Combustion furnace operation scheduling record processing method and system based on artificial influence weather

Abstract

The invention discloses a combustion furnace operation scheduling record processing method and system based on artificial influence weather, and belongs to the technical field of data analysis. The invention aims to realize intelligent upgrading of a scheduling strategy by constructing an efficiency balance optimization mapping method based on combustion furnace operation records and operation disturbance element vectors. In detail, the method not only focuses on improving the formulating efficiency and accuracy of the scheduling strategy, but also focuses on solving the actual problems of uneven resource allocation, response lag and the like, so that the high efficiency and stability of the operation of the combustion furnace can be still kept under the complicated and changeable meteorological conditions, and the development of the artificial influence weather technology is further promoted to a new height.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular relates to a combustion furnace operation scheduling record processing method and system based on artificial weather modification. Background Art

[0002] In the field of artificial weather modification, burner operation, as one of the key technical means, plays an irreplaceable role in regulating local climate and promoting precipitation. However, the traditional burner operation scheduling method often relies on empirical judgment and simple model prediction, which is difficult to fully consider various disturbance factors in actual operations, such as weather changes and equipment status fluctuations, resulting in inaccurate scheduling of the amount of ammunition used in the operation and inefficient resource allocation, which seriously affects the effect and cost-effectiveness of artificial weather modification operations. Summary of the invention

[0003] The present invention provides a combustion furnace operation scheduling record processing method and system based on artificial weather modification, which can solve or partially solve the technical problems involved in the above-mentioned background technology.

[0004] The present invention provides a combustion furnace operation scheduling record processing method based on artificial weather modification, which is applied to an operation scheduling processing system. The method comprises:

[0005] Using the acquired combustion furnace operation records and operation disturbance element vectors to perform cyclic efficiency balance optimization mapping, a semantic vector of the scheduling strategy that has been adjusted is obtained; and a target scheduling strategy is output based on the semantic vector of the scheduling strategy that has been adjusted;

[0006] Based on the target scheduling strategy, the combustion furnace operation intelligent scheduling model is assigned to the scheduling server in the target area to instruct the scheduling server to perform the combustion furnace operation ammunition quantity scheduling processing based on the combustion furnace operation intelligent scheduling model.

[0007] In one implementation, the obtained combustion furnace operation record and operation disturbance element vector are used to perform cyclic efficiency balance optimization mapping to obtain a semantic vector of a scheduling strategy that has been adjusted; and a target scheduling strategy is output based on the semantic vector of the scheduling strategy that has been adjusted, including:

[0008] Obtaining a combustion furnace operation record for constructing a target scheduling strategy, and determining, based on the combustion furnace operation record, a weather monitoring state vector representing x operation weather monitoring events in the target scheduling strategy, and a weather impact change vector of each operation impact label of y operation weather monitoring events, where x is a positive integer and y is a positive integer not greater than x;

[0009] Obtaining a job disturbance element vector, and using the job disturbance element vector as a multi-level derived scheduling execution vector obtained by subjecting the scheduling strategy semantic vector of the target scheduling strategy to a disturbance addition process of R cycles, where R is a positive integer greater than 1;

[0010] The multi-level derivative scheduling execution vector is subjected to performance balancing optimization mapping of the performance balancing process of R cycles to obtain the performance balancing decision vector of the R-th performance balancing process; wherein, for the r-th performance balancing process in the performance balancing process of R cycles, when r=1, the multi-level derivative scheduling execution vector is used as the to-be-processed information of the r-th performance balancing process, when r is greater than 1 and not greater than R, the performance balancing decision vector of the r-1-th performance balancing process is used as the to-be-processed information of the r-th performance balancing process, and when r=R, the performance balancing decision vector of the r-th performance balancing process is the performance balancing decision vector of the R-th performance balancing process;

[0011] In the rth performance balancing process, H performance balancing optimization mapping branches are looped, wherein, for the hth performance balancing optimization mapping branch among the H performance balancing optimization mapping branches, when h=1, the to-be-processed information of the rth performance balancing process is used as the to-be-processed information of the hth performance balancing optimization mapping branch, and when h is greater than 1 and not greater than H, the performance balancing decision vector of the h-1th performance balancing optimization mapping branch is used as at least part of the to-be-processed information of the hth performance balancing optimization mapping branch, and when h=H, the performance balancing decision vector of the hth performance balancing optimization mapping branch is the performance balancing decision vector of the rth performance balancing process;

[0012] In the hth performance balance optimization mapping branch, according to at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events, the performance balance optimization mapping is performed to obtain a first performance balance mapping vector; according to at least part of the information to be processed and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events, the performance balance optimization mapping is performed to obtain a second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events; through the first performance balance mapping vector and the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, the performance balance decision vector of the hth performance balance optimization mapping branch is obtained;

[0013] The efficiency balance decision vector of the Rth efficiency balance process is used as a semantic vector of a scheduling strategy that has completed adjustment, text strategy generation is performed on the semantic vector of the scheduling strategy that has completed adjustment, and a target scheduling strategy is output.

[0014] In one implementation, the obtaining of the performance balance decision vector of the hth performance balance optimization mapping branch through the first performance balance mapping vector and the second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events includes:

[0015] Obtain a list of local feature enhancement coefficients corresponding to the weather monitoring state vectors of the x operational weather monitoring events;

[0016] For each operation impact label of the operation impact labels of the y operation weather monitoring events, determine the operation weather monitoring event matched by the operation impact label of the operation weather monitoring event, and perform feature enhancement processing on the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event through the local feature enhancement coefficient list corresponding to the weather monitoring state vector of the matched operation weather monitoring event, so as to obtain the third performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event;

[0017] The first performance balance mapping vector and the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events are integrated to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

[0018] In one implementation, the first performance balance mapping vector and the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events are integrated to obtain the performance balance decision vector of the hth performance balance optimization mapping branch, including:

[0019] splicing the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events respectively, to obtain the weather impact trend mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events;

[0020] The first performance balance mapping vector and the weather impact trend mapping vector corresponding to the operation impact labels of the y operation weather monitoring events are spliced ​​to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

[0021] In one implementation, the hth performance balance optimization mapping branch performs performance balance optimization mapping based on at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events to obtain a first performance balance mapping vector, and performs performance balance optimization mapping based on at least part of the information to be processed and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events to obtain a second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, including:

[0022] In the hth performance balance optimization mapping branch, based on the feature pooling rule corresponding to the hth performance balance optimization mapping branch, a feature pooling operation is performed on the at least part of the information to be processed to obtain a performance balance pooling vector;

[0023] Performing knowledge collision processing on vector members in the performance balance pooling vector to obtain a performance balance collision vector;

[0024] According to the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events, a performance balance optimization mapping is performed to obtain a first performance balance mapping vector;

[0025] According to the performance balance collision vector and the weather impact change vectors of the operation impact labels of the y operation weather monitoring events, performance balance optimization mapping is performed respectively to obtain second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events.

[0026] In one implementation, the performance balance optimization mapping is performed based on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector, which includes:

[0027] Based on the linkage feature focusing rule, knowledge collision processing is performed on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector.

[0028] In one implementation, the linkage feature focusing rule is based on which the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events are subjected to knowledge collision processing to obtain a first performance balance mapping vector, which includes:

[0029] Based on the linkage feature focusing rule, the performance balance collision vector and the weather monitoring state vector of each operation weather monitoring event in the weather monitoring state vectors of the x operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of each operation weather monitoring event;

[0030] The performance balance mapping vectors corresponding to the weather monitoring state vectors of the x operational weather monitoring events are concatenated to obtain a first performance balance mapping vector.

[0031] In one implementation, the linkage feature focusing rule is based on which the performance balance collision vector and the weather monitoring state vector of each of the x weather monitoring events are subjected to knowledge collision processing, and the performance balance mapping vector corresponding to the weather monitoring state vector of each of the weather monitoring events is obtained, including:

[0032] For each weather monitoring state vector of the x weather monitoring events, the weather monitoring state vector of the weather monitoring event is processed by a first deep residual network based on a linkage feature focusing rule to obtain a first performance situation feature and a first weather impact situation feature, and the performance balance collision vector is processed to obtain a first balance situation feature;

[0033] Determine a feature enhancement coefficient according to the first performance situation feature and the first balance situation feature, and obtain a list of local feature enhancement coefficients corresponding to the weather monitoring state vector for the operational weather monitoring event;

[0034] By utilizing the local feature enhancement coefficient list corresponding to the weather monitoring state vector of the operational weather monitoring event, the first weather impact situation feature is feature enhanced to obtain the efficiency balance mapping vector corresponding to the weather monitoring state vector of the operational weather monitoring event.

[0035] In one implementation, the performance balance optimization mapping is performed based on the performance balance collision vector and the weather impact change vector of each of the operation impact labels of the y operation weather monitoring events to obtain the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, including: based on the linkage feature focusing rule, the performance balance collision vector and the weather impact change vector of each of the operation impact labels of the y operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events.

[0036] In some independent embodiments, the linkage feature focusing rule is based on which the performance balance collision vector and the weather impact change vectors of the operation impact labels of the y operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events, including:

[0037] For the weather impact change vector of each operation impact label of the operation weather monitoring event in the weather impact change vector of each operation impact label of the y operation weather monitoring events, the weather impact change vector of the operation impact label of the operation weather monitoring event is processed by a second deep residual network based on a linkage feature focusing rule to obtain a second performance situation feature and a second weather impact situation feature, and the performance balance collision vector is processed to obtain a second balance situation feature;

[0038] Determine the feature enhancement coefficient according to the second performance situation feature and the second balance situation feature, and obtain a list of local feature enhancement coefficients corresponding to the weather impact change vector of the operation impact label for the operation weather monitoring event;

[0039] By utilizing the list of local feature enhancement coefficients corresponding to the weather impact change vector of the operation impact label of the operation weather monitoring event, the second weather impact situation feature is feature enhanced to obtain the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event.

[0040] In some independent embodiments, the weather monitoring state vectors representing the x operation weather monitoring events in the target scheduling strategy and the weather impact change vectors of the operation impact labels of the y operation weather monitoring events are determined based on the combustion furnace operation record, including:

[0041] Vector extraction is performed on the monitoring event logs that record the x operation weather monitoring events in the target scheduling strategy in the combustion furnace operation record to obtain the weather monitoring state vector that records the x operation weather monitoring events in the target scheduling strategy, and vector extraction is performed on the artificial weather influence logs that record the operation impact labels of the y operation weather monitoring events in the target scheduling strategy in the combustion furnace operation record to obtain the weather impact change vectors of the operation impact labels of the y operation weather monitoring events.

[0042] The present invention provides a job scheduling processing system, comprising at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the above method.

[0043] The present invention provides a readable storage medium, on which a program or instruction is stored, and the program or instruction implements the steps of the above method when executed by a processor.

[0044] The present invention aims to achieve intelligent upgrading of scheduling strategies by constructing an efficiency balance optimization mapping method based on burner operation records and operation disturbance element vectors. In detail, the present invention not only focuses on improving the efficiency and accuracy of scheduling strategy formulation, but also focuses on solving practical problems such as uneven resource allocation and response lag, so as to maintain the efficiency and stability of burner operations under complex and changeable meteorological conditions, thereby promoting the development of artificial weather modification technology to a new level. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The present invention provides a flow chart of a combustion furnace operation scheduling record processing method based on artificial weather modification.

[0046] Figure 2 This is a structural schematic diagram of a job scheduling processing system provided by the present invention. DETAILED DESCRIPTION

[0047] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are 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.

[0048] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, in the present invention, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0049] Figure 1 A combustion furnace operation scheduling record processing method based on artificial weather modification is shown, which is applied to an operation scheduling processing system. The method includes the following steps 110 to 120.

[0050] Step 110, the job scheduling processing system uses the acquired combustion furnace job records and job disturbance element vectors to perform cyclical performance balance optimization mapping to obtain a semantic vector of a scheduling strategy that has been adjusted; and outputs a target scheduling strategy based on the semantic vector of the scheduling strategy that has been adjusted.

[0051] The method uses the acquired combustion furnace operation record and operation disturbance element vector to perform cyclic efficiency balance optimization mapping to obtain a semantic vector of a scheduling strategy that has been adjusted; and outputs a target scheduling strategy based on the semantic vector of the scheduling strategy that has been adjusted, including:

[0052] (1) Obtaining a combustion furnace operation record for constructing a target scheduling strategy, and determining, based on the combustion furnace operation record, a weather monitoring state vector representing x operation weather monitoring events in the target scheduling strategy, and a weather impact change vector of each operation impact label of y operation weather monitoring events, where x is a positive integer and y is a positive integer not greater than x;

[0053] (2) obtaining a job disturbance element vector, and using the job disturbance element vector as a multi-level derived scheduling execution vector obtained by subjecting the scheduling strategy semantic vector of the target scheduling strategy to a disturbance addition process of R cycles, where R is a positive integer greater than 1;

[0054] (3) performing performance balancing optimization mapping of the performance balancing process of R cycles on the multi-level derivative scheduling execution vector to obtain the performance balancing decision vector of the Rth performance balancing process; wherein, for the rth performance balancing process in the R cycles of the performance balancing process, when r=1, the multi-level derivative scheduling execution vector is used as the to-be-processed information of the rth performance balancing process; when r is greater than 1 and not greater than R, the performance balancing decision vector of the r-1th performance balancing process is used as the to-be-processed information of the rth performance balancing process; when r=R, the performance balancing decision vector of the rth performance balancing process is the performance balancing decision vector of the Rth performance balancing process;

[0055] (4) performing a loop processing of H performance balance optimization mapping branches in the rth performance balance process, wherein, for the hth performance balance optimization mapping branch among the H performance balance optimization mapping branches, when h=1, the to-be-processed information of the rth performance balance process is used as the to-be-processed information of the hth performance balance optimization mapping branch; when h is greater than 1 and not greater than H, the performance balance decision vector of the h-1th performance balance optimization mapping branch is used as at least part of the to-be-processed information of the hth performance balance optimization mapping branch; when h=H, the performance balance decision vector of the hth performance balance optimization mapping branch is the performance balance decision vector of the rth performance balance process;

[0056] (5) In the hth performance balance optimization mapping branch, based on at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events, a performance balance optimization mapping is performed to obtain a first performance balance mapping vector; based on at least part of the information to be processed and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events, a performance balance optimization mapping is performed to obtain a second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events; and through the first performance balance mapping vector and the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, a performance balance decision vector of the hth performance balance optimization mapping branch is obtained;

[0057] (6) The efficiency balance decision vector of the Rth efficiency balance process is used as the semantic vector of the scheduling strategy for completing the adjustment, a text strategy is generated for the semantic vector of the scheduling strategy for completing the adjustment, and a target scheduling strategy is output.

[0058] Step 120: The job scheduling processing system assigns the combustion furnace job intelligent scheduling model to the scheduling server in the target area based on the target scheduling strategy to instruct the scheduling server to perform the combustion furnace job ammunition scheduling processing based on the combustion furnace job intelligent scheduling model.

[0059] In the present invention, the job scheduling processing system is responsible for formulating a scientific scheduling strategy based on historical combustion furnace operation records, real-time weather monitoring data, and operation disturbance elements. The following will introduce in detail how the job scheduling processing system uses these data and information to perform cyclic performance balance optimization mapping and finally output the target scheduling strategy in combination with steps 110 to 120.

[0060] (I) Obtaining the combustion furnace operation record and weather monitoring state vector

[0061] The operation scheduling processing system first obtains the combustion furnace operation records used to construct the target scheduling strategy. The combustion furnace operation records include information such as the time, location, catalyst type, spreading amount, and operation effect of each operation.

[0062] Based on these furnace operation records, the operation scheduling processing system further determines the weather monitoring state vector that represents the x operation weather monitoring events in the target scheduling strategy. x can be selected as the most recent 10 operations, and the weather monitoring state vector includes key parameters such as cloud thickness, supercooled water content, and updraft velocity.

[0063] It is also important to note that the burner operation record not only covers traditional operation process data, but also includes detailed operation background condition data extracted through advanced Fengyun-4B satellite products and radar monitoring products. These data cover the cloud distribution, thickness, height, temperature, humidity and other microphysical characteristics in the operation area, as well as dynamic meteorological elements such as wind direction and wind speed. With its high resolution and rich spectral channels, the Fengyun-4B satellite provides comprehensive atmospheric information for burner operations, making the formulation of operation strategies more scientific and accurate. At the same time, radar monitoring products capture the water vapor distribution, the development dynamics of precipitation systems and possible convection activities above the operation area in real time, providing immediate feedback and guidance for operations. These high-value operation background condition data, combined with traditional operation process data, together constitute the rich content of the burner operation record, providing a solid foundation for subsequent performance balance optimization mapping and scheduling strategy formulation.

[0064] At the same time, the job scheduling processing system also determines the weather impact change vector of each job impact label of y job weather monitoring events. y is a positive integer not greater than x, indicating that among x jobs, y jobs have a significant impact on the weather. The job impact labels include rain enhancement effect, job duration, catalyst utilization rate, etc., and the weather impact change vector describes the changes of these labels before and after the job.

[0065] (II) Obtaining the operation disturbance element vector and performing disturbance addition process

[0066] The job scheduling processing system obtains the job disturbance element vectors, which may include uncontrollable factors such as equipment failure, personnel changes, sudden weather changes, etc. The job scheduling processing system uses these disturbance element vectors as the scheduling strategy semantic vectors of the target scheduling strategy, and obtains a multi-level derivative scheduling execution vector after R cycles of disturbance addition processes.

[0067] R is a positive integer greater than 1, which represents the number of cycles of the disturbance and addition process. In each cycle, the scheduling strategy will be adjusted and optimized according to the disturbance element to ensure that the scheduling strategy can adapt to various changes in actual operations.

[0068] (III) Perform performance balance optimization mapping

[0069] Next, the job scheduling processing system performs an R-cycle performance balance optimization mapping of the multi-level derivative scheduling execution vectors. The purpose of this step is to further adjust and optimize the scheduling strategy to ensure its performance and stability under various weather conditions and job disturbances.

[0070] For the rth performance balancing process in the R-cycle performance balancing process (r is an integer from 1 to R), the job scheduling processing system performs processing according to the following steps:

[0071] 1) When r=1, the multi-level derivative scheduling execution vector is used as the to-be-processed information of the rth performance balancing process;

[0072] 2) When r is greater than 1 and not greater than R, the performance balance decision vector of the r-1th performance balance process is used as the information to be processed for the rth performance balance process;

[0073] 3) When r=R, the performance balance decision vector of the rth performance balance process is the performance balance decision vector of the Rth performance balance process.

[0074] In each performance balancing process, the job scheduling processing system will perform a loop processing of H performance balancing optimization mapping branches (H is a positive integer). For the hth performance balancing optimization mapping branch (h is an integer from 1 to H) among the H performance balancing optimization mapping branches, the job scheduling processing system performs processing according to the following steps:

[0075] 1) When h=1, the to-be-processed information of the rth performance balance process is used as the to-be-processed information of the hth performance balance optimization mapping branch;

[0076] 2) when h is greater than 1 and not greater than H, the performance balance decision vector of the h-1th performance balance optimization mapping branch is used as at least part of the to-be-processed information of the hth performance balance optimization mapping branch;

[0077] 3) When h=H, the performance balance decision vector of the hth performance balance optimization mapping branch is the performance balance decision vector of the rth performance balance process.

[0078] In each performance balance optimization mapping branch, the job scheduling processing system will perform performance balance optimization mapping based on at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events to obtain a first performance balance mapping vector. At the same time, the job scheduling processing system will also perform performance balance optimization mapping based on at least part of the information to be processed and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events to obtain a second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events.

[0079] Finally, the job scheduling processing system obtains the performance balance decision vector of the hth performance balance optimization mapping branch through the first performance balance mapping vector and the second performance balance mapping vectors corresponding to the job impact labels of the y job weather monitoring events.

[0080] (IV) Output target scheduling strategy and assign intelligent scheduling model

[0081] After the performance balance optimization mapping of the performance balance process of R cycles, the job scheduling processing system obtains the performance balance decision vector of the Rth performance balance process, which is the semantic vector of the scheduling strategy that completes the adjustment.

[0082] The job scheduling processing system generates a text strategy for the semantic vector of the adjusted scheduling strategy and outputs a target scheduling strategy, which describes in detail how to schedule and manage the combustion furnace operation under different weather conditions and job disturbances.

[0083] Finally, the job scheduling system assigns the intelligent scheduling model of the combustion furnace to the scheduling server in the target area based on the target scheduling strategy. The scheduling server performs the scheduling of the amount of ammunition used in the combustion furnace according to this intelligent scheduling model to ensure the effectiveness and safety of the operation.

[0084] Based on the above content, the following is an exemplary introduction to relevant technical terms.

[0085] Operational weather monitoring events refer to events or time points when specific weather conditions are monitored in real time during meteorological operations. These monitoring data are used to evaluate operating conditions and formulate scheduling strategies. For example, before a certain burner operation, the meteorological department will monitor key weather parameters such as cloud thickness, supercooled water content, wind direction and speed in the operating area in real time. These monitoring events provide important data support for operation scheduling.

[0086] The weather monitoring state vector is a multi-dimensional vector that is used to comprehensively characterize the weather conditions during the operational weather monitoring event, including multiple key parameters such as cloud thickness, supercooled water content, and updraft velocity. For example, before the operation of the burner, the weather monitoring state vector may include specific values ​​such as cloud thickness of 500 meters, supercooled water content of 2 grams / cubic meter, and updraft velocity of 5 meters / second. These parameters together constitute the weather state during the operation.

[0087] Operation impact labels are used to describe the classification or labels of the specific impact of meteorological operations on the weather. These labels reflect different aspects of the operation effect. For example, in a burner operation, the operation impact labels may include rainfall enhancement effect, operation duration, catalyst utilization, etc. For example, the rainfall enhancement effect label is used to evaluate the increase in precipitation after the operation, and the operation duration label records the duration of the operation.

[0088] The weather impact change vector is used to describe the change in weather conditions before and after the operation of the operation impact label, reflecting the actual impact of the operation on the weather. For example, after the operation of the burner, the weather impact change vector may record the specific change values ​​before and after the operation corresponding to the rain enhancement effect label, such as the cloud thickness decreased by 100 meters and the precipitation increased by 5 mm.

[0089] The operation disturbance element vector is a vector containing multiple elements, which is used to represent the uncontrollable factors that affect the meteorological operation, which may disturb the smooth progress of the operation. For example, in the operation of the combustion furnace, the operation disturbance element vector may include uncontrollable factors such as equipment failure (such as catalyst spraying equipment failure), personnel changes (such as key operators taking leave), and sudden weather changes (such as sudden strong winds).

[0090] The scheduling strategy semantic vector is used to represent key information in the scheduling strategy, such as operation time, location, catalyst type, and spreading amount. This information exists in a semantic form, which is easy to understand and process. For example, in the scheduling strategy of the combustion furnace operation, the scheduling strategy semantic vector may contain specific information such as "the operation time is 10 am tomorrow", "the operation location is XX area", "use type A catalyst", and "the spreading amount is 500 kg".

[0091] The disturbance addition process is used to adjust and optimize the scheduling strategy according to the operation disturbance elements to ensure that the scheduling strategy can adapt to various changes in actual operations. For example, in the operation of a combustion furnace, if there is a sudden equipment failure, the disturbance addition process will be started to adjust the original scheduling strategy, such as changing the operation time, replacing the faulty equipment, etc., to ensure that the operation can proceed smoothly.

[0092] The multi-level derivative scheduling execution vector is a collection of multiple derivative scheduling strategies obtained after multiple disturbance and additional processes. These derivative scheduling strategies are possible execution plans formulated after considering various disturbance factors. For example, in the operation of a combustion furnace, considering disturbance factors such as equipment failure and personnel changes, after multiple disturbance and additional processes, multiple derivative scheduling execution vectors may be obtained, such as "use spare equipment, delay the operation time by one hour", "adjust personnel configuration, and keep the operation time unchanged", and other different execution plans.

[0093] The performance balance process is used to optimize the performance balance mapping of the derived scheduling execution vectors, and select the optimal scheduling strategy by comparing the performance and stability of different strategies. For example, in the operation of a combustion furnace, the performance balance process will evaluate and compare multiple derived scheduling execution vectors, such as considering factors such as rain enhancement effect, operation cost, and safety, and finally select the scheduling strategy with the best performance and high stability.

[0094] The efficiency balance optimization mapping is the process of optimizing the mapping of the derived scheduling execution vectors in the efficiency balance process. Through a specific algorithm or model, the derived strategy is mapped to a higher efficiency strategy space. For example, in the efficiency balance optimization mapping of the combustion furnace operation, a machine learning algorithm may be used to analyze and learn multiple derived scheduling execution vectors to find a strategy mapping relationship with better rain enhancement effect, lower operation cost and higher safety.

[0095] The efficiency balance decision vector is the optimized scheduling strategy vector obtained after the efficiency balance optimization mapping. This vector contains the best scheduling decision after considering the efficiency balance. For example, in the operation of the combustion furnace, the efficiency balance decision vector may contain specific decision information such as "the operation time is 10:30 tomorrow morning", "use type B catalyst", "the amount of seeding is 480 kg", etc. These decisions are the best choices after considering the efficiency factors such as rain enhancement effect, operation cost, and safety.

[0096] The first performance balance mapping vector is a mapping vector obtained based on the weather monitoring state vector in the performance balance optimization mapping process, which reflects the impact of weather conditions on the scheduling strategy. For example, in the operation of a combustion furnace, the first performance balance mapping vector may be an operation time vector optimized according to weather parameters such as cloud thickness and supercooled water content, such as "start the operation when the cloud thickness reaches 600 meters and the supercooled water content is 3 grams / cubic meter".

[0097] The second performance balance mapping vector is a mapping vector obtained based on the weather impact change vector of the operation impact label during the performance balance optimization mapping process. This vector reflects the impact of the operation effect on the scheduling strategy. For example, in the combustion furnace operation, the second performance balance mapping vector may be the catalyst dosage vector optimized according to the rain enhancement effect label, such as "In order to achieve the expected rain enhancement effect, the catalyst dosage needs to be adjusted to 520 kg."

[0098] The semantic vector of the adjusted scheduling strategy is the final optimized scheduling strategy vector obtained after all the effective balance processes. This vector represents the best scheduling decision after comprehensive consideration and optimization in a semantic form. For example, in the operation of a combustion furnace, the semantic vector of the adjusted scheduling strategy may contain specific and comprehensive decision information such as "the operation time is from 10:30 am to 2:00 pm tomorrow", "the operation location is XX area", "use type B catalyst", "the amount of seeding is 480 kg", and "the expected rainfall effect is to increase precipitation by 8 mm".

[0099] In summary, the present invention realizes a cyclical performance balance optimization mapping mechanism by innovatively utilizing the comprehensive analysis of the combustion furnace operation records and the operation disturbance element vectors, thereby accurately generating the semantic vector of the scheduling strategy that completes the adjustment. This not only greatly improves the efficiency and accuracy of the scheduling strategy formulation, but also ensures the optimal allocation of resources during the combustion furnace operation process. More importantly, based on the optimized scheduling strategy semantic vector, the present invention can output the target scheduling strategy in real time, and guide the scheduling server in the target area to deploy the combustion furnace operation intelligent scheduling model, thereby realizing the intelligent and refined scheduling of the combustion furnace operation ammunition consumption. This effectively solves the technical problems such as uneven resource allocation and response lag in the traditional scheduling method, significantly improves the overall efficiency and flexibility of the combustion furnace operation, and is of milestone significance for improving the efficiency and quality of artificial weather modification operations.

[0100] In some preferred embodiments, the obtaining of the performance balance decision vector of the hth performance balance optimization mapping branch through the first performance balance mapping vector and the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events includes: obtaining a list of local feature enhancement coefficients corresponding to each of the weather monitoring state vectors of the x operation weather monitoring events; determining the operation weather monitoring event that matches the operation impact label of the operation weather monitoring event for each operation weather monitoring event in the operation impact labels of the y operation weather monitoring events, and performing feature enhancement processing on the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event through the list of local feature enhancement coefficients corresponding to the weather monitoring state vector of the matched operation weather monitoring event to obtain a third performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event; integrating the first performance balance mapping vector and the third performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

[0101] It can be understood that the process of obtaining the performance balance decision vector of the hth performance balance optimization mapping branch through the first performance balance mapping vector and the second performance balance mapping vector corresponding to the operation impact labels of the y operation weather monitoring events involves multi-dimensional data processing and complex mapping relationship construction.

[0102] In detail, the first performance balance mapping vector is a reference vector formed based on global or initial conditions, which reflects the expected performance state of the job scheduling processing system in the absence of specific operation weather monitoring events; the second performance balance mapping vector is generated for each operation weather monitoring event according to its specific operation impact label, reflecting the potential impact of the event on the performance of the job scheduling processing system; and the performance balance decision vector is the final decision guidance formed by integrating the information of the first performance balance mapping vector and all the second performance balance mapping vectors, which aims to optimize the performance of the job scheduling processing system when facing various operation weather monitoring events.

[0103] In the specific implementation, it is necessary to first obtain the corresponding local feature enhancement coefficient list of the weather monitoring state vectors of the x operational weather monitoring events. This step is critical because the local feature enhancement coefficient list contains unique and important feature information for each operational weather monitoring event, which is crucial for subsequent feature enhancement processing. The local feature enhancement coefficient can be understood as a quantitative assessment of the importance of each dimensional feature in a specific weather monitoring state vector, which helps the model identify which features are more critical or sensitive to specific operational impact labels.

[0104] Next, for the operation impact label of each operation weather monitoring event in the operation impact labels of the y operation weather monitoring events, the system needs to determine the operation weather monitoring event that matches the operation impact label of the operation weather monitoring event. The matching process is completed based on the preset association rules between the operation impact label and the operation weather monitoring event or the mapping relationship automatically learned by the learning algorithm. Once the matching is completed, the local feature enhancement coefficient list corresponding to the weather monitoring state vector of the matched operation weather monitoring event can be used to perform feature enhancement processing on the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event. The purpose of feature enhancement processing is to highlight those features that are more important to a specific operation impact label, while possibly suppressing or adjusting other relatively less important features, so as to optimize the second performance balance mapping vector, so that it is more focused on the performance impact of the response to the specific operation weather monitoring event, and then obtain the third performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event.

[0105] Finally, the first performance balance mapping vector and the third performance balance mapping vector corresponding to the operation impact labels of the y operation weather monitoring events are integrated. This integration process is not a simple vector superposition, but needs to take into account the interaction and influence between different vectors, as well as their weight distribution in the overall performance balance decision. Through a sophisticated integration strategy, it can be ensured that the performance balance decision vector of the hth performance balance optimization mapping branch finally formed can not only reflect the global performance balance requirements, but also fully respond to the specific impact of each operation weather monitoring event, so as to achieve the purpose of optimizing the performance performance of the operation scheduling processing system when facing complex and changeable operation weather conditions.

[0106] In this way, by introducing the local feature enhancement coefficient list, the second performance balance mapping vector is finely adjusted, thereby improving the accuracy and pertinence of the performance balance decision vector. It not only takes into account the global performance balance requirements, but also takes into account the specific impact of each operational weather monitoring event on the performance of the job scheduling processing system. It is a comprehensive and sophisticated performance optimization strategy. In practical applications, this strategy can significantly improve the adaptability and robustness of the job scheduling processing system in the face of complex operational weather conditions, which is of great significance for improving the efficiency and quality of artificial weather modification operations.

[0107] In the next step, the first performance balance mapping vector and the third performance balance mapping vector corresponding to the operation impact labels of the y operation weather monitoring events are integrated to obtain the performance balance decision vector of the hth performance balance optimization mapping branch, including: splicing the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events to obtain the weather impact trend mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events; splicing the first performance balance mapping vector and the weather impact trend mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

[0108] It can be understood that this embodiment is dedicated to deeply integrating the first performance balance mapping vector with the third performance balance mapping vector corresponding to each of the job impact labels of the y job weather monitoring events, so as to determine the performance balance decision vector of the hth performance balance optimization mapping branch. This process contains two core splicing operations, which together cast the final generated performance balance decision vector, so that it can comprehensively and accurately map the performance optimization of the job scheduling processing system when facing different job weather monitoring events.

[0109] First, the job scheduling processing system involves splicing the third performance balance mapping vectors corresponding to the job impact labels of y job weather monitoring events. The essence of this step is that each job weather monitoring event carries its unique job impact label, and each job impact label corresponds to a third performance balance mapping vector that has been feature-enhanced. For example, there are y job weather monitoring events, and each event corresponds to an n-dimensional third performance balance mapping vector. In order to integrate these vectors, the system will connect them end to end in a given order to construct a new vector.

[0110] Taking three operational weather monitoring events as an example, their corresponding third performance balance mapping vectors are [1, 0.2, 0.3], [0.4, 0.5, 0.1] and [0.2, 0.1, 0.7]. In this scenario, the concatenation operation is to arrange these three vectors in order to form a new 9-dimensional vector, namely [1, 0.2, 0.3, 0.4, 0.5, 0.1, 0.2, 0.1, 0.7], which maps the potential impact of all operational weather monitoring events on the performance of the job scheduling processing system and outlines the trend of weather impact.

[0111] Subsequently, the system needs to concatenate the first performance balance mapping vector with the weather impact trend mapping vector obtained in the previous step. The first performance balance mapping vector is used to indicate the expected performance state of the job scheduling processing system without the influence of a specific job weather monitoring event. The dimension of this vector may be consistent with the dimension of the third performance balance mapping vector, or it may be very different, depending on the actual situation.

[0112] Furthermore, the first performance balance mapping vector and the weather impact trend mapping vector are arranged in a predetermined order to determine a larger vector. Continuing with the previous numerical example, the first performance balance mapping vector is [0.1, 0.2, 0.3]. Then, the splicing operation is to arrange this vector and the weather impact trend mapping vector [1, 0.2, 0.3, 0.4, 0.5, 0.1, 0.2, 0.1, 0.7] in order to form a 12-dimensional performance balance decision vector, namely [0.1, 0.2, 0.3, 1, 0.2, 0.3, 0.4, 0.5, 0.1, 0.2, 0.1, 0.7]. This performance balance decision vector not only contains the global performance balance requirements, but also encompasses the specific impact of all operational weather monitoring events on the performance of the job scheduling processing system, and can guide the job scheduling processing system in how to make the best performance adjustment when facing complex and changeable operational weather conditions. In this way, it is possible to determine which dimensions of features are crucial to the performance of the job scheduling processing system, and which dimensions of features are relatively less important. This is undoubtedly of great significance for guiding the job scheduling processing system to make accurate performance adjustments when facing different job weather monitoring events.

[0113] It can be seen that the technical solution of obtaining the weather impact trend mapping vector by splicing the third performance balance mapping vectors corresponding to the job impact labels of y job weather monitoring events, and then splicing the first performance balance mapping vector and the weather impact trend mapping vector to obtain the performance balance decision vector of the hth performance balance optimization mapping branch is a comprehensive, accurate and flexible performance optimization strategy. It can not only fully consider the global performance balance requirements and the impact of specific job weather monitoring events, but also provide accurate and effective performance adjustment guidance for the job scheduling processing system when facing complex and changeable job weather conditions.

[0114] In some other optional embodiments, the h-th performance balance optimization mapping branch performs performance balance optimization mapping based on at least part of the information to be processed and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector, and performs performance balance optimization mapping based on at least part of the information to be processed and the weather impact change vectors of each of the operational impact labels of the y operational weather monitoring events to obtain a second performance balance mapping vector corresponding to each of the operational impact labels of the y operational weather monitoring events, including: in the h-th performance balance optimization mapping branch, based on the feature pooling corresponding to the h-th performance balance optimization mapping branch Rule, perform feature pooling operation on at least part of the information to be processed to obtain a performance balance pooling vector; perform knowledge collision processing on the vector members in the performance balance pooling vector to obtain a performance balance collision vector; perform performance balance optimization mapping based on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector; perform performance balance optimization mapping based on the performance balance collision vector and the weather impact change vectors of each of the operational impact labels of the y operational weather monitoring events to obtain second performance balance mapping vectors corresponding to each of the operational impact labels of the y operational weather monitoring events.

[0115] In the actual application process, this embodiment deeply explores how to perform performance balance optimization mapping in the hth performance balance optimization mapping branch based on at least part of the information to be processed and the weather monitoring state vectors of x operational weather monitoring events, so as to obtain the first performance balance mapping vector. At the same time, this embodiment also elaborates on how to perform another round of performance balance optimization mapping based on the same at least part of the information to be processed and the weather impact change vectors of the respective operational impact labels of y operational weather monitoring events, so as to obtain the second performance balance mapping vectors corresponding to the respective operational impact labels of the y operational weather monitoring events.

[0116] First, in the hth performance balance optimization mapping branch, the job scheduling processing system will perform feature pooling operations on at least part of the information to be processed according to the feature pooling rules corresponding to the branch. The core of this step is to extract the most representative and critical features from a large amount of information to be processed to form a compact and efficient performance balance pooling vector. This pooling vector not only contains the core elements of the information to be processed, but is also optimized through specific pooling rules to ensure the accuracy and efficiency of subsequent processing.

[0117] Next, the job scheduling system will perform knowledge collision processing on the vector members in the performance balance pooling vector. The purpose of this step is to cross, fuse and collide the different features in the pooling vector through a specific algorithm or model, thereby stimulating new and more insightful feature information. This knowledge collision processing can dig out the inherent connections and potential laws between features, providing a richer and more comprehensive feature foundation for subsequent performance balance optimization mapping.

[0118] Subsequently, the job scheduling processing system will perform performance balance optimization mapping based on the performance balance collision vector and the weather monitoring state vectors of the x job weather monitoring events. The goal of this step is to effectively fuse and map the feature information in the weather monitoring state vector with the feature information in the performance balance collision vector to obtain a first performance balance mapping vector that can accurately reflect the performance requirements of the job scheduling processing system or model when facing different weather monitoring states. This vector not only contains the core features of the weather monitoring state, but also has been processed by the performance balance optimization mapping to ensure that it can serve as an important basis for subsequent decision-making and optimization.

[0119] Finally, the job scheduling processing system will perform performance balance optimization mapping based on the same performance balance collision vector and the weather impact change vector of each job impact label of the y job weather monitoring events. The purpose of this step is to obtain the second performance balance mapping vector corresponding to each job impact label of the y job weather monitoring events. These vectors not only contain the core features of weather impact changes, but also have been processed by performance balance optimization mapping to ensure that they can accurately reflect the performance requirements of the job scheduling processing system or model when facing different job impact labels.

[0120] It can be seen that through the above steps and algorithms, at least part of the information to be processed and the relevant feature vectors of the operational weather monitoring events have been successfully integrated and optimized. The first performance balance mapping vector and the second performance balance mapping vector finally obtained not only contain the global performance balance requirements, but also comprehensively and accurately map the potential impact of all operational weather monitoring events on the performance of the operation scheduling processing system or model. This technical solution provides strong technical support for improving the efficiency and quality of artificial weather modification operations, enabling the operation scheduling processing system or model to make more accurate and efficient decisions and optimizations when facing complex and changeable weather conditions.

[0121] Furthermore, the feature pooling operation in this embodiment is a crucial step. It removes redundant and irrelevant information by screening and refining at least part of the information to be processed, and retains the most representative and critical features. This operation not only reduces the complexity and amount of calculation of subsequent processing, but also improves the quality and accuracy of feature vectors. At the same time, the feature pooling operation can also be flexibly adjusted and optimized according to different application scenarios and requirements to adapt to different performance balance optimization mapping branches and feature pooling rules.

[0122] In addition, knowledge collision processing is also an innovation in this embodiment. It stimulates new feature information and potential rules by crossing, fusing and colliding the vector members in the performance balance pooling vector. This processing method not only enriches the connotation and extension of the feature vector, but also improves its representation and generalization capabilities. It enables the job scheduling processing system or model to make accurate and reliable performance balance optimization mapping when facing unknown or complex weather monitoring conditions.

[0123] Finally, the performance balance optimization mapping in this embodiment is a comprehensive process. It comprehensively considers factors and influences of multiple aspects such as weather monitoring state vector, weather impact change vector and performance balance collision vector. Through refined mapping and optimization processing, the first performance balance mapping vector and the second performance balance mapping vector that can accurately reflect the performance requirements of the job scheduling processing system or model are obtained. These two vectors not only provide important basis and support for subsequent decision-making and optimization, but also lay a solid foundation for improving the efficiency and quality of artificial weather modification operations.

[0124] In general, this embodiment successfully implements the efficiency balance optimization mapping process in the hth efficiency balance optimization mapping branch through innovative algorithm design and optimization processing. It not only improves the decision-making and optimization capabilities of the job scheduling processing system or model when facing complex and changeable weather conditions, but also provides new ideas and methods for the development and innovation of artificial weather modification operations.

[0125] Under some optional design ideas, the performance balance optimization mapping is performed based on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain the first performance balance mapping vector, including: based on the linkage feature focusing rule, the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events are subjected to knowledge collision processing to obtain the first performance balance mapping vector.

[0126] It can be understood that the design idea aims to achieve the optimal configuration and balanced adjustment of weather monitoring event performance through refined data processing and analysis, thereby improving the overall operation efficiency and quality. The following is a detailed description of the technical solution:

[0127] First of all, understanding the "performance balance collision vector" is the key. This vector is essentially a quantitative representation of the performance status of each component in the current operating system. It comprehensively considers the interaction between the elements within the system and its impact on the overall performance. In this vector, each dimension may represent a specific performance indicator or influencing factor, such as operating speed, resource utilization, failure rate, etc. The construction of the performance balance collision vector is based on a comprehensive and in-depth analysis of the existing operating system, aiming to reveal the potential space and bottlenecks for improving system performance.

[0128] Next, consider the "weather monitoring state vectors for x operational weather monitoring events". These vectors contain detailed information about specific weather monitoring events, such as weather type, intensity, duration, and possible impact on operations. Weather monitoring state vectors are dynamic, and they are updated in real time as weather conditions change, providing important external condition input for optimizing operational performance.

[0129] Based on the above two core inputs, the implementation of the technical solution has entered a critical stage: performance balance optimization mapping. This mapping process is not a simple data superposition or conversion, but requires the use of advanced algorithms and models to conduct in-depth mining and intelligent processing of input data. Among them, the "linked feature focusing rule" is the key to this stage.

[0130] The linkage feature focus rule is an algorithmic framework specially designed to capture the potential associations and mutual influences between different data sources. In the present invention, it is used to guide the knowledge collision processing between the performance balance collision vector and the weather monitoring state vector. Specifically, the rule analyzes the interaction patterns of the elements in the two vectors to identify those specific combinations or patterns that have a significant impact on the performance of the operation. These combinations or patterns represent the key paths and strategies for optimizing the performance of the operation system under different weather conditions.

[0131] In the process of knowledge collision processing, the linkage feature focusing rule will first conduct a detailed comparative analysis of the dimensions of the two vectors to find the similarities and differences between them. This comparison is not limited to numerical comparison, but also includes a deep understanding of the physical meaning and logical relationship behind the data. For example, certain weather conditions may have a significant negative impact on certain types of tasks, while other conditions may promote the improvement of work efficiency. Through the linkage feature focusing rule, these complex interactions can be accurately captured and quantified.

[0132] Subsequently, based on the results of the comparative analysis, the algorithm will further construct a multi-dimensional efficiency optimization model. This model not only considers the direct impact of the weather monitoring state vector on the operating efficiency, but also incorporates the system's internal efficiency distribution characteristics reflected in the efficiency balance collision vector. Through the operation of the model, it is possible to simulate what kind of operating strategy can maximize efficiency under different weather conditions. This process is essentially an optimization process, which traverses and evaluates all possible operating strategies, and finally finds the strategy combination that can achieve the best overall efficiency.

[0133] Finally, after the knowledge collision processing and the calculation of the efficiency optimization model, the first efficiency balance mapping vector was obtained. This vector is an optimization and upgrade of the original efficiency balance collision vector. It not only retains the key information about the system efficiency status in the original vector, but also incorporates the influence of the weather monitoring state vector, forming a more comprehensive and more accurate efficiency evaluation and optimization guidance tool. In practical applications, the first efficiency balance mapping vector can be used to guide the formulation and adjustment of operation strategies, helping operating units to maintain efficient and stable operation under different weather conditions.

[0134] In this way, by introducing the linkage feature focusing rule, the deep integration and optimization mapping of the performance balance collision vector and the weather monitoring state vector are realized. This process not only improves the adaptability and response speed of the operation system to changes in external weather conditions, but also provides strong data support and decision-making basis for the continuous improvement of operation efficiency.

[0135] Under some other preferred design ideas, the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events are subjected to knowledge collision processing based on the linkage feature focusing rule to obtain the first performance balance mapping vector, including: based on the linkage feature focusing rule, the performance balance collision vector and the weather monitoring state vector of each operational weather monitoring event in the weather monitoring state vectors of the x operational weather monitoring events are subjected to knowledge collision processing respectively to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of each operational weather monitoring event; the performance balance mapping vectors corresponding to the weather monitoring state vectors of the x operational weather monitoring events are spliced ​​to obtain the first performance balance mapping vector.

[0136] This embodiment of the present invention is dedicated to deeply integrating and finely processing the performance balance collision vector and the weather monitoring state vector of the operation weather monitoring event through the linkage feature focusing rule, in order to obtain a first performance balance mapping vector that comprehensively reflects the performance balance state of the operation system under various weather conditions. This process requires not only the accurate capture of the unique impact of each operation weather monitoring event, but also the need to ensure that all relevant information can be organically integrated to form a unified and comprehensive performance evaluation framework.

[0137] First, the implementation of the technical solution focuses on the knowledge collision processing between the performance balance collision vector and the weather monitoring state vector of each operational weather monitoring event. This step is the cornerstone of constructing the first performance balance mapping vector. It requires an independent and detailed analysis of each weather monitoring state vector to reveal its potential connection with the performance balance collision vector. Specifically, the linkage feature focus rule is used to guide the analysis process. It deeply explores the interaction patterns of the elements in the two vectors to identify specific combinations or patterns that have a significant impact on the performance of the operating system. This analysis is not limited to numerical comparisons, but also involves a deep understanding of the physical meaning and logical relationships behind the data, thereby ensuring that the extracted features can truly reflect the complex relationship between weather conditions and operational performance.

[0138] Secondly, based on the above analysis, the technical solution further generates a corresponding performance balance mapping vector for the weather monitoring state vector of each operational weather monitoring event. This step is a concrete manifestation of the results of knowledge collision processing. It combines the key information in the weather monitoring state vector with the system performance status in the performance balance collision vector to form a new performance evaluation index rich in weather impact information. These performance balance mapping vectors not only retain the key information about the system performance status in the original vector, but also incorporate the unique influence of the weather monitoring state vector, making each mapping vector an accurate tool that reflects the performance status of the operating system under specific weather conditions.

[0139] Then, the technical solution requires the splicing of the corresponding performance balance mapping vectors of the weather monitoring state vectors of the x operational weather monitoring events. This step is the key to constructing the first performance balance mapping vector. It requires integrating all independent performance balance mapping vectors into a unified whole to form an evaluation framework that comprehensively reflects the performance balance state of the operating system under various weather conditions. The splicing process is not a simple data superposition, but it is necessary to ensure that the position and weight of each mapping vector in the overall framework are properly handled to truly reflect the comprehensive impact of different weather conditions on the performance of the operating system. Through this step, the technical solution is able to integrate the scattered performance evaluation indicators that reflect specific weather impacts into a unified and comprehensive performance balance mapping vector, providing a solid foundation for subsequent decision support.

[0140] Finally, after careful design and implementation of the above steps, the first performance balance mapping vector was successfully obtained. This vector is not only an optimization and upgrade of the original performance balance collision vector, but also a comprehensive and accurate reflection of the performance status of the operating system under various weather conditions. It combines the unique influence of the weather monitoring state vector and the system performance status information of the performance balance collision vector to form a powerful tool with multi-dimensional and multi-level performance evaluation indicators. In practical applications, the first performance balance mapping vector can be used to guide the formulation and adjustment of operating strategies, helping operating units to make more scientific and reasonable decisions under different weather conditions to maximize operating efficiency.

[0141] In this way, by introducing the linkage feature focusing rule, the deep integration and refined processing of the performance balance collision vector and the weather monitoring state vector of the operation weather monitoring event are realized. It not only improves the adaptability and response speed of the operation system to changes in external weather conditions, but also provides strong data support and decision-making basis for the continuous improvement of operation efficiency. In the future development, with the continuous advancement of data processing and analysis technology, this technical solution is expected to be further improved and promoted, providing more accurate and comprehensive support for the optimization of operation efficiency in more fields. At the same time, it also provides new ideas and methods for exploring the complex relationship between the operation system and the external environment, and promotes the in-depth development of theoretical research and practical application in related fields.

[0142] In some other optional embodiments, the linkage feature focusing rule is based on which the performance balance collision vector and the weather monitoring state vector of each of the x operational weather monitoring events are subjected to knowledge collision processing to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of each of the x operational weather monitoring events, including: for the weather monitoring state vector of each of the x operational weather monitoring events, the weather monitoring state vector of the operational weather monitoring event is processed by a first deep residual network based on the linkage feature focusing rule to obtain a first performance situation feature and a first weather impact situation feature, and the performance balance collision vector is processed to obtain a first balance situation feature; the feature enhancement coefficient is determined based on the first performance situation feature and the first balance situation feature to obtain a list of local feature enhancement coefficients corresponding to the weather monitoring state vector of the operational weather monitoring event; the first weather impact situation feature is feature enhanced using the list of local feature enhancement coefficients corresponding to the weather monitoring state vector of the operational weather monitoring event to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of the operational weather monitoring event.

[0143] It can be understood that this embodiment further involves deep mining and integration of the potential connection between the performance balance collision vector and the weather monitoring state vector of the operation weather monitoring event through the linkage feature focusing rule, in order to obtain a series of mapping vectors that can accurately reflect the performance balance state of the operation system under different weather conditions. This process requires not only fine-grained modeling of the unique impact of each operation weather monitoring event, but also ensuring that the core information of the performance balance collision vector can be effectively utilized, thereby forming a comprehensive and in-depth performance evaluation system.

[0144] First, for each of the weather monitoring state vectors of the x operational weather monitoring events, the operation scheduling processing system uses the first deep residual network based on the linkage feature focusing rule for processing. The design of the network structure aims to capture the complex features in the weather monitoring state vector and transform it into a representation that is instructive for performance evaluation. Taking a specific operational weather monitoring event as an example, its weather monitoring state vector may contain numerical features of multiple dimensions, such as temperature, humidity, wind speed, wind direction, etc., which can be represented as an exemplary feature vector, such as [23℃, 60%, 5m / s, southeast wind]. Through the processing of the first deep residual network, these original numerical features are transformed into higher-level representations, namely the first performance situation feature and the first weather impact situation feature. The first performance situation feature is an abstract representation of the performance state of the operating system under the current weather conditions, while the first weather impact situation feature is a quantitative description of how weather conditions affect the performance of the operating system. This conversion process not only considers the direct impact of weather conditions on operational performance, but also retains the important information of the original features through residual connections, ensuring the richness and accuracy of feature representation.

[0145] At the same time, the first deep residual network also processes the performance balance collision vector and extracts the first balance situation feature. As a comprehensive description of the current performance status of the operating system, the information contained in the performance balance collision vector is crucial for understanding how weather conditions affect system performance. This vector can also be represented as an exemplary feature vector, such as [0.7, 0.5, 0.3], where each value represents the performance status of the operating system in different aspects. Through the nonlinear transformation of the network, the key information in the performance balance collision vector is refined and represented as the first balance situation feature, which is a high-level, abstract representation of the performance balance state of the operating system, providing a basis for subsequent feature fusion and enhancement.

[0146] Secondly, the job scheduling processing system determines the feature enhancement coefficient based on the first performance situation feature and the first balance situation feature. The core of this process is to assign different weights to different weather monitoring state vectors to reflect their different degrees of influence on the performance of the job system. By calculating the similarity or correlation between the first performance situation feature and the first balance situation feature, a list of local feature enhancement coefficients can be obtained. Each coefficient in this list corresponds to a specific feature in the weather monitoring state vector, indicating the importance of the feature in the performance evaluation.

[0147] Taking the temperature feature as an example, if the calculation results show that there is a significant positive correlation between temperature and the performance of the operating system, then the local feature enhancement coefficient corresponding to the temperature feature will be higher, which means that more attention should be paid in the subsequent performance evaluation. On the contrary, if the correlation between a certain feature (such as wind speed) and performance is weak or not obvious, then its corresponding enhancement coefficient will be lower. In this way, by determining the feature enhancement coefficient, the job scheduling processing system can achieve a refined quantitative evaluation of the impact of different weather conditions on the performance of the operating system.

[0148] Then, using the obtained local feature enhancement coefficient list, the job scheduling processing system performs feature enhancement on the first weather impact situation feature. The purpose of this step is to weight the weather impact situation features according to the importance of each feature, so that those features that are more critical to performance evaluation are more emphasized. Through this enhancement process, the key information in the weather impact situation features is further highlighted, providing more accurate and targeted input for the subsequent generation of performance balance mapping vectors.

[0149] Specifically, if the temperature feature has a higher reinforcement coefficient, the temperature-related weather impact situation feature will be given a greater weight during the feature reinforcement process, and thus will be more reflected in the final performance balance mapping vector. In this way, the generated performance balance mapping vector will more accurately reflect the impact of temperature on the performance of the operating system.

[0150] Finally, the first weather impact situation feature after feature enhancement is integrated with the first performance situation feature and the first balance situation feature to generate the performance balance mapping vector corresponding to the weather monitoring state vector for each operational weather monitoring event. This mapping vector not only contains the potential impact information of weather conditions on the performance of the operating system, but also incorporates the current performance balance state of the system and the interaction between weather conditions and performance. Therefore, it can be regarded as an evaluation indicator that comprehensively reflects the performance balance state of the operating system under specific weather conditions.

[0151] In practical applications, this series of performance balance mapping vectors can be used to guide the formulation and adjustment of operation strategies. For example, under different weather conditions, the operation unit can adjust the operation plan, optimize resource allocation, and improve operation efficiency according to the corresponding performance balance mapping vector to maximize the operation efficiency. At the same time, this technical solution also provides new ideas and methods for exploring the complex relationship between the operation system and the external environment, and promotes the in-depth development of theoretical research and practical application in related fields.

[0152] It can be seen that by introducing the linkage feature focusing rule and the deep residual network structure, the deep integration and refined processing of the performance balance collision vector and the weather monitoring state vector of the operation weather monitoring event are achieved. It not only improves the adaptability and response speed of the operation system to changes in external weather conditions, but also provides strong data support and decision-making basis for the continuous improvement of operation efficiency. The implementation of this technical solution will help operating units make more scientific and reasonable decisions under different weather conditions, thereby further improving operation efficiency and overall operational benefits.

[0153] In other possible embodiments, the performance balance optimization mapping is performed respectively based on the performance balance collision vector and the weather impact change vector of each of the operation impact labels of the y operation weather monitoring events to obtain the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, including: based on the linkage feature focusing rule, the performance balance collision vector and the weather impact change vector of each of the operation impact labels of the y operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events.

[0154] It can be understood that this embodiment uses an innovative performance balance optimization mapping method to deeply integrate and analyze the weather impact change vectors of the performance balance collision vector and the operation impact label of the operation weather monitoring event, in order to obtain a second performance balance mapping vector that can accurately reflect the performance balance state of the operation system under different weather conditions. This process not only requires refined modeling of the unique impact of each operation weather monitoring event, but also ensures that the core information of the performance balance collision vector can be effectively utilized, thereby forming a comprehensive and in-depth performance evaluation and optimization system.

[0155] First, the performance balance collision vector is a numerical feature vector that integrates multiple performance parameters, which represents the overall performance status of the operating system in the current environment. This vector can contain numerical features of multiple dimensions such as operating efficiency, resource utilization, and energy consumption, such as [0.8, 0.6, 0.5], where each value represents the performance status of the operating system in different aspects. The weather impact change vector is the operating impact label for each operating weather monitoring event, which describes the potential impact of changes in weather conditions on the performance of the operating system. This vector can also be expressed as a specific numerical feature vector. For example, for a certain operating weather monitoring event, its weather impact change vector may be [0.2, -0.1, 0.05], indicating that changes in weather conditions have different degrees of impact on operating efficiency, resource utilization, and energy consumption.

[0156] Based on this data foundation, the job scheduling processing system uses linkage feature focusing rules to perform knowledge collision processing on the performance balance collision vector and the weather impact change vector of each of the job impact labels of y job weather monitoring events. The core of this processing process is to mine the potential connection between the performance balance collision vector and the weather impact change vector through deep learning and feature fusion technology, thereby generating a second performance balance mapping vector that can reflect the performance balance state of the job system under specific weather conditions.

[0157] Specifically, for each job impact label of a job weather monitoring event, the job scheduling processing system will pair its corresponding weather impact change vector with the performance balance collision vector and process it through a deep neural network model. This deep neural network model can be designed as a multi-layer perceptron (MLP) or convolutional neural network (CNN) structure, and the specific choice depends on the characteristics of the data and the complexity of the problem. Through network learning and optimization, the model can capture the nonlinear relationship between the performance balance collision vector and the weather impact change vector, and convert this relationship into a high-level feature representation, namely the second performance balance mapping vector.

[0158] The second performance balance mapping vector is a numerical feature vector that combines the performance balance collision vector and the weather impact change vector information. It represents the optimized mapping result of the performance balance state of the operating system under specific weather conditions. This vector can also be expressed as a specific numerical feature vector. For example, for a certain operational weather monitoring event, its second performance balance mapping vector may be [0.85, 0.62, 0.48], indicating that after considering the impact of weather conditions, the performance state of the operating system in different aspects has been optimized and adjusted accordingly.

[0159] In the process of generating the second performance balance mapping vector, the job scheduling processing system also fully considers the role of the linkage feature focus rule. This rule emphasizes that when processing the performance balance collision vector and the weather impact change vector, it is necessary to pay attention to the linkage relationship and feature focus points between them. Specifically, through means such as feature selection and weight allocation, more attention can be paid to those features and factors that have an important impact on the performance balance state during the processing process. For example, if a certain feature in the weather impact change vector (such as temperature) has a greater impact on the performance of the job system, then when generating the second performance balance mapping vector, this feature will be given a higher weight and attention.

[0160] Through this processing method, the job scheduling processing system not only achieves deep integration and optimization of the performance balance collision vector and the weather impact change vector, but also generates a series of second performance balance mapping vectors that can accurately reflect the performance balance state of the job system under different weather conditions. These vectors not only contain information about the potential impact of weather conditions on the performance of the job system, but also incorporate the current performance balance state of the system and the interaction between weather conditions and performance. Therefore, they can be regarded as optimized evaluation indicators that fully reflect the performance balance state of the job system under specific weather conditions.

[0161] In practical applications, this series of second performance balance mapping vectors can be used to guide the formulation and adjustment of operation strategies. For example, under different weather conditions, the operation unit can adjust the operation plan, optimize resource allocation, improve operation efficiency, etc. according to the corresponding second performance balance mapping vector to maximize the operation efficiency. At the same time, the present invention also provides new ideas and methods for exploring the complex relationship between the operation system and the external environment, and promotes the in-depth development of theoretical research and practical application in related fields.

[0162] In addition, in practical applications, the definition and calculation methods of the performance balance collision vector, weather impact change vector, and second performance balance mapping vector can be flexibly adjusted and optimized according to specific operation scenarios and needs. For example, different features and parameters can be selected to construct these vectors according to different operation types and weather conditions; different machine learning models and algorithms can also be used to perform knowledge collision processing and performance balance optimization mapping. Such a design enables the technical solution to adapt to different application scenarios and needs more flexibly, providing more accurate and powerful support for improving the performance of the operation system.

[0163] Therefore, by introducing the linkage feature focus rule and deep neural network model, the deep integration and refined processing of the weather impact change vectors of the performance balance collision vector and the operation impact label of the operation weather monitoring event are realized. It not only improves the adaptability and response speed of the operation system to changes in external weather conditions, but also provides strong data support and decision-making basis for the continuous improvement of operation efficiency.

[0164] In an independent embodiment, the performance balance collision vector and the weather impact change vectors of the operation impact labels of the y operation weather monitoring events are subjected to knowledge collision processing based on the linkage feature focusing rule to obtain the second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events, including: for the weather impact change vectors of the operation impact labels of the y operation weather monitoring events, the weather impact change vectors of the operation impact labels of each operation weather monitoring event are processed through the second deep residual network based on the linkage feature focusing rule. Processing is performed to obtain the second performance situation characteristic and the second weather impact situation characteristic, and the performance balance collision vector is processed to obtain the second balance situation characteristic; the feature enhancement coefficient is determined according to the second performance situation characteristic and the second balance situation characteristic, and a list of local feature enhancement coefficients corresponding to the weather impact change vector of the operation impact label of the operation weather monitoring event is obtained; using the list of local feature enhancement coefficients corresponding to the weather impact change vector of the operation impact label of the operation weather monitoring event, the second weather impact situation characteristic is feature enhanced to obtain the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event.

[0165] This embodiment further demonstrates how to perform knowledge collision processing on the performance balance collision vector and the weather impact change vectors of the operation impact labels of y operation weather monitoring events based on the linkage feature focusing rule, so as to obtain the second performance balance mapping vector corresponding to the operation impact label of each operation weather monitoring event. This process not only involves complex feature extraction and fusion, but also includes multiple steps such as the generation of situational features, determination of feature enhancement coefficients, and feature enhancement, to ensure that the final second performance balance mapping vector can fully and accurately reflect the potential impact of the operation weather monitoring event on the performance balance of the operation system.

[0166] First, for the weather impact change vectors of the job impact labels of y job weather monitoring events, the job scheduling processing system uses a second deep residual network based on the linkage feature focusing rule to process them. The design of this network structure aims to effectively capture the deep features in the weather impact change vector, and enhance the training effect of the network through residual learning to avoid overfitting. For the weather impact change vector of the job impact label of each job weather monitoring event, such as [0.2, -0.1, 0.05] (representing the impact of temperature, humidity, and wind speed on job efficiency, respectively), the second deep residual network can mine the nonlinear relationship and implicit features therein, and generate the corresponding second performance situation features and second weather impact situation features.

[0167] At the same time, the network also processes the performance balance collision vector to obtain the second balance situation feature. The performance balance collision vector is a numerical feature vector that combines multiple performance parameters, such as [0.8, 0.6, 0.5], which represents the overall performance status of the operating system in the current environment. Through the processing of the second deep residual network, this vector is converted into the second balance situation feature, which contains more deep information and implicit relationships about the performance balance state.

[0168] Secondly, the job scheduling processing system determines the feature enhancement coefficient based on the second performance situation feature and the second balance situation feature. This process is implemented through a complex feature interaction mechanism, which takes into account the interaction and mutual influence between the performance situation and the balance situation. For each weather impact change vector of the job impact label of the operational weather monitoring event, a corresponding local feature enhancement coefficient list is generated. This list contains a series of values ​​​​to indicate which features should be enhanced and which features should be suppressed during the feature enhancement process. For example, for a certain operational weather monitoring event, its local feature enhancement coefficient list may be [1.2, 0.8, 1.5], which means that when the feature is enhanced, the first and third features will be enhanced, while the second feature will be relatively suppressed.

[0169] Then, the second weather impact situation feature is enhanced by using the local feature enhancement coefficient list corresponding to the weather impact change vector of the operation impact label for the operation weather monitoring event. This process is achieved by multiplying the local feature enhancement coefficient list by the second weather impact situation feature element by element. In this way, different parts of the second weather impact situation feature will be enhanced or suppressed to different degrees according to the size of the local feature enhancement coefficient. For example, if the local feature enhancement coefficient of a feature is 1.5, then after feature enhancement, the value of this feature will become 1.5 times the original value.

[0170] Finally, the second weather impact situation feature after feature enhancement is converted into the second performance balance mapping vector corresponding to the operational impact label of the operational weather monitoring event. This vector not only contains the original information of the weather impact change vector, but also incorporates the relevant features of the performance balance collision vector and the deep implicit relationship obtained through the feature enhancement process. Therefore, it can be regarded as an optimized evaluation indicator that comprehensively reflects the potential impact of a specific operational weather monitoring event on the performance balance of the operational system.

[0171] In practical applications, this series of second performance balance mapping vectors can be used to guide the formulation and adjustment of operation strategies. Operation units can adjust operation plans, optimize resource allocation, improve operation efficiency, etc. according to different second performance balance mapping vectors to maximize operation efficiency. At the same time, the present invention also provides new ideas and methods for exploring the complex relationship between the operation system and the external environment, and promotes the in-depth development of theoretical research and practical application in related fields.

[0172] In addition, in practical applications, the definition and calculation methods of the performance balance collision vector, weather impact change vector, and second performance balance mapping vector can be flexibly adjusted and optimized according to specific operation scenarios and needs. For example, different features and parameters can be selected to construct these vectors according to different operation types and weather conditions; different deep learning models and algorithms can also be used to process knowledge collisions and enhance features. Such a design enables the technical solution to adapt to different application scenarios and needs more flexibly, providing more accurate and powerful support for improving the performance of the operation system.

[0173] In summary, by introducing the second deep residual network based on the linkage feature focusing rule, the feature enhancement coefficient determination mechanism and the feature enhancement process, the deep integration and refined processing of the weather impact change vectors of the performance balance collision vector and the operation impact label of the operation weather monitoring event are achieved. It not only improves the adaptability and response speed of the operation system to changes in external weather conditions, but also provides strong data support and decision-making basis for the continuous improvement of operation efficiency.

[0174] In some independent embodiments, determining the weather monitoring state vector representing the x operation weather monitoring events in the target scheduling strategy and the weather impact change vector of each operation impact label of y operation weather monitoring events based on the combustion furnace operation record includes: performing vector extraction on the monitoring event logs recording the x operation weather monitoring events in the target scheduling strategy in the combustion furnace operation record to obtain the weather monitoring state vector recording the x operation weather monitoring events in the target scheduling strategy, and performing vector extraction on the artificial weather influence logs recording the operation impact labels of y operation weather monitoring events in the target scheduling strategy in the combustion furnace operation record to obtain the weather impact change vector of each operation impact label of the y operation weather monitoring events.

[0175] In this embodiment, the job scheduling processing system is dedicated to accurately determining and characterizing the weather monitoring state vectors of the x job weather monitoring events involved in the target scheduling strategy, and the weather impact change vectors of the job impact labels of the y job weather monitoring events, through the combustion furnace operation records. This process involves in-depth data mining and vector extraction of the rich monitoring event logs and artificial weather influence logs in the combustion furnace operation records to ensure that the obtained vectors can comprehensively and accurately reflect the real-time status of the operation weather monitoring events and their actual impact on the operation.

[0176] First, for the x operational weather monitoring events involved in the target scheduling strategy, the job scheduling processing system needs to perform detailed vector extraction operations on the corresponding monitoring event logs in the combustion furnace operation records. The core of this step is to convert the monitoring data of each operational weather monitoring event into a numerical feature vector, namely the weather monitoring state vector. This vector should contain key parameters that can fully describe the state of the weather monitoring event, such as temperature, humidity, wind speed, air pressure, etc. For example, for a specific operational weather monitoring event, its weather monitoring state vector can be expressed as [23.5, 60%, 3.0m / s, 1013.25hPa], which correspond to the real-time monitoring values ​​of the temperature, humidity, wind speed and air pressure of the event, respectively.

[0177] By processing the monitoring event logs of x operational weather monitoring events one by one, the operation scheduling processing system can obtain a set of x weather monitoring state vectors. This set not only fully reflects the real-time status of all operational weather monitoring events under the target scheduling strategy, but also provides a solid foundation for subsequent knowledge collision processing and performance balance analysis.

[0178] Secondly, the job scheduling processing system also needs to pay attention to the weather impact change vectors of each of the job impact labels of the y job weather monitoring events in the target scheduling strategy. This step also requires in-depth vector extraction operations on the artificial weather influence logs in the combustion furnace operation records. Unlike the weather monitoring state vector, the weather impact change vector is designed to capture and describe the potential impact of the job weather monitoring event on the efficiency or effectiveness of the combustion furnace operation. Therefore, this vector should contain key parameters that can reflect the impact of weather changes on operations, such as the rate of change of operation efficiency, the rate of change of fuel consumption, the rate of change of emissions, etc.

[0179] For example, for a specific operational weather monitoring event, if its operational impact label indicates that the event has a significant impact on the operating efficiency of the combustion furnace, then its weather impact change vector can be expressed as [0.05, -0.02, 0.01], which corresponds to the estimated values ​​of 5% improvement in operating efficiency, 2% reduction in fuel consumption, and 1% increase in emissions caused by the event. By processing the artificial weather modification logs of y operational weather monitoring events one by one, the operation scheduling processing system can obtain a set of y weather impact change vectors. This set not only fully reveals the potential impact of all operational weather monitoring events on the combustion furnace operation under the target scheduling strategy, but also provides key input data for subsequent feature enhancement and performance balance mapping.

[0180] In this way, through the refined vector extraction operation, the monitoring event log and artificial weather modification log in the combustion furnace operation record are successfully converted into a numerical feature vector that characterizes the real-time status of the operation weather monitoring event in the target scheduling strategy and its impact on the operation. This conversion process not only ensures the comprehensiveness and accuracy of the obtained vector, but also lays a solid foundation for subsequent knowledge collision processing, feature enhancement and performance balance analysis. In practical applications, the present invention will help the combustion furnace operating unit to more accurately grasp the real-time status of the operation weather monitoring event and its impact on the operation, so as to formulate a more scientific and reasonable scheduling strategy, and further improve the operation efficiency and overall operational benefits of the combustion furnace.

[0181] It is worth mentioning that after introducing how to determine the weather monitoring state vector representing the operation weather monitoring event in the target scheduling strategy and the weather impact change vector of each operation impact label based on the combustion furnace operation record, the following will introduce in detail how to assign the combustion furnace operation intelligent scheduling model to the scheduling server in the target area based on this target scheduling strategy, and guide the scheduling server to perform the combustion furnace operation ammunition scheduling processing according to the intelligent scheduling model.

[0182] First, the target scheduling strategy is the core of the intelligent scheduling model for burner operations. This strategy not only includes real-time status information about operational weather monitoring events, but also covers the potential impact of these events on the efficiency of burner operations. Therefore, when building the intelligent scheduling model for burner operations, the job scheduling processing system must fully consider this information to ensure that the model can accurately reflect the actual requirements of the target scheduling strategy.

[0183] Once the intelligent dispatching model for burner operations is built, the dispatching processing system can dispatch it to the dispatching server in the target area. This dispatching process usually involves transferring the model's algorithm and parameters to the dispatching server and ensuring that the server has the computing resources and software environment required to run the model.

[0184] Next, the scheduling server will schedule the amount of ammunition used in the combustion furnace based on the received intelligent scheduling model for the combustion furnace operation. The core of this process is to dynamically adjust the amount of ammunition used in the combustion furnace operation according to the prediction and recommendation of the model to optimize the operation efficiency and effect. Specifically, the scheduling server will monitor the operation status and environmental conditions of the combustion furnace in real time and input these data into the intelligent scheduling model. The model will calculate the optimal amount of ammunition used in the operation based on the input data and the preset algorithm, and send it as a scheduling instruction to the combustion furnace operation system.

[0185] In practical applications, this intelligent scheduling model will be able to significantly improve the operating efficiency and overall operational benefits of the burner. By dynamically adjusting the amount of ammunition used in the operation, the model can ensure that the burner can maintain the best working condition under different weather conditions, thereby reducing fuel consumption, reducing emissions, and improving the quality of operation. At the same time, because the model is built based on a large amount of historical data and real-time monitoring data, it can also automatically adapt to different operating scenarios and environmental conditions, achieving true intelligence and adaptability.

[0186] It can be seen that assigning the intelligent scheduling model of the burner operation to the scheduling server in the target area based on the target scheduling strategy and guiding it to schedule the amount of ammunition used in the burner operation is an efficient and intelligent burner operation optimization method. It can not only significantly improve the operating efficiency and operational benefits, but also automatically adapt to different operating scenarios and environmental conditions, providing strong support for the intelligent and sustainable development of the burner operation system.

[0187] Further, Figure 2 FIG. 2 is a schematic diagram of a job scheduling processing system 200 provided by the present invention. Figure 2 The job scheduling processing system 200 shown includes a processor 210, and the processor 210 can call and run a computer program from a memory to implement the method of the present invention.

[0188] Alternatively, if Figure 2 As shown, the job scheduling processing system 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method of the present invention.

[0189] The memory 230 may be a separate device independent of the processor 210 , or may be integrated into the processor 210 .

[0190] Alternatively, if Figure 2 As shown, the job scheduling processing system 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0191] Optionally, the job scheduling processing system 200 may implement the corresponding processes corresponding to the storage engine or components in the storage engine (such as a processing module) or a device deployed with a storage engine in each method of the present invention, which will not be described here for the sake of brevity.

[0192] It should be understood that the processor of the present invention may be an integrated circuit chip having signal processing capabilities.

[0193] It is understood that the memory in the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memory. It should be noted that the memory of the systems and methods described herein is intended to include but is not limited to suitable types of memory.

[0194] Based on the above, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0195] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0196] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0197] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose of the present invention and the scope of protection of the present invention, all of which are within the protection of the present invention.

Claims

1. A method for processing combustion furnace operation scheduling records based on artificial weather modification, characterized in that: The method is applied to a job scheduling processing system, and the method comprises: Using the acquired combustion furnace operation records and operation disturbance element vectors to perform cyclic efficiency balance optimization mapping, a semantic vector of the scheduling strategy that has been adjusted is obtained; and a target scheduling strategy is output based on the semantic vector of the scheduling strategy that has been adjusted; Based on the target scheduling strategy, the combustion furnace operation intelligent scheduling model is assigned to the scheduling server in the target area to instruct the scheduling server to perform the combustion furnace operation ammunition quantity scheduling processing based on the combustion furnace operation intelligent scheduling model.

2. The method according to claim 1, characterized in that The method uses the obtained combustion furnace operation record and operation disturbance element vector to perform cyclic efficiency balance optimization mapping to obtain a semantic vector of a scheduling strategy that has been adjusted; and outputs a target scheduling strategy based on the semantic vector of the scheduling strategy that has been adjusted, including: Obtaining a combustion furnace operation record for constructing a target scheduling strategy, and determining, based on the combustion furnace operation record, a weather monitoring state vector representing x operation weather monitoring events in the target scheduling strategy, and a weather impact change vector of each operation impact label of y operation weather monitoring events, where x is a positive integer and y is a positive integer not greater than x; Obtaining a job disturbance element vector, and using the job disturbance element vector as a multi-level derived scheduling execution vector obtained by subjecting the scheduling strategy semantic vector of the target scheduling strategy to a disturbance addition process of R cycles, where R is a positive integer greater than 1; The multi-level derivative scheduling execution vector is subjected to performance balancing optimization mapping of the performance balancing process of R cycles to obtain the performance balancing decision vector of the R-th performance balancing process; wherein, for the r-th performance balancing process in the performance balancing process of R cycles, when r=1, the multi-level derivative scheduling execution vector is used as the to-be-processed information of the r-th performance balancing process, when r is greater than 1 and not greater than R, the performance balancing decision vector of the r-1-th performance balancing process is used as the to-be-processed information of the r-th performance balancing process, and when r=R, the performance balancing decision vector of the r-th performance balancing process is the performance balancing decision vector of the R-th performance balancing process; In the rth performance balancing process, H performance balancing optimization mapping branches are looped, wherein, for the hth performance balancing optimization mapping branch among the H performance balancing optimization mapping branches, when h=1, the to-be-processed information of the rth performance balancing process is used as the to-be-processed information of the hth performance balancing optimization mapping branch, and when h is greater than 1 and not greater than H, the performance balancing decision vector of the h-1th performance balancing optimization mapping branch is used as at least part of the to-be-processed information of the hth performance balancing optimization mapping branch, and when h=H, the performance balancing decision vector of the hth performance balancing optimization mapping branch is the performance balancing decision vector of the rth performance balancing process; In the hth performance balance optimization mapping branch, according to at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events, the performance balance optimization mapping is performed to obtain a first performance balance mapping vector; according to at least part of the information to be processed and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events, the performance balance optimization mapping is performed to obtain a second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events; through the first performance balance mapping vector and the second performance balance mapping vector corresponding to each of the operation impact labels of the y operation weather monitoring events, the performance balance decision vector of the hth performance balance optimization mapping branch is obtained; The efficiency balance decision vector of the Rth efficiency balance process is used as a semantic vector of a scheduling strategy that has completed adjustment, text strategy generation is performed on the semantic vector of the scheduling strategy that has completed adjustment, and a target scheduling strategy is output.

3. The method according to claim 2, characterized in that The performance balance decision vector of the hth performance balance optimization mapping branch is obtained by using the first performance balance mapping vector and the second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events, including: Obtain a list of local feature enhancement coefficients corresponding to the weather monitoring state vectors of the x operational weather monitoring events; For each operation impact label of the operation impact labels of the y operation weather monitoring events, determine the operation weather monitoring event matched by the operation impact label of the operation weather monitoring event, and perform feature enhancement processing on the second performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event through the local feature enhancement coefficient list corresponding to the weather monitoring state vector of the matched operation weather monitoring event, so as to obtain the third performance balance mapping vector corresponding to the operation impact label of the operation weather monitoring event; The first performance balance mapping vector and the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events are integrated to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

4. The method according to claim 3, characterized in that The first performance balance mapping vector and the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events are integrated to obtain the performance balance decision vector of the hth performance balance optimization mapping branch, including: splicing the third performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events respectively, to obtain the weather impact trend mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events; The first performance balance mapping vector and the weather impact trend mapping vector corresponding to the operation impact labels of the y operation weather monitoring events are spliced ​​to obtain the performance balance decision vector of the hth performance balance optimization mapping branch.

5. The method according to any one of claims 2 to 4, characterized in that: The hth performance balance optimization mapping branch performs performance balance optimization mapping according to at least part of the information to be processed and the weather monitoring state vectors of the x operation weather monitoring events to obtain a first performance balance mapping vector, and performs performance balance optimization mapping according to at least part of the information to be processed and the weather impact change vectors of each operation impact label of the y operation weather monitoring events to obtain a second performance balance mapping vector corresponding to each operation impact label of the y operation weather monitoring events, including: In the hth performance balance optimization mapping branch, based on the feature pooling rule corresponding to the hth performance balance optimization mapping branch, a feature pooling operation is performed on the at least part of the information to be processed to obtain a performance balance pooling vector; Performing knowledge collision processing on vector members in the performance balance pooling vector to obtain a performance balance collision vector; According to the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events, a performance balance optimization mapping is performed to obtain a first performance balance mapping vector; According to the performance balance collision vector and the weather impact change vectors of the operation impact labels of the y operation weather monitoring events, performance balance optimization mapping is performed respectively to obtain second performance balance mapping vectors corresponding to the operation impact labels of the y operation weather monitoring events.

6. The method according to claim 5, characterized in that The step of performing performance balance optimization mapping based on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector includes: Based on the linkage feature focusing rule, knowledge collision processing is performed on the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events to obtain a first performance balance mapping vector.

7. The method according to claim 6, characterized in that The linkage feature focusing rule is based on which the performance balance collision vector and the weather monitoring state vectors of the x operational weather monitoring events are subjected to knowledge collision processing to obtain a first performance balance mapping vector, which includes: Based on the linkage feature focusing rule, the performance balance collision vector and the weather monitoring state vector of each operation weather monitoring event in the weather monitoring state vectors of the x operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of each operation weather monitoring event; The performance balance mapping vectors corresponding to the weather monitoring state vectors of the x operational weather monitoring events are concatenated to obtain a first performance balance mapping vector.

8. The method according to claim 7, characterized in that Based on the linkage feature focusing rule, the performance balance collision vector and the weather monitoring state vector of each operation weather monitoring event in the weather monitoring state vectors of the x operation weather monitoring events are respectively subjected to knowledge collision processing to obtain the performance balance mapping vector corresponding to the weather monitoring state vector of each operation weather monitoring event, including: For each weather monitoring state vector of the x weather monitoring events, the weather monitoring state vector of the weather monitoring event is processed by a first deep residual network based on a linkage feature focusing rule to obtain a first performance situation feature and a first weather impact situation feature, and the performance balance collision vector is processed to obtain a first balance situation feature; Determine a feature enhancement coefficient according to the first performance situation feature and the first balance situation feature, and obtain a list of local feature enhancement coefficients corresponding to the weather monitoring state vector for the operational weather monitoring event; By utilizing the local feature enhancement coefficient list corresponding to the weather monitoring state vector of the operational weather monitoring event, the first weather impact situation feature is feature enhanced to obtain the efficiency balance mapping vector corresponding to the weather monitoring state vector of the operational weather monitoring event.

9. The method according to claim 5, characterized in that The method of performing performance balance optimization mapping based on the performance balance collision vector and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events to obtain the second performance balance mapping vectors corresponding to each of the operation impact labels of the y operation weather monitoring events includes: performing knowledge collision processing on the performance balance collision vector and the weather impact change vectors of each of the operation impact labels of the y operation weather monitoring events based on the linkage feature focusing rule to obtain the second performance balance mapping vectors corresponding to each of the operation impact labels of the y operation weather monitoring events.

10. A job scheduling processing system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.

Images