Scheduling transaction management method and system

Abstract

The invention discloses a scheduling transaction management method and system. The method comprises the following steps: acquiring instant data information and historical scheduling data; the instant data information comprises a current ongoing scheduling transaction list and current event data; according to the historical scheduling data and the event data, analyzing relevance between a current event and all scheduling transactions in the scheduling transaction list; if the event does not have relevance with all scheduling transactions, creating a new target scheduling transaction in the scheduling transaction list, and updating the state of the target scheduling transaction; and if the relevance between the event and a certain target scheduling transaction is the strongest, attributing the event to the target scheduling transaction, and updating the state of the target scheduling transaction. According to the method, the data information which just occurs can be analyzed, and the correlation between the information and the scheduling affairs is judged, so that a dispatcher is assisted to process the scheduling affairs, the burden is reduced, and more accurate judgment and response are made.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction data management, and in particular to a scheduling transaction management method and system. Background Art

[0002] According to the trigger start classification, dispatching affairs are divided into two types: scheduled start (such as: regularly executed dispatching plans, accident drills, etc.) and temporary triggers (such as: encountering natural disasters, accidents or failures, etc.), so dispatching affairs are not carried out serially. According to the certainty of the execution process, dispatching affairs are divided into two types: planned affairs executed according to dispatching procedures and plans / plans, and unplanned affairs carried out according to actual conditions and dispatcher experience. Due to the complexity and uncertainty of dispatching work, dispatchers usually need to decompose a transaction into multiple interrelated stages (such as: pre-order-correct order-execution-feedback, etc.) to complete, and the data information generated by each link reflects the stage or status of the transaction progress. When a transaction link occurs or is completed, the dispatcher needs to record the latest progress status of the transaction corresponding to the link. When the dispatcher determines that the last link of the dispatching transaction has occurred or completed, the transaction is completed. Dispatchers need to handle multiple concurrent dispatching affairs at the same time. When an event (such as a dispatching call or a device alarm event) occurs or is completed, the dispatcher needs to determine whether the event is attributed to a link in the current dispatching affairs and update its progress status based on the data information generated by the event, or trigger the start of a new dispatching affair. This not only requires dispatchers to have strong memory retrieval capabilities, but also to have rich work experience to determine whether the event is related to which current dispatching affairs links. This undoubtedly adds more workload to dispatchers while they focus on complex affairs. And as the dispatching business scenarios become more and more complex, the workload of dispatchers in handling dispatching affairs is also heavier, making it difficult for dispatchers to ensure the timeliness and accuracy of handling dispatching affairs. Therefore, it is necessary to provide intelligent auxiliary means to assist dispatchers in handling dispatching affairs, so that dispatchers can quickly obtain key insights and reduce their burden in order to make more accurate judgments and responses. Summary of the invention

[0003] The present invention provides a dispatch affairs management method and system, which analyzes the data information that has just occurred, combines the historical and currently ongoing dispatch affairs, and automatically evaluates the relevance of the information to the dispatch affairs to update the status of the dispatch affairs, thereby assisting the dispatcher in handling the dispatch affairs, enabling the dispatcher to quickly obtain key insights, reduce the burden, and make more accurate judgments and responses.

[0004] In order to achieve the above object, an embodiment of the present invention provides a scheduling transaction management method, including:

[0005] Acquire real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data;

[0006] Analyzing the relevance of the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data;

[0007] If there is no correlation between the event and all scheduling transactions, a new target scheduling transaction is created in the scheduling transaction list, and the state of the target scheduling transaction is updated;

[0008] If the event has the strongest correlation with a certain target scheduling transaction, the event is attributed to the target scheduling transaction, and the state of the target scheduling transaction is updated.

[0009] As an improvement of the above solution, the analysis of the correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data includes:

[0010] Utilizing the natural language processing and semantic understanding capabilities of the generative big model, the event data is analyzed to extract key features of the event data;

[0011] According to the key features and the historical scheduling data, it is determined whether there is any correlation between the currently occurring event and all the scheduling transactions in the scheduling transaction list.

[0012] As an improvement of the above solution, judging whether there is a correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the key features and the historical scheduling data includes:

[0013] Generating a vector representation of the event according to the key features to capture semantic information of the event;

[0014] Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information;

[0015] The relevance of the event to all scheduled transactions is determined based on the similarity.

[0016] As an improvement of the above solution, after updating the state of the target scheduling transaction, the method further includes:

[0017] If the updated target scheduling transaction has ended, deleting the target scheduling transaction from the scheduling transaction list;

[0018] If the updated target scheduling transaction is not completed, a disposal plan for the target scheduling transaction is predicted and recommended.

[0019] As an improvement of the above solution, if the updated target scheduling transaction is not completed, predicting and recommending a disposal solution for the target scheduling transaction includes:

[0020] If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data;

[0021] Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event;

[0022] Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs;

[0023] The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

[0024] In order to achieve the above object, an embodiment of the present invention provides a scheduling transaction management system, including:

[0025] A scheduling data acquisition module is used to acquire real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data;

[0026] A scheduling data analysis module, used for analyzing the correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data;

[0027] A scheduling transaction creation module, used for creating a new target scheduling transaction in the scheduling transaction list and updating the state of the target scheduling transaction if there is no correlation between the event and all scheduling transactions;

[0028] The scheduling transaction updating module is used for attributing the event to a target scheduling transaction and updating the state of the target scheduling transaction if the event has the strongest correlation with the target scheduling transaction.

[0029] As an improvement of the above solution, the scheduling data analysis module is used to:

[0030] Utilizing the natural language processing and semantic understanding capabilities of the generative big model, the event data is analyzed to extract key features of the event data;

[0031] According to the key features and the historical scheduling data, it is determined whether there is any correlation between the currently occurring event and all the scheduling transactions in the scheduling transaction list.

[0032] As an improvement of the above solution, judging whether there is a correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the key features and the historical scheduling data includes:

[0033] Generating a vector representation of the event according to the key features to capture semantic information of the event;

[0034] Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information;

[0035] The relevance of the event to all scheduled transactions is determined based on the similarity.

[0036] As an improvement of the above solution, the system further includes:

[0037] A scheduling transaction deletion module, configured to delete the target scheduling transaction from the scheduling transaction list if the updated target scheduling transaction has ended;

[0038] The disposal plan recommendation module is used to predict and recommend a disposal plan for the target scheduling transaction if the updated target scheduling transaction has not been completed.

[0039] As an improvement of the above solution, the treatment solution recommendation module is used to:

[0040] If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data;

[0041] Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event;

[0042] Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs;

[0043] The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

[0044] Compared with the prior art, the method and system for managing scheduling affairs disclosed in the embodiment of the present invention obtains real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling affairs and currently occurring event data; according to the historical scheduling data and the event data, the correlation between the currently occurring event and all scheduling affairs in the scheduling affairs list is analyzed; if there is no correlation between the event and all scheduling affairs, a new target scheduling affair is created in the scheduling affairs list, and the status of the target scheduling affair is updated; if the event has the strongest correlation with a certain target scheduling affair, the event is attributed to the target scheduling affair, and the status of the target scheduling affair is updated. It is capable of analyzing the data information that has just occurred, combining the historical and currently ongoing scheduling affairs, automatically evaluating the correlation between the information and the scheduling affairs, so as to update the status of the scheduling affairs, thereby assisting the dispatcher in handling the scheduling affairs, enabling the dispatcher to quickly obtain key insights, reduce the burden, and make more accurate judgments and responses. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flowchart of a scheduling transaction management method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of an execution process of a scheduling transaction list provided by an embodiment of the present invention;

[0047] Figure 3 It is a schematic diagram of an execution structure of a command and dispatch system provided by an embodiment of the present invention;

[0048] Figure 4 It is a schematic diagram of a transaction scheduling execution process of a command and dispatch system provided by an embodiment of the present invention;

[0049] Figure 5 It is a structural diagram of a scheduling affairs management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] It should be noted that the terms "comprises" and "specifically" and any variations of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0052] See also Figure 1 , Figure 1 1 is a flow chart of a scheduling transaction management method provided by an embodiment of the present invention, and the scheduling transaction management method includes:

[0053] S1, obtaining real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data;

[0054] S2, analyzing the correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data;

[0055] S3, if there is no correlation between the event and all scheduling transactions, then create a new target scheduling transaction in the scheduling transaction list and update the status of the target scheduling transaction;

[0056] S4: If the event has the strongest correlation with a certain target scheduling transaction, attribute the event to the target scheduling transaction, and update the state of the target scheduling transaction.

[0057] For example, see Figure 2 , Figure 2 A schematic diagram of the execution process of a scheduling transaction list provided by an embodiment of the present invention; the dispatcher needs to handle multiple concurrent scheduling transactions at the same time. Each scheduling transaction can be divided into several states or links in chronological order, and can be transferred from one state to the next state by executing a scheduling task instruction or confirming the occurrence of certain events, forming a timeline of the scheduling transaction until the scheduling transaction ends. Various data information is obtained, including the execution of a scheduling task instruction or the occurrence of a certain event, and the relevance of the information to the scheduling transactions is analyzed to determine whether it is attributed to the most relevant scheduling transaction, or to create a new scheduling transaction, and then the scheduling transaction list and the timeline information of each scheduling transaction are provided to the dispatcher to predict and recommend the next disposal plan.

[0058] Specifically, the step S2 includes:

[0059] S21, using the natural language processing and semantic understanding capabilities of the generative big model to analyze the event data and extract key features of the event data;

[0060] S22: judging whether there is any correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the key feature and the historical scheduling data.

[0061] Exemplarily, the embodiment of the present invention introduces generative big model technology, which can simultaneously obtain structured and unstructured data information and perform correlation reasoning analysis. With the help of big model technology, unstructured data information is reasoned and analyzed. The dispatch transaction management method described in the embodiment of the present invention does not limit the source, format type and receiving method of the input data information, and is more in line with the actual needs of dispatchers facing various complex situations and comprehensively collecting information. For example, data in different formats (such as text, audio, and video) are preprocessed and converted into a unified structured format. Then, natural language processing technology is used to perform semantic analysis on unstructured data to extract key information and contextual relationships. In addition, machine learning algorithms are used to automatically identify and classify data, thereby supporting real-time analysis and decision-making, and meeting the comprehensive information needs of dispatchers in complex environments. Finally, after multi-level data fusion and visualization, dispatchers can quickly obtain key insights in order to make more accurate judgments and responses.

[0062] Specifically, the step S22 includes:

[0063] Generating a vector representation of the event according to the key features to capture semantic information of the event;

[0064] Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information;

[0065] The relevance of the event to all scheduled transactions is determined based on the similarity.

[0066] For example, firstly, event data (such as fault reports, equipment status, dispatch records, etc.) from different sources are collected and integrated into a unified platform. Through the large model technology, the collected event data is feature extracted to generate a vector representation of the event and capture its potential semantic information. For example, the equipment fault information is converted into a vector containing features such as fault type, occurrence time, and impact range. The inference analysis algorithm is used to calculate the correlation between different events and dispatching tasks. The correlation between events and dispatching tasks is evaluated by similarity (such as cosine similarity). After completing the correlation analysis, highly correlated events and dispatching tasks are automatically identified. Taking equipment failure as an example, if the system finds that a certain fault event is highly correlated with the current dispatching task (such as equipment maintenance), it will automatically update the dispatching record and mark the event as requiring special attention. The dispatcher can make real-time decisions based on the updated information, and the system will also collect feedback data to optimize the future correlation analysis model. For example, suppose an event report about "transformer failure" is received, and there is a record of "performing transformer maintenance" in the dispatching task. Through feature extraction and correlation analysis, it was found that the two events were very similar, so the transformer fault event was automatically associated with the maintenance task, the dispatch record was updated, and the dispatcher was reminded to give priority to the fault. This automatic update mechanism greatly improves dispatch efficiency and response speed.

[0067] Further, after updating the state of the target scheduling transaction, the method further includes:

[0068] S5, if the updated target scheduling transaction has ended, deleting the target scheduling transaction from the scheduling transaction list;

[0069] S6: If the updated target scheduling transaction has not been completed, predict and recommend a disposal plan for the target scheduling transaction.

[0070] Exemplarily, the dispatch affairs management method described in the embodiment of the present invention can be implemented by a command and dispatch system, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the execution structure of a command and dispatch system provided by an embodiment of the present invention. The command and dispatch system records a dispatch transaction list, which contains information about currently ongoing dispatch transactions. When a new dispatch transaction is created, the system inserts it into the list; when a dispatch transaction ends, the system deletes it from the list. When an event occurs or a dispatch task is executed, if the system determines that it is related to and attributed to a current dispatch transaction, the status of the dispatch transaction is updated; otherwise, the system will create a new dispatch transaction based on this event or task and insert it into the dispatch transaction list. The workflow of the command and dispatch system is as follows:

[0071] (1) The command and dispatch system obtains data information from internal and external systems;

[0072] (2) The system analyzes its relevance to the transactions in the currently scheduled transaction list;

[0073] (3) When the system determines that there is no related transaction, it continues to determine whether a new scheduling transaction needs to be created. If so, it creates the scheduling transaction and inserts it into the list, predicts and recommends the next disposal plan. Regardless of whether a new transaction needs to be created, it goes to step (1);

[0074] (4) When the system determines that there is a related transaction, the status of the transaction is updated;

[0075] (5) The system determines whether the transaction is completed. If so, the transaction is deleted from the list and the process goes to step (1).

[0076] (6) When the system determines that the transaction is not completed, it predicts and recommends the next disposal plan and goes to step (1).

[0077] It is understandable that the command and dispatch system uses generative big model technology to perform correlation reasoning analysis on various structured and unstructured data information input. The principle is to use the natural language processing and semantic understanding capabilities of the big model to conduct a comprehensive analysis of different types of data such as text, voice, and pictures received during the dispatch process. By extracting key features and combining historical dispatch transaction data, the system can determine whether the current information is associated with existing dispatch transactions. The command and dispatch system provides dispatchers with a list of dispatch transactions and timeline information of each dispatch transaction, and predicts and recommends the next disposal plan for dispatchers based on the reasoning technology of the big model, assisting dispatchers to process multiple dispatch transactions in parallel more intuitively and timely. The principle of big model prediction and recommendation of disposal plans is based on comprehensive processing and deep learning of multi-dimensional data. First, the big model will integrate real-time data of the internal system, historical dispatch records, external environmental factors, etc. to fully understand the context of the current dispatch transaction. Through natural language processing technology, the model can extract key details in the transaction, and use machine learning technology to learn historical successful disposal patterns and infer the evolution trend of events. Based on this information, the big model predicts possible future situations and generates multiple disposal plans. It uses optimization algorithms to evaluate the potential effects of each plan and help dispatchers make the best decision. At the same time, the model will continuously improve itself based on actual execution feedback to ensure that future recommendations are more accurate and efficient.

[0078] Specifically, if the updated target scheduling transaction is not completed, predicting and recommending a disposal plan for the target scheduling transaction includes:

[0079] If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data;

[0080] Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event;

[0081] Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs;

[0082] The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

[0083] Exemplarily, first integrate historical experience data (such as past dispatch cases, successful and failed disposal plans) with real-time on-site situation data (such as equipment status, environmental conditions, personnel distribution, etc.). Then, use large model technology to extract features from the data and build a relationship model between event features and disposal plans. The system combines historical data and on-site situations through reasoning analysis technology to identify potential disposal plans and learn the patterns of historical successful cases to derive effective response strategies. Based on the analysis results, the system generates several recommended plans and provides a success probability assessment for each plan. The dispatcher can choose the most appropriate plan based on the recommendation list. After implementation, the system monitors the results in real time and collects feedback information to continuously optimize the model and improve the accuracy of future predictions and recommendations. For example, when an "equipment overload" occurs on site, the system analyzes historical data and finds that successful treatment plans include "reducing the load" or "increasing spare equipment", and recommends the "reducing the load" plan based on the on-site status and historical success rate, with a success probability of 85%. The dispatcher does this and feeds back the results to the system after implementation to further improve the accuracy of future recommendations. For example, if Figure 4 As shown, Figure 4 This is a schematic diagram of the transaction dispatch execution process of a command and dispatch system provided by an embodiment of the present invention. The dispatcher discusses with the other party to determine the specific process details of an event when making a phone call. When the dispatcher ends the call, the command and dispatch system based on the big model analyzes the voice content of the dispatch call in the background, infers and determines that the call is related to a previous accident handling process, automatically updates the status of the accident handling transaction, and predicts and recommends the next handling plan. The dispatcher views the transaction status timeline and refers to the recommended handling plan.

[0084] The embodiment of the present invention applies large model technology, and through reasoning and analysis technology of historical experience data and on-site situations, it can predict and recommend the next disposal plan for dispatchers, and can deal with more complex situations that have no set plans in the process plan library.

[0085] The embodiment of the present invention discloses a method for managing scheduling affairs, which obtains real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling affairs and currently occurring event data; according to the historical scheduling data and the event data, the correlation between the currently occurring event and all scheduling affairs in the scheduling affairs list is analyzed; if there is no correlation between the event and all scheduling affairs, a new target scheduling affair is created in the scheduling affairs list, and the status of the target scheduling affair is updated; if the event has the strongest correlation with a certain target scheduling affair, the event is attributed to the target scheduling affair, and the status of the target scheduling affair is updated. The method can analyze the data information that has just occurred, combine the historical and currently ongoing scheduling affairs, automatically evaluate the correlation between the information and the scheduling affairs, and update the status of the scheduling affairs, thereby assisting the dispatcher in handling the scheduling affairs, so that the dispatcher can quickly obtain key insights and reduce the burden, so as to make more accurate judgments and responses.

[0086] See also Figure 5 , Figure 5 1 is a schematic diagram of a scheduling affairs management system 10 provided in an embodiment of the present invention. The scheduling affairs management system 10 includes:

[0087] The scheduling data acquisition module 11 is used to acquire real-time data information and historical scheduling data; the real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data;

[0088] A scheduling data analysis module 12, configured to analyze the correlation between a current event and all scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data;

[0089] A scheduling transaction creation module 13, configured to create a new target scheduling transaction in the scheduling transaction list and update the state of the target scheduling transaction if there is no correlation between the event and all scheduling transactions;

[0090] The scheduling transaction updating module 14 is used for attributing the event to a target scheduling transaction and updating the state of the target scheduling transaction if the event has the strongest correlation with the target scheduling transaction.

[0091] Specifically, the scheduling data analysis module 12 is used to:

[0092] Utilizing the natural language processing and semantic understanding capabilities of the generative big model, the event data is analyzed to extract key features of the event data;

[0093] According to the key features and the historical scheduling data, it is determined whether there is any correlation between the currently occurring event and all the scheduling transactions in the scheduling transaction list.

[0094] Specifically, judging whether there is a correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the key feature and the historical scheduling data includes:

[0095] Generating a vector representation of the event according to the key features to capture semantic information of the event;

[0096] Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information;

[0097] The relevance of the event to all scheduled transactions is determined based on the similarity.

[0098] Furthermore, the system also includes:

[0099] A scheduling transaction deletion module, configured to delete the target scheduling transaction from the scheduling transaction list if the updated target scheduling transaction has ended;

[0100] The disposal plan recommendation module is used to predict and recommend a disposal plan for the target scheduling transaction if the updated target scheduling transaction has not been completed.

[0101] Specifically, the treatment plan recommendation module is used to:

[0102] If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data;

[0103] Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event;

[0104] Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs;

[0105] The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

[0106] A scheduling affairs management system 10 provided in an embodiment of the present invention can implement all processes of the scheduling affairs management method of the above-mentioned embodiment. The functions of each module in the system and the technical effects achieved are respectively the same as the functions and technical effects achieved by the scheduling affairs management method of the above-mentioned embodiment, and will not be repeated here.

[0107] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A scheduling affairs management method, characterized in that: include: Obtain real-time data information and historical scheduling data; The real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data; Analyzing the relevance of the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data; If there is no correlation between the event and all scheduling transactions, a new target scheduling transaction is created in the scheduling transaction list, and the state of the target scheduling transaction is updated; If the event has the strongest correlation with a certain target scheduling transaction, the event is attributed to the target scheduling transaction, and the state of the target scheduling transaction is updated.

2. The scheduling affairs management method according to claim 1, characterized in that: The step of analyzing the correlation between the current event and all the scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data includes: Utilizing the natural language processing and semantic understanding capabilities of the generative big model, the event data is analyzed to extract key features of the event data; According to the key features and the historical scheduling data, it is determined whether there is any correlation between the currently occurring event and all the scheduling transactions in the scheduling transaction list.

3. The scheduling affairs management method according to claim 2, characterized in that: The determining, based on the key features and the historical scheduling data, whether there is a correlation between the current event and all the scheduling transactions in the scheduling transaction list includes: Generating a vector representation of the event according to the key features to capture semantic information of the event; Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information; The relevance of the event to all scheduled transactions is determined based on the similarity.

4. The scheduling affairs management method according to claim 1, characterized in that: After updating the state of the target scheduling transaction, the method further includes: If the updated target scheduling transaction has ended, deleting the target scheduling transaction from the scheduling transaction list; If the updated target scheduling transaction is not completed, a disposal plan for the target scheduling transaction is predicted and recommended.

5. The scheduling affairs management method according to claim 4, characterized in that: If the updated target scheduling transaction is not completed, predicting and recommending a disposal plan for the target scheduling transaction includes: If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data; Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event; Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs; The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

6. A scheduling affairs management system, characterized in that: include: Scheduling data acquisition module, used to obtain real-time data information and historical scheduling data; The real-time data information includes a list of currently ongoing scheduling transactions and currently occurring event data; A scheduling data analysis module, used for analyzing the correlation between the current event and all scheduling transactions in the scheduling transaction list according to the historical scheduling data and the event data; A scheduling transaction creation module, used for creating a new target scheduling transaction in the scheduling transaction list and updating the state of the target scheduling transaction if there is no correlation between the event and all scheduling transactions; The scheduling transaction updating module is used for attributing the event to a target scheduling transaction and updating the state of the target scheduling transaction if the event has the strongest correlation with the target scheduling transaction.

7. The dispatch affairs management system according to claim 6, characterized in that: The scheduling data analysis module is used to: Utilizing the natural language processing and semantic understanding capabilities of the generative big model, the event data is analyzed to extract key features of the event data; According to the key features and the historical scheduling data, it is determined whether there is any correlation between the currently occurring event and all the scheduling transactions in the scheduling transaction list.

8. The dispatch affairs management system according to claim 7, characterized in that: The determining, based on the key features and the historical scheduling data, whether there is a correlation between the current event and all the scheduling transactions in the scheduling transaction list includes: Generating a vector representation of the event according to the key features to capture semantic information of the event; Calculate the similarity between the current event and all scheduled transactions in the scheduled transaction list according to the semantic information; The relevance of the event to all scheduled transactions is determined based on the similarity.

9. The dispatch affairs management system according to claim 6, characterized in that: The system further comprises: A scheduling transaction deletion module, configured to delete the target scheduling transaction from the scheduling transaction list if the updated target scheduling transaction has ended; The disposal plan recommendation module is used to predict and recommend a disposal plan for the target scheduling transaction if the updated target scheduling transaction has not been completed.

10. The dispatching affairs management system according to claim 9, characterized in that: The treatment plan recommendation module is used to: If the updated target scheduling transaction is not completed, using the generative big model to understand the context of the updated target scheduling transaction according to the historical scheduling data and the event data; Extract the detailed features of the updated target scheduling transaction and use machine learning technology to infer the evolution trend of the event; Predicting according to the evolution trend and generating multiple disposal plans for the target scheduling affairs; The potential effects of all treatment plans are evaluated, and a treatment plan for the target scheduling transaction is recommended based on the potential effects.

Images