Service operation scheduling method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a service operation scheduling method and device, electronic equipment and a storage medium. The service operation scheduling method comprises the following steps: collecting full-scene service information in a service operation process; preprocessing the full-scene service information to obtain first full-scene service data; according to the first full-scene service data, performing prediction to obtain a first future service operation scheduling prediction analysis result; and obtaining a service operation scheduling scheme according to the first future service operation scheduling prediction analysis result. In the embodiment of the invention, the service information can be described more comprehensively and accurately by effectively utilizing the full-scene service information in the service operation process, and the future service operation scheduling prediction analysis result can be automatically predicted by analyzing the full-scene service information, so that the service operation scheduling scheme is obtained, and the service operation scheduling efficiency is improved. Therefore, the efficiency and accuracy of service operation scheduling are improved, and the requirement of providing efficient services for users is met.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a service operation scheduling method, device, electronic device and storage medium. Background Art

[0002] Service operation refers to the process of transforming production factors (inputs) such as manpower, materials, equipment, capital, information, and technology into intangible services (outputs). Analyzing service types through different classification dimensions and different perspectives will help us gain a deeper understanding of the connotation and essence of the service industry, find commonalities, grasp individuality, and conduct targeted research on the operation and management of service industry enterprises.

[0003] With the continuous development of science and technology, service operation scheduling faces increasingly higher requirements for efficiency and accuracy. Traditional service operation scheduling methods often rely on simple data analysis based on manual experience, resulting in low efficiency and accuracy. Summary of the Invention

[0004] In view of the above problems, the embodiments of the present application propose a service operation scheduling method, device, electronic device and storage medium to solve the problem of low efficiency and accuracy of service operation scheduling.

[0005] According to one aspect of an embodiment of the present application, a service operation scheduling method is provided, the method comprising:

[0006] Collect full-scenario service information during service operation;

[0007] Preprocessing the full-scenario service information to obtain first full-scenario service data;

[0008] Predicting and obtaining a first future service operation scheduling prediction analysis result based on the first full-scenario service data;

[0009] A service operation scheduling plan is obtained based on the first future service operation scheduling prediction analysis result.

[0010] Optionally, the predicting and obtaining of the first future service operation scheduling prediction analysis result based on the first full-scenario service data includes: using the first full-scenario service data as the input of a pre-trained prediction analysis model, and obtaining the first future service operation scheduling prediction analysis result output by the prediction analysis model.

[0011] Optionally, the predictive analysis model is trained in the following manner:

[0012] Obtaining a training sample, where the training sample includes the second full-scenario service data and an actual analysis result of future service operation scheduling corresponding to the second full-scenario service data;

[0013] Using the second full-scenario service data as input to the prediction analysis model to be trained, and obtaining a second future service operation scheduling prediction analysis result output by the prediction analysis model to be trained;

[0014] The loss function is calculated based on the second future service operation scheduling prediction analysis result and the future service operation scheduling actual analysis result. If the loss function does not meet the set conditions, the parameters of the prediction analysis model to be trained are adjusted to continue training until the loss function meets the set conditions, thereby obtaining a trained prediction analysis model.

[0015] Optionally, obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result includes: selecting a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result; and obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy.

[0016] Optionally, obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy includes: using the first future service operation scheduling prediction analysis result, the target service operation scheduling strategy and prompt information as inputs of a large language model to obtain the service operation scheduling plan output by the large language model.

[0017] Optionally, after obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result, the method further includes: obtaining feedback information during the execution of the service operation scheduling plan, and using the feedback information as a basis for adjusting the service operation scheduling plan.

[0018] Optionally, after collecting the full-scenario service information during the service operation process, the method further includes:

[0019] Calculating a first communication transmission evaluation factor corresponding to the full-scenario service information;

[0020] If the first communication transmission evaluation factor is greater than the factor threshold, calculating the second communication transmission evaluation factor corresponding to the full-scenario service information;

[0021] Calculating a communication operation evaluation coefficient corresponding to the full-scenario service information based on the first communication transmission evaluation factor and the second communication transmission evaluation factor;

[0022] If the communication operation evaluation coefficient is less than the coefficient threshold, it is determined that the communication state is abnormal.

[0023] Optionally, the calculation of the first communication transmission evaluation factor corresponding to the full-scene service information includes: obtaining the communication operation parameters corresponding to each first-type transmission of the full-scene service information, the first-type transmission being a transmission in which the amount of data transmitted in a single transmission is greater than a data amount threshold; calculating the first communication transmission evaluation factor based on the communication operation parameters corresponding to each first-type transmission.

[0024] Optionally, the calculation of the second communication transmission evaluation factor corresponding to the full-scene service information includes: obtaining the communication operation parameters corresponding to each second-type transmission of the full-scene service information, the second-type transmission being a transmission in which the amount of data transmitted in a single transmission is less than or equal to a data amount threshold; and calculating the second communication transmission evaluation factor based on the communication operation parameters corresponding to each second-type transmission.

[0025] Optionally, the communication operation evaluation coefficient is calculated using the following formula:

[0026] F=log(1+K)-log(1+S)

[0027] Among them, F represents the communication operation evaluation coefficient, K represents the second communication transmission evaluation factor, and S represents the first communication transmission evaluation factor.

[0028] According to another aspect of an embodiment of the present application, a service operation scheduling device is provided, the device comprising:

[0029] Information collection module, used to collect full-scenario service information during service operation;

[0030] an information processing module, configured to pre-process the full-scenario service information to obtain first full-scenario service data;

[0031] A prediction analysis module, configured to predict and obtain a first future service operation scheduling prediction analysis result based on the first full-scenario service data;

[0032] The decision generation module is used to obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

[0033] Optionally, the predictive analysis module is specifically used to use the first full-scenario service data as input of a pre-trained predictive analysis model to obtain the first future service operation scheduling predictive analysis result output by the predictive analysis model.

[0034] Optionally, the predictive analysis model is trained in the following manner:

[0035] Obtaining a training sample, where the training sample includes the second full-scenario service data and an actual analysis result of future service operation scheduling corresponding to the second full-scenario service data;

[0036] Using the second full-scenario service data as input to the prediction analysis model to be trained, and obtaining a second future service operation scheduling prediction analysis result output by the prediction analysis model to be trained;

[0037] The loss function is calculated based on the second future service operation scheduling prediction analysis result and the future service operation scheduling actual analysis result. If the loss function does not meet the set conditions, the parameters of the prediction analysis model to be trained are adjusted to continue training until the loss function meets the set conditions, thereby obtaining a trained prediction analysis model.

[0038] Optionally, the decision generation module is specifically used to select a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result; and obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy.

[0039] Optionally, the decision generation module is specifically configured to use the first future service operation scheduling prediction analysis result, the target service operation scheduling strategy and prompt information as inputs of a large language model to obtain the service operation scheduling plan output by the large language model.

[0040] Optionally, the apparatus further comprises: an execution optimization module, configured to obtain feedback information during the execution of the service operation scheduling plan, wherein the feedback information serves as a basis for adjusting the service operation scheduling plan.

[0041] Optionally, the device also includes: an evaluation module, used to calculate a first communication transmission evaluation factor corresponding to the full-scene service information; if the first communication transmission evaluation factor is greater than the factor threshold, then calculating the second communication transmission evaluation factor corresponding to the full-scene service information; based on the first communication transmission evaluation factor and the second communication transmission evaluation factor, calculating the communication operation evaluation coefficient corresponding to the full-scene service information; if the communication operation evaluation coefficient is less than the coefficient threshold, determining that the communication status is abnormal.

[0042] Optionally, the evaluation module includes: a first calculation unit, used to obtain the communication operation parameters corresponding to each first-type transmission of the full-scene service information, the first-type transmission being a transmission in which the amount of data transmitted in a single time is greater than a data amount threshold; and calculating the first communication transmission evaluation factor based on the communication operation parameters corresponding to each first-type transmission.

[0043] Optionally, the evaluation module includes: a second calculation unit, used to obtain the communication operation parameters corresponding to each second-type transmission of the full-scene service information, the second-type transmission being a transmission in which the amount of data transmitted in a single transmission is less than or equal to a data amount threshold; and calculating the second communication transmission evaluation factor based on the communication operation parameters corresponding to each second-type transmission.

[0044] Optionally, the evaluation module includes: a third calculation unit, configured to calculate the communication operation evaluation coefficient using the following formula:

[0045] F=log(1+K)-log(1+S)

[0046] Among them, F represents the communication operation evaluation coefficient, K represents the second communication transmission evaluation factor, and S represents the first communication transmission evaluation factor.

[0047] According to another aspect of an embodiment of the present application, an electronic device is provided, which includes a processor and a computer-readable storage medium, on which a computer program is stored; when the computer program is executed by the processor, the processor executes the service operation scheduling method as described in any one of the above items.

[0048] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the service operation scheduling method as described in any one of the above items.

[0049] In an embodiment of the present application, full-scene service information during the service operation process is collected, the full-scene service information is pre-processed to obtain first full-scene service data, a first future service operation scheduling prediction analysis result is predicted based on the first full-scene service data, and a service operation scheduling plan is obtained based on the first future service operation scheduling prediction analysis result. It can be seen that in an embodiment of the present application, by effectively utilizing the full-scene service information during the service operation process, the service information can be described more comprehensively and accurately, and by analyzing the full-scene service information, the future service operation scheduling prediction analysis result can be automatically predicted, and then the service operation scheduling plan can be obtained, thereby improving the efficiency and accuracy of service operation scheduling and meeting the needs of providing efficient services to users.

[0050] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some drawings of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 This is a flow chart of a service operation scheduling method according to an embodiment of the present application;

[0053] Figure 2 is a flow chart of another service operation scheduling method according to an embodiment of the present application;

[0054] Figure 3 This is a structural block diagram of a service operation scheduling device according to an embodiment of the present application;

[0055] Figure 4 This is a structural block diagram of another service operation scheduling device according to an embodiment of the present application;

[0056] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present application;

[0057] Figure 6 This is a structural block diagram of a computer-readable storage medium in an embodiment of the present application. DETAILED DESCRIPTION

[0058] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] Reference Figure 1 , shows a flowchart of a service operation scheduling method in an embodiment of the present application.

[0060] like Figure 1 As shown, the service operation scheduling method may include the following steps:

[0061] Step 101: Collect full-scenario service information during the service operation process.

[0062] In the embodiments of the present application, full-scene perception technology can be used to implement service operation scheduling. Full-scene perception technology mainly refers to the equipment's comprehensive and accurate perception and understanding of the user's environment and situational information through related technologies such as data collection, analysis, and transmission. This perception capability enables products and services to better meet user needs and provide personalized experiences. The implementation of full-scene perception technology can adopt cloud computing, artificial intelligence and other technologies. For example, full-scene perception technology can perceive the service operation status of each environment through the collection of operating data of various lines and resource equipment. In addition, full-scene perception technology also involves data processing and analysis. By collecting and processing large amounts of data, full-scene perception technology can predict user needs and behaviors, thereby providing users with corresponding services and solutions in advance. This predictive capability enables products and services to more proactively and intelligently meet user needs and enhance user experience.

[0063] In the embodiment of the present application, full-scene service information is collected during the service operation process.

[0064] For example, service environment information, device status information, business demand information, personnel configuration information, etc. can be collected when providing services to users during service operations. Based on the collected service environment information, device status information, business demand information, personnel configuration information, etc., full-scene service information based on full-scene perception technology can be determined. For example, the collected service environment information, device status information, business demand information, personnel configuration information, etc. can be determined as the full-scene service information.

[0065] Service environment information may include, but is not limited to, environmental parameters such as temperature, humidity, and lighting at the service location, as well as surrounding traffic conditions and pedestrian flow. Equipment status information may include, but is not limited to, operating status, idle status, waiting status, and fault status. Business demand information may include, but is not limited to, business motivations and business objectives. Staffing information may include, but is not limited to, staffing planning, job analysis, staffing assessment, reasonable staffing, and dynamic optimization and allocation.

[0066] In the embodiment of the present application, data mining, machine learning and other technical means can be used to analyze comprehensive data such as monitoring indicators, alarm information, service call chain topology, historical work orders, fault reports, emergency response plans, etc., analyze the relevance of knowledge information and service request (business) relevance, and provide data support and decision analysis for service operation scheduling.

[0067] Step 102: pre-process the full-scene service information to obtain first full-scene service data.

[0068] For example, in the process of preprocessing the full-scene service information, the collected full-scene service information based on full-scene perception technology can be subjected to preprocessing operations such as cleaning, integration and mining, so as to determine the first full-scene service data with visualization features that is valuable for service operation scheduling.

[0069] First, the full-scene service information is cleaned to obtain cleaned full-scene service information. The cleaning process may include checking the data consistency of the full-scene service information and removing invalid or missing values ​​contained in the full-scene service information, thereby obtaining cleaned full-scene service information that is valuable for service operation scheduling.

[0070] Consistency checking checks data for compliance based on the reasonable value range and interrelationships of each variable. Data outside the normal range, logically illogical, or contradictory data are identified. For example, a variable measured on a 1-7 scale with a value of 0 or a negative weight value should be considered outside the normal range. The specific consistency checking process can be handled based on practical experience and will not be discussed in detail in this embodiment.

[0071] Due to survey, coding and entry errors, there may be some invalid values ​​or missing values ​​in the full-scenario service information, which need to be properly processed. The processing methods can be estimation, whole-case deletion, variable deletion, paired deletion, etc. Estimation is to replace invalid values ​​and missing values ​​with the sample mean, median or mode of a certain variable. This method has a simple processing process. Whole-case deletion is to eliminate samples with missing values. Variable deletion is if there are many invalid values ​​and missing values ​​for a certain variable, and the variable is not particularly important for the problem being studied, then you can consider deleting the variable. Paired deletion is to use special codes to represent invalid values ​​and missing values, while retaining all variables and samples in the data set. In implementation, the corresponding method can be used according to actual needs, and this embodiment does not limit this.

[0072] The cleaned full-scene service information is then integrated to obtain integrated full-scene service information. During the integration process, data integration technology is used to collect, organize, and transform the full-scene service information from different data sources to provide a consistent structure and specifications, thereby determining the integrated full-scene service information in a unified data view. The specific integration process can be handled according to actual needs and will not be discussed in detail in this embodiment.

[0073] Next, the integrated full-scene service information is mined to obtain mined full-scene service information, which is used as the first full-scene service data. During the mining process, patterns that characterize the characteristics of the full-scene service information are found from the integrated full-scene service information in the unified data view, and full-scene service information with visual features is determined. For example, by analyzing the correlation between the data, trend changes, etc., the data is converted into a form that can be intuitively displayed. The specific mining process can be processed according to actual needs and will not be discussed in detail in this embodiment.

[0074] In an embodiment of the present application, the first full-scene service data with visual features can be determined by pre-processing the full-scene service information in the service operation process through cleaning, integration, mining, etc., which can ensure the accuracy and consistency of the first full-scene service data, thereby improving data processing efficiency and data value.

[0075] Step 103: Based on the first full-scenario service data, a first future service operation scheduling prediction analysis result is predicted.

[0076] In the embodiment of the present application, a predictive analysis model can be pre-trained and used to perform predictive analysis on the first full-scenario service data, thereby predicting and obtaining the first future service operation scheduling predictive analysis result. By using the predictive analysis model for prediction, the efficiency and accuracy of the prediction can be improved.

[0077] Exemplarily, the predictive analysis model is trained in the following manner: obtaining training samples, the training samples including second full-scenario service data and actual analysis results of future service operation scheduling corresponding to the second full-scenario service data; using the second full-scenario service data as the input of the predictive analysis model to be trained, and obtaining the second future service operation scheduling predictive analysis result output by the predictive analysis model to be trained; calculating the loss function based on the second future service operation scheduling predictive analysis result and the actual analysis result of the future service operation scheduling; if the loss function does not meet the set conditions, adjusting the parameters of the predictive analysis model to be trained to continue training until the loss function meets the set conditions, thereby obtaining a trained predictive analysis model.

[0078] First, a training sample is obtained and stored. Specifically, historical full-scene data based on full-scene perception technology can be obtained and stored, and the second full-scene service data and the actual analysis results of future service operation scheduling corresponding to the second full-scene service data are extracted from the historical full-scene data to form the training sample.

[0079] Next, a predictive analysis model is constructed. Specifically, an appropriate model type can be selected, using algorithms such as machine learning or deep learning, to construct a predictive analysis model to be trained based on full-scenario perception technology. For example, any applicable model structure, such as a multilayer perceptron, recurrent neural network, convolutional neural network, or large language model, can be used as the predictive analysis model to be trained. The predictive analysis model to be trained is then trained using training samples. The specific training process can be referred to above.

[0080] The loss function may be any applicable type of loss function, such as a cross entropy loss function, a logarithmic loss function, etc. The set condition may be any applicable condition, such as the loss function being less than a set threshold, the loss function converging, etc.

[0081] Exemplarily, the process of predicting the first future service operation scheduling prediction analysis result based on the first full-scenario service data may include: using the first full-scenario service data as the input of a pre-trained prediction analysis model to obtain the first future service operation scheduling prediction analysis result output by the prediction analysis model.

[0082] The first future service operation scheduling prediction analysis results may include, but are not limited to, information such as future service demand and resource distribution. In this embodiment of the present application, an optimized scheduling strategy based on model predictive control implements distributed computing, and uses a finite-time consistency algorithm during the iterative process to exchange information between subsystems to predict future service demand and resource distribution.

[0083] Step 104: Obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

[0084] In an embodiment of the present application, the first future service operation scheduling prediction analysis results based on the full-scene perception technology can be analyzed to determine a service operation scheduling plan.

[0085] Exemplarily, the process of obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result may include: selecting a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result; and obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy.

[0086] In an embodiment of the present application, the first future service operation scheduling prediction analysis results based on full-scene perception technology are deeply mined and relevantly analyzed, and a suitable target service operation scheduling strategy is selected from a variety of service operation scheduling strategies to improve the efficiency of work order processing.

[0087] In implementation, the association relationship between the future service operation scheduling prediction analysis results and the service operation scheduling strategy can be pre-set, and based on the association relationship, the target service operation scheduling strategy associated with the first future service operation scheduling prediction analysis result can be selected from multiple service operation scheduling strategies as the target service operation scheduling strategy.

[0088] Among them, the various service operation scheduling strategies may include but are not limited to first-in-first-out strategy, shortest job first strategy, priority scheduling strategy, and the like.

[0089] After selecting the target service operation scheduling strategy, a service operation scheduling plan based on full-scene perception technology is determined based on the target service operation scheduling strategy.

[0090] Exemplarily, the process of obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis results and the target service operation scheduling strategy may include: using the first future service operation scheduling prediction analysis results, the target service operation scheduling strategy, and prompt information as inputs to a large language model, and obtaining the service operation scheduling plan output by the large language model. The prompt information is used to guide the large language model in analysis and may, for example, include analysis methods. Using the large language model for processing can improve processing efficiency and accuracy.

[0091] Among them, the service operation scheduling plan may include but is not limited to: service process optimization methods, resource scheduling methods, risk warning measures, etc.

[0092] In the embodiment of the present application, by effectively utilizing the full-scene service information in the service operation process, the service information can be described more comprehensively and accurately. By analyzing the full-scene service information, the future service operation scheduling prediction analysis results can be automatically predicted, and then the service operation scheduling plan can be obtained, thereby improving the efficiency and accuracy of service operation scheduling and meeting the needs of providing efficient services to users.

[0093] Reference Figure 2 , shows a flowchart of another service operation scheduling method according to an embodiment of the present application.

[0094] like Figure 2 As shown, the service operation scheduling method may include the following steps:

[0095] Step 201: Collect all-scenario service information during the service operation process.

[0096] Step 202: pre-process the full-scene service information to obtain first full-scene service data.

[0097] Step 203: Based on the first full-scenario service data, a first future service operation scheduling prediction analysis result is predicted.

[0098] Step 204: Obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

[0099] Step 205: Acquire feedback information during the execution of the service operation scheduling plan, and use the feedback information as a basis for adjusting the service operation scheduling plan.

[0100] In an embodiment of the present application, after obtaining the service operation scheduling plan, the service operation scheduling plan is executed, and feedback information during the execution of the service operation scheduling plan is obtained. Subsequently, relevant personnel can adjust and optimize the service operation scheduling plan based on the feedback information, and can also adjust and optimize the prediction analysis model, etc.

[0101] After obtaining the service operation scheduling plan based on full-scene perception technology, the service operation scheduling plan based on full-scene perception technology is executed. Based on the perspective of the manager and the perspective of the executor, feedback is provided on the entire process of executing the service operation scheduling plan based on full-scene perception technology from the process to the final result, and feedback information of the service operation scheduling plan based on full-scene perception technology is determined.

[0102] Obtain feedback information on the service operation scheduling plan based on full-scene perception technology, and adjust and optimize the service operation scheduling plan based on full-scene perception technology based on the feedback information of the service operation scheduling plan to meet the service operation scheduling needs. This can ensure that the algorithm continuously learns and understands the user's goals and expectations, and can also timely adjust the service operation scheduling strategy, predictive analysis model, etc. to further improve the accuracy of service scheduling.

[0103] In the embodiments of the present application, by comprehensively collecting and analyzing full-scene service information, effective perception and utilization of full-scene service information, and its dynamically adjusted and optimized scheduling algorithm, more accurate and efficient service operation management is achieved, the efficiency and quality of service operation scheduling processing are improved, the service operation management process is optimized, and the needs of providing efficient services to users are met. At the same time, operating costs are reduced and customer satisfaction is improved. At the same time, it has good scalability and adaptability, and can be applied to service operation scheduling in various scenarios, helping enterprises to improve operational efficiency, optimize resource allocation, improve service quality, reduce operating costs and enhance security, and provide strong support for the sustainable development of enterprises.

[0104] In an optional embodiment, the information collection module collects full-scene service information during the service operation process and transmits the full-scene service information to the information processing module. The information processing module then pre-processes the full-scene service information to obtain first full-scene service data. Therefore, there is a process of communication between the information collection module and the information processing module to transmit the full-scene service information. In this embodiment, the communication status between the information collection module and the information processing module can be monitored in real time, and a communication anomaly alarm can be issued if the communication status is abnormal.

[0105] Exemplarily, after collecting the full-scene service information during the service operation process, the following steps are also included: calculating the first communication transmission evaluation factor corresponding to the full-scene service information; if the first communication transmission evaluation factor is greater than the factor threshold, determining that the communication status is abnormal; if the first communication transmission evaluation factor is less than or equal to the factor threshold, determining that the communication status is normal.

[0106] Exemplarily, the process of calculating the first communication transmission evaluation factor corresponding to the full-scenario service information may include: obtaining the communication operating parameters corresponding to each first-type transmission of the full-scenario service information, the first-type transmission being a transmission in which the amount of data transmitted in a single transmission is greater than a data amount threshold; calculating the first communication transmission evaluation factor based on the communication operating parameters corresponding to each first-type transmission.

[0107] The information collection module collects in real time the data volume of a single transmission when transmitting the full-scenario service information, compares the data volume of a single transmission with a preset data volume threshold, classifies transmissions with a data volume greater than the data volume threshold as first-class transmissions, and extracts communication operation parameters corresponding to each first-class transmission. The communication operation parameters may include, but are not limited to, the data volume of the transmission, the transmission duration, and the network bandwidth utilization rate.

[0108] The first communication transmission evaluation factor is calculated according to the communication operation parameters corresponding to each first-type transmission by the following formula 1:

[0109]

[0110] Wherein, S represents the first communication transmission evaluation factor, m represents the number of transmissions with a single transmission data volume greater than the data volume threshold (i.e., the first type of transmission), T i represents the transmission duration corresponding to the first type of transmission of the i-th time, T c Indicates the theoretical transmission time corresponding to the data volume threshold, X i represents the amount of data transmitted corresponding to the first type of transmission for the i-th time, X c represents the data volume threshold, P irepresents the change in network bandwidth utilization corresponding to the first type of transmission for the i-th time, P ci It represents the maximum allowable increase in the network bandwidth corresponding to the i-th first-class transmission.

[0111] The change in network bandwidth utilization for the i-th first-class transmission is calculated as follows: the change in network bandwidth utilization for the i-th first-class transmission relative to the network bandwidth utilization for the previous transmission. The maximum allowable increase in network bandwidth for the i-th first-class transmission is calculated as the difference between the upper limit of the rated network bandwidth utilization range and the network bandwidth utilization for the previous transmission. The maximum allowable increase is calculated as the difference between the upper limit and the utilization. This is done to dynamically assess the network's remaining carrying capacity in the current state and prevent network congestion caused by data transmission.

[0112] In the above-described method, by collecting data transmission information in real time, continuous and uninterrupted monitoring of the communication status can be achieved. The first communication transmission evaluation factor is a quantitative indicator that comprehensively considers multiple factors, such as data transmission duration, network bandwidth utilization, the growth rate of network bandwidth utilization, and the maximum allowable increase in network bandwidth. It can more comprehensively and accurately reflect the efficiency and stability of communication transmission. By comparing the amount of data transmitted in a single transmission with a preset data volume threshold, when the amount of data transmitted in a single transmission exceeds the threshold, further analysis of communication operating parameters is performed. Based on this comprehensive analysis and quantitative evaluation of communication operating parameters, it has higher accuracy and reliability, and can intelligently identify potential communication anomalies, ensuring the stability and reliability of the communication system. Through real-time monitoring of communication status and anomaly alarms, system administrators can promptly detect and resolve communication problems, thereby preventing communication failures from affecting the overall performance of the system. It also helps system maintenance personnel perform preventive maintenance, further improving system stability and availability, reducing the risk of communication failures, and providing strong guarantees for the normal operation of the system.

[0113] Exemplarily, after collecting the full-scene service information during the service operation process, the following steps are also included: calculating the first communication transmission evaluation factor corresponding to the full-scene service information; if the first communication transmission evaluation factor is greater than the factor threshold, calculating the second communication transmission evaluation factor corresponding to the full-scene service information; calculating the communication operation evaluation coefficient corresponding to the full-scene service information based on the first communication transmission evaluation factor and the second communication transmission evaluation factor; if the communication operation evaluation coefficient is less than the coefficient threshold, determining that the communication status is abnormal; if the first communication transmission evaluation factor is less than or equal to the factor threshold, or the communication operation evaluation coefficient is greater than or equal to the coefficient threshold, determining that the communication status is normal.

[0114] For the calculation process of the first communication transmission evaluation factor, reference may be made to the relevant description above.

[0115] In this embodiment, if the first communication transmission evaluation factor is greater than the factor threshold, the second communication transmission evaluation factor corresponding to the full-scene service information is continued to be calculated, and the communication operation evaluation coefficient corresponding to the full-scene service information is calculated based on the first communication transmission evaluation factor and the second communication transmission evaluation factor.

[0116] Exemplarily, the process of calculating the second communication transmission evaluation factor corresponding to the full-scene service information may include: obtaining the communication operating parameters corresponding to each second-type transmission of the full-scene service information, the second-type transmission being a transmission in which the amount of data transmitted in a single transmission is less than or equal to a data amount threshold; and calculating the second communication transmission evaluation factor based on the communication operating parameters corresponding to each second-type transmission.

[0117] The information collection module collects in real time the data volume of a single transmission when transmitting the full-scenario service information, compares the single transmission data volume with a preset data volume threshold, classifies transmissions with a single transmission data volume less than or equal to the data volume threshold as second-category transmissions, and extracts communication operation parameters corresponding to each second-category transmission. The communication operation parameters may include, but are not limited to, the transmission data volume, transmission duration, network bandwidth utilization, and the like.

[0118] According to the communication operation parameters corresponding to each second type of transmission, the second communication transmission evaluation factor is calculated using the following formula 2:

[0119]

[0120] Wherein, K represents the second communication transmission evaluation factor, n represents the number of transmissions with a single transmission data volume less than or equal to the data volume threshold (i.e., the second type of transmission), T j represents the transmission duration corresponding to the jth second-class transmission, T c Indicates the theoretical transmission time corresponding to the data volume threshold, X j represents the amount of data transmitted corresponding to the jth second-class transmission, X c represents the data volume threshold, p j represents the change in network bandwidth utilization corresponding to the jth second-class transmission, p cj It represents the maximum allowable increase in the network bandwidth corresponding to the j-th second-class transmission.

[0121] The change range of the network bandwidth utilization corresponding to the jth second-class transmission is: the change range of the network bandwidth utilization corresponding to the jth second-class transmission relative to the network bandwidth utilization corresponding to the transmission at the previous moment; the maximum allowable increase range of the network bandwidth corresponding to the jth second-class transmission is: the difference between the upper limit of the rated network bandwidth utilization range and the network bandwidth utilization corresponding to the transmission at the previous moment of the jth second-class transmission. cj Reflects the dynamic changes of the remaining network bandwidth, p j The combination of the two can reflect the actual occupancy situation and evaluate the impact of transmission on the network in real time. It can comprehensively evaluate the communication status from the two dimensions of bandwidth capacity and utilization efficiency to ensure stable network operation.

[0122] Exemplarily, the communication operation evaluation coefficient is calculated using the following formula 3:

[0123] F=log(1+K)-log(1+S) Formula 3

[0124] Among them, F represents the communication operation evaluation coefficient, K represents the second communication transmission evaluation factor, and S represents the first communication transmission evaluation factor.

[0125] The above approach not only considers situations where the amount of data transmitted exceeds the data volume threshold, but also considers situations where the amount of data transmitted does not exceed the data volume threshold but the communication operating parameters are abnormal. Two different levels of communication transmission evaluation factors (a first communication transmission evaluation factor and a second communication transmission evaluation factor) are used to assess the communication status. The first communication transmission evaluation factor focuses on data transmission situations that exceed the data volume threshold, while the second communication transmission evaluation factor focuses on data transmission situations that do not exceed the data volume threshold but may have performance issues. This allows for more comprehensive and accurate detection of abnormalities in the communication process. By introducing the communication operation evaluation factor, the communication operation status is quantified into a specific value, allowing administrators to more intuitively understand the operating status of the communication system. This evaluation factor also considers the first communication transmission evaluation factor and the second communication transmission evaluation factor, thus comprehensively reflecting the overall performance of the communication system. When the communication operation evaluation factor falls below the preset coefficient threshold, the system automatically determines that the communication status is abnormal and issues an alarm. This intelligent alarm mechanism can promptly detect and address communication problems, avoid the impact of communication failures on system performance, improve the reliability and stability of the communication system, and provide a strong guarantee for the normal operation of the system.

[0126] Reference Figure 3 , shows a structural block diagram of a service operation scheduling device in an embodiment of the present application.

[0127] like Figure 3 As shown, the service operation scheduling device may include the following modules:

[0128] Information collection module 301, used to collect full-scenario service information during service operation;

[0129] An information processing module 302 is configured to pre-process the full-scenario service information to obtain first full-scenario service data;

[0130] The prediction analysis module 303 is configured to predict and obtain a first future service operation scheduling prediction analysis result based on the first full-scenario service data;

[0131] The decision generation module 304 is configured to obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

[0132] Optionally, the prediction analysis module 303 is specifically used to use the first full-scenario service data as the input of a pre-trained prediction analysis model to obtain the first future service operation scheduling prediction analysis result output by the prediction analysis model.

[0133] Optionally, the predictive analysis model is trained in the following manner:

[0134] Obtaining a training sample, where the training sample includes the second full-scenario service data and an actual analysis result of future service operation scheduling corresponding to the second full-scenario service data;

[0135] Using the second full-scenario service data as input to the prediction analysis model to be trained, and obtaining a second future service operation scheduling prediction analysis result output by the prediction analysis model to be trained;

[0136] The loss function is calculated based on the second future service operation scheduling prediction analysis result and the future service operation scheduling actual analysis result. If the loss function does not meet the set conditions, the parameters of the prediction analysis model to be trained are adjusted to continue training until the loss function meets the set conditions, thereby obtaining a trained prediction analysis model.

[0137] Optionally, the decision generation module 304 is specifically configured to select a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result; and obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy.

[0138] Optionally, the decision generation module 304 is specifically configured to use the first future service operation scheduling prediction analysis result, the target service operation scheduling strategy and prompt information as inputs of a large language model to obtain the service operation scheduling solution output by the large language model.

[0139] Optionally, the apparatus further comprises: an execution optimization module, configured to obtain feedback information during the execution of the service operation scheduling plan, wherein the feedback information serves as a basis for adjusting the service operation scheduling plan.

[0140] Optionally, the device also includes: an evaluation module, used to calculate a first communication transmission evaluation factor corresponding to the full-scene service information; if the first communication transmission evaluation factor is greater than the factor threshold, then calculating the second communication transmission evaluation factor corresponding to the full-scene service information; based on the first communication transmission evaluation factor and the second communication transmission evaluation factor, calculating the communication operation evaluation coefficient corresponding to the full-scene service information; if the communication operation evaluation coefficient is less than the coefficient threshold, determining that the communication status is abnormal.

[0141] Optionally, the evaluation module includes: a first calculation unit, used to obtain the communication operation parameters corresponding to each first-type transmission of the full-scene service information, the first-type transmission being a transmission in which the amount of data transmitted in a single time is greater than a data amount threshold; and calculating the first communication transmission evaluation factor based on the communication operation parameters corresponding to each first-type transmission.

[0142] Optionally, the evaluation module includes: a second calculation unit, used to obtain the communication operation parameters corresponding to each second-type transmission of the full-scene service information, the second-type transmission being a transmission in which the amount of data transmitted in a single transmission is less than or equal to a data amount threshold; and calculating the second communication transmission evaluation factor based on the communication operation parameters corresponding to each second-type transmission.

[0143] Optionally, the evaluation module includes: a third calculation unit, configured to calculate the communication operation evaluation coefficient using the following formula:

[0144] F=log(1+K)-log(1+S)

[0145] Among them, F represents the communication operation evaluation coefficient, K represents the second communication transmission evaluation factor, and S represents the first communication transmission evaluation factor.

[0146] In the embodiment of the present application, by effectively utilizing the full-scene service information in the service operation process, the service information can be described more comprehensively and accurately. By analyzing the full-scene service information, the future service operation scheduling prediction analysis results can be automatically predicted, and then the service operation scheduling plan can be obtained, thereby improving the efficiency and accuracy of service operation scheduling and meeting the needs of providing efficient services to users.

[0147] Reference Figure 4 , shows a structural block diagram of another service operation scheduling device according to an embodiment of the present application.

[0148] like Figure 4As shown, the service operation scheduling device may include:

[0149] The information collection module is used to collect full-scenario service information during the service operation process.

[0150] In this embodiment of the present application, the information collection module includes:

[0151] A service collection unit, used to collect service environment information when providing services to users;

[0152] Device collection unit, used to collect device status information when providing services to users;

[0153] A business collection unit is used to collect business demand information when providing services to users;

[0154] The personnel collection unit is used to collect personnel configuration information when providing services to users.

[0155] The information processing module is used to pre-process the full-scene service information to obtain first full-scene service data.

[0156] In this embodiment of the present application, the information processing module includes:

[0157] A data cleaning unit, configured to clean the collected full-scene service information to obtain cleaned full-scene service information;

[0158] A data integration unit, configured to integrate the cleaned full-scene service information to obtain integrated full-scene service information;

[0159] The data mining unit is used to mine the integrated full-scene service information to obtain the first full-scene service data.

[0160] The prediction and analysis module is used to predict and obtain the first future service operation scheduling prediction and analysis results based on the first full-scene service data.

[0161] In this embodiment of the present application, the prediction analysis module includes:

[0162] Data storage unit, used for First Future Service Operation Scheduling Prediction Analysis Results. Acquire and store training samples;

[0163] A model building unit, used for building a predictive analysis model;

[0164] The model prediction unit is used to use the prediction analysis model to predict and analyze the first full-scene service data to obtain the first future service operation scheduling prediction analysis result.

[0165] The decision generation module is used to obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

[0166] In the embodiment of the present application, the decision generation module includes:

[0167] a strategy selection unit, configured to select a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result;

[0168] The decision generation unit is used to generate a service operation scheduling plan based on the target service operation scheduling strategy.

[0169] The execution optimization module is used to obtain feedback information during the execution of the service operation scheduling plan, and the feedback information is used as a basis for adjusting the service operation scheduling plan.

[0170] In the embodiment of the present application, the execution optimization module includes:

[0171] An execution feedback unit, used to execute the service operation scheduling plan and obtain feedback information during the execution of the service operation scheduling plan;

[0172] The adjustment and optimization unit is used to adjust and optimize the service operation scheduling plan based on feedback information.

[0173] Among them, the information collection module, information processing module, prediction analysis module, decision generation module and execution optimization module communicate with each other through data interfaces, which can realize real-time sharing and collaborative processing of information.

[0174] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0175] Reference Figure 5 , shows a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device 11 includes a processor 111 and a computer-readable storage medium 112 , on which a computer program 1121 is stored.

[0176] The processor 111 is used to execute the computer program 1121 stored on the computer-readable storage medium 112. When executing the computer program 1121, the processor 111 implements the service operation scheduling method of any of the above embodiments and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0177] The processor 111 mentioned above may include but is not limited to: a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0178] The computer-readable storage medium 112 mentioned above may include, but is not limited to, read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), electronic erasable programmable read-only memory (EEPROM), hard disk, floppy disk, flash memory, and the like.

[0179] Reference Figure 6 , shows a block diagram of a computer-readable storage medium according to an embodiment of the present application. Figure 6 As shown, a computer program 211 is stored on the computer-readable storage medium 21, and the computer program 211 can be executed by a processor of an electronic device. When the computer program 211 is executed by the processor, the processor executes the service operation scheduling method described in any of the above embodiments and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0180] The various embodiments in this specification are interrelated and are described in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referenced to each other.

[0181] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant local data protection laws and policies and with the authorization given by the owner of the corresponding device.

[0182] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device that includes 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 terminal 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 terminal device that includes the element.

[0183] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0184] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application 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 this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0185] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0186] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0187] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0190] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. In summary, the contents of this specification should not be construed as limiting the present application.

Claims

1. A service operation scheduling method, characterized in that: The method comprises: Collect full-scenario service information during service operation; Preprocessing the full-scenario service information to obtain first full-scenario service data; Predicting and obtaining a first future service operation scheduling prediction analysis result based on the first full-scenario service data; A service operation scheduling plan is obtained based on the first future service operation scheduling prediction analysis result.

2. The method according to claim 1, characterized in that The predicting and obtaining a first future service operation scheduling prediction analysis result based on the first full-scenario service data includes: The first full-scenario service data is used as input to a pre-trained predictive analysis model to obtain the first future service operation scheduling predictive analysis result output by the predictive analysis model.

3. The method according to claim 2, characterized in that The predictive analysis model is trained in the following way: Obtaining a training sample, where the training sample includes the second full-scenario service data and an actual analysis result of future service operation scheduling corresponding to the second full-scenario service data; Using the second full-scenario service data as input to the prediction analysis model to be trained, and obtaining a second future service operation scheduling prediction analysis result output by the prediction analysis model to be trained; The loss function is calculated based on the second future service operation scheduling prediction analysis result and the future service operation scheduling actual analysis result. If the loss function does not meet the set conditions, the parameters of the prediction analysis model to be trained are adjusted to continue training until the loss function meets the set conditions, thereby obtaining a trained prediction analysis model.

4. The method according to claim 1, wherein The obtaining of a service operation scheduling plan according to the first future service operation scheduling prediction analysis result includes: Selecting a target service operation scheduling strategy based on the first future service operation scheduling prediction analysis result; A service operation scheduling plan is obtained according to the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy.

5. The method according to claim 4, characterized in that The obtaining of a service operation scheduling plan according to the first future service operation scheduling prediction analysis result and the target service operation scheduling strategy includes: The first future service operation scheduling prediction analysis result, the target service operation scheduling strategy and prompt information are used as inputs of a large language model to obtain the service operation scheduling solution output by the large language model.

6. The method according to claim 1, characterized in that After obtaining a service operation scheduling plan based on the first future service operation scheduling prediction analysis result, the method further includes: Acquire feedback information during the execution of the service operation scheduling plan, and use the feedback information as a basis for adjusting the service operation scheduling plan.

7. The method according to claim 1, characterized in that After collecting the full-scenario service information during the service operation process, it also includes: Calculating a first communication transmission evaluation factor corresponding to the full-scenario service information; If the first communication transmission evaluation factor is greater than the factor threshold, calculating the second communication transmission evaluation factor corresponding to the full-scenario service information; Calculating a communication operation evaluation coefficient corresponding to the full-scenario service information based on the first communication transmission evaluation factor and the second communication transmission evaluation factor; If the communication operation evaluation coefficient is less than the coefficient threshold, it is determined that the communication state is abnormal.

8. The method according to claim 7, characterized in that The calculating the first communication transmission evaluation factor corresponding to the full-scenario service information includes: Obtaining communication operating parameters corresponding to each first-category transmission of the full-scenario service information, where the first-category transmission is a transmission in which a single transmission data volume is greater than a data volume threshold; The first communication transmission evaluation factor is calculated according to the communication operation parameters corresponding to each first type of transmission.

9. The method according to claim 7, characterized in that The calculating the second communication transmission evaluation factor corresponding to the full-scenario service information includes: Obtaining communication operating parameters corresponding to each second-type transmission of the full-scenario service information, where the second-type transmission is a transmission in which a single transmission data volume is less than or equal to a data volume threshold; The second communication transmission evaluation factor is calculated according to the communication operation parameters corresponding to each second type of transmission.

10. The method according to claim 7, characterized in that The communication operation evaluation coefficient is calculated by the following formula: F=log(1+K)-log(1+S) Among them, F represents the communication operation evaluation coefficient, K represents the second communication transmission evaluation factor, and S represents the first communication transmission evaluation factor.

11. A service operation scheduling device, characterized in that: The device comprises: Information collection module, used to collect full-scenario service information during service operation; an information processing module, configured to pre-process the full-scenario service information to obtain first full-scenario service data; A prediction analysis module, configured to predict and obtain a first future service operation scheduling prediction analysis result based on the first full-scenario service data; The decision generation module is used to obtain a service operation scheduling plan based on the first future service operation scheduling prediction analysis result.

12. An electronic device, characterized in that: The electronic device includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program; When the computer program is executed by the processor, the processor is caused to execute the service operation scheduling method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the service operation scheduling method according to any one of claims 1 to 10.

Images