Data processing method and device and electronic equipment

Abstract

The invention relates to a data processing method and device and electronic equipment, and the method comprises the steps: obtaining target business data corresponding to a specified item from a business data set of a target object, inputting the target business data into a pre-trained data prediction model, and obtaining a target index prediction value corresponding to the specified item, and outputting early warning prompt information according to the target business data and the target index prediction value.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular, to a data processing method and device and electronic equipment. BACKGROUND

[0002] With the comprehensive deepening of digital information transformation construction, the audit tasks of energy units are increasingly heavy, and the audit difficulty is increasing.

[0003] At present, the audit work is usually carried out by adopting the mode of manual on-site audit, however, the audit efficiency of this work mode is low, and the cost required by the audit is high. SUMMARY

[0004] In order to solve the above problems, the present disclosure provides a data processing method, device and electronic equipment.

[0005] According to a first aspect of an embodiment of the present disclosure, a data processing method is provided, the method comprising: obtaining target business data corresponding to a specified project from a business data set of a target object; inputting the target business data into a pre-trained data prediction model to obtain a target index prediction value corresponding to the specified project; and outputting a warning prompt information according to the target business data and the target index prediction value.

[0006] Optionally, the obtaining of the target business data corresponding to the specified project from the business data set of the target object comprises: obtaining at least one project characteristic information of the specified project; and obtaining business data including the project characteristic information in the business data set within a preset time period according to the at least one project characteristic information, to obtain the target business data.

[0007] Optionally, the data prediction model is pre-trained by the following way: obtaining historical business data in a plurality of historical time periods from the business data set, the historical business data including the project characteristic information; performing abnormal data processing on the historical business data; and training the data prediction model by taking the historical business data as training data.

[0008] Optionally, the abnormal data processing on the historical business data comprises: determining abnormal data from the historical business data based on an isolation forest algorithm; and performing data conversion on the abnormal data based on a principal component analysis method.

[0009] Optionally, the outputting of the warning prompt information according to the target business data and the target index prediction value comprises: obtaining a target index statistical value corresponding to the specified project based on a preset data statistical method according to the target business data; and outputting warning prompt information with different prompt intensities according to the target index statistical value and the target index prediction value.

[0010] Optionally, the step of outputting warning information with different prompt intensities based on the target indicator statistical value and the target indicator predicted value includes: obtaining the deviation value between the target indicator statistical value and the target indicator predicted value; obtaining the standard deviation of the historical indicator statistical values ​​corresponding to the specified item within multiple historical time periods; and outputting warning information with different prompt intensities based on the deviation value and the standard deviation.

[0011] Optionally, the warning information includes a first warning information, a second warning information, and a third warning information; the warning intensity of the second warning information is greater than that of the first warning information, and the warning intensity of the third warning information is greater than that of the second warning information; the step of outputting warning information with different warning intensities based on the deviation value and the standard deviation includes: outputting the first warning information when the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value; or, outputting the second warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than a third preset value; or, outputting the third warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value.

[0012] Optionally, the method further includes: displaying the statistical value of the target indicator and the predicted value of the target indicator.

[0013] According to a second aspect of the present disclosure, a data processing apparatus is provided, the apparatus comprising: The acquisition module is used to retrieve the target business data corresponding to the specified project from the business dataset of the target object; The determination module is used to input the target business data into a pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project; The output module is used to output early warning information based on the target business data and the predicted value of the target indicator.

[0014] Optionally, the acquisition module is used to acquire at least one project feature information of the specified project; and based on the at least one project feature information, acquire business data including the project feature information in the business dataset within a preset time period to obtain the target business data.

[0015] Optionally, the apparatus further includes: a model training module, configured to acquire historical business data from the business dataset within multiple historical time periods, the historical business data including the project feature information; perform anomaly processing on the historical business data; and use the historical business data as training data to train the data prediction model.

[0016] Optionally, the model training module is used to identify abnormal data from the historical business data based on the isolated forest algorithm; and to perform data transformation on the abnormal data based on principal component analysis.

[0017] Optionally, the output module is used to obtain the target indicator statistical value corresponding to the specified project based on the target business data and a preset data statistical method; and to output early warning information with different prompt intensities based on the target indicator statistical value and the target indicator predicted value.

[0018] Optionally, the output module is used to obtain the deviation value between the statistical value of the target indicator and the predicted value of the target indicator; obtain the standard deviation of the historical indicator statistical values ​​corresponding to the specified item within multiple historical time periods; and output early warning information with different prompt intensities based on the deviation value and the standard deviation.

[0019] Optionally, the warning information includes a first warning information, a second warning information, and a third warning information; the warning intensity of the second warning information is greater than that of the first warning information, and the warning intensity of the third warning information is greater than that of the second warning information; the output module is configured to output the first warning information when the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value; or, output the second warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than a third preset value; or, output the third warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value.

[0020] Optionally, the output module is also used to display the statistical value of the target indicator and the predicted value of the target indicator.

[0021] According to a third aspect of the present disclosure, an electronic device is provided, comprising: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method described in the first aspect of this disclosure.

[0022] According to the above technical solution, target business data corresponding to a specified project is obtained from the target object's business dataset. This target business data is then input into a pre-trained data prediction model to obtain predicted values ​​for the target indicators corresponding to the specified project. Based on the target business data and the predicted target indicator values, early warning information is output. In this way, analyzing business data through a prediction model can improve audit efficiency, reduce audit costs, and avoid interference from human factors, thereby improving audit quality. Furthermore, outputting early warning information based on the prediction results of business data can also provide risk alerts to energy-related entities, enabling them to implement risk control measures.

[0023] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a data processing method according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating another data processing method according to an exemplary embodiment.

[0026] Figure 3 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment.

[0027] Figure 4 This is a block diagram illustrating another data processing apparatus according to an exemplary embodiment.

[0028] Figure 5 This is a block diagram of an electronic device provided according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0029] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0030] In the following description, the words "first" and "second" are used only to distinguish the purpose of the description and should not be interpreted as indicating or implying relative importance or order.

[0031] In related technologies, with the comprehensive deepening of digital and information-based transformation, the audit tasks of energy companies are becoming increasingly heavy and the auditing difficulty is increasing. Currently, the audit work is usually carried out by manual on-site audits; however, this work mode has low audit efficiency and high audit costs.

[0032] To address the aforementioned issues, this disclosure provides a data processing method, apparatus, and electronic device. This device can obtain target business data corresponding to a specified project from the target object's business dataset, input the target business data into a pre-trained data prediction model to obtain predicted values ​​for target indicators corresponding to the specified project, and output early warning information based on the target business data and the predicted target indicator values. In this way, analyzing business data through a prediction model can improve audit efficiency, reduce audit costs, and avoid interference from human factors, thereby improving audit quality. Furthermore, outputting early warning information based on the prediction results of business data can also provide risk alerts to energy-related entities, enabling them to implement risk control measures.

[0033] The present disclosure will now be described in conjunction with specific embodiments.

[0034] Figure 1 This is a flowchart illustrating a data processing method according to an exemplary embodiment, such as... Figure 1 As shown, the method may include the following steps: In step S101, target business data corresponding to the specified project is obtained from the business dataset of the target object.

[0035] The target entity can be an energy-related unit to be audited, and the designated project can include the projects within that energy-related unit to be audited. The business dataset can include business data from multiple information systems within that energy-related unit. This data can be collected using pre-configured data collection tools at preset collection cycles (e.g., daily or weekly). These multiple information systems can include investment management systems, operations management systems, financial management systems, legal management systems, email management systems, etc. The business data in this dataset can include project investment data from the investment management system, project completion progress from the operations management system, project revenue and expenditure data from the financial management system, project contract data from the legal management system, and project email text from the email management system.

[0036] In one possible implementation, at least one project feature information of the specified project can be obtained, and based on the at least one project feature information, business data including the project feature information in the business dataset within a preset time period can be obtained to obtain the target business data.

[0037] The project feature information can be the project name, project number, or project QR code; this disclosure does not specify any particular limitation. The preset time period can include the time period for auditing a designated project of the target object. For example, the following can be obtained from the project investment data: Based on the project number, the project investment data corresponding to the project number within the preset time period can be retrieved. This project investment data may include the invested amount and investment budget, thus obtaining the target invested amount and target investment budget in the target business data. Similarly, based on the project completion progress data, the project progress percentage corresponding to the project number within the preset time period can be retrieved, thus obtaining the target project progress percentage in the target business data. Furthermore, based on the project revenue and expenditure data, the expenditure amount and revenue amount corresponding to the project number within the preset time period can be retrieved, thus obtaining the target expenditure amount and target revenue amount in the target business data. Also, based on the project contract data, the contract amount completion progress of the project corresponding to the project number within the preset time period can be retrieved, thus obtaining the target contract amount completion progress in the target business data. Finally, based on the project email text, the node information related to the project number in the email text can be retrieved, thus obtaining the target node information in the target business data. This node information can be demand analysis node information, development node information, and launch node information in a digital system construction project, or design node information, construction node information, and delivery node information in an engineering construction project.

[0038] In step S102, the target business data is input into a pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project.

[0039] The target indicator can be the transaction amount corresponding to the specified project, and the predicted value of the target indicator can be the predicted transaction amount corresponding to the specified project. This data prediction model, through input target business data including the target invested amount and target investment budget, target project progress percentage, target expenditure and target revenue, target contract amount completion progress, and target node information, obtains the predicted transaction amount corresponding to the specified project.

[0040] In step S103, an early warning message is output based on the target business data and the predicted value of the target indicator.

[0041] The warning message is used to alert users to data risks associated with the target business data. These data risks can include audit risks, such as the risk of data deviation between the target business data and the predicted value of the target indicator.

[0042] The aforementioned technical solution can obtain target business data corresponding to a specified project from the target object's business dataset, input the target business data into a pre-trained data prediction model, obtain predicted values ​​of target indicators for the specified project, and output early warning information based on the target business data and the predicted target indicator values. In this way, analyzing business data through a prediction model can improve audit efficiency, reduce audit costs, and avoid interference from human factors, thereby improving audit quality. Furthermore, outputting early warning information based on the prediction results of business data can also provide risk alerts to energy-related entities, enabling them to implement risk control measures.

[0043] In some embodiments, the data prediction model in step S102 above can be pre-trained in the following manner: S121. Obtain historical business data from multiple historical time periods from this business dataset.

[0044] The historical business data may include the project's characteristic information. The historical time period may be the time period before the preset time period for auditing the specified project of the target object. For example, multiple time periods (such as 6 months) before the preset time period may be obtained as the multiple historical time periods, and the business data of each month in the 6 months may be used as the historical business data.

[0045] S122. Perform abnormal data processing on the historical business data.

[0046] In order to address the possibility of anomalies such as data deviation, missing data, and data redundancy in the historical business data, it is necessary to perform anomaly processing on the historical business data before training the model.

[0047] In one possible implementation, the isolated forest algorithm can be used to identify anomalous data from the historical business data, and the anomalous data can be transformed using principal component analysis.

[0048] For example, the target investment amount, target investment budget, target project progress percentage, target expenditure, target revenue, target contract amount completion progress, and target node information for each historical time period can be used as a set of training samples. An isolation tree can be generated and calculated for each set of training samples to obtain the anomaly score for each set of training samples in that isolation tree, denoted as... ,in The number of historical time periods. For example, when multiple time periods are 6 months, the outlier score of the training samples in the first month before the preset time period is recorded as... The abnormal scores of the training samples from the second month prior to the preset time period are recorded as follows: Similarly, the abnormal scores of the training samples from the 6th month prior to the preset time period are recorded as follows: The score for this anomaly can be determined. A set of training samples whose scores are less than a scoring threshold is identified as outlier data. This scoring threshold can be predetermined based on the experiment; for example, it can be set to 0.12, which means that outlier data will be classified as abnormal. Training samples with values ​​less than 0.12 are identified as outliers. After identifying outliers, principal component analysis (PCA) can be used to reduce their dimensionality. For example, indicators such as target investment amount, target investment budget, target project progress percentage, target expenditure amount, target revenue amount, target contract amount completion progress, and target node information can be transformed using PCA to obtain PCA calculated values.

[0049] In this way, by performing anomaly processing on historical business data, errors caused by data anomalies can be eliminated, the stability of business data distribution can be improved, thereby enhancing the accuracy of model training and the accuracy of prediction results. Additionally, the specific implementation steps of the Isolation Forest algorithm and Principal Component Analysis method will not be elaborated here.

[0050] S123. Use the historical business data as training data to train the data prediction model.

[0051] For example, historical business data after anomaly data processing can be used as training data for model training. The model can be trained using the Auto Arima (Autoregressive Integrated Moving Average) algorithm. The p and q parameters in the Auto Arima algorithm can be obtained automatically, and the d parameter in the Auto Arima algorithm can be specified as 1 to represent the first-order difference.

[0052] It should be noted that the specific implementation steps of the Auto Arima algorithm can be found in the relevant steps of the existing Auto Arima algorithm, and will not be repeated here.

[0053] In some embodiments, step S103 may include: obtaining the target indicator statistical value corresponding to the specified project based on the target business data and a preset data statistical method, and outputting warning prompt information with different prompt intensities based on the target indicator statistical value and the target indicator prediction value.

[0054] The preset data statistics method can include existing auditing methods. The target indicator statistical value can be the transaction amount statistical value corresponding to the specified project. This transaction amount statistical value can be obtained by auditing the target business data using existing auditing methods. For example, the transaction amount statistical value can be obtained by auditing the target investment amount, target investment budget, target project progress percentage, target expenditure amount, target revenue amount, target contract amount completion progress, and target node information using existing auditing methods. Thus, based on the predicted and statistical results of the business data, early warning information can be output, providing risk alerts to energy-related entities to facilitate risk control.

[0055] In some embodiments, the deviation between the statistical value of the target indicator and the predicted value of the target indicator can be obtained; the standard deviation of the historical indicator statistical value corresponding to the specified item in multiple historical time periods can be obtained; and warning prompts with different prompt intensities can be output based on the deviation value and the standard deviation.

[0056] For example, you can obtain the target indicator statistics for the current time period when auditing a specified item of the target object. and target indicator prediction value The deviation value is calculated using the following formula:

[0057] in, This is the deviation value. This is the statistical value of the target indicator. This is the predicted value for the target indicator.

[0058] In addition, these multiple historical time periods can be the time periods preceding a preset time period for auditing a specified project of the target object, and the historical indicator statistics for each historical time period are recorded as follows: , The value can be 1-N, representing the historical statistical value of the indicator over the previous N months. This standard deviation can be calculated using the following formula:

[0059] in, This is the standard deviation. Let be the historical indicator statistics for the i-th historical time period. The number of historical time periods, for example It can be 12.

[0060] In one possible implementation, the warning message may include a first warning message, a second warning message, and a third warning message. The first warning message is output when the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value; or the second warning message is output when the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than a third preset value; or the third warning message is output when the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value.

[0061] Wherein, the alert strength of the second warning message is greater than that of the first warning message, and the alert strength of the third warning message is greater than that of the second warning message. The first preset value can be 1.5, the second preset value can be 1.75, and the third preset value can be 2.0. For example, it can be possible to satisfy... In this case, the deviation between the statistical value and the predicted value is negligible, and no prompt message is output; under the condition that... In this case, the deviation between the statistical value and the predicted value is small, and the first early warning message is output, such as a yellow warning signal or the text warning message "Abnormal: Low risk!"; under the condition that... In this case, if the deviation between the statistical value and the predicted value is large, a second early warning message will be output, such as an orange warning signal or a text warning message "Abnormal: Medium Risk!"; if the following conditions are met... In this case, the deviation between the statistical value and the predicted value is large, and a third early warning message is output, such as a red warning signal or a text warning message "Abnormal: High Risk!". Among the above formulas, This is the deviation value. This is the standard deviation.

[0062] The above technical solution outputs early warning information of different intensities based on the statistical and predicted values ​​of the target indicators, enabling energy entities to provide different levels of risk warnings so that they can carry out risk control accordingly.

[0063] In some embodiments, the statistical value of the target indicator and the predicted value of the target indicator may be displayed.

[0064] For example, the statistical value and predicted value of the target indicator can be displayed using a visualization device within an energy-related unit. This visualization device can be a projection device, a touch screen query device, or a personal terminal of the energy-related unit. In this way, by displaying the statistical and predicted values ​​of the audit results, users can easily identify risks and improve the effectiveness of risk control.

[0065] Figure 2 This is a flowchart illustrating another data processing method according to an exemplary embodiment, such as... Figure 2 As shown, the method may include: S201. Obtain at least one project feature information of the specified project from the business dataset of the target object.

[0066] The target object can be an energy-related entity to be audited, the business dataset can include business data from multiple information systems within that energy-related entity, and the designated project can include the project to be audited within that energy-related entity. The project's characteristic information can be the project name, the project number, or the project's QR code; this disclosure does not impose specific limitations on these.

[0067] S202. Based on the at least one project feature information, obtain the business data containing the project feature information in the business dataset within a preset time period, and obtain the target business data corresponding to the specified project.

[0068] The preset time period may include the time period for auditing a specified item of the target object.

[0069] S203. Input the target business data into the pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project.

[0070] The data prediction model can be pre-trained in the following way: obtain historical business data from multiple historical time periods from the business dataset, identify abnormal data from the historical business data based on the isolated forest algorithm, perform data transformation on the abnormal data based on the principal component analysis method, and use the historical business data after abnormal data processing as training data to train the model and obtain the data prediction model.

[0071] S204. Based on the target business data and using a preset data statistics method, obtain the target indicator statistics value corresponding to the specified project.

[0072] The preset data statistics method may include auditing methods in the prior art. The target indicator statistical value may be the transaction amount statistical value corresponding to the specified project. The transaction amount statistical value can be obtained by auditing the target business data based on the auditing methods in the prior art.

[0073] S205. Obtain the deviation between the statistical value and the predicted value of the target indicator.

[0074] The deviation value can be calculated using the following formula:

[0075] in, This is the deviation value. This is the statistical value of the target indicator. This is the predicted value for the target indicator.

[0076] S206. Obtain the standard deviation of the historical indicator statistics for the specified item within multiple historical time periods.

[0077] The multiple historical time periods can be the time periods preceding a preset time period for auditing a specific project of the target object, and the standard deviation can be calculated using the following formula:

[0078] in, This is the standard deviation. Let be the historical indicator statistics for the i-th historical time period. The number of historical time periods, for example It can be 12.

[0079] S207. Based on the deviation value and the standard deviation, output warning messages with different warning intensities.

[0080] The warning information may include a first warning information, a second warning information, and a third warning information. The warning intensity of the second warning information is greater than that of the first warning information, and the warning intensity of the third warning information is greater than that of the second warning information. The first warning information may be output when the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value; or the second warning information may be output when the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than a third preset value; or the third warning information may be output when the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value.

[0081] Using the above method, at least one project feature information corresponding to a specified project can be obtained from the business dataset of the target object. Based on this project feature information, business data containing the project feature information within the business dataset within a preset time period can be obtained to obtain the target business data corresponding to the specified project. This target business data is then input into a pre-trained data prediction model to obtain the predicted value of the target indicator corresponding to the specified project. Based on the target business data and a preset data statistical method, the statistical value of the target indicator corresponding to the specified project is obtained. Finally, based on the statistical value and the predicted value of the target indicator, different warning prompts are output. In this way, analyzing business data through a prediction model can improve audit efficiency, reduce audit costs, and avoid interference from human factors, thereby improving audit quality. Furthermore, outputting different warning prompts based on the predicted and actual statistical results of the business data can also provide risk warnings to energy-related units, enabling them to implement risk control measures according to different levels of risk.

[0082] It should be noted that the above Figure 2 The descriptions of each step in the illustrated embodiments can be found in the descriptions of the relevant steps in the foregoing embodiments, and will not be repeated here.

[0083] Furthermore, for the sake of simplicity, the above method embodiments are described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions. For example, steps S203 and S204 are not limited to the order shown in the current embodiment; step S204 can be executed first, followed by step S203, or steps S203 and S204 can be executed simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0084] Figure 3 This is a block diagram illustrating a data processing apparatus 300 according to an exemplary embodiment, with reference to... Figure 3 The device includes: The acquisition module 301 is used to acquire the target business data corresponding to the specified project from the business dataset of the target object; The determination module 302 is used to input the target business data into a pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project. The output module 303 is used to output early warning information based on the target business data and the predicted value of the target indicator.

[0085] Optionally, the acquisition module 301 is used to acquire at least one project feature information of the specified project; based on the at least one project feature information, acquire business data in the business dataset that includes the project feature information within a preset time period, and obtain the target business data.

[0086] Optionally, such as Figure 4 As shown, the device also includes: a model training module 304, used to obtain historical business data from the business dataset within multiple historical time periods, the historical business data including the project feature information; to perform abnormal data processing on the historical business data; and to train the data prediction model using the historical business data as training data.

[0087] Optionally, the model training module 304 is used to identify anomalous data from the historical business data based on the isolated forest algorithm; and to perform data transformation on the anomalous data based on principal component analysis.

[0088] Optionally, the output module 303 is used to obtain the target indicator statistical value corresponding to the specified project based on the target business data and a preset data statistical method; and to output early warning information with different prompt intensities based on the target indicator statistical value and the target indicator prediction value.

[0089] Optionally, the output module 303 is used to obtain the deviation value between the statistical value of the target indicator and the predicted value of the target indicator; obtain the standard deviation of the historical indicator statistical value corresponding to the specified item in multiple historical time periods; and output early warning information with different prompting intensities based on the deviation value and the standard deviation.

[0090] Optionally, the warning information includes a first warning information, a second warning information, and a third warning information; the warning intensity of the second warning information is greater than that of the first warning information, and the warning intensity of the third warning information is greater than that of the second warning information; the output module 303 is used to output the first warning information when the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value; or, output the second warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than a third preset value; or, output the third warning information when the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value.

[0091] Optionally, the output module 303 is also used to display the statistical value of the target indicator and the predicted value of the target indicator.

[0092] Using the aforementioned apparatus, at least one project feature information corresponding to a specified project can be obtained from the business dataset of the target object. Based on this project feature information, business data containing the project feature information from the business dataset within a preset time period can be obtained to obtain the target business data corresponding to the specified project. This target business data is then input into a pre-trained data prediction model to obtain the predicted value of the target indicator corresponding to the specified project. Based on the target business data and a preset data statistical method, the statistical value of the target indicator corresponding to the specified project is obtained. Finally, based on the statistical value and the predicted value of the target indicator, different warning prompts are output. In this way, analyzing business data through a prediction model can improve audit efficiency, reduce audit costs, and avoid interference from human factors, thereby improving audit quality. Furthermore, outputting different warning prompts based on the predicted and actual statistical results of the business data can also provide risk warnings to energy-related entities, enabling them to implement risk control measures according to different levels of risk.

[0093] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0094] Figure 5 This is a block diagram of an electronic device 500 provided according to an exemplary embodiment of the present disclosure. Figure 5 As shown, the electronic device 500 may include a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0095] The processor 501 controls the overall operation of the electronic device 500 to complete all or part of the steps in the data processing method described above. The memory 502 stores various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 503 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 502 or transmitted via communication component 505. The audio component also includes at least one speaker for outputting audio signals. I / O interface 504 provides an interface between processor 501 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical. Communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 505 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0096] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the data processing method described above.

[0097] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the data processing method described above. For example, the computer-readable storage medium may be the memory 502 including program instructions described above, which may be executed by the processor 501 of the electronic device 500 to complete the data processing method described above.

[0098] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0099] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0100] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A data processing method, characterized in that, The method includes: Retrieve the target business data corresponding to the specified project from the business dataset of the target object; The target business data is input into a pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project. Based on the target business data and the predicted value of the target indicator, an early warning message is output.

2. The method according to claim 1, characterized in that, The step of obtaining the target business data corresponding to the specified project from the business dataset of the target object includes: Obtain at least one project feature information of the specified project; Based on the at least one project feature information, obtain the business data including the project feature information in the business dataset within a preset time period to obtain the target business data.

3. The method according to claim 2, characterized in that, The data prediction model is pre-trained in the following manner: From the business dataset, obtain historical business data within multiple historical time periods, the historical business data including the project feature information; Perform anomaly processing on the historical business data; The historical business data is used as training data to train the data prediction model.

4. The method according to claim 3, characterized in that, The abnormal data processing of the historical business data includes: Based on the isolated forest algorithm, abnormal data is identified from the historical business data; The abnormal data is transformed based on principal component analysis.

5. The method according to claim 1, characterized in that, The step of outputting early warning information based on the target business data and the predicted value of the target indicator includes: Based on the target business data and a preset data statistics method, the target indicator statistical values ​​corresponding to the specified project are obtained. Based on the statistical value and predicted value of the target indicator, warning messages with different levels of intensity are output.

6. The method according to claim 5, characterized in that, The step of outputting early warning information with different levels of alert based on the statistical value and predicted value of the target indicator includes: Obtain the deviation between the statistical value of the target indicator and the predicted value of the target indicator; Obtain the standard deviation of the historical indicator statistics for the specified item within multiple historical time periods; Based on the deviation value and the standard deviation, warning messages with different warning intensities are output.

7. The method according to claim 6, characterized in that, The warning information includes a first warning information, a second warning information, and a third warning information; the warning intensity of the second warning information is greater than that of the first warning information, and the warning intensity of the third warning information is greater than that of the second warning information. The step of outputting warning messages of different intensities based on the deviation value and the standard deviation includes: If the ratio of the deviation value to the standard deviation is greater than or equal to a first preset value and less than a second preset value, the first warning message is output; or, If the ratio of the deviation value to the standard deviation is greater than or equal to the second preset value and less than the third preset value, the second warning message is output; or, If the ratio of the deviation value to the standard deviation is greater than or equal to the third preset value, the third warning message is output.

8. The method according to claim 5, characterized in that, The method further includes: Display the statistical value and the predicted value of the target indicator.

9. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to retrieve the target business data corresponding to the specified project from the business dataset of the target object; The determination module is used to input the target business data into a pre-trained data prediction model to obtain the target indicator prediction value corresponding to the specified project; The output module is used to output early warning information based on the target business data and the predicted value of the target indicator.

10. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-8.

Images