AI-based intelligent resource scheduling system for wireless communication networks

Abstract

The application discloses an AI-based intelligent resource scheduling system for a wireless communication network, and belongs to the technical field of resource scheduling of wireless communication networks.The system comprises the following steps: establishing a regional prediction model;analyzing regional material data according to the regional prediction model to obtain unit prediction data of each unit region at a prediction time within a prediction period;generating a unit prediction graph at the prediction time according to the unit prediction data;establishing a digital twin model;simulating resource scheduling of the unit prediction graph according to the digital twin model to obtain a basic scheduling scheme;collecting user information in real time at a device end;generating a unit region graph according to each user information in the unit region;evaluating whether the basic scheduling scheme needs to be adjusted according to the unit region graph;when it is evaluated that the basic scheduling scheme does not need to be adjusted, marking the basic scheduling scheme as a target scheduling scheme;when it is evaluated that the basic scheduling scheme needs to be adjusted, optimizing and adjusting the basic scheduling scheme to obtain the target scheduling scheme.

Description

Technical Field

[0001] This invention belongs to the field of resource scheduling technology in wireless communication networks, specifically an AI-based intelligent resource scheduling system for wireless communication networks. Background Technology

[0002] With the rapid development of wireless communication technology, wireless communication networks face numerous challenges, including a sharp increase in the number of users, increasingly diversified service types, and explosive growth in data traffic. Traditional wireless communication network resource scheduling methods, mainly based on fixed rules and preset parameters, are difficult to adapt to complex and ever-changing network environments and dynamic user needs. For example, in densely populated areas, traditional scheduling methods may fail to allocate spectrum resources reasonably, leading to problems such as signal congestion and reduced data transmission rates for some users. For different service types, such as real-time voice calls and video conferencing with high requirements and file downloads with high latency tolerance, traditional methods struggle to differentiate resource allocation based on service characteristics, thus affecting overall network performance and user experience. Furthermore, traditional methods are inefficient when handling large-scale data and complex computational tasks, unable to respond promptly to changes in network status, and fail to meet the high efficiency and flexibility requirements of modern wireless communication networks for resource scheduling.

[0003] Based on this, in order to solve the resource scheduling problem of wireless communication networks, this invention provides an AI-based intelligent resource scheduling system for wireless communication networks. Summary of the Invention

[0004] To address the problems of the above solutions, this invention provides an AI-based intelligent resource scheduling system for wireless communication networks.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] An AI-based intelligent resource scheduling system for wireless communication networks, comprising a cloud management platform and device terminals;

[0007] Furthermore, the cloud management platform communicates with each device.

[0008] The cloud management platform includes a platform analysis module;

[0009] The platform analysis module is used to perform reserve analysis, receive regional material data sent by various devices, and establish regional prediction models based on the regional material data.

[0010] The real-time acquired regional material data is analyzed based on the regional prediction model to obtain the unit prediction data of each unit region within the prediction period; and a unit prediction map of the prediction time is generated based on the unit prediction data of each unit region.

[0011] A digital twin model is established based on the current wireless communication network. Resource scheduling simulation is performed on the unit prediction map of each unit area based on the digital twin model to obtain the resource scheduling scheme for the corresponding prediction time, which is marked as the basic scheduling scheme. The basic scheduling scheme and the unit prediction map are integrated into the scheduling guidance data of the unit area, and the scheduling guidance data is sent to the area analysis module of the corresponding device.

[0012] Furthermore, before simulating resource scheduling in the unit prediction maps of each unit region based on the digital twin model, each user in the unit prediction map is classified.

[0013] Furthermore, the users in the cell prediction graph are classified, including:

[0014] Pre-defined classification criteria are established, and the platform develops a classification evaluation model.

[0015] The user information of each user in the unit prediction graph is combined in pairs to obtain several sets of combined information. The corresponding combined information and classification criteria are then input into the classification evaluation model for analysis to obtain the classification results between the corresponding users.

[0016] Users are categorized based on the classification results among them.

[0017] Furthermore, the regional material data for each unit area is adapted, and the adaptation methods include:

[0018] Establish an adaptation evaluation model; extract features from the material data of each region based on the adaptation anomaly feature set to obtain the user adaptation features of each user;

[0019] The user adaptation features and the set of adaptation anomalies are integrated into the corresponding input data and input into the adaptation evaluation model for analysis to obtain the user adaptation value of the corresponding user. The user adaptation value is 1 or 0.

[0020] When the user adaptation value is 0, the user adaptation result is that the user adaptation is normal.

[0021] When the user adaptation value is 1, the user adaptation result is user adaptation error.

[0022] The material data for the corresponding region is processed based on the user adaptation results for each user.

[0023] Furthermore, the expression for the adaptation evaluation model is:

[0024] ;

[0025] In the formula: (r, U) are the input data, r represents the user adaptation feature of the corresponding user, U is the set of adaptation anomalies; r→U means that the user adaptation feature conforms to the set of adaptation anomalies; the output data is the user adaptation value DP(r, U).

[0026] The device includes a data acquisition module, a regional analysis module, and a resource scheduling module;

[0027] The acquisition module is used to collect user information in real time from the unit area of ​​the corresponding base station.

[0028] The regional analysis module is used to perform regional analysis, generate a unit regional map based on the user information of each user in the unit region, generate regional material data based on the real-time unit regional map, and send the regional material data to the platform analysis module of the cloud management platform.

[0029] The system receives scheduling guidance data sent by the cloud management platform in real time, identifies the basic scheduling scheme corresponding to the scheduling guidance data, and evaluates whether the basic scheduling scheme needs to be adjusted based on the unit area map.

[0030] When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme;

[0031] When the evaluation requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme.

[0032] Furthermore, based on the unit area map, assess whether adjustments to the basic scheduling scheme are necessary, including:

[0033] The unit area map is analyzed based on the basic scheduling scheme to obtain the communication satisfaction results for each user. The communication satisfaction results include those that satisfy user communication and those that do not.

[0034] Based on the communication satisfaction results of users at each location, determine whether the basic scheduling scheme meets the regional communication requirements of the unit area;

[0035] When it is determined that the basic scheduling scheme does not meet the regional communication requirements, an assessment is needed to adjust the basic scheduling scheme.

[0036] When it is determined that the basic scheduling scheme meets the regional communication requirements, the evaluation does not require adjustments to the basic scheduling scheme.

[0037] The resource scheduling module is used to perform resource scheduling, obtain the target scheduling plan for the unit area in real time, and perform resource scheduling for the unit area according to the target scheduling plan.

[0038] AI-based intelligent resource scheduling methods for wireless communication networks include:

[0039] Acquire regional material data for each unit area, and build a regional prediction model based on the material data for each region.

[0040] The regional forecasting model is used to analyze the regional material data to obtain the unit forecasting data of each unit region during the forecasting period; and the unit forecasting map of the forecasting time is generated based on the unit forecasting data of each unit region.

[0041] Establish a digital twin model, simulate resource scheduling for the unit prediction map of each unit area based on the digital twin model, and obtain the basic scheduling scheme for the corresponding prediction time; integrate the basic scheduling scheme and the unit prediction map into scheduling guidance data for the unit area, and send the scheduling guidance data to the corresponding device terminal;

[0042] The device collects user information entering the corresponding base station's unit area in real time and generates a unit area map based on the user information of each user in the unit area.

[0043] Receive scheduling guidance data in real time, identify the basic scheduling scheme corresponding to the scheduling guidance data, and evaluate whether the basic scheduling scheme needs to be adjusted based on the unit area map;

[0044] When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme;

[0045] When the assessment requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme;

[0046] Resource scheduling is performed on the unit area according to the target scheduling plan.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] The AI-based intelligent resource scheduling system for wireless communication networks proposed in this invention achieves adaptive perception and dynamic decision-making in complex and ever-changing network environments by introducing artificial intelligence technology. The system can automatically optimize spectrum resource allocation strategies based on user distribution density, differences in service characteristics, and real-time network status, effectively alleviating signal congestion in densely populated areas and significantly improving data transmission rate stability. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0051] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, the AI-based intelligent resource scheduling system for wireless communication networks includes a cloud management platform and device terminals; the cloud management platform and each device terminal are generally connected via a communication link; one device terminal corresponds to one base station.

[0053] The cloud management platform includes a platform analysis module;

[0054] The platform analysis module is used to perform platform analysis, receive regional material data sent by various devices, and establish regional prediction models based on the regional material data. That is, taking the current user information of each unit region as input, it predicts the user information of each user in each unit region in the future time period, mainly estimating information related to wireless communication network resource scheduling such as location and communication classification, forming unit prediction data for each unit region. The future time period is marked as the prediction time period, and the prediction accuracy of the regional prediction model is determined based on relevant information such as changes in the prediction accuracy of the regional prediction model. Based on the unit prediction data of each unit region, a unit prediction map for the corresponding prediction time is generated, that is, a unit region map for the corresponding prediction time.

[0055] A digital twin model is established based on the current wireless communication network to simulate the resource scheduling of the wireless communication network. The digital twin model is then adjusted according to data changes. Resource scheduling analysis is performed on the unit prediction map of each unit area based on the digital twin model to obtain the resource scheduling scheme for the corresponding prediction time, which is marked as the basic scheduling scheme. In other words, the optimal wireless communication network resource scheduling method is determined by simulation analysis using the digital twin model under the current conditions. The basic scheduling scheme and the unit prediction map are integrated into the scheduling guidance data for the corresponding unit area, and the scheduling guidance data is sent to the area analysis module of the corresponding device.

[0056] In one embodiment, the regional material data of each unit area is adapted. Because of the mobility of users between different unit areas, some users will have adaptability in adjacent or non-adjacent unit areas. For example, if a user works from unit area A, through unit areas B and C to unit area D, their location trajectory, time, etc. will have adaptability. Based on the adaptability, it is determined whether the relevant data of the user in the regional material data of the corresponding unit area is normal. If it is normal, no processing is performed; if it is abnormal, the data is corrected.

[0057] The specific adaptation analysis and processing methods can be based on existing methods, such as machine learning.

[0058] In one embodiment, the adaptation processing of the regional material data for each unit area includes:

[0059] An adaptation evaluation model is established and trained using a manually labeled training set. Labeling is based on factors such as temporal continuity and non-conflict, and normal location changes. Data is then categorized as adaptation anomalies. For example, discontinuous or overlapping time periods, or abnormal location jumps in user data after entering the system are considered adaptation anomalies—cases that should not occur under normal circumstances. These anomalies are summarized to form an adaptation anomaly feature set. Based on this feature set, corresponding historical data is labeled to determine which users exhibit adaptation anomalies. The expression for the adaptation evaluation model is:

[0060] ;

[0061] In the formula: (r, U) are the input data, r represents the user adaptation feature of the corresponding user, and U is the set of adaptation anomaly features; r→U means that the user adaptation feature conforms to the set of adaptation anomaly features, that is, the user adaptation feature has the corresponding adaptation anomaly feature in the set of adaptation anomaly features; the output data is the user adaptation value DP(r, U), and the user adaptation value is 1 or 0.

[0062] Based on the adaptation anomaly feature set, feature extraction is performed on the material data of each region to obtain the unit user features of each user in each unit region. The unit user features are integrated into the user adaptation features of the user. The user adaptation features and the adaptation anomaly feature set are integrated into the corresponding input data and input into the adaptation evaluation model for analysis to obtain the user adaptation value of the corresponding user.

[0063] When the user adaptation value is 0, the user adaptation result is that the user adaptation is normal.

[0064] When the user adaptation value is 1, the user adaptation result is user adaptation error.

[0065] The corresponding regional material data is processed based on the user adaptation results of each user; that is, the regional material data of the corresponding user in the corresponding unit area with user adaptation anomalies is processed. The specific processing method follows the existing abnormal data processing method to ensure data consistency and other properties.

[0066] In one embodiment, the regional prediction model is built based on existing intelligent technologies, such as deep learning computing, or it can be built using large model technology. In particular, a variety of prediction technologies can be used for prediction.

[0067] In one embodiment, the digital twin model is built based on existing digital twin technology.

[0068] In one embodiment, to improve the simulation efficiency of the digital twin model, users within each unit prediction map can be pre-classified and evaluated based on whether they are simulated as a whole, such as based on user location, communication type, etc., or based on existing clustering algorithms, classification algorithms, etc.

[0069] For example, a classification standard is preset, and a classification evaluation model is established based on algorithms such as the Isolation Forest algorithm, machine learning, and deep learning. The classification evaluation model is used to analyze whether the user information of two users meets the classification standard; the platform presets a corresponding training set for training.

[0070] The user information of each user in the unit prediction graph is combined in pairs to obtain several sets of combination information. For example, three users A, B and C can be combined in pairs to form AB, AC, and BC. The corresponding combination information and classification criteria are used as input data into the classification evaluation model for analysis to obtain the classification results between the corresponding users.

[0071] Users are categorized based on the classification results among them.

[0072] The device includes a data acquisition module, a regional analysis module, and a resource scheduling module;

[0073] The acquisition module is used to collect user information entering the unit area of ​​the base station in real time. The unit area is the communication area that the base station is responsible for, such as a base station cell. The user information includes user number, location, communication category and other related information. The communication category is determined according to the communication type corresponding to the current user, such as voice call, video service, data service (mainly involving Internet browsing, file download, mobile payment, etc.), Internet of Things service (such as intelligent parking system, intelligent lighting system, etc.).

[0074] In one embodiment, the platform pre-defines various communication categories, and then intelligently determines the communication category based on the user's current communication situation.

[0075] The region analysis module is used to perform region analysis, generate a unit region map based on the user information of each user in the unit region, and generate region material data based on the real-time unit region map. The region material data is the accumulated unit region map data in the unit region, which is used to analyze the user communication situation in the unit region; and send the region material data to the platform analysis module of the cloud management platform.

[0076] It receives scheduling guidance data sent by the cloud management platform in real time, identifies the basic scheduling scheme and unit prediction map corresponding to the scheduling guidance data, compares the unit prediction map with the unit area map, and assesses whether the basic scheduling scheme needs to be adjusted.

[0077] When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme;

[0078] When the evaluation requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme.

[0079] In one embodiment, assessing whether adjustments to the basic scheduling scheme are needed includes:

[0080] By comparing the cell region map and the cell prediction map, prediction difference data is obtained, which is the data that is different between the cell prediction map and the cell region map. Based on the degree of deviation of the prediction difference data, it is determined whether the basic scheduling scheme meets the communication requirements of each region, and then it is determined whether the basic scheduling scheme needs to be optimized and adjusted. This can be evaluated based on the existing methods.

[0081] In one embodiment, assessing whether adjustments to the basic scheduling scheme are needed includes:

[0082] The unit area map is analyzed based on the basic scheduling scheme to obtain the communication satisfaction results for each user. The communication satisfaction results include those that satisfy user communication and those that do not. Intelligent judgment is made based on user communication needs, regional communication resources, etc., and the judgment is made based on historical communication data using the existing judgment results.

[0083] Based on the communication satisfaction results of users at each location, determine whether the basic scheduling scheme meets the regional communication requirements of the unit area; the regional communication requirements are set by the users according to the communication requirements guarantee, or can be set according to relevant regulations and specifications; specifically, determine whether the regional communication requirements are met based on the existing methods, such as preset different communication categories or user weight coefficients, calculate the non-compliance rate of the unit area, and make a judgment based on the non-compliance rate;

[0084] When it is determined that the basic scheduling scheme does not meet the regional communication requirements, an assessment is needed to adjust the basic scheduling scheme.

[0085] When it is determined that the basic scheduling scheme meets the regional communication requirements, the evaluation does not require adjustments to the basic scheduling scheme.

[0086] In one embodiment, the basic scheduling scheme is optimized and adjusted. Based on the evaluation process of the basic scheduling scheme, unqualified issues are identified, and the basic scheduling scheme is adjusted to overcome these unqualified issues, so that the adjusted basic scheduling scheme meets the requirements and the evaluation does not require further adjustment of the basic scheduling scheme. Adaptive intelligent optimization models can be established using resources on the device side, such as those based on machine learning and deep learning algorithms, and processed using techniques such as pruning and knowledge distillation, so that they can run on the device side.

[0087] The resource scheduling module is used to perform resource scheduling, obtain the target scheduling plan for the unit area in real time, and perform resource scheduling for the unit area according to the target scheduling plan.

[0088] AI-based intelligent resource scheduling methods for wireless communication networks include:

[0089] Acquire regional material data for each unit area, and build a regional prediction model based on the material data for each region.

[0090] The regional forecasting model is used to analyze the regional material data to obtain the unit forecasting data of each unit region during the forecasting period; and the unit forecasting map of the forecasting time is generated based on the unit forecasting data of each unit region.

[0091] Establish a digital twin model, simulate resource scheduling for the unit prediction map of each unit area based on the digital twin model, and obtain the basic scheduling scheme for the corresponding prediction time; integrate the basic scheduling scheme and the unit prediction map into scheduling guidance data for the unit area, and send the scheduling guidance data to the corresponding device terminal;

[0092] The device collects user information entering the corresponding base station's unit area in real time and generates a unit area map based on the user information of each user in the unit area.

[0093] Receive scheduling guidance data in real time, identify the basic scheduling scheme corresponding to the scheduling guidance data, and evaluate whether the basic scheduling scheme needs to be adjusted based on the unit area map;

[0094] When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme;

[0095] When the assessment requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme;

[0096] Resource scheduling is performed on the unit area according to the target scheduling plan.

[0097] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0098] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An AI-based intelligent resource scheduling system for wireless communication networks, characterized in that, This includes cloud management platforms and device terminals; The cloud management platform includes a platform analysis module; the device includes a data acquisition module, a regional analysis module, and a resource scheduling module. The platform analysis module is used to perform reserve analysis, receive regional material data sent by various devices, and establish regional prediction models based on the regional material data. The real-time acquired regional material data is analyzed based on the regional prediction model to obtain the unit prediction data of each unit region within the prediction period; and a unit prediction map of the prediction time is generated based on the unit prediction data of each unit region. A digital twin model is established based on the current wireless communication network. Based on the digital twin model, resource scheduling simulation is performed on the unit prediction map of each unit area to obtain the resource scheduling scheme for the corresponding prediction time, which is marked as the basic scheduling scheme. The basic scheduling scheme and the unit prediction map are integrated into the scheduling guidance data of the unit area and sent to the area analysis module of the corresponding device. The acquisition module is used to collect user information entering the unit area of ​​the corresponding base station in real time; The regional analysis module is used to perform regional analysis, generate a unit regional map based on the user information of each user in the unit region, generate regional material data based on the real-time unit regional map, and send the regional material data to the platform analysis module of the cloud management platform. It receives scheduling guidance data sent by the cloud management platform in real time, identifies the basic scheduling scheme corresponding to the scheduling guidance data, and evaluates whether the basic scheduling scheme needs to be adjusted based on the unit area map; When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme; When the assessment requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme; The resource scheduling module is used to perform resource scheduling, obtain the target scheduling plan for the unit area in real time, and perform resource scheduling for the unit area according to the target scheduling plan.

2. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 1, characterized in that, The cloud management platform communicates with each device.

3. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 1, characterized in that, Before performing resource scheduling simulation on the unit prediction map of each unit region based on the digital twin model, each user in the unit prediction map is classified.

4. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 3, characterized in that, Classify each user in the cell prediction graph, including: Pre-defined classification criteria are established, and the platform develops a classification evaluation model. The user information of each user in the unit prediction graph is combined in pairs to obtain several sets of combined information. The corresponding combined information and classification criteria are then input into the classification evaluation model for analysis to obtain the classification results between the corresponding users. Users are categorized based on the classification results among them.

5. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 1, characterized in that, The regional material data for each unit area is adapted, and the adaptation methods include: Establish an adaptation evaluation model; extract features from the material data of each region based on the adaptation anomaly feature set to obtain the user adaptation features of each user; The user adaptation features and the set of adaptation anomalies are integrated into the corresponding input data and input into the adaptation evaluation model for analysis to obtain the user adaptation value of the corresponding user. The user adaptation value is 1 or 0. When the user adaptation value is 0, the user adaptation result is that the user adaptation is normal. When the user adaptation value is 1, the user adaptation result is user adaptation error. The material data for the corresponding region is processed based on the user adaptation results for each user.

6. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 5, characterized in that, The expression for the fit evaluation model is: ； In the formula: (r, U) are the input data, r represents the user adaptation feature of the corresponding user, U is the set of adaptation anomalies; r→U means that the user adaptation feature conforms to the set of adaptation anomalies; the output data is the user adaptation value DP(r, U).

7. The AI-based intelligent resource scheduling system for wireless communication networks according to claim 1, characterized in that, Assess whether adjustments to the basic scheduling scheme are needed based on the unit area map, including: The unit area map is analyzed based on the basic scheduling scheme to obtain the communication satisfaction results for each user. The communication satisfaction results include those that satisfy user communication and those that do not. Based on the communication satisfaction results of users at each location, determine whether the basic scheduling scheme meets the regional communication requirements of the unit area; When it is determined that the basic scheduling scheme does not meet the regional communication requirements, an assessment is needed to adjust the basic scheduling scheme. When it is determined that the basic scheduling scheme meets the regional communication requirements, the evaluation does not require adjustments to the basic scheduling scheme.

8. An AI-based intelligent resource scheduling method for wireless communication networks, characterized in that, An AI-based intelligent resource scheduling system for wireless communication networks, as described in any one of claims 1 to 7, comprising: Acquire regional material data for each unit area, and build a regional prediction model based on the material data for each region. The regional forecasting model is used to analyze the regional material data to obtain the unit forecasting data of each unit region during the forecasting period; and the unit forecasting map of the forecasting time is generated based on the unit forecasting data of each unit region. Establish a digital twin model, simulate resource scheduling for the unit prediction map of each unit area based on the digital twin model, and obtain the basic scheduling scheme for the corresponding prediction time; integrate the basic scheduling scheme and the unit prediction map into scheduling guidance data for the unit area, and send the scheduling guidance data to the corresponding device terminal; The device collects user information entering the corresponding base station's unit area in real time and generates a unit area map based on the user information of each user in the unit area. Receive scheduling guidance data in real time, identify the basic scheduling scheme corresponding to the scheduling guidance data, and evaluate whether the basic scheduling scheme needs to be adjusted based on the unit area map; When the evaluation does not require adjustments to the basic scheduling scheme, the basic scheduling scheme is marked as the target scheduling scheme; When the assessment requires adjustments to the basic scheduling scheme, the basic scheduling scheme is optimized and adjusted to obtain the target scheduling scheme; Resource scheduling is performed on the unit area according to the target scheduling plan.

Images