Scheduling information co-processing method and system and electronic equipment

Abstract

The invention provides a scheduling information cooperative processing method and system and electronic equipment, and the method comprises the steps: obtaining production data, and inputting the production data into a large model to obtain push information; receiving push information pushed by the large model, and determining the information type of the push information; wherein the push information comprises a production report and to-be-handled information; if the push information is a production report, marking the production report as an unread report; and if the push information is to-be-handled information, generating a scheduling task based on the to-be-handled information, and sending the scheduling task to the corresponding execution role. According to the invention, the information processing efficiency is improved, and the labor cost and the error rate are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial scheduling, and in particular to a scheduling information collaborative processing method and system and electronic equipment. BACKGROUND

[0002] At present, the processing of most industrial scheduling information mainly relies on manual collection and arrangement, manual summary of shift tasks, and relies on static table records or simple electronic documents for production data flow. Accident backtracking needs to manually retrieve scattered logs and videos. The generation of production reports is mostly manually written or based on preset templates for standardized text report generation, lacking multi-modal data processing capability. This approach results in low work efficiency, high error rate, and difficulty in effectively summarizing and analyzing multi-modal information. At the same time, for production accident backtracking, a large amount of time is spent manually searching for relevant information from massive data. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a scheduling information collaborative processing method and system and electronic equipment to improve information processing efficiency and reduce labor costs and error rates.

[0004] To achieve the above purpose, the technical solutions adopted by the embodiments of the present application are as follows: In a first aspect, the embodiments of the present application provide a scheduling information collaborative processing method, comprising: obtaining production data and inputting the production data into a large model to obtain push information; receiving the push information pushed by the large model and determining the information type of the push information; wherein the push information includes production reports and to-do information; if the push information is a production report, marking the production report as an unread report; if the push information is to-do information, generating a scheduling task based on the to-do information and sending the scheduling task to the corresponding execution role.

[0005] Optionally, obtaining production data and inputting the production data into a large model to obtain push information comprises: collecting production data in real time through an API or an Internet of Things device, and performing data cleaning and standardization processing on the production data, storing the processed production data into a standard database; using a large model to perform predictive analysis on the production data to generate to-do information; and / or using a large model to query report data in the standard database according to a preset report requirement, and analyzing the report data, generating a production report based on the report data and the analysis result.

[0006] Optionally, after analyzing the report data, further comprising: when the large model predicts an abnormal event, generating to-do information based on the abnormal event; wherein the to-do information includes: prediction information and real-time production information, and the prediction information at least includes: abnormal event name, cause analysis, treatment solution suggestion, information level, scene type, business department, and knowledge graph.

[0007] Optionally, the large model is used to perform prediction analysis on the production data to generate to-do information, including: determining a display mode of the to-do information based on an information level in the to-do information; if the information level is level one or level two, the to-do information is displayed in the form of a pop-up box, and after obtaining processing information of the to-do information by the user, the pop-up box is closed; if the information level of the to-do information is level three, the to-do information is displayed in the form of a pop-up box, and the pop-up box is closed after a preset time.

[0008] Optionally, a dispatch task is generated based on the to-do information, including: if the to-do information is correct, the to-do information is matched to a corresponding workflow based on pre-configured workflow information to generate the dispatch task; if an error rate of the to-do information is less than a preset value, modified to-do information is obtained in response to a modification operation of the to-do information by the user, and the modified to-do information is matched to the corresponding workflow based on the pre-configured workflow information to generate the dispatch task; if the error rate of the to-do information is greater than or equal to the preset value, a rejection feedback information is sent to the large model in response to a rejection operation of the to-do information by the user, so that the large model is modified based on the rejection feedback information.

[0009] Optionally, after the dispatch task is sent to the corresponding execution role, further comprising: if a response time of the execution role to the dispatch task exceeds a time threshold or a planned completion time of the dispatch task, prompt information is sent to the execution role; if the execution role accepts the dispatch task, a task progress of the dispatch task is tracked until the dispatch task ends.

[0010] In a second aspect, an embodiment of the present application provides a dispatch information collaborative processing system, including: a data acquisition module, configured to acquire production data and input the production data into a large model to obtain push information; an information receiving module, configured to receive the push information pushed by the large model and determine an information type of the push information; wherein the push information includes production reports and to-do information; a report marking module, configured to mark the production reports as unread reports if the push information is the production reports; and a dispatch module, configured to generate a dispatch task based on the to-do information if the push information is the to-do information, and send the dispatch task to a corresponding execution role.

[0011] Optionally, the data acquisition module is specifically configured to: collect production data in real time through an API or an Internet of Things device, and perform data cleaning and standardization processing on the production data, and store the processed production data into a standard database; perform prediction analysis on the production data by using a large model to generate to-be-done information; and / or, query report data from the standard database according to a preset report requirement by using the large model, and perform analysis on the report data, and generate a production report based on the report data and the analysis result.

[0012] In a third aspect, an electronic device is provided, which includes a processor and a memory. The memory stores computer executable instructions that are executable by the processor. The processor executes the computer executable instructions to implement the steps of the method of any one of the first aspect.

[0013] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores a computer program. When the computer program is run by a processor, the steps of the method of any one of the first aspect are executed.

[0014] The embodiments of the present application have the following beneficial effects: The above scheduling information collaborative processing method, system and electronic device provided by the present application first acquire production data, and input the production data into a large model to obtain push information. Then, the push information pushed by the large model is received, and the information type of the push information is determined. The push information includes production reports and to-be-done information. If the push information is a production report, the production report is marked as unread report. If the push information is to-be-done information, a scheduling task is generated based on the to-be-done information, and the scheduling task is sent to the corresponding execution role. The above method can analyze production data by using a large model to generate to-be-done information and production reports, and automatically generate scheduling tasks according to to-be-done information and send them to the corresponding execution role, thereby realizing automatic summary generation of scheduling information, automatic flow of shift task and automatic generation of production report, improving the efficiency of information processing, and reducing the labor cost and error rate.

[0015] Other features and advantages of the present application will be further apparent from the following detailed description, and to some extent will be apparent from the description that is made with the accompanying drawings. The purposes and other advantages of the present application can be realized and obtained by the structure particularly pointed out in the description, claims and accompanying drawings.

[0016] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are referred to for detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to make the technical solutions in the specific embodiments or prior art of the present application clearer, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0018] Figure 1 A flow chart of a dispatch information collaborative processing method provided for an embodiment of the present application; Figure 2 A workflow schematic diagram of a dispatch task provided for an embodiment of the present application; Figure 3 A flow chart of another dispatch information collaborative processing method provided for an embodiment of the present application; Figure 4 A structural schematic diagram of a dispatch information collaborative processing system provided for an embodiment of the present application; Figure 5 A structural schematic diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the technical solutions in the specific embodiments or prior art of the present application clearer, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0020] At present, most of the existing dispatch information is collected and processed manually, which leads to low information aggregation efficiency and easy omission of key information. After a production accident occurs, the key data and information at the time of the accident cannot be quickly retrieved, which leads to a complicated process of locating the cause of the accident and a long time consumption. The generation of production reports depends on manual work or only supports structured data (such as database tables, log files), and the report is generated by matching a preset template through a rule engine, which cannot process unstructured data such as videos and audios. It is impossible to use multi-modal data processing capability and real-time data to automatically generate improvement suggestions, and the accuracy is difficult to guarantee.

[0021] Based on this, the dispatch information collaborative processing method, system and electronic device provided by the embodiments of the present application can improve the efficiency of information processing and reduce the labor cost and error rate.

[0022] To facilitate understanding of this embodiment, a method for collaboratively processing dispatch information disclosed in an embodiment of the present invention is first introduced in detail. This method is applied to the dispatch system of a coal preparation plant and can be executed by electronic devices such as computers, smart phones, tablet computers, etc. Figure 1 The flowchart of a method for collaboratively processing scheduling information is shown, which illustrates that the method mainly includes the following steps S101 to S104: Step S101: Obtain production data and input the production data into the large model to obtain push information.

[0023] In one embodiment, production data such as equipment status, output, quality, energy consumption, etc. can be collected in real time through APIs, IoT devices, etc., and then the collected production data can be input into a pre-trained large model. The production data is analyzed and predicted by the large model. If the large model predicts an abnormal event, to-do information is generated, or a production report is automatically generated according to the production data and user needs. Finally, the to-do information or production report is pushed as push information to a server connected to the large model server, such as a dispatching system server of a coal preparation plant.

[0024] Step S102: receiving the push information pushed by the large model and determining the information type of the push information.

[0025] Step S103: If the pushed information is a production report, the production report is marked as an unread report; Step S104: If the pushed information is to-do information, a scheduling task is generated based on the to-do information, and the scheduling task is sent to the corresponding execution role.

[0026] In one embodiment, the push information includes: production reports and to-do information. When the scheduling system server receives the push information pushed by the large model, it needs to first determine the type of the received push information, that is, whether the push information is a production report or to-do information.

[0027] If the push information is a production report, the production report will be added to the report list and the status of the production report will be marked as unread. After the user views the production report, the status of the production report will be changed to read. By marking the status of the production report, the user is reminded to check the production report in time.

[0028] If the pushed information is a to-do information, the status of the to-do information is first marked as unread to-do information, and then the corresponding scheduling task is generated according to the to-do information, and the scheduling task is sent to the corresponding execution role so that the execution role can handle the abnormal event.

[0029] The above scheduling information cooperative processing method provided by the present application can utilize a large model to analyze production data to generate to-be-done information and a production report, and automatically generate a scheduling task according to the to-be-done information and send the scheduling task to a corresponding execution role, thereby realizing automatic summarization and generation of scheduling information, automatic circulation of shift handover tasks, and automatic generation of production reports, improving the efficiency of information processing, and reducing labor costs and error rates.

[0030] In one embodiment, for the foregoing step S101, that is, when the production data is acquired and input into the large model to obtain the push information, the following methods can be used, but are not limited thereto: First, real-time collection of production data is performed through an API or an Internet of Things device, and data cleaning and standardization processing are performed on the production data, and the processed production data is stored in a standard database.

[0031] In specific implementation, the production execution management system (MES), the supervisory control and data acquisition system (SCADA), the enterprise resource planning system (ERP), and the like of the coal preparation plant can be connected through an API, an Internet of Things device, and the like to collect device state, yield, quality, energy consumption, and the like in real time, perform data cleaning and standardization processing on the production data, and store the processed production data in a standard database.

[0032] Then, the production data is analyzed by using a large model to generate to-be-done information, and / or report data is queried in the standard database according to a preset report requirement by using the large model, the report data is analyzed, and a production report is generated based on the report data and the analysis result.

[0033] In specific implementation, the production data can be analyzed and / or the production report can be generated by using a large model according to a requirement.

[0034] When a large model predicts an abnormal event during predictive analysis, to-do information is generated based on the abnormal event; wherein the to-do information includes: prediction information and real-time production information, and the prediction information at least includes: abnormal event name, cause analysis, treatment suggestion, information level, scene type, business department, knowledge graph. Specifically, the real-time production data collected is input into the large model, the large model can call the pre-constructed knowledge graph of the coal preparation plant, and combine the prediction model to analyze the production data. If the large model predicts an abnormal event (such as equipment failure, coal quality fluctuation, etc., the scene types of abnormal events are mainly divided into four categories: production, coal quality, mechanical and electrical, and safety), to-do information is generated, which contains prediction information (such as abnormal situation name, cause analysis, treatment suggestion, information level, scene type, business department, knowledge graph) and real-time production information (such as real-time video, historical video, etc.) in production. The cause of the abnormal event and the treatment suggestion pushed by the large model can provide comprehensive and accurate basis for accident analysis, and the real-time video and historical video at the time of occurrence can also provide convenience for tracing the cause of the accident. Among them, the knowledge graph is obtained by clustering analysis on the historical production data of the coal preparation plant, and the knowledge graph contains the correlation between production equipment and process flow under different scenes, as well as the correlation between abnormal events and equipment and process flow.

[0035] When generating production reports using a large model, the large model can automatically query the required data (i.e. report data) in the standard database according to the user's report requirements (such as daily report, weekly report analysis, shift summary, frequently occurring problems, etc.), then use the queried report data to calculate KPI, identify the trend of production data changes and abnormal events, and speculate the potential root cause of the abnormality (such as the correlation between equipment failure and a specific shift); then combine structured data (tables, charts) with natural language analysis (key findings, problem description, preliminary suggestions) to generate production reports with pictures and texts according to templates. The generation process of the production report can realize the minute-level automation from raw data to business insight, greatly improving the efficiency and decision-making timeliness.

[0036] The large model automatically generates production reports through the summary and analysis of the collected production data. In addition to traditional production daily reports and scheduling logs, the report also includes summary analysis of frequently occurring historical problems. The report is displayed in time dimensions such as shifts, days, and weeks, and includes conclusion-based analysis based on the report, providing accurate, comprehensive, and easy-to-understand report content for users.

[0037] In one embodiment, after receiving the to-do information, the scheduling system can differentiate and display it according to the information level of the to-do information, including: determining the display method of the to-do information based on the information level in the to-do information; wherein, if the information level is level one or level two, the to-do information is displayed in the form of a pop-up box, and after obtaining the user's processing information on the to-do information, the pop-up box is closed; if the information level of the to-do information is level three, the to-do information is displayed in the form of a pop-up box, and the pop-up box is closed after a preset time.

[0038] In specific implementation, relatively important first- or second-level to-do items are displayed directly in a pop-up window, and the pop-up window can only be closed after the user has processed the to-do item. For third-level to-do items, the pop-up window automatically closes after 10 seconds of display, and the item is marked as unread. The pop-up window information mainly includes the title of the to-do item, the level of the item, the time of occurrence, and the big model's analysis of the cause of the abnormal information and the provided handling suggestions.

[0039] In one embodiment, the aforementioned step S104, i.e., generating a scheduling task based on the to-do information, can be implemented in the following ways, including but not limited to: (1) If the to-do information is correct, the to-do information is matched to the corresponding workflow based on the pre-configured workflow information to generate a scheduling task.

[0040] In specific implementation, in order to avoid errors in to-do information affecting the flow of subsequent handover tasks, in an embodiment of the present invention, the to-do information pushed by the large model can be confirmed according to pre-set judgment rules, or the user can confirm the to-do information pushed by the large model. If the to-do information is correct and reasonable, the to-do information is matched with the corresponding workflow to generate a scheduling task, and the scheduling task is directly dispatched, and the task is assigned to a specific execution role according to the design of the workflow. Among them, the pre-set judgment rules can be knowledge graphs and historical abnormal events, etc. By comparing the to-do information with the knowledge graph and historical abnormal events, it is judged whether the abnormal event is reasonable.

[0041] Specifically, the scheduling system includes workflow module configuration, which can pre-configure workflow information based on scenario type, business department, skill group, position information, etc. When receiving to-do information pushed by the big model, it can automatically match the corresponding workflow based on the scenario type, business department, etc. in the to-do information and assign it to the corresponding execution role. Figure 2 shown.

[0042] (2) If the error rate of the to-do information is less than a preset value, in response to the user's modification operation on the to-do information, the modified to-do information is obtained, and based on the pre-configured workflow information, the modified to-do information is matched to the corresponding workflow to generate a scheduling task.

[0043] In specific implementation, if the to-do information has part error (i.e. the error rate is less than the preset value), the user can perform secondary editing on the to-do information to obtain modified to-do information, and then match the corresponding workflow according to the modified to-do information, generate a scheduling task, and distribute it to the corresponding execution role.

[0044] (3) If the error rate of the to-do information is greater than or equal to the preset value, in response to the user's rejection operation on the to-do information, the rejection feedback information is sent to the large model to make the large model correct the large model based on the rejection feedback information.

[0045] In specific implementation, if the to-do information has too much error information (i.e. the error rate is greater than or equal to the preset value), the user can reject the to-do information and send the rejection feedback information to the large model. After receiving the rejection feedback information, the large model can correct the large model, thereby improving the accuracy of the large model.

[0046] Further, after the scheduling task is sent out and enters the task list, the scheduling task will be distributed to the specific execution role according to the corresponding configured workflow information, and the scheduling system can automatically track the task progress until the task is completed. Based on this, the above method further includes: if the response time of the execution role to the scheduling task exceeds the time threshold or the planned completion time, sending prompt information to the execution role; if the execution role accepts the scheduling task, tracking the task progress of the scheduling task until the scheduling task is completed.

[0047] In specific implementation, when the scheduling task is distributed, the response time of the execution role to the scheduling task can be monitored. If the response time of the execution role to the scheduling task exceeds the time threshold (such as 30 minutes) or exceeds the planned completion time of the scheduling task (i.e. the execution role still does not accept the scheduling task after exceeding the planned completion time of the scheduling task), prompt information is sent to the execution role to remind the execution role to handle the scheduling task in time. If the execution role accepts the scheduling task, the task progress of the scheduling task is tracked until the scheduling task is completed.

[0048] For ease of understanding, the present embodiment also provides a flow of a scheduling information collaborative processing method, as shown in Figure 3 After the system receives the push information of the large model, it first judges the type of the push information. If it is a production report, the production report is marked as an unread report, and after the user opens the production report, it is modified to a read report.

[0049] If it is a to-do information, it is marked as unread to-do information and added to the to-do information list, and then the information level of the to-do information is determined, if the information level is one or two, the to-do information is popped up through a pop-up box, if the information level is three, the to-do information is popped up through a pop-up box, and the pop-up box is closed after 10 seconds, and the to-do information is marked as unread.

[0050] After the user views the to-do information, it is modified as read information, if the to-do information is correct and reasonable, the corresponding workflow is matched according to the to-do information, and the dispatch task is assigned; if the to-do information has some errors, the modified to-do information is obtained through secondary editing of the user, and the corresponding workflow is matched according to the modified to-do information, and the dispatch task is assigned; if the to-do information has too many errors, the large model error information is fed back.

[0051] After the task is assigned, if the execution role does not accept the task, the system feedbacks that the execution role does not accept the task, the task is added again or the task is assigned again; if the response time of the execution role exceeds 30 minutes or is greater than the planned completion time, a prompt information is sent through the system; if the execution role accepts the task, the task progress is tracked until the dispatch task ends. If the task is not completed, it is judged whether the current time is greater than the planned completion time, if yes, the task is marked as an overdue task.

[0052] In addition, in the embodiment of the application, the user can manually add a task, and the task is assigned to the corresponding execution role according to the corresponding workflow of the task.

[0053] The above-mentioned dispatch information collaborative processing method provided by the embodiment of the application realizes automatic summary generation of dispatch information collaboration through the push information of the large model, and contains multiple types of information, which significantly improves the efficiency of information summary and processing, reduces the labor cost, can quickly retrieve the data, tasks, video and other information at the time of the accident, provides comprehensive and accurate basis for accident analysis, and improves the efficiency of accident processing, can automatically identify shift handover tasks, and automatically process task flow according to the preset rules, ensures seamless connection of tasks, and avoids omission or delay, and can automatically generate a production report according to the collected information, including production data, equipment status, personnel information and the like, the report content is accurate, comprehensive and easy to understand.

[0054] For the dispatch information collaborative processing method provided by the foregoing embodiment, the embodiment of the application further provides a dispatch information collaborative processing system, which refers to Figure 4 The system can include the following parts: The data acquisition module 401 is configured to acquire production data and input the production data into the large model to obtain push information.

[0055] The information receiving module 402 is configured to receive push information pushed by the large model and determine the information type of the push information; wherein the push information comprises production reports and to-do information.

[0056] The report marking module 403 is configured to mark the production report as an unread report if the push information is a production report.

[0057] The scheduling module 404 is configured to generate a scheduling task based on the to-do information if the push information is to-do information, and send the scheduling task to a corresponding execution role.

[0058] The scheduling information collaborative processing system provided by the present application can use a large model to analyze production data to generate to-do information and production reports, and automatically generate a scheduling task based on the to-do information and send it to a corresponding execution role, thereby realizing automatic summary generation of scheduling information, automatic circulation of shift tasks, and automatic generation of production reports, improving the efficiency of information processing and reducing labor costs and error rates.

[0059] In an embodiment, the data acquisition module 401 is specifically configured to: collect production data in real time through an API or an Internet of Things device, and perform data cleaning and standardization processing on the production data, and store the processed production data into a standard database; use a large model to perform predictive analysis on the production data to generate to-do information; and / or use a large model to query report data from the standard database according to a preset report requirement, and analyze the report data to generate a production report based on the report data and the analysis result.

[0060] In an embodiment, the data acquisition module 401 is further configured to: generate to-do information based on an abnormal event when the large model predicts the abnormal event; wherein the to-do information comprises prediction information and real-time production information, and the prediction information at least comprises an abnormal event name, a cause analysis, a treatment solution suggestion, an information level, a scene type, a business department, and a knowledge graph.

[0061] In an embodiment, the scheduling module 404 is further configured to: determine a display mode of the to-do information based on the information level in the to-do information; wherein if the information level is level one or level two, the to-do information is displayed in the form of a pop-up box, and the pop-up box is closed after the processing information of the to-do information by a user is obtained; and if the information level of the to-do information is level three, the to-do information is displayed in the form of a pop-up box, and the pop-up box is closed after a preset time.

[0062] In an implementation, the scheduling module 404 is further configured to: if the to-do information is correct, match the to-do information to a corresponding workflow based on preconfigured workflow information to generate a scheduling task; if an error rate of the to-do information is less than a preset value, obtain modified to-do information in response to a modification operation of a user on the to-do information, and match the modified to-do information to the corresponding workflow based on the preconfigured workflow information to generate the scheduling task; and if the error rate of the to-do information is greater than or equal to the preset value, send a rejection feedback information to the large model in response to a rejection operation of the user on the to-do information, so that the large model is modified based on the rejection feedback information.

[0063] In an implementation, the scheduling module 404 is further configured to: if a response time of an execution role to the scheduling task exceeds a time threshold or a planned completion time, send prompt information to the execution role; and if the execution role accepts the scheduling task, track a task progress of the scheduling task until the scheduling task ends.

[0064] The device provided by the embodiment of the present application has the same implementation principle and technical effects as the foregoing method embodiment. For brevity, the part not mentioned in the device embodiment part can be referred to the corresponding content in the foregoing method embodiment.

[0065] The embodiment of the present application further provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program performs the method according to any one of the foregoing embodiments when executed by the processor.

[0066] Figure 5 A structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in FIG. 1. The electronic device 100 includes a processor 50, a memory 51, a bus 52 and a communication interface 53, and the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is configured to execute an executable module stored in the memory 51, such as a computer program.

[0067] The memory 51 can include a high-speed random access memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0068] The bus 52 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation,Figure 5 Only one bus or type of bus might exist but there is a possibility of the existence of more buses or more types of buses.

[0069] The memory 51 is configured to store a program, and the processor 50 executes the program after receiving an execution instruction. The method executed by the device for defining a flow process according to any of the foregoing embodiments of the application can be applied to the processor 50 or implemented by the processor 50.

[0070] The processor 50 can be an integrated circuit chip having a processing capability of signals. In the implementation process, each step of the foregoing method can be completed by an integrated logic circuit of hardware in the processor 50 or an instruction in the form of software. The foregoing processor 50 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), and the like; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and combines the hardware to complete the steps of the foregoing method.

[0071] The computer program product of the readable storage medium provided by the embodiments of the application includes a computer readable storage medium storing a program code, and the program code includes instructions for executing the method described in the foregoing method embodiments. For specific implementation, reference can be made to the foregoing method embodiments, which will not be described here.

[0072] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0073] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for collaborative processing of scheduling information, characterized in that: include: Acquire production data, and input the production data into the big model to obtain push information; Receiving the push information pushed by the large model and determining the information type of the push information; wherein the push information includes: production reports and to-do information; If the pushed information is a production report, marking the production report as an unread report; If the pushed information is to-do information, a scheduling task is generated based on the to-do information, and the scheduling task is sent to a corresponding execution role.

2. The method according to claim 1, characterized in that Acquire production data and input the production data into the big model to obtain push information, including: Collect production data in real time through APIs or IoT devices, clean and standardize the production data, and store the processed production data in a standard database; Using the large model to perform predictive analysis on the production data to generate to-do information; And / or, using the large model, performing data query in the standard database according to preset report requirements to obtain report data, analyzing the report data, and generating the production report based on the report data and the analysis results.

3. The method according to claim 2, characterized in that Using the large model to perform predictive analysis on the production data and generate to-do information includes: When the large model predicts an abnormal event, the to-do information is generated based on the abnormal event; wherein, the to-do information includes: prediction information and real-time production information, and the prediction information includes at least: abnormal event name, cause analysis, processing and solution suggestions, information level, scenario type, business department, and knowledge graph.

4. The method according to claim 3, characterized in that Before generating a scheduling task based on the to-do information, the method further includes: The display method of the to-do information is determined based on the information level of the to-do information; if the information level is level one or level two, the to-do information is displayed in the form of a pop-up box, and after obtaining the user's processing information on the to-do information, the pop-up box is closed; if the information level of the to-do information is level three, the to-do information is displayed in the form of a pop-up box, and the pop-up box is closed after a preset time.

5. The method according to claim 4, characterized in that Generating a scheduling task based on the to-do information includes: If the to-do information is correct, then based on the pre-configured workflow information, the to-do information is matched to the corresponding workflow to generate a scheduling task; If the error rate of the to-do information is less than a preset value, in response to the user's modification operation on the to-do information, the modified to-do information is obtained, and based on the pre-configured workflow information, the modified to-do information is matched to the corresponding workflow to generate a scheduling task; If the error rate of the to-do information is greater than or equal to a preset value, in response to the user's rejection operation of the to-do information, rejection feedback information is sent to the large model, so that the large model corrects the large model based on the rejection feedback information.

6. The method according to claim 1, characterized in that After sending the scheduling task to the corresponding execution role, the method further includes: If the response time of the execution role to the scheduling task exceeds a time threshold or a planned completion time of the scheduling task, sending a prompt message to the execution role; If the execution role accepts the scheduling task, the task progress of the scheduling task is tracked until the scheduling task is completed.

7. A scheduling information collaborative processing system, characterized in that: include: A data acquisition module is used to acquire production data and input the production data into the large model to obtain push information; An information receiving module, configured to receive the push information pushed by the large model and determine the information type of the push information; wherein the push information includes: production reports and to-do information; a report marking module, configured to mark the production report as an unread report if the pushed information is a production report; The scheduling module is used to generate a scheduling task based on the to-do information if the pushed information is to-do information, and send the scheduling task to the corresponding execution role.

8. The system according to claim 7, characterized in that The data acquisition module is specifically used for: Collect production data in real time through APIs or IoT devices, clean and standardize the production data, and store the processed production data in a standard database; Using the large model to perform predictive analysis on the production data to generate to-do information; And / or, using the large model, performing data query in the standard database according to preset report requirements to obtain report data, analyzing the report data, and generating the production report based on the report data and the analysis results.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.

Images