Resource consumption abnormity early warning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a resource consumption abnormity early warning method and device, electronic equipment and a storage medium, belongs to the technical field of data processing, and is suitable for the fields of financial science and technology and medical treatment. The method comprises the following steps: constructing a target resource consumption prediction model based on historical resource consumption data and resource market data; performing preliminary resource consumption prediction based on the target resource consumption prediction model and the current resource market data to obtain resource consumption prediction data; acquiring resource consumption real-time data; performing associated data fluctuation prediction based on the historical resource market data and the current resource market data to obtain resource market prediction parameters; performing resource consumption adjustment on the resource consumption prediction data based on the resource market prediction parameters to obtain a resource consumption early warning threshold; and performing resource consumption data abnormity early warning based on the resource consumption early warning threshold and the resource consumption real-time data. According to the embodiment of the invention, the accuracy of the resource consumption abnormity early warning threshold can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and is applicable to the fields of financial technology and medicine, and in particular to a method and device for warning of abnormal resource consumption, an electronic device, and a storage medium. Background Art

[0002] Resource consumption anomaly warnings monitor resource consumption data in real time and trigger alerts when consumption exceeds pre-set thresholds. For example, in the fintech sector, warnings of resource consumption anomalies in pension insurance marketing projects can help insurance companies more effectively allocate human resources. Similarly, in the healthcare sector, resource consumption forecasts for equipment resources in medical research projects can help project teams rationally allocate medical equipment, thereby improving project completion efficiency.

[0003] At present, the method of abnormal resource consumption warning usually relies on manual experience to set the warning threshold. However, in this method of abnormal resource consumption warning, setting the warning threshold through manual experience requires a lot of time and energy, resulting in the accuracy of the abnormal resource consumption warning threshold is not high. Therefore, how to improve the accuracy of the abnormal resource consumption warning threshold has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a resource consumption abnormality warning method and device, electronic device and storage medium, aiming to improve the accuracy of the resource consumption abnormality warning threshold.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application provides a method for warning of abnormal resource consumption, the method comprising:

[0006] Obtain historical resource consumption data, historical resource market data and current resource market data;

[0007] Building a target resource consumption prediction model based on the historical resource consumption data and the resource market data;

[0008] Based on the target resource consumption prediction model and the current resource market data, a preliminary resource consumption prediction is performed to obtain resource consumption prediction data;

[0009] Based on the current resource market data, real-time recording of resource consumption is performed to obtain real-time resource consumption data;

[0010] Based on the historical resource market data and the current resource market data, performing correlation data fluctuation prediction to obtain resource market prediction parameters;

[0011] Based on the resource market forecast parameters, adjusting the resource consumption forecast data to obtain a resource consumption warning threshold;

[0012] Based on the resource consumption warning threshold and the real-time resource consumption data, an abnormal resource consumption data warning is performed.

[0013] In some embodiments, the method further includes training the target resource consumption prediction model, including:

[0014] The method of performing correlation data fluctuation prediction based on the historical resource market data and the current resource market data to obtain resource market prediction parameters includes:

[0015] Merging the historical resource market data and the current resource market data to obtain a resource market data set;

[0016] Extracting features from the resource market data set to obtain market data fluctuation features;

[0017] Based on the market data fluctuation characteristics, a preset initial fluctuation prediction model is trained to obtain a target fluctuation prediction model;

[0018] Based on the target fluctuation prediction model and the current resource market data, resource market data prediction is performed to obtain the resource market prediction parameters.

[0019] In some embodiments, recording resource consumption in real time based on the current resource market data to obtain real-time resource consumption data includes:

[0020] Perform resource consumption calculation based on the current resource market data to obtain current resource consumption data;

[0021] The current resource consumption data is stored to obtain the real-time resource consumption data.

[0022] In some embodiments, constructing a target resource consumption prediction model based on the historical resource consumption data and the historical resource market data includes:

[0023] Based on the historical resource market data, a preset model library is screened to obtain an initial resource consumption forecast model;

[0024] Based on the historical resource consumption data and the resource market data, the initial resource consumption prediction model is trained to obtain the target resource consumption prediction model.

[0025] In some embodiments, the method of screening a preset model library based on the historical resource market data to obtain an initial resource consumption prediction model includes:

[0026] Extracting features from the historical resource market data to obtain resource market data features;

[0027] Based on the resource market data characteristics, the model library is screened to obtain candidate models;

[0028] Based on the historical resource consumption data, performing model evaluation on the candidate model to obtain model evaluation data;

[0029] Based on the model evaluation data, the candidate models are screened to obtain the initial resource consumption prediction model.

[0030] In some embodiments, performing an abnormal warning of resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data includes:

[0031] Comparing the real-time resource consumption data with the resource consumption warning threshold to obtain a numerical comparison result, wherein the numerical comparison result includes a result that the value does not exceed the threshold and a result that the value exceeds the threshold;

[0032] If the numerical comparison result is a result that the numerical value does not exceed the threshold value, information packaging is performed on the result that the numerical value does not exceed the threshold value to obtain resource consumption data detection information;

[0033] If the numerical comparison result is the numerical value exceeding the threshold value result, information packaging is performed on the numerical value exceeding the threshold value result to obtain resource consumption data detection information;

[0034] Based on the resource consumption data detection information, an abnormality warning is performed to obtain resource consumption warning data.

[0035] In some embodiments, after performing an abnormal warning on resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data, the method further includes:

[0036] Based on the resource consumption warning data, performing deviation calculation on the real-time resource consumption data and the resource consumption prediction data to obtain resource consumption deviation data;

[0037] Based on the resource consumption deviation data, parameters of the target resource consumption prediction model are fine-tuned to obtain a fine-tuned resource consumption prediction model.

[0038] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a resource consumption abnormality warning device, the device comprising:

[0039] Data acquisition module, used to obtain historical resource consumption data, historical resource market data and current resource market data;

[0040] A model building module, configured to build a target resource consumption prediction model based on the historical resource consumption data and the resource market data;

[0041] A data prediction module, configured to perform preliminary resource consumption prediction based on the target resource consumption prediction model and the current resource market data to obtain resource consumption prediction data;

[0042] A data recording module, configured to record resource consumption in real time based on the current resource market data to obtain real-time resource consumption data;

[0043] A fluctuation prediction module, configured to perform correlation data fluctuation prediction based on the historical resource market data and the current resource market data to obtain resource market prediction parameters;

[0044] A data adjustment module, configured to adjust the resource consumption forecast data based on the resource market forecast parameters to obtain a resource consumption warning threshold;

[0045] The abnormality warning module is used to provide abnormality warning of resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data.

[0046] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0047] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0048] The resource consumption abnormality warning method and device, electronic device and storage medium proposed in this application can achieve preliminary and accurate prediction of resource consumption by acquiring historical and current resource market data and building a target prediction model in combination with historical resource consumption data. On this basis, by recording resource consumption in real time and predicting fluctuations in related data, the resource consumption prediction data is dynamically adjusted to obtain a reasonable resource consumption warning threshold. Finally, the real-time resource consumption data is compared with the warning threshold to achieve abnormal warning of resource consumption data, which can effectively improve the accuracy of the abnormal resource consumption warning threshold, prevent resource waste and potential risks, and improve resource management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flowchart of the resource consumption abnormality warning method provided in an embodiment of the present application;

[0050] Figure 2 yes Figure 1 Flowchart of step S102 in FIG.

[0051] Figure 3 yes Figure 2 Flowchart of step S201 in FIG.

[0052] Figure 4 yes Figure 1 Flowchart of step S104 in FIG.

[0053] Figure 5 yes Figure 1 Flowchart of step S105 in FIG.

[0054] Figure 6 yes Figure 1 Flowchart of step S107 in FIG.

[0055] Figure 7 This is a flowchart of a method for warning abnormal resource consumption provided by another embodiment of the present application;

[0056] Figure 8 This is a schematic diagram of the structure of the abnormal resource consumption warning device provided in an embodiment of the present application;

[0057] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0061] First, let’s analyze some of the terms used in this application:

[0062] Resource Consumption Forecasting System: This integrated solution collects and analyzes historical and current resource consumption and market data, builds and trains forecasting models, and estimates future resource demand. The system monitors resource usage in real time, dynamically adjusts forecasts based on market fluctuations, sets appropriate warning thresholds, and issues timely alerts when anomalies occur, optimizing resource allocation, reducing costs, and improving management efficiency.

[0063] Resource market data: Resource market data refers to information related to resource market transactions during a specific timeframe, covering key factors such as transaction prices, supply and demand, and market fluctuations. In the financial sector, resource market data includes information such as stock prices, foreign exchange rates, and market conditions. In the healthcare sector, resource market data includes data such as drug prices, medical device utilization rates, and medical service charges. Resource market data provides a foundation for building resource consumption forecasting models, assisting in analyzing market trends and predicting changes in resource demand. It is a crucial basis for optimizing resource allocation, reducing costs, and improving management efficiency.

[0064] Resource consumption anomaly warnings monitor resource consumption data in real time and trigger alerts when consumption exceeds pre-set thresholds. For example, in the fintech sector, warnings of resource consumption anomalies in pension insurance marketing projects can help insurance companies more effectively allocate human resources. Similarly, in the healthcare sector, resource consumption forecasts for equipment resources in medical research projects can help project teams rationally allocate medical equipment, thereby improving project completion efficiency.

[0065] At present, the method of abnormal resource consumption warning usually relies on manual experience to set the warning threshold. However, in this method of abnormal resource consumption warning, setting the warning threshold through manual experience requires a lot of time and energy, resulting in the accuracy of the abnormal resource consumption warning threshold is not high. Therefore, how to improve the accuracy of the abnormal resource consumption warning threshold has become a technical problem that needs to be solved urgently.

[0066] Based on this, the embodiments of the present application provide a resource consumption abnormality warning method and device, an electronic device and a storage medium, aiming to improve the accuracy of the resource consumption abnormality warning threshold.

[0067] The resource consumption abnormality warning method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the resource consumption abnormality warning method in the embodiments of the present application is described.

[0068] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0069] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0070] The resource consumption abnormality warning method provided in the embodiment of the present application relates to the field of data processing technology and is applicable to the fields of financial technology and medicine. The resource consumption abnormality warning method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the resource consumption abnormality warning method, etc., but is not limited to the above forms.

[0071] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0072] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0073] Figure 1 This is an optional flowchart of the resource consumption abnormality warning method provided in the embodiment of the present application, which can be used in the resource consumption prediction system. Figure 1 The method may include but is not limited to steps S101 to S107.

[0074] Step S101, obtaining historical resource consumption data, historical resource market data and current resource market data;

[0075] Step S102: constructing a target resource consumption prediction model based on historical resource consumption data and resource market data;

[0076] Step S103: Based on the target resource consumption prediction model and current resource market data, a preliminary resource consumption prediction is performed to obtain resource consumption prediction data;

[0077] Step S104: Based on the current resource market data, real-time recording of resource consumption is performed to obtain real-time resource consumption data;

[0078] Step S105, based on historical resource market data and current resource market data, performing correlation data fluctuation prediction to obtain resource market prediction parameters;

[0079] Step S106: Based on the resource market forecast parameters, the resource consumption forecast data is adjusted to obtain a resource consumption warning threshold;

[0080] Step S107: Based on the resource consumption warning threshold and the real-time resource consumption data, an abnormal resource consumption data warning is issued.

[0081] Steps S101 to S107 shown in the embodiment of the present application can achieve a preliminary and accurate prediction of resource consumption by acquiring historical and current resource market data and building a target prediction model in combination with historical resource consumption data. On this basis, by recording resource consumption in real time and predicting fluctuations in related data, the resource consumption prediction data is dynamically adjusted to obtain a reasonable resource consumption warning threshold. Finally, the real-time resource consumption data is compared with the warning threshold to achieve an abnormal warning of resource consumption data, which can effectively improve the accuracy of the abnormal resource consumption warning threshold, prevent resource waste and potential risks, and improve resource management efficiency.

[0082] In step S101 of some embodiments, historical resource consumption data refers to records and statistical information about various types of resources consumed by an institution or project during its operations over a period of time. Historical resource consumption data can reflect the status and trends of resource usage. For example, in the financial sector, a bank's historical resource consumption data may include electricity consumption, office supply usage, server operating costs, etc. for each past quarter. In the medical sector, a hospital's historical resource consumption data may cover monthly drug usage, medical equipment consumables consumption, ward usage time, etc. Historical resource market data refers to records of information such as supply, demand, and price of resources in the market over a period of time. For example, in the financial sector, historical resource market data may include historical interest rate fluctuations, stock market conditions, and foreign exchange market trends. In the medical sector, historical resource market data may include historical prices of drugs and medical equipment, and historical charging standards for medical services. Current resource market data refers to the latest information on resource supply, demand, and price in the market at the current moment or in the recent period. For example, in the financial field, current resource market data may include real-time stock prices, current interest rates, and the latest exchange rates in the foreign exchange market. In the medical field, current resource market data may include the current market prices of drugs and medical equipment, the latest charging standards for medical services, etc.

[0083] The embodiments of the present application can extract historical resource consumption data from the enterprise's internal systems such as resource management systems, financial systems, and equipment management systems, such as electricity consumption, office supplies usage, server operating costs, and drug usage. It can also obtain resource consumption of hardware devices, such as servers and medical equipment, by querying device operation logs.

[0084] In the embodiment of the present application, historical resource market data and current resource market data can be obtained by querying websites related to resource market information, such as the website of the China Securities Regulatory Commission and the website of the stock exchange.

[0085] In step S102 of some embodiments, the target resource consumption prediction model refers to a model constructed through mathematical modeling and data analysis methods, which is used to predict resource consumption in a future period of time. For example, in the financial field, the target resource consumption prediction model can be used to predict the bank's electricity consumption and bank server operating costs in the next quarter. In the medical field, the target resource consumption prediction model can be used to predict the hospital's drug usage and medical equipment consumables consumption in the next month.

[0086] For details, see Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S202:

[0087] Step S201: Based on historical resource market data, a preset model library is screened to obtain an initial resource consumption prediction model;

[0088] Step S202 : Based on historical resource consumption data and resource market data, the initial resource consumption prediction model is trained to obtain a target resource consumption prediction model.

[0089] In step S201 of some embodiments, the model library refers to a collection of various machine learning or data analysis models, such as generalized linear models and neural networks. The initial resource consumption prediction model refers to the model used by the model library to predict resource consumption. It should be noted that the initial resource consumption prediction model has not yet been trained and optimized.

[0090] The embodiment of the present application obtains resource market data characteristics by extracting characteristics of historical resource market data, and then screens out candidate models suitable for resource market data characteristics from a model library. Furthermore, the candidate models are evaluated through historical resource consumption data to obtain evaluation data, and then an initial resource consumption prediction model is screened out from the candidate models based on the evaluation data.

[0091] For details, see Figure 3 In some embodiments, step S201 may include but is not limited to steps S301 to S304:

[0092] Step S301, extracting features from historical resource market data to obtain resource market data features;

[0093] Step S302: Screen the model library based on resource market data characteristics to obtain candidate models;

[0094] Step S303: Based on the historical resource consumption data, the candidate model is evaluated to obtain model evaluation data;

[0095] Step S304: Based on the model evaluation data, candidate models are screened to obtain an initial resource consumption prediction model.

[0096] In step S301 of some embodiments, the resource market data characteristics refer to characteristics reflecting key information of the resource market data, such as market volatility, trend, price fluctuation range, supply and demand change trend, etc.

[0097] The embodiments of the present application can analyze historical resource market data to identify data fluctuations or trends in the historical resource market data, thereby obtaining resource market data characteristics.

[0098] In step S302 of some embodiments, the candidate model refers to a model selected from a model library that may be applicable to the historical resource consumption data.

[0099] The embodiment of the present application filters out models that are applicable to resource market data characteristics by querying the input data requirements, data application scope, etc. of each model in the model library, and obtains candidate models.

[0100] In step S303 of some embodiments, the model evaluation data refers to result data obtained through the model evaluation process, and the model evaluation data can be used to compare and select a target model.

[0101] The embodiment of the present application can input part of the historical resource consumption data into each candidate model for training, and then use the preliminary trained candidate model to predict the remaining historical resource consumption data. Furthermore, the performance of the candidate model can be evaluated based on the prediction results of the preliminary trained candidate model and the remaining historical resource consumption data, thereby obtaining model evaluation data.

[0102] In step S304 of some embodiments, after obtaining the model evaluation data, the model with the best model evaluation data is selected from the candidate models as the initial resource consumption prediction model.

[0103] In steps S301 and S304 shown in the embodiment of the present application, by extracting features from historical resource market data, resource market data features are obtained, which can improve data processing efficiency. Secondly, based on the resource market data features, the model library is screened to obtain candidate models, thereby improving the initial adaptability of the model. Then, based on the historical resource consumption data, the candidate models are evaluated to obtain model evaluation data, which can quantify the model performance. Finally, based on the model evaluation data, the candidate models are screened to obtain an initial resource consumption prediction model, so that the screened initial resource consumption prediction model has high accuracy and reliability.

[0104] In step S202 of some embodiments, after the initial resource consumption prediction model is screened out, the initial resource consumption prediction model can be trained using historical resource consumption data and resource market data, so that the trained target resource consumption prediction model can learn the patterns and rules in the historical resource consumption data and resource market data.

[0105] In steps S201 and S202 shown in the embodiment of the present application, by using historical resource market data to screen models in a preset model library, the initial target resource consumption prediction model that best matches the historical resource market data can be accurately identified. Secondly, the initial model is trained based on the historical resource consumption data and resource market data to obtain a target resource consumption prediction model, which optimizes the model's parameters and structure, so that the target resource consumption prediction model can more accurately capture the inherent laws of resource consumption.

[0106] In step S103 of some embodiments, resource consumption forecast data refers to the forecast results of resource consumption in a future period of time. For example, in the financial field, resource consumption forecast data can be the predicted bank operating costs in the next six months. In the medical field, resource consumption forecast data can be the predicted hospital drug demand in the next three months.

[0107] In the embodiment of the present application, by inputting current resource market data into the target resource consumption prediction model, the target resource consumption prediction model can predict resource consumption data for a period of time in the future based on the current resource market data, that is, resource consumption prediction data.

[0108] In step S104 of some embodiments, real-time resource consumption data refers to data on resource consumption at the current moment or updated in real time. For example, in the financial field, real-time resource consumption data may be a bank's real-time electricity consumption monitoring data; in the medical field, real-time resource consumption data may be a hospital's real-time drug inventory consumption data.

[0109] The embodiment of the present application can calculate the resource consumption in real time based on the current resource market data to obtain the current resource consumption data. Furthermore, the current resource consumption data is stored to obtain the real-time resource consumption data.

[0110] For details, see Figure 4 In some embodiments, step S104 may include but is not limited to steps S401 to S402:

[0111] Step S401, performing resource consumption calculation based on current resource market data to obtain current resource consumption data;

[0112] Step S402: storing the current resource consumption data to obtain real-time resource consumption data.

[0113] In step S401 of some embodiments, the current resource consumption data refers to the specific value of resource consumption at the current moment or in the most recent period of time, obtained through resource consumption calculation.

[0114] The embodiment of the present application can calculate the resource consumption at the current time node based on the current resource market data to obtain the current resource consumption data.

[0115] In step S402 of some embodiments, real-time resource consumption data can be obtained by storing current resource consumption data in a database.

[0116] In steps S401 and S402 shown in the embodiment of the present application, resource consumption calculations are performed based on current resource market data to obtain current resource consumption data, which can ensure the timeliness and accuracy of the current resource consumption data. Furthermore, the current resource consumption data is stored to obtain real-time resource consumption data, which is convenient for real-time monitoring and analysis and provides solid data support for subsequent resource management and decision-making.

[0117] In step S105 of some embodiments, the resource market forecast parameter refers to a parameter indicating changes and fluctuations in the future resource market.

[0118] The embodiments of the present application can obtain market data fluctuation characteristics by extracting data features from historical resource market data and current resource market data. Furthermore, based on the market data fluctuation characteristics, a fluctuation prediction model is constructed, and the constructed fluctuation prediction model is used to predict resource market prediction parameters under the current resource market data.

[0119] For details, see Figure 5 In some embodiments, step S105 may include but is not limited to steps S501 to S504:

[0120] Step S501: Merge historical resource market data and current resource market data to obtain a resource market data set;

[0121] Step S502: extracting features from the resource market dataset to obtain market data fluctuation features;

[0122] Step S503: training a preset initial fluctuation prediction model based on the market data fluctuation characteristics to obtain a target fluctuation prediction model;

[0123] Step S504 : performing resource market data forecasting based on the target fluctuation forecasting model and current resource market data to obtain resource market forecasting parameters.

[0124] In step S501 of some embodiments, the resource market data set refers to a complete data set obtained by merging historical resource market data and current resource market data.

[0125] The embodiment of the present application can embed historical resource market data and current resource market data into a pre-set empty set, thereby merging the historical resource market data and the current resource market data to obtain a resource market data set.

[0126] In step S502 of some embodiments, the market data fluctuation characteristics refer to characteristics that can reflect the fluctuation of market data, for example, the fluctuation amplitude of the stock market in the financial field, the fluctuation frequency of the foreign exchange market, etc., the fluctuation amplitude of drug prices in the medical field, the changing trend of medical equipment utilization rate, etc.

[0127] The embodiment of the present application can obtain market data fluctuation characteristics by extracting characteristics such as volatility and frequency of various data in the resource market data set.

[0128] In step S503 of some embodiments, the target fluctuation prediction model refers to a model that can predict market data fluctuations.

[0129] The embodiment of the present application can utilize the fluctuation characteristics of market data to adjust and optimize the parameters of the pre-built initial fluctuation prediction model, so that the trained target fluctuation prediction model can accurately predict resource market data for a period of time in the future.

[0130] In step S504 of some embodiments, current resource market data is input into a target fluctuation prediction model. The target fluctuation prediction model can predict resource market data for a period of time in the future based on the current resource market data, that is, resource market prediction parameters.

[0131] In step S501 and step S504 shown in the embodiment of the present application, a resource market data set is obtained by merging historical and current resource market data, which can ensure the comprehensiveness and timeliness of the data. Furthermore, feature extraction is performed on the resource market data set to obtain market data fluctuation characteristics, which facilitates the accurate capture of key information on market changes. Secondly, the initial fluctuation prediction model is trained based on these characteristics to obtain a target fluctuation prediction model, which can improve the prediction accuracy of the model. Finally, prediction is performed based on the target model and current resource market data to obtain resource market prediction parameters, providing strong support for resource planning and decision-making.

[0132] In step S106 of some embodiments, the resource consumption warning threshold is a limit value used to determine whether resource consumption is abnormal.

[0133] After obtaining the resource market forecast parameters, the embodiment of the present application can clarify the resource market data for a period of time in the future. Therefore, the resource consumption forecast data can be adjusted according to the resource market forecast parameters so that the resource consumption warning threshold obtained after adjustment is closer to the actual resource consumption data for a period of time in the future.

[0134] In step S107 of some embodiments, after obtaining the resource consumption warning threshold, it is possible to determine whether the resource consumption data is abnormal by comparing the numerical values ​​of the real-time resource consumption data with the resource consumption warning threshold.

[0135] For details, see Figure 6 In some embodiments, step S107 may include but is not limited to steps S601 to S604:

[0136] Step S601: compare the real-time resource consumption data with the resource consumption warning threshold to obtain a numerical comparison result, wherein the numerical comparison result includes a result that the value does not exceed the threshold and a result that the value exceeds the threshold;

[0137] Step S602: If the value comparison result is that the value does not exceed the threshold, the value does not exceed the threshold result is packaged to obtain resource consumption data detection information;

[0138] Step S603: If the numerical comparison result is a numerical value exceeding the threshold value, the numerical value exceeding the threshold value result is packaged to obtain resource consumption data detection information;

[0139] Step S604: Based on the resource consumption data detection information, an abnormality warning is performed to obtain resource consumption warning data.

[0140] In step S601 of some embodiments, the numerical comparison result refers to the result of comparing the real-time resource consumption data with the warning threshold. The numerical under-threshold result refers to the comparison result that the real-time resource consumption data does not exceed the warning threshold. The numerical over-threshold result refers to the comparison result that the real-time resource consumption data exceeds the warning threshold.

[0141] By comparing the numerical values ​​of the real-time resource consumption data and the resource consumption warning threshold, the embodiment of the present application can obtain a comparison result that the real-time resource consumption data does not exceed the warning threshold, that is, the numerical value does not exceed the threshold result, or a comparison result that the real-time resource consumption data exceeds the warning threshold, that is, the numerical value exceeds the threshold result.

[0142] In step S602 of some embodiments, the resource consumption data detection information refers to packaged numerical comparison result information.

[0143] When the numerical comparison result includes a result that the numerical value does not exceed the threshold value, the embodiment of the present application encapsulates information through the result that the numerical value does not exceed the threshold value, and can obtain resource consumption data detection information that no abnormality is found in the resource consumption data.

[0144] In steps S603 and S604 of some embodiments, the resource consumption warning data refers to data generated after the abnormal warning is triggered, including processed data of the warning information.

[0145] When the numerical comparison result includes a numerical value exceeding the threshold value result, the embodiment of the present application performs information encapsulation through the numerical value exceeding the threshold value result, and can obtain resource consumption data detection information that finds abnormal resource consumption data. Furthermore, based on the resource consumption data detection information, an abnormal warning is issued, and resource consumption early warning data can be generated.

[0146] In step S601 and step S604 shown in the embodiment of the present application, by numerically comparing the real-time data of resource consumption with the warning threshold, a numerical comparison result is obtained, which can monitor the resource consumption situation in real time. Secondly, the numerical comparison result is information packaged to obtain resource consumption data detection information, which is convenient for unified management and subsequent processing. Finally, when the numerical comparison result is a numerical over-threshold result, an abnormal warning is performed based on the resource consumption data detection information to obtain resource consumption warning data, which can timely remind relevant personnel to take measures to effectively prevent resource waste and potential risks.

[0147] After obtaining the resource consumption warning data, in order to improve the prediction accuracy of the target resource consumption prediction model, the embodiment of the present application can fine-tune the parameters of the target resource consumption prediction model based on the real-time resource consumption data and the resource consumption prediction data.

[0148] For details, see Figure 7 In some embodiments, the resource consumption abnormality warning method may further include but is not limited to steps S701 to S702:

[0149] Step S701: Based on the resource consumption warning data, a deviation calculation is performed on the real-time resource consumption data and the resource consumption prediction data to obtain resource consumption deviation data;

[0150] Step S702 : fine-tuning parameters of the target resource consumption prediction model based on the resource consumption deviation data to obtain a fine-tuned resource consumption prediction model.

[0151] In step S701 of some embodiments, the resource consumption deviation data refers to the difference data between the actual resource consumption and the predicted resource consumption obtained through deviation calculation.

[0152] In an embodiment of the present application, when resource consumption warning data is obtained, the difference between the real-time resource consumption data and the resource consumption prediction data is calculated to obtain resource consumption deviation data.

[0153] In step S702 of some embodiments, after obtaining the resource consumption deviation data, the resource consumption deviation data is input into the target resource consumption prediction model and the parameters are adjusted to obtain a fine-tuned resource consumption prediction model with higher resource consumption prediction accuracy.

[0154] In steps S701 and S702 shown in the embodiment of the present application, deviation calculation is performed on the real-time resource consumption data and the resource consumption prediction data based on the resource consumption warning data to obtain resource consumption deviation data, which can accurately identify abnormal fluctuations in resource consumption. Furthermore, based on the resource consumption deviation data, the parameters of the target resource consumption prediction model are fine-tuned to obtain a fine-tuned resource consumption prediction model, which can improve the prediction accuracy and adaptability of the model, thereby achieving more accurate resource consumption prediction and more effective resource management.

[0155] This application obtains historical and current resource market data and builds a target prediction model based on historical resource consumption data to achieve preliminary and accurate prediction of resource consumption. On this basis, by recording resource consumption in real time and predicting fluctuations in related data, the resource consumption prediction data is dynamically adjusted to obtain a reasonable resource consumption warning threshold. Finally, the real-time resource consumption data is compared with the warning threshold to achieve abnormal warning of resource consumption data, which can effectively improve the accuracy of the abnormal resource consumption warning threshold, prevent resource waste and potential risks, and improve resource management efficiency.

[0156] See also Figure 8 The embodiment of the present application further provides a resource consumption abnormality warning device, which can implement the above-mentioned resource consumption abnormality warning method, and the device includes:

[0157] Data acquisition module 801, used to acquire historical resource consumption data, historical resource market data and current resource market data;

[0158] Model building module 802, for building a target resource consumption prediction model based on historical resource consumption data and resource market data;

[0159] The data prediction module 803 is used to perform preliminary resource consumption prediction based on the target resource consumption prediction model and current resource market data to obtain resource consumption prediction data;

[0160] The data recording module 804 is used to record resource consumption in real time based on current resource market data to obtain real-time resource consumption data;

[0161] Fluctuation prediction module 805, used to perform correlation data fluctuation prediction based on historical resource market data and current resource market data to obtain resource market prediction parameters;

[0162] The data adjustment module 806 is used to adjust the resource consumption forecast data based on the resource market forecast parameters to obtain a resource consumption warning threshold;

[0163] The abnormality warning module 807 is used to issue an abnormality warning for resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data.

[0164] The specific implementation of the resource consumption abnormality warning device is basically the same as the specific embodiment of the above-mentioned resource consumption abnormality warning method, and will not be repeated here.

[0165] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned resource consumption abnormality warning method. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0166] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0167] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0168] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the resource consumption abnormality warning method of the embodiment of the present application;

[0169] Input / output interface 903, used to implement information input and output;

[0170] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0171] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0172] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0173] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned resource consumption abnormality warning method is implemented.

[0174] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The embodiments of the present application provide a method for warning abnormal resource consumption, a device for warning abnormal resource consumption, an electronic device, and a storage medium. The method obtains historical resource consumption data, obtains historical resource market data, and current resource market data, constructs a target resource consumption prediction model based on the historical resource consumption data and the resource market data, performs a preliminary resource consumption prediction based on the target resource consumption prediction model and the current resource market data, obtains resource consumption prediction data, performs real-time resource consumption recording based on the current resource market data, obtains real-time resource consumption data, performs associated data fluctuation prediction based on the historical resource market data and the current resource market data, obtains resource market prediction parameters, adjusts resource consumption for the resource consumption prediction data based on the resource market prediction parameters, obtains a resource consumption warning threshold, and performs a warning of abnormal resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data.

[0176] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0177] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0178] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0179] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0180] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0181] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0182] In the several 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 above-mentioned units is only 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. 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.

[0183] The units described above 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 according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0185] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A resource consumption abnormality early warning method, characterized in that: The method comprises: Obtain historical resource consumption data, historical resource market data and current resource market data; Building a target resource consumption prediction model based on the historical resource consumption data and the resource market data; Based on the target resource consumption prediction model and the current resource market data, a preliminary resource consumption prediction is performed to obtain resource consumption prediction data; Based on the current resource market data, real-time recording of resource consumption is performed to obtain real-time resource consumption data; Based on the historical resource market data and the current resource market data, performing correlation data fluctuation prediction to obtain resource market prediction parameters; Based on the resource market forecast parameters, adjusting the resource consumption forecast data to obtain a resource consumption warning threshold; Based on the resource consumption warning threshold and the real-time resource consumption data, an abnormal resource consumption data warning is performed.

2. The method according to claim 1, characterized in that The method of performing correlation data fluctuation prediction based on the historical resource market data and the current resource market data to obtain resource market prediction parameters includes: Merging the historical resource market data and the current resource market data to obtain a resource market data set; Extracting features from the resource market data set to obtain market data fluctuation features; Based on the market data fluctuation characteristics, a preset initial fluctuation prediction model is trained to obtain a target fluctuation prediction model; Based on the target fluctuation prediction model and the current resource market data, resource market data prediction is performed to obtain the resource market prediction parameters.

3. The method according to claim 1, characterized in that The real-time recording of resource consumption based on the current resource market data to obtain real-time resource consumption data includes: Perform resource consumption calculation based on the current resource market data to obtain current resource consumption data; The current resource consumption data is stored to obtain the real-time resource consumption data.

4. The method according to any one of claim 1, characterized in that The constructing of a target resource consumption prediction model based on the historical resource consumption data and the historical resource market data includes: Based on the historical resource market data, a preset model library is screened to obtain an initial resource consumption forecast model; Based on the historical resource consumption data and the resource market data, the initial resource consumption prediction model is trained to obtain the target resource consumption prediction model.

5. The method according to claim 4, characterized in that The method of screening a preset model library based on the historical resource market data to obtain an initial resource consumption prediction model includes: Extracting features from the historical resource market data to obtain resource market data features; Based on the resource market data characteristics, the model library is screened to obtain candidate models; Based on the historical resource consumption data, performing model evaluation on the candidate model to obtain model evaluation data; Based on the model evaluation data, the candidate models are screened to obtain the initial resource consumption prediction model.

6. The method according to any one of claims 1 to 5, characterized in that The performing of abnormal warning of resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data includes: Comparing the real-time resource consumption data with the resource consumption warning threshold to obtain a numerical comparison result, wherein the numerical comparison result includes a result that the value does not exceed the threshold and a result that the value exceeds the threshold; If the numerical comparison result is a result that the numerical value does not exceed the threshold value, information packaging is performed on the result that the numerical value does not exceed the threshold value to obtain resource consumption data detection information; If the numerical comparison result is the numerical value exceeding the threshold value result, information packaging is performed on the numerical value exceeding the threshold value result to obtain resource consumption data detection information; Based on the resource consumption data detection information, an abnormality warning is performed to obtain resource consumption warning data.

7. The method according to claim 6, characterized in that After performing an abnormal warning on resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data, the method further includes: Based on the resource consumption warning data, performing deviation calculation on the real-time resource consumption data and the resource consumption prediction data to obtain resource consumption deviation data; Based on the resource consumption deviation data, parameters of the target resource consumption prediction model are fine-tuned to obtain a fine-tuned resource consumption prediction model.

8. A resource consumption abnormality warning device, characterized in that: The device comprises: Data acquisition module, used to obtain historical resource consumption data, historical resource market data and current resource market data; A model building module, configured to build a target resource consumption prediction model based on the historical resource consumption data and the resource market data; A data prediction module, configured to perform preliminary resource consumption prediction based on the target resource consumption prediction model and the current resource market data to obtain resource consumption prediction data; A data recording module, configured to record resource consumption in real time based on the current resource market data to obtain real-time resource consumption data; A fluctuation prediction module, configured to perform correlation data fluctuation prediction based on the historical resource market data and the current resource market data to obtain resource market prediction parameters; A data adjustment module, configured to adjust the resource consumption forecast data based on the resource market forecast parameters to obtain a resource consumption warning threshold; The abnormality warning module is used to provide abnormality warning of resource consumption data based on the resource consumption warning threshold and the real-time resource consumption data.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the resource consumption abnormality warning method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the resource consumption abnormality warning method according to any one of claims 1 to 7 is implemented.

Images