CN114092275A

CN114092275A - Enterprise operation abnormity monitoring method and device, computer equipment and storage medium

Info

Publication number: CN114092275A
Application number: CN202111297943.1A
Authority: CN
Inventors: 杜美华; 杨荣霞; 曹熙; 张仙梅; 郭鑫
Original assignee: China Southern Power Grid Big Data Service Co ltd
Current assignee: China Southern Power Grid Big Data Service Co ltd
Priority date: 2021-11-04
Filing date: 2021-11-04
Publication date: 2022-02-25

Abstract

The application relates to a method and a device for monitoring enterprise operation abnormity, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring monitoring data of a target enterprise; acquiring a trained enterprise operation abnormity monitoring model; inputting the monitoring data into an enterprise operation abnormity monitoring model to obtain an output result; and determining the operation state of the target enterprise according to the output result. By adopting the method, the enterprises with abnormal operation or the enterprises with abnormal operation risk can be quickly positioned, the monitored enterprise list is sent to corresponding reminding information, so that government departments can quickly and accurately carry out work, and meanwhile, the work of the government supporting enterprises is advanced, so that the regulation and control functions of the government are fully exerted, and the administrative efficiency of the government is improved.

Description

Enterprise operation abnormity monitoring method and device, computer equipment and storage medium

Technical Field

The application relates to the technical field of power grid data processing, in particular to a method and a device for monitoring enterprise operation abnormity, computer equipment and a storage medium.

Background

With the development of power grid data analysis technology, a technology for monitoring enterprise operation abnormity appears. In the current society, governments and enterprises are in a cooperative and friendly relationship, and when the enterprises are in abnormal operation, relevant government departments can develop the work of policy assistance, material assistance, communication coordination and the like for the enterprises, so that the enterprises can be helped to go through difficulty together.

In the related art, when an enterprise has an abnormal operation, the way for the enterprise to ask for help to the government is mainly through ways of visiting, calling for a call, consulting on line and the like, however, the ways have the problems of message processing delay and the like. Particularly, since the outbreak of new coronavirus epidemic situation, enterprises are influenced by raw materials, personnel, capital and the like, wherein the operation of many small and medium-sized micro-enterprises is attacked to cause shutdown and production halt, and if the enterprises cannot obtain quick and targeted help at the moment, the enterprises can hardly bridge operational difficulties. In addition, when the government department acquires the enterprise operation information, the problems of non-objective, inaccurate and untimely information acquisition and the like may exist, and the advance judgment on the enterprise operation state is lacked, so that the government is not favorable for providing targeted and effective help before the enterprise operation is abnormal. Therefore, a method for monitoring abnormal business operations is urgently needed.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an enterprise operation anomaly monitoring method, an enterprise operation anomaly monitoring apparatus, a computer device, a computer readable storage medium and a computer program product.

In a first aspect, the application provides a method for monitoring enterprise operation abnormity. The method comprises the following steps:

acquiring monitoring data of a target enterprise;

acquiring a trained enterprise operation abnormity monitoring model;

inputting the monitoring data into an enterprise operation abnormity monitoring model to obtain an output result;

and determining the operation state of the target enterprise according to the output result.

In one embodiment, obtaining the trained enterprise business anomaly monitoring model includes:

acquiring historical monitoring data of a plurality of sample enterprises, wherein the historical monitoring data comprises the industry, the region and the power utilization information of the sample enterprises;

acquiring an enterprise operation abnormity monitoring initial model according to historical monitoring data of a plurality of sample enterprises;

and training the enterprise operation abnormity monitoring initial model to obtain the trained enterprise operation abnormity monitoring model.

In one embodiment, obtaining an initial model for monitoring enterprise business anomaly according to historical monitoring data of a plurality of sample enterprises comprises:

determining the weight corresponding to each industry and the weight corresponding to each region according to the industry and the region to which each sample enterprise belongs;

cleaning the power utilization information of each sample enterprise to obtain the cleaned power utilization information, wherein the cleaned power utilization information comprises payment ways, arrearage conditions, illegal power utilization conditions, work order complaint conditions, customer satisfaction, power utilization increase conditions and power consumption, and the power consumption comprises night power consumption and weekend power consumption;

determining all power utilization characteristics of each sample enterprise according to the cleaned power utilization information of each sample enterprise;

determining the weight corresponding to each electricity utilization characteristic type according to all electricity utilization characteristics of each sample enterprise;

and acquiring an enterprise operation abnormity monitoring initial model according to the weight corresponding to each power utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region.

In one embodiment, all the electricity utilization characteristic types comprise enterprise electricity utilization levels, enterprise categories, whether the enterprises belong to night electricity utilization enterprises and whether the enterprises belong to single-break or double-break enterprises; correspondingly, all the electricity utilization characteristics of each sample enterprise are determined according to the cleaned electricity utilization information of each sample enterprise, and the method comprises the following steps:

determining the enterprise electricity utilization level of each sample enterprise according to the arrearage condition and the electricity utilization violation condition of each sample enterprise;

determining the enterprise category of each sample enterprise according to the customer satisfaction, the payment way, the arrearage condition, the work order complaint condition and the electricity utilization increase condition of each sample enterprise;

determining whether each sample enterprise belongs to a night electricity utilization enterprise or not according to the night electricity utilization quantity of each sample enterprise;

and determining whether each sample enterprise belongs to a single-break enterprise or a double-break enterprise according to the weekend electricity consumption of each sample enterprise.

In one embodiment, the weights corresponding to all the electricity utilization feature types comprise an enterprise electricity utilization level weight, an enterprise category weight, a night electricity utilization weight and a single-double-break weight; correspondingly, according to all the electricity utilization characteristics of each sample enterprise, determining the weight corresponding to each electricity utilization characteristic, wherein the weight comprises the following steps:

determining the enterprise power utilization level weight according to the enterprise power utilization level of each sample enterprise;

determining the enterprise category weight according to the enterprise category of each sample enterprise;

determining the weight of the night power utilization enterprises according to whether each sample enterprise belongs to the night power utilization enterprises;

and determining the single-double break weight according to whether each sample enterprise belongs to a single-break or double-break enterprise.

In one embodiment, the enterprise operation abnormity monitoring initial model comprises a weight corresponding to each power utilization characteristic type, a weight corresponding to each industry and a weight corresponding to each region; correspondingly, train enterprise abnormal operation monitoring initial model, obtain the enterprise abnormal operation monitoring model after the training, include:

acquiring a training sample set, wherein each training sample comprises sample monitoring data and a corresponding enterprise operation state marking result;

inputting sample monitoring data in each training sample into an enterprise operation abnormity monitoring initial model, outputting an enterprise operation state judgment result corresponding to each training sample, and determining the accuracy of the enterprise operation abnormity monitoring initial model when the enterprise operation state judgment is performed on a training sample set according to the enterprise operation state judgment result corresponding to each training sample and an enterprise operation state marking result;

if the error between the accuracy and the preset accuracy is larger than a preset error threshold, adjusting the weight corresponding to each power utilization feature type, the weight corresponding to each industry and the weight corresponding to each region in the enterprise operation abnormity monitoring initial model, and repeatedly executing the processes of inputting, outputting, determining the accuracy and adjusting the weight until the error between the determined accuracy and the preset accuracy is not larger than the preset error threshold, so as to obtain the trained enterprise operation abnormity monitoring model.

In a second aspect, the application further provides an enterprise operation abnormity monitoring device. The device comprises:

the first acquisition module is used for acquiring monitoring data of a target enterprise;

the second acquisition module is used for acquiring the trained enterprise operation abnormity monitoring model;

the third acquisition module is used for inputting the monitoring data into the enterprise operation abnormity monitoring model and acquiring an output result;

and the first determining module is used for determining the operation state of the target enterprise according to the output result.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

According to the enterprise operation abnormity monitoring method, the device, the computer equipment, the storage medium and the computer program product, monitoring data of a target enterprise are obtained; acquiring a trained enterprise operation abnormity monitoring model; inputting the monitoring data into an enterprise operation abnormity monitoring model to obtain an output result; according to the output result, the operation state of the target enterprise is determined, convenience is provided for the government to obtain the operation state of the enterprise, particularly when the government needs to confirm the operation states of a large number of enterprises, the enterprises with abnormal operation or the enterprises with abnormal operation risk are quickly positioned or judged in advance, the enterprise list is monitored to send corresponding reminding information, the government department can quickly and accurately carry out work, meanwhile, the government assists the enterprises to work in the front, the regulation and control functions of the government are fully played, and the administrative efficiency of the government is improved.

Drawings

FIG. 1 is a diagram of an exemplary embodiment of a method for monitoring enterprise business anomalies;

FIG. 2 is a schematic flow chart illustrating a method for monitoring business misoperations in one embodiment;

FIG. 3 is a block diagram of an embodiment of an enterprise mismanagement monitoring apparatus;

FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The enterprise operation abnormity monitoring method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 101 communicates with the server 102 via a network. The data storage system may store data that the server 102 needs to process. The data storage system may be integrated on the server 102, or may be located on the cloud or other network server. The terminal 101 acquires monitoring data of a target enterprise and transmits the data to the server 102, and the server 102 inputs the monitoring data into an enterprise operation abnormity monitoring model to acquire an output result; and determining the operation state of the target enterprise according to the output result.

The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 102 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.

In one embodiment, as shown in fig. 2, a method for monitoring enterprise operation anomaly is provided, which is described by taking the method as an example applied to the server 102 in fig. 1, and includes the following steps:

201. acquiring monitoring data of a target enterprise;

202. acquiring a trained enterprise operation abnormity monitoring model;

203. inputting the monitoring data into an enterprise operation abnormity monitoring model to obtain an output result;

204. and determining the operation state of the target enterprise according to the output result.

In step 201, the target enterprise refers to an enterprise whose business status to be monitored is abnormal, and the target enterprise does not refer to a specific enterprise, and may be one or multiple. The monitoring data refers to data which can be used for judging whether the target enterprise has abnormal operation, and the selection of the type of the monitoring data is related to the enterprise abnormal operation monitoring model.

In step 202, the trained business abnormal operation monitoring model refers to that the model can be used for monitoring the business state of the target enterprise after being trained, the business state of the target enterprise can be evaluated by the trained business abnormal operation monitoring model, and the evaluation result can also reflect the business state of the target enterprise more correctly.

In step 203, the outputting the result means that after the monitored data of the target enterprise is analyzed and processed by the enterprise operation anomaly monitoring model, the enterprise operation anomaly monitoring model outputs an evaluation result, and the evaluation result can reflect the judgment of the enterprise operation anomaly monitoring model on the operation state of the target enterprise. For example, if a government needs to acquire the business state of an enterprise, the monitoring data of the enterprise can be input into the enterprise abnormal operation monitoring model, so as to acquire the business state of the enterprise.

In addition, the output result of the enterprise operation abnormity monitoring model can be used as a reference, the output result only reflects the judgment of the enterprise operation abnormity monitoring model on the target enterprise according to the corresponding monitoring data, and the actual operation state of the target enterprise may need to be judged by combining other conditions.

In step 204, the output result may reflect that the operation status of the target enterprise is abnormal or normal. It should be noted that the output result is only the result obtained by analyzing and processing the monitoring data input by the enterprise operation anomaly monitoring model to the target enterprise, and does not completely reflect the actual operation state of the target enterprise. For example, if the output result of the enterprise operation abnormality monitoring model indicates that the operation state of the target enterprise is abnormal, the actual operation state of the target enterprise can be determined only by comprehensively judging the information obtained by actual visits.

Specifically, after the monitoring data of the target enterprise is obtained, the monitoring data needs to be cleaned, and errors and invalid data in the monitoring data are removed, so that the accuracy of the output result is improved. The enterprise operation abnormity monitoring model needs to be obtained by training through a large number of training samples, the more training samples of the enterprise operation abnormity monitoring model are, and the higher the accuracy of the output result is. Therefore, in order to improve the accuracy of the enterprise operation anomaly monitoring model, the number of the selected training samples should be enough, and the more accurate the operation state of the target enterprise can be reflected according to the output result.

According to the method provided by the embodiment of the invention, the monitoring data of the target enterprise is input into the enterprise operation abnormity monitoring model, so that the operation state of the target enterprise can be obtained, and convenience is provided for the government to obtain the operation state of the enterprise. Especially when the administrative departments need to confirm the operation states of a large number of enterprises, the enterprises with abnormal operation or the enterprises with abnormal operation risk can be quickly positioned, the monitored enterprise list is sent to corresponding reminding information, so that government departments can quickly and accurately carry out work, and meanwhile, the government supporting enterprises are preposed to fully play the regulating and controlling functions of the government and improve the administrative efficiency of the government.

In one embodiment, obtaining a trained business operation anomaly monitoring model comprises:

301. acquiring historical monitoring data of a plurality of sample enterprises, wherein the historical monitoring data comprises the industry, the region and the power utilization information of the sample enterprises;

302. acquiring an enterprise operation abnormity monitoring initial model according to historical monitoring data of a plurality of sample enterprises;

303. and training the enterprise operation abnormity monitoring initial model to obtain the trained enterprise operation abnormity monitoring model.

In step 301, the sample enterprise refers to enterprises in many industries and regions, the industry and the region to which the enterprise belongs are not specifically limited in the embodiments of the present invention, and the industries and the regions to which the sample enterprises belong in a plurality of sample enterprises may be the same or different. Historical monitoring data does not refer to a certain kind of data, and is a general term for many different kinds of data. Specifically, the obtaining of the historical monitoring data of the plurality of sample enterprises includes obtaining the industry, the region and the electricity consumption information of the plurality of sample enterprises, wherein the electricity consumption information includes a plurality of different types of data related to electricity consumption.

In the step 302, the initial enterprise power consumption abnormality monitoring model means that the adjustable parameters in the initial enterprise power consumption abnormality monitoring model are not adjusted, the size of the adjustable parameters in the initial enterprise power consumption abnormality monitoring model depends on historical monitoring data of a plurality of sample enterprises, and in addition, the number of the adjustable parameters is not only one.

Specifically, historical monitoring data of a plurality of sample enterprises are analyzed and processed by using a data mining algorithm, so that an enterprise power utilization abnormity monitoring initial model is obtained. The real-time embodiment of the present invention does not specifically limit the data mining algorithm, and includes but is not limited to: a K-Means algorithm, a K-Nearest Neighbor (KNN) classification algorithm, a decision-making algorithm, and the like.

In step 303, the enterprise operation anomaly monitoring initial model is trained to automatically adjust adjustable parameters in the enterprise operation anomaly monitoring initial model. When the initial model for monitoring the enterprise operation abnormity is determined, the model can be used for determining the operation state of the target enterprise without representing the model, continuous training is also needed, all adjustable parameters are automatically adjusted until the output result of the model achieves the expected effect, the training process of the model is indicated to be finished, and the adjustment of the size of the adjustable parameters is stopped because the size of the adjustable parameters is adjusted to the optimal state.

It is worth mentioning that the adjustment of the adjustable parameter can not only be automatically adjusted in the training process, but also be adjusted manually, so that the adjustable parameter can reach the optimal state, and the output result of the model can reach the expected effect.

According to the method provided by the embodiment of the invention, for the enterprise operation abnormity monitoring initial model, the model can be repeatedly trained, so that the adjustable parameters in the model are automatically adjusted to the optimal state, the accuracy of the output result of the enterprise operation abnormity monitoring model is higher, and the efficiency of the enterprise operation abnormity monitoring model is improved.

401. determining the weight corresponding to each industry and the weight corresponding to each region according to the industry and the region to which each sample enterprise belongs;

402. cleaning the power utilization information of each sample enterprise to obtain the cleaned power utilization information; the cleaned electricity utilization information comprises a payment way, an arrearage condition, a violation electricity utilization condition, a work order complaint condition, customer satisfaction, an electricity utilization increase condition and electricity consumption, wherein the electricity consumption comprises night electricity consumption and weekend electricity consumption;

403. determining all power utilization characteristics of each sample enterprise according to the cleaned power utilization information of each sample enterprise;

404. determining the weight corresponding to each electricity utilization characteristic type according to all electricity utilization characteristics of each sample enterprise;

405. and acquiring an enterprise operation abnormity monitoring initial model according to the weight corresponding to each power utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region.

In step 401, the weights corresponding to different industries are different, and the weights corresponding to different regions are also different. Specifically, the size of the weight corresponding to each industry and each region is related to all the sample enterprises obtained. It should be noted that the industry-corresponding weight and the region-corresponding weight in this embodiment belong to two adjustable parameters of all the adjustable parameters in the step 303.

In the above step 402, the cleaning means to remove the error information and the invalid information in the electricity consumption information. The payment ways mainly comprise two kinds, namely electronic channel payment and non-electronic channel payment. The arrearage condition refers to the judgment of whether the enterprise is arrearage and arrearage duration. The condition of illegal power utilization refers to the condition that whether the enterprise illegally utilizes power is judged. The work order complaint condition refers to whether the work order complaint exists or not. Customer satisfaction refers to determining customer satisfaction as either satisfied or not satisfied depending on whether a power outage has occurred. The electricity consumption increase condition refers to judging the electricity consumption proportional increase rate of the enterprise. The embodiment of the present invention does not specifically limit the used amount, and includes but is not limited to: night electricity consumption, weekend electricity consumption, month electricity consumption, season electricity consumption and annual electricity consumption.

In step 403, a data mining algorithm is applied to the cleaned power utilization information, so that all power utilization characteristics of each sample enterprise can be determined, where the power utilization characteristics refer to power utilization behaviors of the sample enterprises that can be reflected and extracted by the data mining algorithm in combination with the power utilization information of all the sample enterprises. The power utilization characteristics are extracted, so that convenience can be provided for subsequent machine learning. Specifically, each sample enterprise has the same type of electricity usage characteristic, but each type of electricity usage characteristic may be different.

For example, the electricity usage characteristics are classified into A, B, C, D, and the electricity usage characteristics a can be classified into different cases, such as first, second, third, etc. according to the classification, and the other electricity usage characteristics B, C, D can be classified into different cases as the electricity usage characteristics a. If the sample enterprise is a, and a, therefore, the sample enterprise a, b, or c has A, B, C, D four types of electricity usage characteristics, but the electricity usage characteristic a of the sample enterprise a may have a different grade from the electricity usage characteristic a of the sample enterprise b, that is, the electricity usage characteristic a of the sample enterprise a may have a first grade, and the electricity usage characteristic a of the sample enterprise b may have a second grade.

In step 404, the weight corresponding to each electricity utilization characteristic type refers to a part of adjustable parameters in the enterprise operation anomaly monitoring initial model, which needs to be determined according to all the electricity utilization characteristics of each sample enterprise.

In step 405, according to the weight corresponding to each power utilization feature type, the weight corresponding to each industry, and the weight corresponding to each region, the initial values of all adjustable parameters in the enterprise operation anomaly monitoring initial model can be determined. Specifically, the weight corresponding to each electricity utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region form initial values of all adjustable parameters in the enterprise operation abnormity monitoring initial model.

For example, the weight corresponding to the electricity utilization characteristic type is 30%, 30%, 20%, 10%, the weight corresponding to each industry is 5%, and the weight corresponding to each region is 5%, so that the initial values of all adjustable parameters in the enterprise operation anomaly monitoring initial model are 30%, 30%, 20%, 10%, 5%, and 5%, respectively. Before the enterprise operation abnormity monitoring initial model is trained, the values of all adjustable parameters are determined, and when the enterprise operation abnormity monitoring initial model is trained, the values of all adjustable parameters can be automatically adjusted through a machine automatic learning technology until the model meets the preset requirement.

According to the method provided by the embodiment of the invention, all the electricity utilization characteristics of each sample enterprise can be extracted from the electricity utilization information of all the sample enterprises through a data mining algorithm, so that the weight of each electricity utilization characteristic type is determined according to all the electricity utilization characteristics, the initial value of the adjustable parameter in the enterprise operation abnormity monitoring initial model is determined, and the machine learning efficiency is improved.

In one embodiment, all power utilization characteristic types comprise enterprise power utilization levels, enterprise categories, whether the power utilization enterprises belong to night power utilization enterprises and whether the power utilization enterprises belong to single-break or double-break enterprises; correspondingly, all the electricity utilization characteristics of each sample enterprise are determined according to the cleaned electricity utilization information of each sample enterprise, and the method comprises the following steps:

501. determining the enterprise electricity utilization level of each sample enterprise according to the arrearage condition and the electricity utilization violation condition of each sample enterprise;

502. determining the enterprise category of each sample enterprise according to the customer satisfaction, the payment way, the arrearage condition, the work order complaint condition and the electricity utilization increase condition of each sample enterprise;

503. determining whether each sample enterprise belongs to a night electricity utilization enterprise or not according to the night electricity utilization quantity of each sample enterprise;

504. and determining whether each sample enterprise belongs to a single-break enterprise or a double-break enterprise according to the weekend electricity consumption of each sample enterprise.

In step 501, regarding the dividing manner of the power consumption level of the enterprise, the embodiment of the present invention does not specifically limit the dividing manner, and includes but is not limited to: the power utilization level of an enterprise can be divided into a first level, a second level, a third level and a fourth level. The enterprise electricity utilization level of each sample enterprise is related to the arrearage condition and the violation electricity utilization condition of each sample enterprise, for example, if a certain enterprise is an arrearage and violation enterprise, the electricity utilization level of the enterprise can be determined as one level, if a certain enterprise is an arrearage and violation enterprise, the electricity utilization level of the enterprise can be determined as two levels, if a certain enterprise is an arrearage and violation enterprise, the electricity utilization level of the enterprise can be determined as three levels, and if a certain enterprise is an arrearage and violation enterprise, the electricity utilization level of the enterprise can be determined as four levels.

In step 502, regarding the dividing manner of the enterprise categories, the embodiment of the present invention does not specifically limit the dividing manner, and includes but is not limited to: the enterprise categories can be classified into potential enterprises, silent enterprises, risk enterprises and weak enterprises, and the enterprise category of each sample enterprise is related to the customer satisfaction, the payment route, the arrearage condition, the work order complaint condition and the electricity utilization increase condition of each sample enterprise.

Specifically, the customer satisfaction is determined by the power failure condition and the complaint condition of the enterprise, and the power failure condition is divided into power failure and power failure. The complaints of the work order are classified into complaints and non-complaints. The payment path is divided into an electronic payment channel payment and an electronic channel payment. The arrearage situation is divided into arrearage and non-arrearage. The electricity consumption increase condition comprises that the electricity consumption increase rate is more than 10 percent, the electricity consumption increase rate is between 0 percent and 10 percent, and the electricity consumption increase rate is less than 0 percent.

If a certain enterprise has no power failure, no complaint, no arrearage, no low insurance, the percentage increase of the same proportion of the electricity consumption is more than 10 percent, and the payment channel is an electronic channel, the enterprise category of the enterprise can be determined as a potential enterprise. If a certain enterprise has no power failure, has complaints, has arrearage, no low insurance users, has a power consumption percentage increase rate of 0-10% on a same scale, and the payment channel is a non-electronic channel, the enterprise category of the enterprise can be determined as a risk type enterprise. If the enterprise has no power failure, no complaints, no arrearages, no low insurance customers, the percentage increase of the same proportion of the electricity consumption is less than 0 percent, and the payment channel is a non-electronic channel, the enterprise category of the enterprise can be determined as a risk-type enterprise. If a certain enterprise has power failure, has no complaints, has no arrearages, has low insured customers, has a power consumption same-proportion increase rate of less than 0 percent, and the payment channel is a non-electronic channel, the enterprise category of the enterprise can be determined as a disadvantaged enterprise.

In step 503, the night electricity consumption of the enterprise may reflect whether the enterprise is a night electricity consumption enterprise, for example, if the night electricity consumption of an enterprise is relatively low, it indicates that the enterprise does not belong to the night electricity consumption enterprise, and if the night electricity consumption of an enterprise is relatively high, it indicates that the enterprise belongs to the night electricity consumption enterprise.

In step 504, the weekend power consumption of the enterprise may reflect whether the enterprise belongs to a single-family or double-family enterprise, for example, if the power consumption of a certain enterprise on saturday or sunday is relatively high, it indicates that the enterprise belongs to a single-family enterprise, and if the power consumption of a certain enterprise on saturday and sunday is low, it indicates that the enterprise belongs to a double-family enterprise.

According to the method provided by the embodiment of the invention, all the electricity utilization characteristics of each sample enterprise can be determined through the cleaned electricity utilization information of each sample enterprise.

601. determining the enterprise power utilization level weight according to the enterprise power utilization level of each sample enterprise;

602. determining the enterprise category weight according to the enterprise category of each sample enterprise;

603. determining the weight of the night power utilization enterprises according to whether each sample enterprise belongs to the night power utilization enterprises;

604. and determining the single-double break weight according to whether each sample enterprise belongs to a single-break or double-break enterprise.

Specifically, the weight corresponding to each electricity utilization characteristic is the initial value of a part of adjustable parameters in the enterprise business anomaly monitoring initial model mentioned in the above step 405. In this embodiment, the weights corresponding to all the electricity consumption characteristics are determined by combining all the electricity consumption characteristics of all the sample enterprises, so that the selected sample enterprise quantity and the properties of the sample enterprises can influence the weights corresponding to the types of the electricity consumption characteristics. It should be noted that the different corresponding weights of the enterprise electricity utilization levels are also different, and the weight range may be 0-100%, for example, the enterprise electricity utilization level is one level, the corresponding weight thereof may be 10%, the enterprise electricity utilization level is two levels, and the corresponding weight thereof may be 15%. The weighting may be 20% for example for an at risk business and 0% for a disadvantaged business in the business category.

According to the method provided by the embodiment of the invention, the weight corresponding to each electricity utilization characteristic is determined through all the electricity utilization characteristics of each sample enterprise, so that the determined weight corresponding to each electricity utilization characteristic is more reliable, and the accuracy of the output result of the enterprise operation abnormity monitoring model can be improved.

701. acquiring a training sample set, wherein each training sample comprises sample monitoring data and a corresponding enterprise operation state marking result;

702. inputting sample monitoring data in each training sample into an enterprise operation abnormity monitoring initial model, outputting an enterprise operation state judgment result corresponding to each training sample, and determining the accuracy of the enterprise operation abnormity monitoring initial model when the enterprise operation state judgment is performed on a training sample set according to the enterprise operation state judgment result corresponding to each training sample and an enterprise operation state marking result;

703. if the error between the accuracy and the preset accuracy is larger than a preset error threshold, adjusting the weight corresponding to each power utilization feature type, the weight corresponding to each industry and the weight corresponding to each region in the enterprise operation abnormity monitoring initial model, and repeatedly executing the processes of inputting, outputting, determining the accuracy and adjusting the weight until the error between the determined accuracy and the preset accuracy is not larger than the preset error threshold, so as to obtain the trained enterprise operation abnormity monitoring model.

The implementation of the invention is not particularly limited as to the accuracy of the output result of the enterprise operation anomaly monitoring model. The higher the accuracy of the output result is, the higher the accuracy of the enterprise operation abnormity monitoring model judgment is.

Specifically, since the initial enterprise operation anomaly monitoring model determined by the historical monitoring data of the sample enterprise is not trained, the result output by the initial enterprise operation anomaly monitoring model is inaccurate, so that the initial enterprise operation anomaly monitoring model needs to be monitored by using a training sample set, and the weight corresponding to each power consumption feature type, the weight corresponding to each industry and the weight corresponding to each region in the initial enterprise operation anomaly monitoring model can be adjusted to be proper values mainly through continuous training, so that the result output by the initial enterprise operation anomaly monitoring model can achieve the expected effect.

For example, the expected effect may be that when the error between the accuracy and the preset accuracy of the initial enterprise operation anomaly monitoring model is greater than 0.01% of the preset error threshold when the initial enterprise operation state judgment is performed on the training sample set, it indicates that the weight corresponding to each power consumption feature type, the weight corresponding to each industry, and the weight corresponding to each region in the initial enterprise operation anomaly monitoring model have been adjusted to appropriate values.

The method provided by the embodiment of the invention can train the initial enterprise operation abnormity monitoring model through the training sample set, can improve the accuracy of the output result of the enterprise operation abnormity monitoring model, thereby providing convenience for the government to acquire the operation state of the enterprise, and particularly can quickly position the enterprise with abnormal operation or pre-judge the enterprise with abnormal operation risk when the government needs to confirm the operation state of a large number of enterprises, and send the corresponding reminding information to the monitored enterprise list, so that the government department can quickly and accurately carry out work.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the application also provides an enterprise operation abnormity monitoring device for realizing the enterprise operation abnormity monitoring method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the enterprise operation abnormity monitoring device provided below can be referred to the limitations of the enterprise operation abnormity monitoring method in the above, and details are not described herein again.

In one embodiment, as shown in fig. 3, there is provided an enterprise operation anomaly monitoring device, including: a first obtaining module 311, a second obtaining module 312, a third obtaining module 313, and a first determining module 314, wherein:

the first obtaining module 311 is configured to obtain monitoring data of a target enterprise;

a second obtaining module 312, configured to obtain the trained enterprise operation anomaly monitoring model;

the third obtaining module 313 is used for inputting the monitoring data into the enterprise operation abnormity monitoring model and obtaining an output result;

and the first determining module 314 is configured to determine the operation status of the target enterprise according to the output result.

In one embodiment, the second obtaining module 312 includes:

the system comprises a first obtaining submodule and a second obtaining submodule, wherein the first obtaining submodule is used for obtaining historical monitoring data of a plurality of sample enterprises, and the historical monitoring data comprises the industries and the regions of the sample enterprises and power utilization information;

the second acquisition submodule is used for acquiring an enterprise operation abnormity monitoring initial model according to historical monitoring data of a plurality of sample enterprises;

and the third acquisition submodule is used for training the enterprise operation abnormity monitoring initial model and acquiring the trained enterprise operation abnormity monitoring model.

In one embodiment, the second obtaining sub-module includes:

the first determining unit is used for determining the weight corresponding to each industry and the weight corresponding to each region according to the industry and the region of each sample enterprise;

the first acquisition unit is used for cleaning the electricity utilization information of each sample enterprise and acquiring the cleaned electricity utilization information, wherein the cleaned electricity utilization information comprises a payment way, an arrearage condition, a violation electricity utilization condition, a work order complaint condition, customer satisfaction, an electricity utilization increase condition and electricity consumption, and the electricity consumption comprises night electricity consumption and weekend electricity consumption;

the second determining unit is used for determining all power utilization characteristics of each sample enterprise according to the cleaned power utilization information of each sample enterprise;

the third determining unit is used for determining the weight corresponding to each type of the electricity utilization characteristics according to all the electricity utilization characteristics of each sample enterprise;

and the second acquisition unit is used for acquiring the enterprise operation abnormity monitoring initial model according to the weight corresponding to each power utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region.

In one embodiment, the second determination unit includes:

the first determining subunit is used for determining the enterprise electricity utilization level of each sample enterprise according to the arrearage condition and the electricity consumption violation condition of each sample enterprise;

the second determining subunit is used for determining the enterprise category of each sample enterprise according to the customer satisfaction, the payment route, the arrearage condition, the work order complaint condition and the electricity utilization increase condition of each sample enterprise;

the third determining subunit is used for determining whether each sample enterprise belongs to the night electricity utilization enterprise or not according to the night electricity utilization quantity of each sample enterprise;

and the fourth determining subunit is used for determining whether each sample enterprise belongs to a single-break enterprise or a double-break enterprise according to the weekend electricity consumption of each sample enterprise.

In one embodiment, the third determining unit includes:

the fifth determining subunit is used for determining the enterprise electricity utilization level weight according to the enterprise electricity utilization level of each sample enterprise;

the sixth determining subunit is configured to determine a business category weight according to the business category of each sample business;

the seventh determining subunit is configured to determine the weight of the night power utilization enterprise according to whether each sample enterprise belongs to a night power utilization enterprise;

and the eighth determining subunit is used for determining the single-double break weight according to whether each sample enterprise belongs to a single-break enterprise or a double-break enterprise.

In one embodiment, the third obtaining sub-module includes:

the third acquisition unit is used for acquiring a training sample set, and each training sample comprises sample monitoring data and a corresponding enterprise operation state marking result;

the fourth determining unit is used for inputting the sample monitoring data in each training sample into the enterprise operation abnormity monitoring initial model, outputting an enterprise operation state judgment result corresponding to each training sample, and determining the accuracy of the enterprise operation abnormity monitoring initial model when the enterprise operation state judgment is carried out on the training sample set according to the enterprise operation state judgment result corresponding to each training sample and the enterprise operation state marking result;

and the first adjusting unit is used for adjusting the weight corresponding to each power utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region in the enterprise operation abnormity monitoring initial model if the error between the accuracy and the preset accuracy is greater than a preset error threshold, and repeatedly executing the processes of inputting, outputting, determining the accuracy and adjusting the weight until the error between the determined accuracy and the preset accuracy is not greater than the preset error threshold, so as to obtain the trained enterprise operation abnormity monitoring model.

All or part of the modules in the enterprise operation abnormity monitoring device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing monitoring data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an enterprise operation anomaly monitoring method.

Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

acquiring monitoring data of a target enterprise;

acquiring a trained enterprise operation abnormity monitoring model;

In one embodiment, the processor, when executing the computer program, further performs the steps of:

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring monitoring data of a target enterprise;

acquiring a trained enterprise operation abnormity monitoring model;

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:

acquiring monitoring data of a target enterprise;

acquiring a trained enterprise operation abnormity monitoring model;

It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An enterprise operation abnormity monitoring method is characterized by comprising the following steps:

acquiring monitoring data of a target enterprise;

acquiring a trained enterprise operation abnormity monitoring model;

2. The method of claim 1, wherein obtaining the trained business anomaly monitoring model comprises:

3. The method of claim 2, wherein obtaining an initial model of enterprise business anomaly monitoring based on historical monitoring data for a plurality of sample enterprises comprises:

and acquiring the enterprise operation abnormity monitoring initial model according to the weight corresponding to each power utilization characteristic type, the weight corresponding to each industry and the weight corresponding to each region.

4. The method of claim 3, wherein all power usage characteristic types include enterprise power usage level, enterprise category, whether it belongs to nighttime power usage enterprise, and whether it belongs to single-break or double-break enterprise; correspondingly, the determining all the electricity utilization characteristics of each sample enterprise according to the cleaned electricity utilization information of each sample enterprise comprises the following steps:

5. The method according to claim 4, wherein the weights corresponding to all the electricity utilization feature types comprise an enterprise electricity utilization level weight, an enterprise category weight, a night electricity utilization weight and a single-double break weight; correspondingly, the determining the weight corresponding to each electricity utilization characteristic according to all the electricity utilization characteristics of each sample enterprise comprises the following steps:

6. The method according to claim 3, wherein the initial enterprise business anomaly monitoring model comprises a weight corresponding to each power utilization characteristic type, a weight corresponding to each industry and a weight corresponding to each region; correspondingly, the training the enterprise operation abnormity monitoring initial model to obtain the trained enterprise operation abnormity monitoring model comprises:

inputting sample monitoring data in each training sample into the enterprise operation abnormity monitoring initial model, outputting an enterprise operation state judgment result corresponding to each training sample, and determining the accuracy of the enterprise operation abnormity monitoring initial model when the enterprise operation state judgment is performed on the training sample set according to the enterprise operation state judgment result corresponding to each training sample and the enterprise operation state marking result;

7. An enterprise operation anomaly monitoring device, characterized in that the device includes:

the third acquisition module is used for inputting the monitoring data into an enterprise operation abnormity monitoring model and acquiring an output result;

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.