A process notice board based on power big data

CN114707968BActive Publication Date: 2024-11-26STATE GRID JIANGSU ELECTRIC POWER CO LTD TAIZHOU POWER SUPPLY BRANCH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210448079.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-27
Publication Date
2024-11-26
Estimated Expiration
2042-04-27

Smart Images

  • Figure CN114707968B_ABST
    Figure CN114707968B_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of power operation process management system, and in particular, it relates to a process bulletin board based on power big data. It includes a field entry component, a data prediction component, and a process display component; the field entry component is used to collect and store the necessary business items and existing business information required by the user to execute the process, and generate the final process; the data prediction component is used to establish an autonomous learning model, train to form a prediction algorithm model, and the process display component is used to output process data. The process bulletin board based on power big data of the present application is mainly used to improve the functions of the existing process bulletin board on the basis of the existing process bulletin board, and use a simple interactive management process to plan and process the execution process of complex process tasks in advance, reduce unnecessary repeated processing processes, and use the autonomous learning model to establish an automatically updated and upgraded database, so that it can be trained and improved according to the execution data of daily business processes, thereby improving the efficiency of process execution.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the technical field of power operation process management systems, and in particular, relates to a process notice board based on power big data. Background Art

[0002] A process notice board, also known as a notice window, refers to a system or device used in process and job control management centers to achieve interactive management of supply-side and user-side processes. It is used for real-time display of process management and control ends and management of execution processes. However, the current system functions and structures of process notice boards are relatively simple, and are generally only used for single-end data transmission. In actual process management and execution, it often involves repeated transmission or logical processing of multiple businesses and their business data associated with the process. As a result, existing process notice boards can generally only be used as information transmission and output devices, and cannot achieve more functions. They do not produce substantial gains for the actual execution of process operations. Summary of the invention

[0003] The purpose of this application is to provide a process bulletin board based on power big data, which has richer functions and is combined with the system structure and functions of the existing process bulletin board, so as to improve the efficiency of process and business execution.

[0004] To achieve the above objectives, this application adopts the following technical solutions.

[0005] A process notice board based on power big data, including a field input component, a data prediction component, and a process display component;

[0006] The on-site entry component is used to collect and store necessary business items and existing business data required by the user to execute the process, and generate the final process based on the necessary business items and existing business data;

[0007] The data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database;

[0008] The process flow display component is used to output process data through a visual interactive interface and establish an interactive channel between the user and the field input component and the data prediction component.

[0009] A further improvement or preferred implementation scheme of the aforementioned process bulletin board based on power big data, wherein the field input component is specifically used for:

[0010] A1. Obtain the process goals given by the customer based on active or passive interaction steps;

[0011] A2. Perform comparison processing based on the existing process database, provide recommended processes containing one or more business items, and output them through the process display component to obtain several selected processes obtained after customer screening;

[0012] A3. After step A2 is completed or during step A2 execution, determine that the business items included in the recommended process or the selected process constitute a forecast business set, determine the forecast business data set required to implement the forecast business set, and output it through the process display component;

[0013] A4. After step A3 is completed or during step A3, the client deletes the business data that it does not have from the forecast business data set based on active interaction to obtain an existing forecast business data set;

[0014] A5. Based on the existing forecast business data set, the selected process in step A2 is modified, specifically including: according to the deleted business data, locating the unavailable business items whose business data in the process do not meet the requirements, determining the business item whose business output is closest to the unavailable business item according to the output matching principle, obtaining the recommended business item, generating the business data corresponding to the recommended business item, deleting the business data existing in the forecast business data set, obtaining a new forecast business data set, and returning to step A3; until there are no unavailable business items or all new forecast business data sets do not exist;

[0015] A6. Obtain the final business item obtained in step A5, determine the order of the corresponding process windows according to the order of association of input and output of each business item and the principle of minimum process windows, and output the final process.

[0016] A further improvement or preferred implementation scheme of the aforementioned process notice board based on power big data, wherein the process display component is implemented based on a B / S architecture, data access is achieved through a server, and output display and real-time interaction are performed using a web browser; data page elements are standardized using CSS and HTML languages, and some visual frame elements are implemented using D3 plug-ins;

[0017] A further improvement or preferred implementation scheme of the aforementioned process bulletin board based on power big data, wherein the data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database; during the model training process, a condition class consisting of business data and process windows is defined, and a generative adversarial network GAN is used to classify and judge whether the condition class can meet the execution requirements of the corresponding business item; wherein the random data is a random combination of business data and process windows, and the real data is a combination of business data and process windows corresponding to actual business items. The generation network generates virtual business items based on the random combination, and the discrimination network is used to judge the virtual business items and the real business items without outputting the validity judgment results of the business data and process windows.

[0018] A further improvement or preferred implementation scheme of the aforementioned process bulletin board based on power big data also includes a background processing component, which includes a data module and a process data storage module; the data module is used to collect and organize existing business types, determine the business information and corresponding process windows required for all business types, and establish a basic database containing all business information and process windows; the process data storage module is used to collect and organize existing processes, as well as the process results obtained by training the data prediction component.

[0019] A further improvement or preferred implementation scheme of the aforementioned process bulletin board based on power big data, the background processing component generates and obtains valid data according to the inspection results of the data prediction component or external input data, and the valid data refers to the business information and process window corresponding to the specific business item; and sends it to the data storage module to establish a process database.

[0020] A further improvement or preferred implementation scheme of the aforementioned process bulletin board based on power big data, the basic data storage module includes a main node, a secondary node and several data nodes; the main node is used to manage the data nodes stored on the local disk, and the secondary node is used to merge, back up and extract data according to preset parameters; the data node is used to save specific data blocks and interact with the main node, and perform operations such as reading and writing data according to the instructions of the main node. The data blocks are obtained after splitting operations on specific data files.

[0021] Its beneficial effects are:

[0022] The process bulletin board based on power big data of the present application is mainly used to improve the functions of the existing process bulletin board, utilize its general characteristics of direct interaction with specific processes and business request ends, and use a simple interactive management process to plan and process the execution process of complex process tasks in advance, reduce unnecessary repeated processing processes, and use an autonomous learning model to establish an automatically updated and upgraded database, so that it can be trained and improved according to the execution data of daily business processes, thereby improving the efficiency of process execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the system structure of the process bulletin board based on power big data. DETAILED DESCRIPTION

[0024] The present application is described in detail below in conjunction with specific embodiments.

[0025] The present application designs a process bulletin board based on power big data. The process bulletin board in the present application refers to a complete system used for information transmission and management in process and job management and execution scenarios. Because its front end is generally manifested in the form of a human-computer interaction interface or interactive equipment (mainly including various display screens, human-computer interfaces), etc., it is usually referred to as a process bulletin board. It should be understood that it also includes an invisible back-end software and hardware management system.

[0026] The process notice board based on power big data of the present application includes a field input component, a data prediction component, and a process display component;

[0027] The field entry component is used to collect and store the necessary business items and existing business data required by users to execute the process, and generate the final process based on the necessary business items and existing business data;

[0028] The data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database;

[0029] The process flow display component is used to output process data through a visual interactive interface and establish an interactive channel between users and the field input component and data prediction component.

[0030] The field entry component is specifically used for:

[0031] A1. Obtain the process goals given by the customer based on active or passive interaction steps;

[0032] A2. Perform comparison processing based on the existing process database, provide recommended processes containing one or more business items, and output them through the process display component to obtain several selected processes obtained after customer screening;

[0033] A3. After step A2 is completed or during step A2 execution, determine that the business items included in the recommended process or the selected process constitute a forecast business set, determine the forecast business data set required to implement the forecast business set, and output it through the process display component;

[0034] A4. After step A3 is completed or during step A3, the client deletes the business data that it does not have from the forecast business data set based on active interaction to obtain an existing forecast business data set;

[0035] A5. Based on the existing forecast business data set, the selected process in step A2 is modified, specifically including: according to the deleted business data, locating the unavailable business items whose business data in the process do not meet the requirements, determining the business item whose business output is closest to the unavailable business item according to the output matching principle, obtaining the recommended business item, generating the business data corresponding to the recommended business item, deleting the business data existing in the forecast business data set, obtaining a new forecast business data set, and returning to step A3; until there are no unavailable business items or all new forecast business data sets do not exist;

[0036] A6. Obtain the final business item obtained in step A5, determine the order of the corresponding process windows according to the order of association of input and output of each business item and the principle of minimum process windows, and output the final process.

[0037] The process display component is implemented based on the B / S architecture, data access is achieved through the server, and output display and real-time interaction are performed using a web browser; CSS and HTML languages ​​are used to standardize data page elements, and D3 plug-ins are used to implement some visual frame elements;

[0038] The data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database; during the model training process, a condition class consisting of business data and process windows is defined, and a generative adversarial network GAN is used to classify and judge whether the condition class can meet the execution requirements of the corresponding business item; the random data is a random combination of business data and process windows, and the real data is a combination of business data and process windows corresponding to actual business items. The generation network generates virtual business items based on random combinations, and the discrimination network is used to judge virtual business items and real business items without outputting the validity judgment results of business data and process windows.

[0039] It also includes a background processing component, which includes a data module and a process data storage module; the data module is used to collect and organize existing business types, determine the business information and corresponding process windows required for all business types, and establish a basic database containing all business information and process windows; the process data storage module is used to collect and organize existing processes, as well as the process results obtained by training the data prediction component.

[0040] The background processing component generates and obtains valid data based on the inspection results of the data prediction component or external input data. The valid data refers to the business information and process windows corresponding to specific business items; and sends it to the data storage module to establish a process database.

[0041] The basic data storage module includes a master node, a secondary node and several data nodes; the master node is used to manage the data nodes stored on the local disk, and the secondary node is used to merge, back up and extract data according to preset parameters; the data node is used to save specific data blocks and interact with the master node, and perform operations such as reading and writing data according to the instructions of the master node. The data blocks are obtained after the specific data files are split.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, rather than to limit the scope of protection of the present application. Although the present application has been described in detail with reference to the preferred embodiments, ordinary technicians in this field should understand that the technical solution of the present application can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present application.

Claims

1. A process notice board based on power big data, characterized in that: Includes field entry components, data prediction components, and process display components; The on-site entry component is used to collect and store necessary business items and existing business data required by the user to execute the process, and generate the final process based on the necessary business items and existing business data; The data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database; The process flow display component is used to output process data through a visual interactive interface and establish an interactive channel between the user and the field input component and the data prediction component; During the model training process, a conditional class consisting of business data and process windows is defined, and a generative adversarial network (GAN) is used to classify and judge whether the conditional class can meet the execution requirements of the corresponding business item. The on-site input component is specifically used for: A1. Obtain the process goals given by the customer based on active or passive interaction steps; A2. Perform comparison processing based on the existing process database, provide recommended processes containing one or more business items, and output them through the process display component to obtain several selected processes obtained after customer screening; A3. After step A2 is completed or during step A2 execution, determine that the business items included in the recommended process or the selected process constitute a forecast business set, determine the forecast business data set required to implement the forecast business set, and output it through the process display component; A4. After step A3 is completed or during step A3, the client deletes the business data that it does not have from the forecast business data set based on active interaction to obtain an existing forecast business data set; A5. Based on the existing forecast business data set, the selected process in step A2 is modified, specifically including: according to the deleted business data, locating the unavailable business items whose business data in the process do not meet the requirements, determining the business item whose business output is closest to the unavailable business item according to the output matching principle, obtaining the recommended business item, generating the business data corresponding to the recommended business item, deleting the business data existing in the forecast business data set, obtaining a new forecast business data set, and returning to step A3; until there are no unavailable business items or all new forecast business data sets do not exist; A6. Obtain the final business item obtained in step A5, determine the order of the corresponding process windows according to the order of association of input and output of each business item and the principle of minimum process windows, and output the final process.

2. A process notice board based on power big data according to claim 1, characterized in that: The process display component is implemented based on the B / S architecture, data access is achieved through the server, and output display and real-time interaction are performed using a web browser; data page elements are standardized through CSS and HTML languages, and some visual frame elements are implemented using D3 plug-ins.

3. According to the process notice board based on power big data of claim 1, it is characterized in that: The data prediction component is used to establish an autonomous learning model, train the model to form a prediction algorithm model, and generate a prediction algorithm model database; wherein the random data is a random combination of business information and process windows, the real data is a combination of business information and process windows corresponding to actual business items, the generation network generates virtual business items based on the random combination, and the discrimination network is used to judge the virtual business items and the real business items without outputting the validity judgment results of the business information and process windows.

4. A process notice board based on power big data according to claim 1, characterized in that: It also includes a background processing component, which includes a data module and a process data storage module; the data module is used to collect and organize existing business types, determine the business information and corresponding process windows required for all business types, and establish a basic database containing all business information and process windows; the process data storage module is used to collect and organize existing processes, as well as the process results obtained by training the data prediction component.

5. A process notice board based on electric power big data according to claim 4, characterized in that: The background processing component generates and obtains valid data according to the inspection results of the data prediction component or external input data, and the valid data refers to the business information and process window corresponding to the specific business item; and sends it to the data storage module to establish a process database.

6. A process notice board based on electric power big data according to claim 5, characterized in that: The basic data storage module includes a master node, a secondary node and several data nodes; the master node is used to manage the data nodes stored in the local disk, and the secondary node is used to merge, back up and extract data according to preset parameters; The data node is used to store specific data blocks and interact with the master node, and perform operations such as reading and writing data according to the master node instructions. The data blocks are obtained by splitting specific data files.