CN115456682A

CN115456682A - Bill data auditing method, device, equipment and storage medium

Info

Publication number: CN115456682A
Application number: CN202211152785.5A
Authority: CN
Inventors: 董莹莹; 李坤树; 刘桂志; 熊建胜; 王瑜; 黄双双
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2022-09-21
Filing date: 2022-09-21
Publication date: 2022-12-09

Abstract

The application provides a bill data auditing method, device, equipment and storage medium. The method comprises the following steps: acquiring current real electric charge bill data, previous real electric charge bill data and current predicted electric charge bill data corresponding to the target device; the previous real electric charge bill data is real electric charge bill data of a period before the current real electric charge bill data; determining a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset circular comparison auditing strategy; determining a current second audit state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison audit strategy; and sending audit abnormity prompting information to the user terminal in response to that the current first audit state and the current second audit state are abnormal states. The method and the device give an accurate audit result according to the actual situation of the target device.

Description

Bill data auditing method, device, equipment and storage medium

Technical Field

The present application relates to data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for auditing bill data.

Background

As the demand of people on the internet increases, the number of base station devices also increases, which increases the attention of developers to audit the billing data of the base station devices.

In the prior art, the auditing of the bill data of the base station equipment can be completed by a conventional strategy method. The conventional strategy method sets a general fluctuation range threshold value based on the historical electric bill data of part of base station equipment, and realizes the audit of the current real electric bill data of all the base station equipment. And if the fluctuation range of the current real electric bill data and the historical electric bill data is larger than or equal to the general fluctuation range threshold value, determining that the current real electric bill data is in an abnormal state.

Because the conventional strategy method is based on the historical electricity bill data of part of base station equipment, the characteristics of the base station equipment are not considered, and the electricity bill data of the base station equipment cannot be audited according to the actual situation of the base station equipment, so that an accurate audit result cannot be given.

Disclosure of Invention

The application provides a bill data auditing method, device, equipment and storage medium, which are used for solving the problem that the electricity bill data of base station equipment cannot be audited according to the actual situation of the base station equipment, and further, an accurate auditing result cannot be given.

In a first aspect, the present application provides a method for auditing bill data, including:

acquiring current real electric charge bill data, previous real electric charge bill data and current predicted electric charge bill data corresponding to the target device; the previous real electric charge bill data is real electric charge bill data of a period previous to the current real electric charge bill data;

determining a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset ring ratio auditing strategy;

determining a current second auditing state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison auditing strategy;

and sending audit abnormity prompting information to the user terminal in response to that the current first audit state and the current second audit state are abnormal states.

In one possible manner, the current real electricity bill data includes: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: the previous real day-to-day average ring ratio data having the same dimension as the current real day-to-day average ring ratio data, determining a current first audit state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset ring ratio audit strategy, and the method comprises the following steps:

calculating the rise and fall amplitude of each daily average ring ratio between the current real daily average ring ratio data and the previous real daily average ring ratio data of each dimension;

acquiring a daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data;

comparing the rise and fall amplitude of each daily average ring ratio with the corresponding rise and fall amplitude threshold value of the daily average ring ratio to obtain rise and fall comparison results;

and determining the current first auditing state of the current real electric bill data according to each rising and falling comparison result.

In a possible manner, the obtaining of the daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data includes:

determining a current time range corresponding to the current real electric bill data;

acquiring a mapping relation between a preset time range and a daily average cycle ratio fluctuation range threshold;

and acquiring a daily average ring ratio fluctuation amplitude threshold corresponding to the current time range from the mapping relation according to the current time range, and using the daily average ring ratio fluctuation amplitude threshold as a daily average ring ratio fluctuation amplitude threshold corresponding to the current real electric bill data.

In one possible manner, the determining a current first audit state of the current real electric bill data according to each of the rise-fall comparison results includes:

in response to that at least two daily average ring ratio rise-fall ranges in each rise-fall comparison result are greater than or equal to the corresponding daily average ring ratio rise-fall range threshold, determining that the current first audit state is an abnormal state;

and in response to the existence or non-existence of one or more daily average ring ratio rise-fall ranges larger than or equal to the corresponding daily average ring ratio rise-fall range threshold value in each comparison result, determining that the current first audit state is a normal state.

In one possible manner, the current real electricity bill data includes: current real day-to-average ring ratio data of at least one dimension, wherein the current predicted electric bill data comprises: current predicted day-to-average ring ratio data with the same dimension as the current real day-to-average ring ratio data;

the determining a current second audit state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison audit strategy comprises:

calculating the deviation amplitude of each day average ring ratio between the current real day average ring ratio data and the current prediction day average ring ratio data of each dimension;

comparing each daily average ring ratio deviation amplitude threshold with a preset daily average ring ratio deviation amplitude threshold to obtain each deviation comparison result;

and determining the current second auditing state of the current real electric bill data according to each deviation comparison result.

In one possible manner, determining a current second audit state of the current real electric bill data according to each deviation comparison result includes:

responding to at least two daily average ring ratio deviation amplitudes greater than or equal to a preset daily average ring ratio deviation amplitude threshold value in each deviation comparison result, and determining that the current second auditing state is an abnormal state;

and determining that the current second auditing state is a normal state in response to the fact that one or no day-to-average ring ratio deviation amplitude is larger than or equal to a preset day-to-average ring ratio deviation amplitude threshold value exists in each deviation comparison result.

In one possible manner, the obtaining of the current predicted electric bill data includes:

acquiring real electricity bill data of a historical preset time period;

inputting the real electric bill data of the historical preset time period into a timing sequence model trained to be convergent;

predicting the current electric charge bill data by adopting the trained to converged time sequence model based on the real electric charge bill data of the historical preset time period, and outputting the current predicted electric charge bill data;

and acquiring the output current predicted electric bill data.

In one possible manner, before predicting the current electric bill data based on the real electric bill data of the historical preset time period by using the time sequence model trained to converge, the method further includes:

obtaining a training sample for training a preset time sequence model, wherein the training sample comprises: at least one piece of real electric bill data of a historical preset time period and corresponding real electric bill data of a future preset time period;

training the preset time sequence model by adopting the training sample until a preset model convergence condition is met;

and determining the time sequence model meeting the preset model convergence condition as the time sequence model trained to be converged.

In a second aspect, the present application provides a bill data auditing apparatus, including:

the acquisition module is used for acquiring current real electric charge bill data, previous real electric charge bill data and current predicted electric charge bill data corresponding to the target equipment; the previous real electric charge bill data is real electric charge bill data of a period previous to the current real electric charge bill data;

a first determining module, configured to determine a current first auditing state of the current real electric bill data based on the current real electric bill data and previous real electric bill data by using a preset ring ratio auditing strategy;

a second determination module, configured to determine a current second audit state of the current real electric bill data based on the current real electric bill data and the current predicted electric bill data by using a preset real and predicted data comparison audit policy;

and the sending module is used for sending audit abnormity prompting information to the user terminal in response to that the current first audit state and the current second audit state are abnormal states.

In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory and transceiver communicatively coupled to the processor;

the memory stores computer execution instructions; the transceiver is used for receiving and transmitting data with a user terminal;

the processor executes computer-executable instructions stored by the memory to implement the method as described in the first aspect or any one of the possible ways described above.

In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used for implementing the method as described in the first aspect or any one of the possible manners.

The method comprises the steps of obtaining current real electric charge bill data, previous real electric charge bill data and current predicted electric charge bill data corresponding to target equipment; the previous real electric charge bill data is real electric charge bill data of a period before the current real electric charge bill data; determining a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset ring ratio auditing strategy; determining a current second auditing state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison auditing strategy; and sending audit abnormity prompting information to the user terminal in response to that the current first audit state and the current second audit state are abnormal states. The method comprises the steps that a preset ring ratio auditing strategy is adopted to determine a current first auditing state of current real electric charge bill data based on obtained current real electric charge bill data and previous real electric charge bill data, the first auditing state is finally determined based on comparison with the previous real electric charge bill data, so that the state of the current real electric charge bill data can be accurately reflected, then a current second auditing state of the current real electric charge bill data is determined based on the obtained current real electric charge bill data and current predicted electric charge bill data, the current second auditing state is determined based on current predicted electric charge bill data of target devices in different time ranges, so that the time change rule of the target devices is better met, and the auditing result is higher in accuracy; in response to that the current first audit state and the current second audit state are both abnormal states, the current real electric charge bill data can be finally determined to be abnormal states, and further, audit abnormity prompting information can be sent to the user terminal in time, and the user terminal staff is prompted as early as possible that the current real electric charge bill data are abnormal; meanwhile, the first audit state and the second audit state can be determined according to the self characteristics of different target devices, so that the final audit result is more targeted and better conforms to the self condition of each target device.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

Fig. 1 is an application scenario diagram of a bill data auditing method provided by the present application;

fig. 2 is a schematic flowchart illustrating a method for auditing bill data according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart illustrating a method for auditing bill data according to a second embodiment of the present application;

fig. 4 is a schematic flowchart illustrating a method for auditing bill data according to a third embodiment of the present application;

fig. 5 is a schematic flowchart illustrating a bill data auditing method according to a fourth embodiment of the present application;

fig. 6 is a schematic flowchart illustrating a method for auditing bill data according to a fifth embodiment of the present application;

fig. 7 is a schematic flowchart illustrating a method for auditing bill data according to a sixth embodiment of the present application;

fig. 8 is a schematic diagram illustrating a bill data auditing apparatus according to a seventh embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an electronic device according to an eighth embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terms referred to in this application are explained first:

a time sequence model: the full-name time series model is different time point data sets collected under the condition that the time interval is unchanged, and the sets are analyzed (by a theory and a method for establishing a mathematical model through curve fitting and parameter estimation) to know the long-term development trend and predict future values;

base station equipment: refers to public mobile communication base station equipment, an interface equipment for accessing the internet of mobile equipment, and is a form of radio station. Can be a radio transceiver station for information transmission with a mobile telephone terminal through a mobile communication switching center in a certain radio coverage area;

ring ratio refers to the ratio of the change in the number of consecutive two statistical periods.

In recent years, the number of base station devices is increasing, so that auditing of electric bill data of the base station devices becomes a big problem. In the prior art, a conventional strategy method can be adopted to audit the current electric bill data, and the method specifically comprises the following steps: the conventional strategy method sets a general fluctuation range threshold value based on historical electric charge bill data of part of a plurality of base station devices, and determines that the current real electric charge bill data of the base station device is abnormal if the fluctuation range of the current real electric charge bill data relative to the historical electric charge bill data is larger than or equal to the general fluctuation range threshold value, so that the base station device can be determined to be abnormal.

However, the prior art has some defects, the above-mentioned general fluctuation range threshold is set based on the historical electric bill data of some base station devices, and the general fluctuation range threshold has universality, so that the respective fluctuation range threshold is not determined according to the characteristics of each base station device, and further the electric bill data of the base station device cannot be audited according to the actual situation of the base station device, and therefore, an accurate audit result cannot be given.

In order to solve the defects of the prior art, the inventor of the scheme designs a new scheme through creative research. The scheme firstly determines a current first auditing state based on the current real electric charge bill data and the previous real electric charge bill data, and the determination of the current first auditing state is related to the previous real electric charge bill data of target equipment, so that the current first auditing state can be determined according to the actual condition of the target equipment, and the current first auditing state can better accord with the actual condition of the target equipment; meanwhile, a current second audit state of the current real electric charge bill data is determined based on the current real electric charge bill data and the current predicted electric charge bill data, the determination of the second audit state depends on the comparison between the current predicted electric charge bill data predicted by the historical electric charge bill data corresponding to the target equipment and the current real electric charge bill data, the current predicted electric charge bill data of the target equipment can be determined according to the actual condition of the target equipment, and then the current second audit state which is more in line with the actual condition of the target equipment can be determined; in order to solve the problem that an accurate audit result cannot be given, the current first audit state and the current second audit state in the application can be started by combining the actual situation of the target device, so that the current first audit state and the current second audit state are more accurate.

The application scenarios of the method, the device, the equipment and the storage medium for auditing the bill data provided by the application are introduced below.

Fig. 1 is an application scenario diagram of a bill data auditing method provided by the present application. As shown in fig. 1, the application scenario diagram includes a target device 101, an electronic device 102 and a user terminal 104. The electronic device 102 includes an account data auditing device (hereinafter referred to as an auditing device) 103, and the auditing device 103 includes a timing model trained to converge. The target device 101 may be a base station device, the target devices 101 may be multiple, and the user terminal 104 may be a client device of a worker corresponding to the target device. The target device 101 is communicatively connected to the electronic device 102, and the electronic device 102 is communicatively connected to the user terminal 104, and the connection mode may be wired connection or wireless connection.

Specifically, the electronic device 102 obtains corresponding current real electric charge bill data and previous real electric charge bill data from the target device 101, the electronic device 102 includes a bill data auditing device 103, then sends the current real electric charge bill data and the previous real electric charge bill data to the auditing device 103, and a preset ring ratio auditing policy is adopted in the auditing device 103 to determine a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data, where the current first auditing state includes an abnormal state and a normal state. Before that, the trained to converged time sequence model predicts the current electric charge bill data based on the historical real electric charge bill data, so as to obtain the current predicted electric charge bill data, and stores the current predicted electric charge bill data in the storage region of the auditing device 103, the auditing device 103 obtains the current predicted electric charge bill data, then adopts a preset real and predicted data comparison auditing strategy, compares the current real electric charge bill data with the current predicted electric charge bill data, and determines a current second auditing state of the current real electric charge bill data according to the comparison result, wherein the current second auditing state comprises an abnormal state and a normal state.

Further, in response to that the current first audit state and the current second audit state are both abnormal states, it may be determined that the current real electricity bill data is in an abnormal state, and meanwhile, an audit abnormal prompt message is triggered, and the audit abnormal prompt message is sent to the user terminal 104 for timely prompting the user terminal 104 to handle the abnormality.

The application provides a bill data auditing method, device, equipment and storage medium, and aims to solve the technical problems in the prior art.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Example one

Fig. 2 is a flowchart illustrating a method for auditing bill data according to an embodiment of the present disclosure. The execution subject of the method of the present embodiment is a bill data auditing device, as shown in fig. 2, and the specific steps are as follows.

S201, obtaining current real electric charge bill data, previous real electric charge bill data and current prediction electric charge bill data corresponding to the target device; the previous real electricity bill data refers to real electricity bill data of one period before the current real electricity bill data.

The current real electric charge bill data refers to bill data which needs to be audited currently and comprises current real daily average ring ratio data of at least one dimension, and the daily average ring ratio data can comprise a daily average electric charge ring ratio, a daily average electric quantity ring ratio, a daily average unit price ring ratio, a daily average power supply use efficiency ring ratio and other related daily average ring ratio data.

The previous real electricity bill data is real electricity bill data of a previous period of the current real electricity bill data. For example, assuming that the current real electricity bill data is the bill data of the month of fourths, the previous real electricity bill data is the bill data of the month of thirths. The previous real electric bill data includes previous real day average ring ratio data having the same dimension as the current real day average ring ratio data.

The current predicted electric charge bill data refers to the fact that future real electric charge bill data are predicted on the basis of historical real electric charge bill data through a trained to converged time sequence model and are stored in a storage area of the auditing device. And the current prediction day average ring ratio data is the same as the current real electric charge bill data in dimension. Wherein the historical real electricity bill data may be real electricity bill data in a past period of time.

The target device may be a base station device including a target server serving a base station.

Specifically, the trained to converged time sequence model predicts future real electric bill data based on the historical real electric bill data, so that current predicted electric bill data can be obtained, and the current predicted electric bill data is stored in the storage area of the auditing device.

Specifically, the target server stores current real electric charge bill data and previous real electric charge bill data of the corresponding target device, and the auditing device acquires the corresponding real electric charge bill data and the previous real electric charge bill data of the corresponding target device from the target server and stores the data in the internal storage area. Meanwhile, the auditing device acquires the current predicted electric bill data of the internal storage area.

S202, a preset ring ratio auditing strategy is adopted to determine a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data.

The current first audit state is a state of the current real electric bill data, and includes an abnormal state and a normal state.

The preset ring ratio auditing strategy is a preset strategy for auditing the daily-average ring ratio data of the current real electric bill data.

Specifically, the auditing device adopts a preset ring ratio auditing strategy to compare the current real electric charge bill data with the previous real electric charge bill data, and can determine the current first auditing state of the current real electric charge bill data based on the comparison result.

It can be understood that, when the comparison result meets the preset condition, the current first audit state is a normal state; and when the comparison result does not meet the preset condition, the current first audit state is an abnormal state. The preset condition may be set according to an actual situation, and is not limited herein.

S203, determining a current second auditing state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison auditing strategy.

The current second audit state is also a state of the current real electric bill data, and includes an abnormal state and a normal state.

The preset real and predicted data comparison auditing strategy is an auditing strategy which is preset in advance and compares real electric charge bill data with current predicted electric charge bill data predicted by a trained to convergent time sequence model.

Specifically, the auditing device compares the current real electric charge bill data with the current predicted electric charge bill data by adopting a preset real and predicted data strategy, and can determine the current second auditing state of the current real electric charge bill data based on the comparison result.

It can be understood that, when the comparison result meets the preset condition, the current second audit state is the normal state; and when the comparison result does not meet the preset condition, the current second auditing state is an abnormal state. The preset condition may be set according to an actual situation, and is not limited herein.

S204, in response to the fact that the current first audit state and the current second audit state are both abnormal states, audit abnormal prompt information is sent to the user terminal.

The audit abnormity prompting information is a prompting information used for prompting the user terminal staff that the current real electric bill data may be abnormal. The audit abnormity prompting information comprises a comparison result of the audit abnormity and warning information. The comparison result of the audit abnormity refers to a comparison result that the first audit state and the second audit state are abnormal states, and the warning information is a notice for reminding a user terminal staff that the abnormity may exist.

The user terminal may be a client device of a worker corresponding to the target device, and the client device may be a device such as a mobile phone or a computer, which is not limited herein.

Specifically, the auditing device determines whether the first auditing state and the second auditing state obtained in S203 are abnormal states or normal states, and if the auditing device responds that the first auditing state is abnormal and the second auditing state is also abnormal, the auditing device determines that the first auditing state and the second auditing state are both abnormal states, and at this time, the auditing device can finally determine that the current electric bill data is in an abnormal state. It can be understood that the auditing device further determines that the target device is in an abnormal state, and the auditing device triggers an auditing abnormal prompt message, and then sends the auditing abnormal prompt message to the user terminal. And the user terminal performs corresponding processing based on the audit exception prompt information.

The embodiment provides a bill data auditing method, which comprises the steps of obtaining current real electric bill data, previous real electric bill data and current predicted electric bill data corresponding to target equipment; the previous real electric bill data is real electric bill data of a previous period of the current real electric bill data; determining a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset ring ratio auditing strategy; determining a current second auditing state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison auditing strategy; and sending audit abnormity prompting information to the user terminal in response to that the current first audit state and the current second audit state are abnormal states. The auditing device adopts a preset circular ratio strategy to compare current real electric charge bill data with previous real electric charge bill data to determine a current first auditing state, wherein the current first auditing state is determined based on the two real electric charge bill data, and meanwhile, the current first auditing state can be determined in a targeted manner according to self conditions of different target devices, so that the actual conditions of the target devices are met; and then, comparing the current real electric charge bill data with the current predicted electric charge bill data by adopting a preset real and prediction strategy to determine a current second auditing state, wherein the current predicted electric charge bill data is predicted according to the historical real electric charge bill data of each target device, and is predicted to accord with the respective current predicted electric charge bill data according to the respective characteristics of the target devices, so that the current second auditing state is more accordant with the actual condition of the target devices.

Example two

The embodiment of the present application is further detailed in the first embodiment, and the current real electric bill data of the present embodiment includes: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: and the previous real day average ring ratio data has the same dimensionality as the current real day average ring ratio data.

The current real electricity bill data includes current real day-to-average ring ratio data of at least one dimension, which may be a current real day-to-average electricity charge ring ratio, a current real day-to-average electric quantity ring ratio, a current real day-to-average unit price ring ratio, and a current real day-to-average power source usage efficiency ring ratio.

The previous real electric charge bill data includes previous real day average power rate data having the same dimension as the current real day average power rate data, and may be a previous real day average electric charge rate, a previous real day average electric quantity rate, a previous real day average unit price rate, and a previous real day average power source usage efficiency rate.

It can be understood that the current real daily average ring ratio data of each dimension in the current real electric bill data and the previous real daily average ring ratio data of each dimension in the previous real electric bill data correspond to each other. Illustratively, the current real-day-average power charge ring ratio and the previous real-day-average power charge ring ratio correspond to each other.

Fig. 3 is a flowchart illustrating a bill data auditing method according to a second embodiment of the present application. In the embodiment, a preset environment ratio auditing strategy is adopted to determine a current first auditing state of current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data in an optional mode, as shown in fig. 3, and the specific steps are as follows.

S301, calculating the rise and fall amplitude of each daily average ring ratio between the current real daily average ring ratio data and the previous real daily average ring ratio data of each dimension.

The current real day-to-average ring ratio data has four-dimensional day-to-average ring ratio data, and correspondingly, the previous real day-to-average ring ratio data also has four-dimensional day-to-average ring ratio data corresponding to the current real day-to-average ring ratio data.

Specifically, the auditing device adopts a preset ring ratio auditing strategy to calculate the fluctuation range between the current real day-to-average ring ratio data and the previous real day-to-average ring ratio data of each dimension. The auditing device firstly calculates the difference between the current real day-to-average ring ratio data of each dimensionality and the previous day-to-average ring ratio data, and calculates the percentage of the quotient between the difference and the current real day-to-average ring ratio data of each dimensionality according to the difference, so as to obtain the fluctuation range of each day-to-average ring ratio.

Illustratively, the auditing device calculates the daily average power charge ring ratio rise and fall amplitude of the current real daily average power charge ring ratio and the previous real daily average power charge ring ratio. The method comprises the steps that a current real-day average power charge ring ratio is A1, a previous real-day average power charge ring ratio is B1, an auditing device firstly calculates a difference value C1= A1-B1 between the current real-day average power charge ring ratio and the previous real-day average power charge ring ratio, and then calculates a percentage W1= (| C1 |/A1) |) 100% of a quotient value of the difference value and the current real-day average power charge ring ratio, wherein | C1| represents an absolute value made for C1. It can be understood that if C1 is a negative number, it indicates that the current real day-average power rate ring ratio is less than the previous real day-average power rate ring ratio, and therefore W1 is the falling amplitude; if C1 is a positive number, it indicates that the current real day-average power rate ring ratio is larger than the previous real day-average power rate ring ratio, and therefore W1 is an increasing magnitude. And then the rise and fall amplitude W1 of the average daily power charge ring ratio of the current real average daily power charge ring ratio and the previous real average daily power charge ring ratio can be determined.

It can be understood that, according to the above exemplary example, the ring ratio data rising and falling amplitude of the current real day-average ring ratio data and the previous real day-average ring ratio data of the remaining dimensions can also be determined, and details are not described here.

S302, acquiring a daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data.

The daily average cycle ratio fluctuation range threshold is a preset daily average cycle ratio fluctuation range critical value and is stored in an internal storage area of the auditing device. The current real electric bill data of one target device corresponds to a daily average cycle ratio fluctuation range threshold value.

Wherein the daily-average-cycle-ratio rise-fall amplitude threshold represents a rise amplitude threshold and a fall amplitude threshold. Illustratively, if the daily average cycle ratio rise-fall threshold is set to 30%, the rise amplitude threshold is 30% and the fall amplitude threshold is 30%.

Specifically, the auditing device acquires a daily average cycle ratio fluctuation range threshold value corresponding to the current real electric bill data in an internal storage area, wherein the daily average cycle ratio fluctuation range threshold value is H.

And S303, comparing the rise-fall amplitude of each daily average ring ratio with the corresponding rise-fall amplitude threshold value of the daily average ring ratio to obtain the rise-fall comparison result.

Each rise-fall comparison result can comprise a daily average power charge ring ratio rise-fall comparison result, a daily average power ring ratio rise-fall comparison result, a daily average unit price ring ratio rise-fall comparison result and a daily average power supply use efficiency ring ratio rise-fall comparison result.

Specifically, the auditing device compares the rise and fall amplitude of each daily average cycle ratio calculated in S301 with the corresponding rise and fall amplitude threshold of the daily average cycle ratio, and generates a rise and fall comparison result, where the rise and fall comparison result may be that the rise and fall amplitude of the daily average cycle ratio is greater than or equal to the rise and fall amplitude threshold of the daily average cycle ratio, or that the rise and fall amplitude of the daily average cycle ratio is less than the rise and fall amplitude threshold of the daily average cycle ratio. Further, the auditing device obtains the comparison result of each rise and fall and stores the comparison result in an internal storage area.

Illustratively, based on the example in S302, the daily average power rate ring ratio fluctuation range W1 is compared with the corresponding daily average ring ratio fluctuation range threshold H, and the fluctuation comparison result of the daily average power rate ring ratio may be that the daily average power rate ring ratio fluctuation range W1 is greater than or equal to the corresponding daily average ring ratio fluctuation range threshold H, or that the daily average power rate ring ratio fluctuation range W1 is smaller than the corresponding daily average ring ratio fluctuation range threshold H.

Further, according to the method, the auditing device can also obtain the rise-fall comparison results of the other rise-fall ranges of the daily-average ring ratio and the corresponding rise-fall range threshold H of the daily-average ring ratio.

S304, determining the current first auditing state of the current real electric bill data according to the rise-fall comparison result.

Specifically, the auditing device determines whether the current first auditing state of the current real electric bill data is an abnormal state or a normal state according to the rise and fall comparison results.

It can be understood that the current real electric bill data corresponds to the rise-fall comparison results of four dimensions, the auditing device further determines the current first auditing state of the current real electric bill data according to the rise-fall comparison results of the four dimensions, and the rise-fall comparison results of each dimension include the magnitude of the rise-fall amplitude of the current real day-to-ring ratio and the magnitude of the rise-fall amplitude threshold of the corresponding day-to-ring ratio.

In one mode, this mode is a possible mode of determining the current first audit state of the current real electricity bill data according to the comparison result of each rise and fall, and the content of this mode is as follows.

And determining that the current first audit state is an abnormal state in response to the fact that at least two daily average ring ratio rise-fall ranges exist in each rise-fall comparison result, wherein the daily average ring ratio rise-fall ranges are larger than or equal to the corresponding daily average ring ratio rise-fall range threshold values.

Specifically, in response to the existence of at least two daily-average ring ratio rise-fall ranges in the four-dimensional rise-fall comparison results, the auditing device determines that the first auditing state of the current real electric bill data is an abnormal state.

Illustratively, the average daily power charge-to-loop ratio rise-fall comparison result is that the average daily power charge-to-loop ratio rise-fall amplitude is greater than or equal to the corresponding average daily loop ratio rise-fall amplitude threshold H, the average daily unit price loop ratio rise-fall comparison result is that the average daily unit price loop ratio rise-fall amplitude is greater than or equal to the corresponding average daily loop ratio rise-fall amplitude threshold H, and the average daily power utilization efficiency loop ratio rise-fall comparison result is that the daily power utilization efficiency is less than the corresponding average daily loop ratio rise-fall amplitude threshold H.

Specifically, in response to the existence or non-existence of the daily-average cycle ratio fluctuation range larger than or equal to the corresponding daily-average cycle ratio fluctuation range threshold in the four-dimensional fluctuation and fluctuation comparison results, the auditing device determines that the first auditing state of the current real electric bill data is a normal state.

Illustratively, the average daily power rate ring ratio rise-fall comparison result is that the average daily power rate ring ratio rise-fall amplitude is greater than or equal to the corresponding average daily ring ratio rise-fall amplitude threshold H, the average daily power rate ring ratio rise-fall comparison result is that the average daily power rate ring ratio rise-fall amplitude is less than the corresponding average daily ring ratio rise-fall amplitude threshold H, the average daily unit price ring ratio rise-fall comparison result is that the average daily unit price ring ratio rise-fall amplitude is less than the corresponding average daily ring ratio rise-fall amplitude threshold H, and the average daily power use efficiency ring ratio rise-fall comparison result is that the daily power use efficiency is less than the corresponding average daily ring ratio rise-fall amplitude threshold H.

The method comprises the steps that in response to the fact that at least two daily average ring ratio rising and falling ranges are larger than or equal to corresponding daily average ring ratio rising and falling range thresholds exist in each rising and falling comparison result, the current first audit state is determined to be an abnormal state; and in response to the existence or non-existence of one or more daily average ring ratio rise-fall ranges larger than or equal to the corresponding daily average ring ratio rise-fall range threshold value in each comparison result, determining that the current first audit state is a normal state. The auditing device determines that the current first auditing state is an abnormal state when at least two daily average ring ratio rise-fall ranges in the rise-fall comparison results of four dimensions are greater than or equal to corresponding daily average ring ratio rise-fall range thresholds, and can improve the accuracy of determining the current first auditing state because the first auditing state can be determined to be the abnormal state when the at least two daily average ring ratio rise-fall ranges are greater than or equal to the corresponding daily average ring ratio rise-fall range thresholds; when the condition that one or no daily-average-cycle-ratio fluctuation range is larger than or equal to the corresponding daily-average-cycle-ratio fluctuation range threshold is met, the influence of error determination of the auditing device on one daily-average-cycle-ratio fluctuation range comparison result can be weakened, the fault tolerance rate is further improved, and the accuracy is further improved.

The embodiment provides a bill data auditing method, and the current real electric bill data of the method comprises the following steps: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: the previous real day-to-day average ring ratio data having the same dimension as the current real day-to-day average ring ratio data specifically includes, when a preset ring ratio audit policy is adopted to determine a current first audit state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data: calculating the rise and fall amplitude of each daily average ring ratio between the current real daily average ring ratio data and the previous real daily average ring ratio data of each dimension; acquiring a daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data; comparing the rise and fall amplitude of each daily average ring ratio with the corresponding rise and fall amplitude threshold value of the daily average ring ratio to obtain each rise and fall comparison result; and determining the current first audit state of the current real electric bill data according to the rise and fall comparison results. The auditing device of the embodiment firstly calculates the rise and fall amplitude of each day average ring ratio between the current real day average ring ratio data and the previous real day average ring ratio data, and then compares the rise and fall amplitude of each day average ring ratio with the corresponding rise and fall amplitude threshold of each day average ring ratio, so as to obtain an accurate rise and fall comparison result, wherein the corresponding rise and fall amplitude threshold of each day average ring ratio can be set according to the actual conditions of different target devices, so that the final comparison result is more accurate, and further the current first auditing state can be determined according to the truest condition of the target devices.

EXAMPLE III

Fig. 4 is a flowchart illustrating a method for auditing bill data according to a third embodiment of the present application. The embodiment of the present application is further detailed in any one of the above embodiments, and this embodiment is a feasible way of obtaining the daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data, as shown in fig. 4, and the specific steps are as follows.

S401, determining a current time range corresponding to the current real electric bill data.

The current time range refers to a time range corresponding to the current real electric bill data. Specifically, the current real electricity bill data is monthly bill data, and thus, the current time range is a complete one-month time range.

The current real electric charge bill data may further include the time of paying the electric charge by the electric charge bill data, and it can be understood that the time of paying the electric charge may reflect which month of the electric charge is paid. For example, if the time for paying the electricity fee is the beginning of the current month, the electricity fee is paid for the previous month of january, i.e., the electricity fee paid for january number one is paid for august.

Specifically, the auditing device reads the time of paying the electric charge of the current real electric charge bill data, and then determines the month corresponding to the current real electric charge bill data, and further determines the current time range. For example, the time for the auditing device to read the payment of the electric charge is September I, and then the month corresponding to the current real electric charge bill data is determined to be August, so that the current time range is determined to be August I to August thirty-one.

S402, obtaining a mapping relation between a preset time range and a daily average cycle ratio fluctuation range threshold value.

Wherein the preset time range may be a range of one month.

The mapping relation refers to a relation between a preset time range and a daily average cycle ratio rise-fall amplitude threshold value. It is understood that when the preset time ranges are different, different daily-average ring ratio rise-fall amplitude thresholds can be corresponded. The mapping relationship between the preset time range and the daily average cycle ratio fluctuation range threshold value can be stored in the target server.

Specifically, the auditing device obtains a mapping relation between a preset time range and a daily-average cycle ratio fluctuation range threshold value from the target server. Optionally, the mapping relationship may be displayed in a form of a graph, so as to facilitate viewing.

And S403, acquiring the daily average ring ratio fluctuation amplitude threshold corresponding to the current time range from the mapping relation according to the current time range, and taking the daily average ring ratio fluctuation amplitude threshold corresponding to the current real electric bill data.

Specifically, the auditing device finds a preset time range consistent with the current time range in the mapping relation according to the current time range, further determines a daily-average ring ratio rise-fall amplitude threshold corresponding to the preset time range, acquires the corresponding daily-average ring ratio rise-fall amplitude threshold, and takes the daily-average ring ratio rise-fall amplitude threshold as the daily-average ring ratio rise-fall amplitude threshold corresponding to the current real electric charge bill data.

The embodiment provides a bill data auditing method, which specifically includes the following steps when a daily average cycle ratio fluctuation range threshold corresponding to current real electric charge bill data is obtained: determining a current time range corresponding to the current real electric bill data; acquiring a mapping relation between a preset time range and a daily average cycle ratio fluctuation range threshold; and acquiring the daily average ring ratio fluctuation amplitude threshold corresponding to the current time range from the mapping relation according to the current time range, and using the daily average ring ratio fluctuation amplitude threshold as the daily average ring ratio fluctuation amplitude threshold corresponding to the current real electric bill data. The implementation auditing device determines a daily average fluctuation range threshold corresponding to current real electric charge bill data according to the mapping relation between the acquired preset time range and the daily average fluctuation range threshold, finds the preset time range consistent with the time range according to the current time range, and then determines the daily average fluctuation range threshold corresponding to the preset time range, so that the daily average fluctuation range threshold corresponding to the current real electric charge bill data can be accurately determined, and the daily average fluctuation range threshold can be correspondingly changed according to the change of the current time range, therefore, the daily average fluctuation range threshold is more flexible, and the daily average fluctuation range threshold is determined based on the self condition of target equipment.

Example four

The embodiment of the present application is further detailed in any one of the above embodiments, and the current real electric bill data of the present embodiment includes: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: and the previous real day average ring ratio data has the same dimension as the current real day average ring ratio data.

Fig. 5 is a flowchart illustrating a bill data auditing method according to a fourth embodiment of the present application. The present embodiment is a feasible way of determining the current second audit state of the current real electric bill data based on the current real electric bill data and the current predicted electric bill data by using a preset real and predicted data comparison audit policy, as shown in fig. 5. The method comprises the following specific steps.

S501, calculating the deviation amplitude of each daily average ring ratio between the current real daily average ring ratio data and the current prediction daily average ring ratio data of each dimension.

The current prediction day-to-average ring ratio data correspond to dimensions of the current real day-to-average ring ratio data, and the current prediction day-to-average ring ratio data can comprise a current prediction day-to-average power rate ring ratio, a current prediction electric quantity ring ratio, a current prediction unit price ring ratio and a current prediction power supply use efficiency ring ratio.

Wherein, each day average ring ratio deviation amplitude can include a day average electric charge ring ratio deviation amplitude, a day average electric quantity ring ratio deviation amplitude, a day average unit price ring ratio deviation amplitude and a day average power supply use efficiency ring ratio deviation amplitude.

Specifically, the auditing device calculates the deviation amplitude of each day-average ring ratio between the current real day-average ring ratio data of each dimension and the corresponding current prediction day-average ring ratio data.

For example, the auditing device first calculates a difference D1 between the current real daily average power charge ring ratio A1 and the current predicted daily average power charge ring ratio Y1, where D1= A1-Y1, and calculates a percentage E1 of a quotient of the difference D1 and the current predicted daily average power charge ring ratio Y1 according to the difference D1, where E1= (| D1 |/Y1) × 100%, and E1 is a deviation amplitude of the daily average power charge ring ratio.

And S502, comparing the deviation amplitude of each daily average ring ratio with a preset threshold value of the deviation amplitude of the daily average ring ratio to obtain a comparison result of each deviation.

The preset daily average ring ratio deviation amplitude threshold is a preset daily average ring ratio deviation critical value.

Wherein, each deviation comparison result has the deviation comparison result of four dimensions, can contain daily average power rate ring ratio deviation comparison result, daily average electric quantity ring ratio deviation comparison result, daily average unit price ring ratio deviation comparison result and daily average power efficiency ring ratio deviation comparison result.

Specifically, the auditing device compares each daily average ring ratio deviation amplitude with a preset daily average ring ratio deviation amplitude threshold value to obtain each deviation comparison result, and the deviation comparison result may include that the daily average ring ratio deviation amplitude threshold value is greater than or equal to the preset daily average ring ratio deviation amplitude threshold value, or the daily average ring ratio deviation amplitude threshold value is less than the preset daily average ring ratio deviation amplitude threshold value.

For example, assuming that the preset daily average power rate ring ratio deviation threshold is G, based on the example in S501, the daily average power rate ring ratio deviation E1 is compared with the preset daily average power rate ring ratio deviation threshold G, and the comparison result of the daily average power rate ring ratio deviation may be that the daily average power rate ring ratio deviation amplitude E1 is greater than or equal to the preset daily average ring ratio deviation amplitude threshold G, or that the daily average power rate ring ratio deviation amplitude E1 is smaller than the preset daily average ring ratio deviation amplitude threshold G, so that the auditing device obtains the comparison result of the daily average power rate ring ratio deviation.

Further, according to the method, the auditing device can also obtain the deviation comparison result of the deviation amplitude of the other day-to-average ring ratio and the preset threshold value of the deviation amplitude of the day-to-average ring ratio.

S503, determining the current second auditing state of the current real electric bill data according to each deviation comparison result.

Specifically, the auditing device determines whether the current second auditing state of the current real electric bill data is an abnormal state or a normal state according to each deviation comparison result.

It can be understood that the current real electric charge bill data corresponds to a deviation comparison result of four dimensions, and the auditing device determines a current second auditing state of the current real electric charge bill data according to the deviation comparison result of the four dimensions, wherein the deviation comparison result of each dimension comprises the magnitude of the deviation amplitude of the current real daily average ring ratio corresponding to each dimension and a preset daily average ring ratio deviation amplitude threshold value.

In one embodiment, the present embodiment is a possible embodiment of determining the current second audit state of the current real electricity bill data according to the deviation comparison results, and the present embodiment is as follows.

And determining that the current second audit state is an abnormal state in response to the fact that at least two daily average ring ratio deviation amplitudes in each deviation comparison result are larger than or equal to a preset daily average ring ratio deviation amplitude threshold value.

Specifically, in response to the fact that at least two daily average cycle ratio deviation ranges in the deviation comparison results of the four dimensions are greater than or equal to a preset daily average cycle ratio deviation range threshold value, the auditing device determines that the second auditing state of the current real electric bill data is an abnormal state.

Illustratively, the comparison result of the daily average power charge ring ratio deviation is that the daily average power charge ring ratio deviation amplitude is greater than or equal to a preset daily average ring ratio deviation amplitude threshold G, the comparison result of the daily average power charge ring ratio deviation is greater than or equal to the preset daily average ring ratio deviation amplitude threshold G, the comparison result of the daily average unit price ring ratio deviation is greater than or equal to the preset daily average ring ratio deviation amplitude threshold G, and the comparison result of the daily average power usage efficiency ring ratio deviation is that the daily average power usage efficiency is smaller than the preset daily average ring ratio deviation amplitude threshold G, so that it can be seen that three pieces of daily average ring ratio data are greater than or equal to the preset daily average ring ratio deviation amplitude threshold in the comparison result of the daily average power ratio deviation, a preset condition that at least two pieces of daily average ring ratio deviation amplitudes are greater than or equal to the preset daily average ring ratio deviation amplitude threshold is satisfied, and the current second audit state is determined to be an abnormal state.

And determining that the current second auditing state is a normal state in response to the fact that one or no day-average ring ratio deviation amplitude is larger than or equal to a preset day-average ring ratio deviation amplitude threshold value exists in each deviation comparison result.

Specifically, in response to the existence or non-existence of one or non-existence of the daily average ratio deviation range greater than or equal to the preset daily average ratio deviation range threshold in the deviation comparison results of the four dimensions, the auditing device determines that the second auditing state of the current real electric bill data is a normal state.

Illustratively, the daily average power charge ring ratio deviation comparison result is that the daily average power charge ring ratio deviation amplitude is greater than or equal to a preset daily average ring ratio deviation amplitude threshold G, the daily average power ring ratio deviation comparison result is that the daily average power ring ratio deviation amplitude is smaller than the preset daily average ring ratio deviation amplitude threshold G, the daily average unit price ring ratio deviation comparison result is that the daily average unit price ring ratio deviation amplitude is smaller than the preset daily average ring ratio deviation amplitude threshold G, and the daily average power usage efficiency ring ratio deviation comparison result is that the daily average power usage efficiency is smaller than the preset daily average ring ratio deviation amplitude threshold G, so that it can be seen that one daily average ring ratio data in each daily average ring ratio deviation comparison result is greater than or equal to the preset daily average ring ratio deviation amplitude threshold, a preset condition that one or no daily average ring ratio deviation amplitude is greater than or equal to the preset daily average ring ratio deviation amplitude threshold is met, and the current second audit state is determined to be a normal state.

The method comprises the steps that in response to the fact that at least two daily average ring ratio deviation ranges are larger than or equal to a preset daily average ring ratio deviation range threshold value in each deviation comparison result, the current second auditing state is determined to be an abnormal state; and determining that the current second auditing state is a normal state in response to the fact that one or no day-average ring ratio deviation amplitude is larger than or equal to a preset day-average ring ratio deviation amplitude threshold value exists in each deviation comparison result. The method auditing device responds to the situation that when at least two daily average ring ratio deviation amplitudes in deviation comparison results of four dimensions are larger than or equal to a preset daily average ring ratio deviation amplitude threshold value, the current second auditing state is determined to be an abnormal state, and because the situation that the second auditing state is determined to be the abnormal state only when the situation that the at least two daily average ring ratio deviation amplitudes are larger than or equal to the preset daily average ring ratio deviation amplitude threshold value is met, the accuracy of determining the current second auditing state can be improved; when the condition that one or no daily average ring ratio deviation amplitude is larger than or equal to a preset daily average ring ratio deviation amplitude threshold value is met, the judgment error caused by the error determination of the auditing device in one daily average ring ratio deviation comparison result can be weakened, the fault tolerance rate is further improved, and the accuracy rate is further improved.

The embodiment provides a bill data auditing method, and the method comprises the following steps: the current real daily average ring ratio data of at least one dimension comprises the following data in the current predicted electric bill data: when a preset real and predicted data comparison auditing strategy is adopted to determine a current second auditing state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data, the method specifically comprises the following steps: calculating the difference amplitude of the daily average ring ratio between the current real daily average ring ratio data and the current prediction daily average ring ratio data of each dimension; comparing the deviation amplitude of each daily average ring ratio with a preset threshold value of the deviation amplitude of the daily average ring ratio to obtain a comparison result of each deviation; and determining the current second audit state of the current real electric bill data according to each deviation comparison result. The implementation auditing device calculates the deviation amplitude of each daily average ring ratio, and then compares the deviation amplitude of each daily average ring ratio with a preset daily average ring ratio deviation amplitude threshold value based on the daily average ring ratio deviation amplitude to obtain an accurate deviation comparison result, wherein the preset daily average ring ratio deviation amplitude threshold value can be preset according to different target equipment regions or seasonal periods so as to better accord with the actual condition of target equipment, so that the final deviation comparison result is more accurate, and the current second auditing state can be determined according to the most real condition of the target equipment; the embodiment provides current predicted day-to-average ring ratio data, and because the current real day-to-average ring ratio data is different from the current predicted ring ratio data, in order to allow the current real day-to-average ring ratio data to have a small-range deviation from the current predicted day-to-average ring ratio data, a day-to-average ring ratio deviation amplitude threshold is preset, so that it can be ensured that the current real day-to-average ring ratio data is still in a normal state when the current real day-to-average ring ratio data and the current predicted day-to-average ring ratio data have a small-range deviation.

EXAMPLE five

Fig. 6 is a flowchart illustrating a method for auditing bill data according to a fifth embodiment of the present application. The embodiment of the present application is further detailed in any one of the above embodiments, and the embodiment is a feasible way of obtaining the current predicted electric bill data, as shown in fig. 6, and the specific steps are as follows.

S601, acquiring real electric bill data of a historical preset time period.

The real electricity bill data of the historical preset time period refers to the real bill data of the historical bill of the target device in the preset time period. The preset time period may elapse from 1-12 months. The real electricity bill data of the historical preset time period is stored in the target server.

Specifically, the auditing device obtains real electricity bill data of a historical preset time period from the target server. For example, the auditing device may obtain actual electricity bill data for the past 1-12 months.

And S602, inputting the real electric bill data of the historical preset time period into the timing sequence model trained to be convergent.

The timing model trained to converge refers to a timing model that has satisfied a convergence condition.

And S603, predicting the current electric charge bill data by adopting the trained to converged time sequence model based on the real electric charge bill data of the historical preset time period, and outputting the current predicted electric charge bill data.

Specifically, the real bill data of the historical preset time period is read by a timing sequence model trained to be convergent in the auditing device, the auditing device determines the current month based on the current real electric charge bill data, and further determines the electric charge bill data of the month to be predicted, then the auditing device finds the historical month corresponding to the current month in the historical preset time period based on the current month, and simultaneously determines the real electric charge bill data of the historical month corresponding to the historical month, and the current predicted electric charge bill data of the current month is predicted based on the real electric charge bill data of the historical month. Specifically, the auditing device may determine current predicted electric charge bill data of the current month based on a function y = kx + b according to the actual electric charge bill data of the month, where k and b may be set by themselves, x is the actual electric charge bill data of the historical month, and y is the current predicted electric charge bill data, and therefore, when the actual electric charge bill data x of the historical month is determined, the actual electric charge bill data x is input to the function y = kx + b, and the current predicted electric charge bill data y is determined.

And S604, acquiring the output current predicted electric bill data.

Specifically, the auditing device acquires current predicted electric bill data output from the trained to converged time sequence model and stores the current predicted electric bill data in the storage area.

The embodiment provides a bill data auditing method, and when acquiring current predicted electric bill data, the method comprises the following steps: acquiring real electricity bill data of a historical preset time period; inputting real electric bill data of a historical preset time period into a time sequence model trained to be converged; predicting the current electric charge bill data by adopting a trained to converged time sequence model based on the real electric charge bill data of a historical preset time period, and outputting the current predicted electric charge bill data; and acquiring the output current predicted electric bill data. The auditing device of the embodiment predicts the current electric charge bill data according to the real electric charge bill data in the historical preset time period, and then obtains the current predicted electric charge bill data. The current predicted electric charge bill data is the real electric charge bill data based on the historical preset time period, so that the prediction of the current predicted electric charge bill data is based on the real data prediction, the current predicted electric charge bill data can be closer to the current real electric charge bill data, and the current predicted electric charge bill data can be more accurate and more consistent with the actual situation of the target device.

EXAMPLE six

Fig. 7 is a flowchart illustrating a method for auditing bill data according to a sixth embodiment of the present application. The embodiment of the present application is further detailed in any one of the above embodiments, and the embodiment is a feasible manner before predicting the current electricity bill data based on the real electricity bill data of the historical preset time period by using the trained to converged time sequence model, as shown in fig. 7, and the specific steps are as follows.

S701, acquiring a training sample for training a preset time sequence model, wherein the training sample comprises: and the real electric bill data of at least one historical preset time period and the corresponding real electric bill data of the future preset time period.

The training samples are input data used for training the preset time sequence model, and the training samples can be stored in a storage area of the target server. The preset time sequence model is an initial time sequence model and comprises model parameters, the model parameters are trained based on training samples, and then the optimal model parameters are obtained, and the model parameters can be set by self before training.

Wherein, the real electricity bill data of the historical preset time period may be real electricity bill data of 1-12 months in a certain year. The real electricity bill data for the future preset time period is the real electricity bill data for the future 1-12 months.

Specifically, the auditing device obtains a training sample for training a preset time sequence model from the target server.

S702, training the preset time sequence model by using the training sample until the preset model convergence condition is met.

The preset model convergence condition may be a preset convergence condition, and the convergence condition may be that the convergence condition is satisfied when the model parameter in the preset time sequence model reaches a certain threshold, or may be in another feasible manner, which is not limited herein.

Specifically, the auditing device inputs training samples to train the model parameters, and when the training samples meet the preset model convergence condition, the training of the preset time sequence model is not continued. At this time, the model parameters are changed after training, so as to achieve better optimization.

And S703, determining the time sequence model meeting the preset model convergence condition as the time sequence model trained to be converged.

The present embodiment provides a method for auditing bill data, before predicting current electric bill data based on real electric bill data of a historical preset time period by using a timing model trained to converge, specifically including: obtaining a training sample for training a preset time sequence model, wherein the training sample comprises: at least one real electric bill data of a historical preset time period and a corresponding real electric bill data of a future preset time period; training a preset time sequence model by using a training sample until a preset model convergence condition is met; and determining the time sequence model meeting the preset model convergence condition as the time sequence model trained to be converged. The method includes the steps that a training sample is obtained firstly, a preset time sequence model is trained based on the training sample until a preset model convergence condition is met, and the trained-to-converged time sequence model can be determined.

EXAMPLE seven

Next, an embodiment of the device of the present application is described, and fig. 8 is a schematic diagram of a bill data auditing device provided in a seventh embodiment of the present application. As shown in fig. 8, the apparatus 800 includes the following modules.

An obtaining module 801, configured to obtain current real electric charge billing data, previous real electric charge billing data, and current predicted electric charge billing data corresponding to the target device; the previous real electric bill data is real electric bill data of a previous period of the current real electric bill data;

a first determining module 802, configured to determine a current first auditing state of current real electric bill data based on the current real electric bill data and previous real electric bill data by using a preset ring ratio auditing policy;

a second determining module 803, configured to determine a current second auditing state of the current real electric bill data based on the current real electric bill data and the current predicted electric bill data by using a preset real and predicted data comparison auditing strategy;

the sending module 804 is configured to send audit exception prompt information to the user terminal in response to that the current first audit state and the current second audit state are both in an exception state.

In one possible manner, the current real electricity bill data includes: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: the first determining module 802 is specifically configured to, when determining a current first audit state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by using a preset ring ratio audit policy, determine the previous real daily average ring ratio data having the same dimension as the current real daily average ring ratio data, and specifically:

calculating the rise and fall amplitude of each daily average ring ratio between the current real daily average ring ratio data and the previous real daily average ring ratio data of each dimension; acquiring a daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data; comparing the rise and fall amplitude of each daily average ring ratio with the corresponding rise and fall amplitude threshold value of the daily average ring ratio to obtain each rise and fall comparison result; and determining the current first auditing state of the current real electric bill data according to the rise and fall comparison results.

In a feasible manner, when obtaining the daily average cycle ratio fluctuation range threshold corresponding to the current real electric bill data, the first determining module 802 is specifically configured to:

determining a current time range corresponding to the current real electric bill data; acquiring a mapping relation between a preset time range and a daily average cycle ratio fluctuation range threshold; and acquiring the daily average ring ratio fluctuation amplitude threshold corresponding to the current time range from the mapping relation according to the current time range, and using the daily average ring ratio fluctuation amplitude threshold as the daily average ring ratio fluctuation amplitude threshold corresponding to the current real electric bill data.

In a possible manner, the first determining module 802, when determining the current first auditing status of the current real electric bill data according to the rise and fall comparison results, is specifically configured to:

in response to the fact that at least two daily average ring ratio rise-fall ranges are larger than or equal to the corresponding daily average ring ratio rise-fall range threshold value in each rise-fall comparison result, determining that the current first audit state is an abnormal state;

and in response to the existence or non-existence of one or non-existence of the daily average cycle ratio fluctuation range threshold value, determining that the current first audit state is a normal state.

In one possible manner, the current real electricity bill data includes: the current real daily average ring ratio data of at least one dimension comprises the following data in the current predicted electric bill data: the second determining module 803 is specifically configured to, when determining the current second audit state of the current real electricity bill data based on the current real electricity bill data and the current predicted electricity bill data by using a preset real and predicted data comparison audit policy based on the current real electricity bill data and the current predicted electricity bill data, determine current predicted day-to-ring ratio data having the same dimension as the current real day-to-ring ratio data:

calculating the difference amplitude of the daily average ring ratio between the current real daily average ring ratio data and the current prediction daily average ring ratio data of each dimension; comparing the deviation amplitude of each daily average ring ratio with a preset threshold value of the deviation amplitude of the daily average ring ratio to obtain a comparison result of each deviation; and determining the current second audit state of the current real electric bill data according to each deviation comparison result.

In a feasible manner, the second determining module 803, when determining the current second auditing status of the current real electric bill data according to the deviation comparison results, is specifically configured to:

in response to the fact that at least two daily average ring ratio deviation amplitudes in each deviation comparison result are larger than or equal to a preset daily average ring ratio deviation amplitude threshold value, determining that the current second auditing state is an abnormal state; and determining that the current second auditing state is a normal state in response to the fact that one or no day-average ring ratio deviation amplitude is larger than or equal to a preset day-average ring ratio deviation amplitude threshold value exists in each deviation comparison result.

In one possible manner, the obtaining module 801, when obtaining the current predicted electric bill data, is specifically configured to:

acquiring real electric bill data of a historical preset time period; inputting real electric bill data of a historical preset time period into a timing sequence model trained to be convergent; predicting the current electric charge bill data by adopting a trained to converged time sequence model based on the real electric charge bill data of a historical preset time period, and outputting the current predicted electric charge bill data; and acquiring the output current predicted electric bill data.

In a possible manner, before predicting the current electric bill data based on the real electric bill data of the historical preset time period by using the time sequence model trained to converge, the embodiment provides a bill data auditing apparatus, further comprising: a training module and a third determination module.

Wherein, the obtaining module 801 is further configured to obtain a training sample for training a preset time sequence model, where the training sample includes: at least one real electric bill data of a historical preset time period and a corresponding real electric bill data of a future preset time period; the training module is used for training the preset time sequence model by adopting a training sample until a preset model convergence condition is met; and the third determining module is used for determining the time sequence model meeting the preset model convergence condition as the time sequence model trained to be converged.

Example eight

Fig. 9 is a schematic structural diagram of an electronic device according to an eighth embodiment of the present application. As shown in fig. 9, the electronic device 900 may include: a processor 901, and a memory 902 and transceiver 903 communicatively coupled to the processor 901. Wherein the memory 902 stores computer-executable instructions; a transceiver 903 for transmitting and receiving data to and from a user terminal; the processor 901 executes the computer execution instructions stored in the memory 902 to implement any one of the method embodiments of the first to sixth embodiments, which have similar specific implementation and technical effects and are not described herein again.

In this embodiment, the memory 902 and the processor 901 are connected by a bus. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 9, but that does not indicate only one bus or one type of bus.

Example nine

The present application provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement any one of the method embodiments in the first to sixth embodiments, and specific implementation manners and technical effects are similar, and are not described herein again.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for auditing bill data, the method comprising:

acquiring current real electric charge bill data, previous real electric charge bill data and current predicted electric charge bill data corresponding to the target device; the previous real electric bill data is real electric bill data of a previous period of the current real electric bill data;

2. The method as set forth in claim 1, wherein the current real electric bill data includes: current real day-to-average ring ratio data for at least one dimension; the previous real electricity bill data includes: previous real day average ring ratio data with the same dimensionality as the current real day average ring ratio data;

the determining a current first auditing state of the current real electric charge bill data based on the current real electric charge bill data and the previous real electric charge bill data by adopting a preset ring ratio auditing strategy comprises the following steps:

3. The method according to claim 2, wherein the obtaining of the daily average ratio fluctuation range threshold corresponding to the current real electric bill data comprises:

determining a current time range corresponding to the current real electric charge bill data;

4. The method as claimed in claim 2, wherein the determining the current first audit state of the current real electric bill data according to the comparison result of the fluctuation comprises:

5. The method of claim 1, wherein the current real electricity bill data comprises: current real day-to-average ring ratio data of at least one dimension, wherein the current predicted electric bill data comprises: current predicted day-to-average ring ratio data with the same dimension as the current real day-to-average ring ratio data;

the determining a current second audit state of the current real electric charge bill data based on the current real electric charge bill data and the current predicted electric charge bill data by adopting a preset real and predicted data comparison audit strategy comprises the following steps:

calculating the difference amplitude of the daily average ring ratio between the current real daily average ring ratio data and the current prediction daily average ring ratio data of each dimension;

comparing each daily average ring ratio deviation amplitude with a preset daily average ring ratio deviation amplitude threshold value to obtain each deviation comparison result;

and determining the current second audit state of the current real electric bill data according to each deviation comparison result.

6. The method as claimed in claim 5, wherein the determining the current second audit status of the current real electric bill data according to the deviation comparison result comprises:

and determining that the current second audit state is a normal state in response to the existence or nonexistence of one or more day-to-day average ring ratio deviation ranges greater than or equal to a preset day-to-day average ring ratio deviation range threshold in each deviation comparison result.

7. The method according to any one of claims 1 to 6, wherein obtaining the current predicted electric bill data comprises:

acquiring real electric bill data of a historical preset time period;

inputting the real electric bill data of the historical preset time period into a time sequence model trained to be converged;

and acquiring the output current predicted electric bill data.

8. The method of claim 7, wherein before predicting current electric bill data based on the real electric bill data for the historical preset time period using the trained to converged timing model, further comprising:

obtaining a training sample for training a preset time sequence model, wherein the training sample comprises: at least one real electric bill data of a historical preset time period and a corresponding real electric bill data of a future preset time period;

9. A billing data auditing apparatus, the apparatus comprising:

10. An electronic device, comprising: a processor, and a memory and transceiver communicatively coupled to the processor;

the memory stores computer-executable instructions; the transceiver is used for receiving and transmitting data with a user terminal;

the processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1-8.

11. A computer-readable storage medium having computer-executable instructions stored therein, which when executed by a processor, are configured to implement the method of any one of claims 1-8.