reasoning based on the reasoning model, real-time system data, preset running time, and automatic commissioning conditions.

[0035] Specifically, the multiple specific event inference logic flows obtained by repeatedly executing steps 1 and 2 are compiled into rule files; historical data is selected as the data source, and the rule files are added to the task queue in the inference model for inference calculation. The generated event inference results are used to verify the validity of the rule files; real-time data is selected as the data source, and valid rule files are added to the task queue in the inference model for inference calculation. Trial run time and automatic commissioning conditions (cumulative number of alarm triggers) are set, event inference is executed, and the results are displayed in the alarm window. By combining a large number of alarms into events, the number of alarms monitored is greatly reduced; feature events record the rule triggering conditions and data sources, supporting backtracking of the diagnostic process and making the results interpretable.

[0036] This invention also proposes an event reasoning system based on visual orchestration for power system protection master stations, comprising: The generalized event flow generation module is used to generate generalized event reasoning logic flow based on generalized data templates and using primitives. The specific event flow generation module is used to retrieve typical generalized data from the database and assign it to each element in the generalized event reasoning logic flow; based on a preset synonym dictionary, it performs normalization processing on the attributes of the signals of each measurement point of the main station; based on a preset keyword dictionary, it determines the number of high-priority keywords, low-priority keywords, and keyword order matching that match the normalized attributes, in order to calculate the matching degree; when the matching degree is greater than a set threshold, it uses the instance data obtained by combining the normalized attributes and typical generalized data to instantiate the generalized event reasoning logic flow, thus obtaining the specific event reasoning logic flow. The event reasoning module is used to compile the specific event reasoning logic flow into a rule file; based on the reasoning model and historical data, it verifies the validity of the rule file; when the rule file is determined to be valid, it executes event reasoning based on the reasoning model, real-time system data, preset running time, and automatic commissioning conditions.

[0037] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0038] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0039] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0040] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. An event reasoning method based on visual orchestration for power system protection master stations, characterized in that, include: Step 1: Based on the generalized data template, generate a generalized event reasoning logic flow using primitives; Step 2: Obtain typical generalized data from the database and assign it to each element in the generalized event reasoning logic flow. The typical generalized data assigned to the elements is generalized data stored in a keyword dictionary based on relay protection business data. Based on a preset synonym dictionary, the attributes of the signals at each measuring point of the main station are normalized. Based on a preset keyword dictionary, the number of high-priority keywords, low-priority keywords, and keyword order matching numbers that match the normalized attributes are determined to calculate the matching degree. When the matching degree is greater than a set threshold, the instance data obtained by combining the normalized attributes and the typical generalized data is used to instantiate the generalized event reasoning logic flow to obtain the specific event reasoning logic flow. The priority of keywords is determined based on the priority of various protections in different scenarios, specifically as follows: 1) Scenario 1: Line Protection The main protection has the highest priority and includes: longitudinal differential protection, high frequency protection, and fiber optic current differential protection; the backup protection has the second highest priority and includes: distance protection and zero-sequence current protection; the abnormal alarm has the lowest priority and includes: overload alarm and TV / TA disconnection detection. 2) Scenario 2: Transformer Protection Differential protection and heavy gas protection have the highest priority; backup protection has the second priority, including: composite voltage blocking overcurrent protection and zero-sequence current and voltage protection; abnormal operation protection has the third priority, including: overload protection and light gas protection. 3) Scenario 3: Busbar Protection Busbar differential protection and circuit breaker failure protection have the highest priority; the remaining protections have the second highest priority. Keywords covered by the highest and second-highest priority protection are considered high-priority keywords, while keywords covered by the third-highest priority protection are considered low-priority keywords. The matching degree is calculated as the weighted sum of the ratios of the number of high-priority keywords to the number of high-priority keywords in typical generalized data, the ratio of the number of low-priority keywords to the number of low-priority keywords in typical generalized data, and the ratio of the number of keyword order matches to the number of keywords in typical generalized data, as shown in the following formula: In the formula, For matching degree; , , All are weighting coefficients, and + + =1; , , These are the number of high-priority keywords, the number of low-priority keywords, and the number of keywords matched in sequence. , , These represent the number of high-priority keywords, low-priority keywords, and the total number of keywords in typical generalized data, respectively. = + ; Step 3: Compile the specific event reasoning logic flow into a rule file; based on the reasoning model and historical data, verify the validity of the rule file; when the rule file is determined to be valid, execute event reasoning based on the reasoning model, real-time system data, preset running time, and automatic commissioning conditions.

2. The event reasoning method based on visual orchestration according to claim 1, characterized in that, The attributes of the measurement point signal include: substation, voltage level, bay, and equipment.

3. The event reasoning method based on visual orchestration according to claim 1, characterized in that, If typical generalized data exists that matches multiple normalized attributes and all of them have a matching degree greater than a set threshold, then the normalized attribute with the highest matching degree is combined with the typical generalized data to obtain instance data.

4. The event reasoning method based on visual orchestration according to claim 1, characterized in that, The signals from each measuring point at the main station include the analog quantities and status quantities of the device. Based on keywords that match the standardized attributes, the interval is located in the plant. After traversing the equipment under the interval to determine the characteristic quantities, the device is located. The analog quantities and status quantities of the device are segmented and the attributes of the measuring point signals are optimized.

5. An event reasoning system based on visual orchestration, used in a power system protection master station, implementing the event reasoning method based on visual orchestration as described in any one of claims 1 to 4, characterized in that, include: The generalized event flow generation module is used to generate generalized event reasoning logic flow based on generalized data templates and using primitives. The specific event flow generation module is used to retrieve typical generalized data from the database and assign it to each element in the generalized event reasoning logic flow; Based on a pre-defined thesaurus, the attributes of the signals from each measuring point of the main station are standardized. Based on a pre-defined keyword dictionary, the number of high-priority keywords, low-priority keywords, and keyword order matching keywords that match the normalized attributes are determined to calculate the matching degree. When the matching degree is greater than the set threshold, the instance data obtained by combining normalized attributes and typical generalized data is used to instantiate the generalized event reasoning logic flow to obtain the specific event reasoning logic flow. The event reasoning module is used to compile specific event reasoning logic into rule files; Based on the reasoning model and historical data, the validity of the rule file is verified. When the rule file is determined to be valid, event reasoning is performed based on the reasoning model, real-time system data, preset runtime, and automatic commissioning conditions.

6. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-4.

Images