CN113268524A

CN113268524A - Method and device for detecting abnormal oil consumption data, electronic equipment and storage medium

Info

Publication number: CN113268524A
Application number: CN202110570814.9A
Authority: CN
Inventors: 李泽远; 王健宗
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-05-25
Filing date: 2021-05-25
Publication date: 2021-08-17

Abstract

The invention relates to a detection model technology, and discloses a method for detecting abnormal oil consumption data, which comprises the following steps: in each local node, performing iterative training on an auto-encoder model by using local oil consumption data and global auto-encoder parameters received from a central node until a preset condition is met, and obtaining a target auto-encoder model, wherein the global auto-encoder parameters are obtained by integrating iterative training results of all local nodes. And eliminating local oil consumption abnormal data by using the target self-encoder model. The invention also provides a device for detecting the abnormal oil consumption data, electronic equipment and a computer readable storage medium. The method can solve the problems of low accuracy and low efficiency of local oil consumption abnormal data detection.

Description

Method and device for detecting abnormal oil consumption data, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence detection models, in particular to a method and a device for detecting abnormal oil consumption data, electronic equipment and a computer readable storage medium.

Background

The abnormal fuel consumption data refers to data with different actual fuel consumption data from normal fuel consumption data provided by a vehicle manufacturer due to personal driving habits, road conditions, vehicle-mounted conditions, weather changes and the like. Generally, a vehicle manufacturer needs to acquire normal oil consumption data of an actual vehicle to research and develop and improve the performance of the vehicle and externally release normal oil consumption conditions of the vehicle, and based on the requirement, the vehicle manufacturer needs to detect abnormal data from the actual oil consumption data of the vehicle.

At present, two methods are mainly used for detecting abnormal oil consumption data:

one method is to perform abnormal data evaluation on fuel consumption system data acquired by a vehicle-mounted sensor according to a threshold value preset by vehicle-mounted equipment, but this method is difficult to perform weighted evaluation according to different local fuel consumption data qualities, and the threshold value may not be suitable for the current situation along with the change of the environment. Therefore, the method has the defect of low detection accuracy of the abnormal oil consumption data.

Another method is to uniformly transmit the local user data back to the server, and detect abnormal data through manual identification. According to the method, judgment of abnormal data depends on personal experience accumulation, so that the local oil consumption abnormal data detection efficiency is low, and on the other hand, potential safety hazards invading the privacy of users can be introduced due to the sharing of local user data.

Disclosure of Invention

The invention provides a method and a device for detecting abnormal oil consumption data and a computer readable storage medium, and mainly aims to improve the accuracy and efficiency of detecting the abnormal local oil consumption data.

In order to achieve the above object, the present invention provides a method for detecting abnormal oil consumption data, where the method is applied to each local node, and includes:

acquiring local oil consumption data and receiving a global self-encoder model parameter issued by a central node;

taking the local oil consumption data as a training sample, and performing iterative training on a pre-constructed self-encoder model by using the global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

uploading the local self-encoder model parameters to the central node, and receiving updated global self-encoder model parameters obtained by the central node by integrating all received local self-encoder model parameters;

removing the local abnormal oil consumption data from the local oil consumption data to serve as an updated training sample, and performing iterative training on a pre-constructed self-encoder model according to the updated global self-encoder model parameters to obtain local self-encoder model parameters and local abnormal oil consumption data;

returning to the step of uploading the parameters of the local self-encoder model to the central node to perform iterative training of the self-encoder model, and stopping the iterative training until a preset condition is met to obtain a target self-encoder model;

and carrying out anomaly detection on the local oil consumption data by using the target self-encoder model to obtain local oil consumption anomaly data, and removing the local oil consumption anomaly data from the local oil consumption data.

In order to achieve the above object, the present invention further provides a method for detecting abnormal oil consumption data, where the method is applied to a central node, and includes:

in the central node, setting weight for the local self-encoder model parameters uploaded by each local node;

performing an averaging operation according to all the local self-encoder model parameters and the corresponding weights to obtain the updated global self-encoder model parameters;

and issuing the updated global self-encoder model parameters to each local node. In order to solve the above problem, the present invention further provides a device for detecting abnormal oil consumption data, where the device is applied to a local node, and the device includes:

the local training module is used for acquiring local oil consumption data, receiving global self-encoder model parameters issued by a central node, taking the local oil consumption data as a training sample, and performing iterative training on a pre-constructed self-encoder model by using the global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

the joint training module is used for uploading the local self-encoder model parameters to the central node, receiving updated global self-encoder model parameters obtained by integrating all received local self-encoder model parameters by the central node, removing the local oil consumption data from the local oil consumption data as updated training samples, and performing iterative training on a pre-constructed self-encoder model according to the updated global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

the iterative training module is used for stopping iterative training when a preset condition is met to obtain a target self-encoder model;

and the anomaly detection module is used for carrying out anomaly detection on the local oil consumption data by using the target self-encoder model to obtain local oil consumption anomaly data and eliminating the local oil consumption anomaly data from the local oil consumption data.

In order to solve the above problem, the present invention further provides a device for detecting abnormal oil consumption data, where the device is applied to a central node, and the device includes:

the global parameter generation module is used for setting weight for the local self-encoder model parameters uploaded by each local node; performing an averaging operation according to all the local self-encoder model parameters and the corresponding weights to obtain the updated global self-encoder model parameters;

and the global parameter issuing module is used for issuing the updated global self-encoder model parameters to each local node.

In order to solve the above problem, the present invention also provides an electronic device, including:

a memory storing at least one computer program; and

and the processor executes the computer program stored in the memory to realize the oil consumption abnormal data detection method.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, where at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above oil consumption abnormal data detection method.

According to the embodiment of the invention, through a federal learning technology, a central node is utilized to integrate local self-encoder model parameters obtained by a plurality of local nodes according to local oil consumption data training, updated global self-encoder model parameters are obtained, iterative training of the local self-encoder model parameters is further executed according to the updated global self-encoder model parameters on each local node until preset conditions are met, a target self-encoder model is obtained, and the target self-encoder model is utilized to carry out anomaly detection on the local oil consumption data. By utilizing the federal learning technology, the joint training of the center node on the self-encoder models on a plurality of local nodes is realized on the basis of not uploading the oil consumption data on each local node to the center node, and the effect of expanding the number of training samples is achieved on the premise of protecting the personal data from being leaked, so that the accuracy of the target self-encoder model can be improved, the accuracy of the detection of the abnormal oil consumption data is improved, meanwhile, the abnormal oil consumption data is detected by utilizing the target self-encoder model, the abnormal oil consumption data is not detected manually, and the detection efficiency of the abnormal oil consumption data in the local oil consumption data is improved.

Drawings

Fig. 1 is a schematic flow chart illustrating a method for detecting abnormal fuel consumption data, which is provided in an embodiment of the present invention, applied to a local node;

FIG. 2 is a schematic flow chart showing a detailed implementation of one of the steps in FIG. 1;

FIG. 3 is a schematic flow chart showing another step of FIG. 1;

FIG. 4 is a schematic flow chart showing another step of FIG. 1;

fig. 5 is a schematic flow chart illustrating that the abnormal oil consumption data detection method provided in an embodiment of the present invention is applied to a central node;

fig. 6 is a functional block diagram of the abnormal fuel consumption data detection apparatus applied to a local node according to an embodiment of the present invention;

fig. 7 is a functional block diagram of an abnormal fuel consumption data detection apparatus applied to a central node according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device for implementing the method for detecting abnormal fuel consumption data according to an embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a method for detecting abnormal oil consumption data. The execution subject of the abnormal fuel consumption data detection method includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the abnormal fuel consumption data detection method may be executed by software or hardware installed in the terminal device or the server device, where the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Fig. 1 is a schematic flow chart of a method for detecting abnormal fuel consumption data according to an embodiment of the present invention. In this embodiment, the abnormal oil consumption data detection method is applied to each local node performing federal learning. In the embodiment of the invention, a self-encoder model pre-constructed by all local nodes is jointly trained by a central node by using a federal learning technology, and the oil consumption abnormal data can be better identified by using the self-encoder model.

The federal learning technology is a novel artificial intelligence basic technology and is applied to high-efficiency machine learning among multiple participants or multiple computing nodes. In the embodiment of the invention, machine learning is developed between each local node and each central node by utilizing the federal learning technology.

In detail, in the embodiment of the present invention, the local node may be an onboard device of any vehicle. The central node may be deployed on a vehicle factory server or on a third party server, and the local node and the central node communicate via a network.

In the embodiment of the present invention, the method for detecting abnormal oil consumption data, which is executed at each local node, includes:

s1, acquiring local oil consumption data and receiving a global self-encoder model parameter issued by a central node;

the local oil consumption data refers to actual oil consumption information of the vehicle, such as oil consumed by hundred kilometers, acquired by the vehicle-mounted equipment of the local node. Due to different individual driving habits, different vehicle loads and different road conditions, the local oil consumption coefficient data also comprises abnormal oil consumption data besides normal oil consumption data.

The global self-encoder model parameters issued by the central node comprise encoder parameters and decoder parameters.

S2, taking the local oil consumption data as a training sample, and performing iterative training on a pre-constructed self-encoder model by using the global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

in the embodiment of the invention, the self-encoder model is a deep learning model based on a multilayer neural network structure and comprises an encoder and a decoder. And the local oil consumption data is encoded and compressed through an encoder to obtain a compressed representation corresponding to the local oil consumption data, and the compressed representation corresponding to the local oil consumption data is decoded and reduced through a decoder to obtain a reduced representation corresponding to the local oil consumption data. By comparing the local oil consumption data with the corresponding reduction representation, the data with large reduction errors can be classified as abnormal data.

In detail, referring to fig. 2, the S2 includes:

s21, synchronizing the global self-encoder model parameters into the parameters of the self-encoder model;

s22, inputting the training samples into the self-encoder model, and performing anomaly detection on the training samples by using an encoder and a decoder in the self-encoder model to obtain decoded data;

and S23, calculating to obtain the local oil consumption abnormal data and the local self-encoder model parameters by using the decoded data.

In an embodiment of the present invention, the calculating the local abnormal oil consumption data and the local self-encoder model parameter by using the decoded data includes:

identifying abnormal distribution data in the decoded data, and taking the abnormal distribution data as local oil consumption coefficient abnormal data;

and calculating a loss function value of the to-be-trained self-encoder model by using the training sample and the decoding data, and updating an encoder parameter and a decoder parameter in the to-be-trained self-encoder model according to the loss function value to obtain the local self-encoder model parameter.

In detail, the embodiment of the present invention calculates a reduction error corresponding to each decoded data, sets a reference value according to all the calculated reduction errors, and classifies the decoded data corresponding to the reduction error higher than the reference value into data that does not conform to normal distribution, so as to obtain local abnormal oil consumption data.

In detail, in the embodiment of the present invention, the data characteristics corresponding to the training samples are converted into variables of a real result, the data characteristics corresponding to the decoded data are converted into variables of a decoded result, and the variables of the real result and the variables of the decoded result are respectively input into a preset loss function, so as to obtain a loss function value of the self-encoder model.

In the embodiment of the present invention, the reduction Error may be calculated by using an MSE (Mean Squared Error) algorithm or an MAE (Mean Absolute Error) algorithm.

The data characteristic corresponding to the training sample or the data characteristic corresponding to the decoded data may include a maximum value, a minimum value, a variance, or a mean value of the data.

In this embodiment, the loss function is used to represent the magnitude of the error between the training samples and the decoded data. And calculating gradients corresponding to the encoder parameters and the decoder parameters of the self-encoder model according to the loss function, and respectively updating the encoder parameters and the decoder parameters of the self-encoder model according to the gradients.

The gradient may be understood as a parameter representing different training costs for the self-encoder model, and in the iterative training of the self-encoder model, the different gradients are tried to find a parameter that can obtain a minimized cost, so that the self-encoder model algorithm is more optimal.

S3, uploading the local self-encoder model parameters to the central node, and receiving updated global self-encoder model parameters obtained by the central node by integrating all received local self-encoder model parameters;

in the embodiment of the present invention, referring to fig. 5, the updated global self-encoder model parameters obtained by integrating all received local self-encoder model parameters by the central node include:

s30, setting weight for the local self-encoder model parameters uploaded by each local node;

s31, performing an averaging operation according to all the local self-encoder model parameters and the corresponding weights to obtain the updated global self-encoder model parameters;

and S32, issuing the updated global self-encoder model parameters to each local node.

In the embodiment of the present invention, FedAvg (FedAvg) algorithm in the federal learning technology may be used to integrate the local self-encoding model parameters uploaded by the plurality of local nodes, so as to obtain the updated global self-encoder model parameters.

S4, removing the local oil consumption abnormal data from the local oil consumption data to serve as an updated training sample, and performing iterative training on a pre-constructed self-encoder model according to the updated global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

in the embodiment of the invention, the iterative training belongs to unsupervised training, and the training sample does not contain local abnormal oil consumption data, so that the embodiment of the invention eliminates the local abnormal oil consumption data from the local oil consumption data as an updated training sample. The unsupervised training refers to that the training samples are not distinguished or the labels are set, namely normal data and abnormal data are not distinguished.

In detail, referring to fig. 3, the S4 includes:

s41, removing the local oil consumption abnormal data from the local oil consumption data to serve as an updated training sample;

s42, synchronizing the global self-encoder model parameters into the parameters of the self-encoder model;

s43, inputting the training samples into the self-encoder model, and performing anomaly detection on the training samples by using an encoder and a decoder in the self-encoder model to obtain decoded data;

and S44, calculating to obtain the local oil consumption abnormal data and the local self-encoder model parameters by using the decoded data.

S5, judging whether the iterative training meets a preset condition;

in an embodiment of the present invention, the preset condition includes one of the following conditions: the number of times of iterative training reaches a preset number, the loss function value is converged, or the time length of the iterative training reaches a preset time length, and in practical application, the number of times of the iterative training can be set according to practical situations.

And when the iterative training does not meet the preset condition, returning to the S3, and when the iterative training meets the preset condition, executing S6, stopping the iterative training to obtain a target self-encoder model, performing anomaly detection on the local node oil consumption data by using the target self-encoder model to obtain local oil consumption abnormal data, and removing the local oil consumption abnormal data from the local oil consumption data.

In the embodiment of the invention, before each iterative training, the updated global self-encoder model parameters corresponding to the previous iteration are obtained, and the aim of ensuring that the result of each iterative training is applied to the next iterative training is to continuously optimize the self-encoder model.

In detail, referring to fig. 4, the S6 includes:

s61, obtaining local oil consumption data from the local node;

s62, inputting the local oil consumption data into the target self-encoder model;

s63, performing local abnormal oil consumption detection on the local oil consumption data by using an encoder and a decoder in the target self-encoder model to obtain the local abnormal oil consumption data;

and S64, removing the local oil consumption abnormal data from the local oil consumption data.

According to the embodiment of the invention, through a federal learning technology, a central node is utilized to integrate local self-encoder model parameters obtained by a plurality of local nodes according to local oil consumption data training, updated global self-encoder model parameters are obtained, iterative training of the local self-encoder model parameters is further executed according to the updated global self-encoder model parameters on each local node until preset conditions are met, a target self-encoder model is obtained, and the target self-encoder model is utilized to carry out anomaly detection on the local oil consumption data. By utilizing the federal learning technology, the combined training of the central node on the self-encoder models on a plurality of local nodes can be realized on the basis of the central node without uploading the oil consumption data on each local node, and the effect of expanding the number of training samples is achieved on the premise of protecting personal data from being leaked, so that the accuracy of the target self-encoder model can be improved, the accuracy of the detection of the abnormal oil consumption data is improved, meanwhile, the abnormal oil consumption data is detected by utilizing the target self-encoder model, the abnormal oil consumption data is not detected manually, and the detection efficiency of the abnormal oil consumption data in the local oil consumption data is improved.

Fig. 6 is a functional block diagram of the abnormal fuel consumption data detection apparatus applied to a local node according to an embodiment of the present invention.

The abnormal fuel consumption data detection apparatus 100 according to the present invention may be installed in an electronic device. In the embodiment of the present invention, the abnormal fuel consumption data detection apparatus 100 may be installed in an onboard device of any vehicle. According to the realized functions, the oil consumption abnormal data detection device 100 may include a local training module 101, a joint training module 102, a loop iteration module 103, and an abnormality detection module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

Wherein:

the local training module 101 is configured to obtain local oil consumption data, receive a global self-encoder model parameter issued by a central node, use the local oil consumption data as a training sample, and perform iterative training on a pre-constructed self-encoder model by using the global self-encoder model parameter to obtain a local self-encoder model parameter and local oil consumption abnormal data;

the joint training module 102 is configured to upload the local self-encoder model parameters to the central node, receive updated global self-encoder model parameters obtained by integrating all received local self-encoder model parameters by the central node, remove the local oil consumption data from the local oil consumption data as an updated training sample, and perform iterative training on a pre-constructed self-encoder model according to the updated global self-encoder model parameters to obtain local self-encoder model parameters and local oil consumption abnormal data;

the iterative training module 103 is configured to stop iterative training when a preset condition is met, so as to obtain a target self-encoder model;

the anomaly detection module 104 is configured to perform anomaly detection on the local oil consumption data by using the target self-encoder model to obtain local oil consumption anomaly data, and remove the local oil consumption anomaly data from the local oil consumption data.

In detail, when used, each module in the abnormal fuel consumption data detection apparatus 100 in the embodiment of the present invention adopts the same technical means as the abnormal fuel consumption data detection method described in fig. 1 to 4, and can produce the same technical effect, which is not described herein again.

Fig. 7 is a functional block diagram of the abnormal fuel consumption data detection apparatus applied to a central node according to an embodiment of the present invention.

The abnormal fuel consumption data detection device 200 according to the present invention may be installed in an electronic device. In the embodiment of the present invention, the abnormal fuel consumption data detection apparatus 200 may be installed in a central server communicating with an onboard device of any vehicle. According to the realized function, the oil consumption abnormal data detection device 200 may include a global parameter generation module 201 and a global parameter issuing module 202. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device. Wherein:

the global parameter generating module 201 is configured to set a weight for a local self-encoder model parameter uploaded by each local node; performing an averaging operation according to all the local self-encoder model parameters and the corresponding weights to obtain the updated global self-encoder model parameters;

the global parameter issuing module 202 is configured to issue the updated global self-encoder model parameter to each local node.

In detail, when used, each module in the abnormal fuel consumption data detection apparatus 200 in the embodiment of the present invention adopts the same technical means as the abnormal fuel consumption data detection method described in fig. 5, and can produce the same technical effect, which is not described herein again.

Fig. 8 is a schematic structural diagram of an electronic device of a method for detecting abnormal fuel consumption data according to an embodiment of the present invention.

The electronic device 1 may include a processor 10, a memory 11, and a bus, and may further include a computer program, such as a fuel consumption abnormal data detection program, stored in the memory 11 and executable on the processor 10.

The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used to store not only application software installed in the electronic device 1 and various types of data, such as codes of a fuel consumption abnormality data detection program, but also temporarily store data that has been output or is to be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit of the electronic device, and is connected to each component of the electronic device through various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing a program or a module (for example, a fuel consumption abnormal data detection program) stored in the memory 11 and calling data stored in the memory 11.

The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

Fig. 8 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 8 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.

Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The fuel consumption abnormal data detection program stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when the fuel consumption abnormal data detection program runs in the processor 10, a fuel consumption abnormal data detection method can be realized.

Optionally, when the electronic device 1 is a local node, the method for detecting abnormal oil consumption data includes:

uploading the local self-encoder model parameters to the central node, and receiving updated global self-encoder model parameters obtained by integrating the local self-encoder model parameters by the central node;

Optionally, when the electronic device 1 is a central node, the method for detecting abnormal oil consumption data includes:

setting weight for the local self-encoder model parameters uploaded by each local node;

and issuing the updated global self-encoder model parameters to each local node.

Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.

Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The invention also provides a computer readable storage medium, which stores a computer program, and the computer program can realize a method for detecting abnormal oil consumption data when being executed by a processor of electronic equipment.

Optionally, when the readable storage medium stores a computer program of the local node, the computer program, when executed by a processor of the electronic device, may implement:

Optionally, when the readable storage medium stores a computer program of a central node, the computer program, when executed by a processor of an electronic device, may implement:

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for detecting abnormal oil consumption data is applied to a local node and is characterized by comprising the following steps:

2. The method for detecting abnormal oil consumption data according to claim 1, wherein the step of iteratively training a pre-constructed self-encoder model by using the local oil consumption data as a training sample and using the global self-encoder model parameters to obtain local self-encoder model parameters and local abnormal oil consumption data comprises:

synchronizing the global auto-encoder model parameters into the parameters of the auto-encoder model;

inputting the training samples into the self-encoder model, and performing anomaly detection on the training samples by using an encoder and a decoder in the self-encoder model to obtain decoded data;

and calculating to obtain the local oil consumption abnormal data and the local self-encoder model parameters by utilizing the decoded data.

3. The method for detecting abnormal oil consumption data according to claim 2, wherein the step of calculating the local abnormal oil consumption data and the local self-encoder model parameters by using the decoded data comprises:

identifying abnormal distribution data in the decoded data, and taking the abnormal distribution data as local oil consumption abnormal data;

calculating a loss function value of the self-encoder model by using the training sample and the decoding data;

and updating the parameters of the encoder and the parameters of the decoder in the self-encoder model according to the loss function values to obtain the parameters of the local self-encoder model.

4. The method for detecting abnormal oil consumption data according to claim 3, wherein the step of identifying the data which do not conform to the normal distribution in the decoded data and using the data which do not conform to the normal distribution as the local abnormal oil consumption data comprises:

calculating a reduction error corresponding to each decoded data;

setting a reference value according to all the reduction errors obtained by calculation;

and classifying the decoded data corresponding to the reduction error higher than the reference value into data which are not in accordance with normal distribution to obtain local abnormal oil consumption data.

5. The method for detecting abnormal oil consumption data according to claim 3, wherein the calculating the loss function value of the self-encoder model by using the training samples and the decoded data includes:

converting the data characteristics corresponding to the training samples into variables of real results, and converting the data characteristics corresponding to the decoding data into variables of decoding results;

and respectively inputting the variable of the real result and the variable of the decoding result into a preset loss function to obtain a loss function value of the self-encoder model.

6. A method for detecting abnormal oil consumption data is applied to a central node and is characterized by comprising the following steps:

7. The utility model provides an abnormal data detection device of oil consumption, is applied to local node, its characterized in that, the device includes:

8. The utility model provides an abnormal data detection device of oil consumption, is applied to central node, its characterized in that, the device includes:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of detecting abnormal fuel consumption data as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements a method for detecting abnormal fuel consumption data according to any one of claims 1 to 6.