CN114970648A - New energy equipment identification method, device and medium - Google Patents
New energy equipment identification method, device and medium Download PDFInfo
- Publication number
- CN114970648A CN114970648A CN202110192479.3A CN202110192479A CN114970648A CN 114970648 A CN114970648 A CN 114970648A CN 202110192479 A CN202110192479 A CN 202110192479A CN 114970648 A CN114970648 A CN 114970648A
- Authority
- CN
- China
- Prior art keywords
- model
- charging
- actual
- historical
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
Abstract
The application discloses a new energy device identification method, a device and a medium, wherein the method comprises the steps of inputting a plurality of sets of historical data sets including historical charging messages and corresponding historical device model data as training samples into a classification learning model for training to obtain a model identification model, and identifying the actual charging messages through the model identification model under the condition of obtaining the actual charging messages so as to output actual device model data. Therefore, the model of the new energy device can be identified through the actual charging message of the new energy device, the historical charging message is from the real charging process of the electric vehicle, so that the data source is reliable, the accuracy of the identification result can be improved, and in addition, the VIN is not needed, so that the method is suitable for the electric vehicle with the charging message not containing the VIN, and the application range is wider. Finally, the technical scheme does not relate to the improvement of a hardware structure, and effectively reduces the modification cost.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a new energy device identification method, apparatus, and medium.
Background
The new energy device mentioned in the present application is a device that supplies kinetic energy by a battery, for example, an automobile using a battery, hereinafter referred to as an electric automobile.
In various situations, the model of the electric vehicle needs to be used, for example, during the charging process of the electric vehicle, the model of the current vehicle needs to be identified in order to provide input electric signals suitable for the current vehicle, such as current, voltage, and the like.
Therefore, how to identify the model of the new energy device is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The application aims to provide a new energy device identification method which is used for identifying the model of a new energy device. In addition, the purpose of this application still provides a new forms of energy equipment recognition device and medium.
In order to solve the technical problem, the present application provides a new energy device identification method, including:
acquiring a plurality of sets of historical data sets, wherein each historical data set comprises a historical charging message and corresponding historical equipment model data;
obtaining a model identification model, wherein the model identification model is obtained by training the multiple groups of historical data sets serving as training samples in a classification learning model;
acquiring an actual charging message;
and outputting actual equipment model data, wherein the actual equipment model data is obtained by the model identification model according to the actual charging message.
Preferably, the historical charging packet has N historical charging packet data, the actual charging packet has M actual charging packet data, M is less than or equal to N, and M historical charging packet data in the historical charging packet corresponds to M actual charging packet data in the actual charging packet.
Preferably, the acquiring the plurality of sets of historical data comprises:
acquiring a multi-order historical charging order;
and screening out a target historical charging order containing VIN from the plurality of historical charging orders so as to obtain the historical data set from the target historical charging order.
Preferably, the actual charging messages are multiple, and the step of outputting actual device model data further includes:
respectively acquiring actual equipment model data corresponding to a plurality of actual charging messages in the classification learning model;
selecting the actual device model data with the highest frequency of occurrence from the plurality of actual device model data as the final actual device model data.
Preferably, the classification learning model has at least two types, and the obtaining actual device model data corresponding to the plurality of actual charging packets in the classification learning model respectively includes: and respectively acquiring actual equipment model data corresponding to the actual charging messages in the classification learning model.
Preferably, the classification learning model is a C50 decision tree model.
Preferably, the historical charging message data includes a required voltage, a minimum voltage of the single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage, and an actual current.
In order to solve the above technical problem, the present application provides a new energy device identification apparatus, including:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of sets of historical data sets, and each historical data set comprises a historical charging message and corresponding historical equipment model data;
the training module is used for obtaining a model identification model, and the model identification model is obtained by training the multiple groups of historical data sets serving as training samples in a classification learning model;
the second acquisition module is used for acquiring an actual charging message;
and the output module is used for outputting actual equipment model data, and the actual equipment model data is obtained by the model identification model according to the actual charging message.
In order to solve the above technical problem, the present application provides a new energy device identification apparatus, including a memory for storing a computer program;
a processor for implementing the steps of the new energy device identification method when executing the computer program.
In order to solve the above technical problem, the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the new energy device identification method as described above.
According to the new energy equipment identification method, multiple groups of historical data sets including historical charging messages and corresponding historical equipment model data are used as training samples and input into a classification learning model for training to obtain a model identification model, and under the condition that an actual charging message is obtained, the actual charging message is identified through the model identification model, so that actual equipment model data are output. Therefore, the model of the new energy device can be identified through the actual charging message of the new energy device, the historical charging message is from the real charging process of the electric vehicle, so that the data source is reliable, the accuracy of the identification result can be improved, and in addition, the VIN is not needed, so that the method is suitable for the electric vehicle with the charging message not containing the VIN, and the application range is wider. Finally, the technical scheme does not relate to the improvement of a hardware structure, and effectively reduces the modification cost.
In addition, the new energy equipment identification device and the medium provided by the application correspond to the method, and the effects are the same as those of the method.
Drawings
In order to more clearly illustrate the embodiments of the present application, the drawings needed for the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a structural diagram of a charging management system of an electric vehicle according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a new energy device identification method according to an embodiment of the present application;
FIG. 3 is a Gini index profile provided in an embodiment of the present application;
fig. 4 is a structural diagram of a new energy device identification apparatus according to an embodiment of the present application;
fig. 5 is a block diagram of another new energy device identification apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
The core of the application is to provide a new energy device identification method, a new energy device identification device and a new energy device identification medium.
The new energy device proposed by the present application may be an electric vehicle or other electric devices, and the electric vehicle is taken as an example hereinafter. The new energy device identification method can be applied to the charging cloud platform and can also be applied to charging devices. The charging cloud platform is in communication connection with the charging equipment and is used for managing the plurality of charging equipment in a unified mode. In general, a charging cloud platform realizes corresponding functions by mutual cooperation of a plurality of computers. The charging equipment generally has two hardware composition modes, one is that a charger and a charging terminal are integrally arranged, the size is large, the charging equipment is often used in a high-speed service area and other fast charging scenes, the other is that the charger and the charging terminal are separately arranged, one charger can be in communication connection with a plurality of charging terminals and is used for managing the plurality of charging terminals in a unified manner. Because the charger and the charging terminal are arranged in a split manner, the charging terminal is small in size, can directly perform data interaction with the electric vehicle, is simple in function, generally sends acquired vehicle data to the corresponding charger, completes complex data operation by the charger, and then returns an operation result to the charging terminal. Fig. 1 is a structural diagram of a charging management system of an electric vehicle according to an embodiment of the present application. As shown in fig. 1, the charging management system includes a charging cloud platform 1 and a plurality of charging devices 2 in communication connection with the charging cloud platform 1, where the charging devices 2 acquire data related to the electric vehicle, for example, a charging message, and send the charging message to the charging cloud platform 1, and the charging cloud platform 1 identifies a vehicle model according to a model identification model and sends the vehicle model to the charging devices 2. It should be noted that fig. 1 is only a specific application scenario and does not represent that the identification of the vehicle model must be implemented by the charging cloud platform.
The hardware usage scenario corresponding to the new energy device identification method provided by the application is described above. An embodiment of the new energy device identification method is explained below. In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings. Fig. 2 is a flowchart of a new energy device identification method according to an embodiment of the present application. As shown in fig. 2, the method includes:
s10: and acquiring a plurality of sets of historical data sets, wherein each historical data set comprises a historical charging message and corresponding historical equipment model data.
In specific implementation, in a scene of charging an electric vehicle, the vehicle model needs to be identified so as to provide reasonable charging management measures.
Since a vehicle transmits a charging message at certain time intervals (for example, one minute) during a charging process, a plurality of charging messages may be generated during a charging process. Each charging message comprises at least one charging message data. In this embodiment, data acquired in the historical charging process is used as a training sample of the model identification model. The historical charging message mentioned in this embodiment is one of the charging messages mentioned above, and is only distinguished from the actual charging message, so that each historical charging message also includes at least one charging message data (the historical charging message data mentioned below). Because the charging messages are historical charging messages, each historical charging message corresponds to one device model data, namely the historical device model data, and the historical device model data have a corresponding relation. The multiple sets of historical data sets are composed of multiple historical charging messages and historical equipment model data corresponding to the historical charging messages. In this embodiment, the charging message data may include a required voltage, a minimum voltage of the single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage, an actual current, an SOC, and the like. Different vehicles of the same vehicle type have the same power storage battery and Battery Management System (BMS) generally, and the charging rules of the vehicles are consistent. Based on this, the rules of the charging messages of the same vehicle model are the same, so in this embodiment, the historical charging messages and the corresponding historical device model data are used as data sources. It is understood that the historical charging message and corresponding historical device model data may be obtained from a charging order, as described in detail below. Because the historical charging message comes from the real charging process of the electric automobile, the data source is reliable, the accuracy of the identification result can be improved, and a vehicle identification code (VIN) is not needed, so that the method is suitable for the electric automobile of which the charging message does not contain the VIN, and has a wider application range.
S11: and obtaining a model identification model, wherein the model identification model is obtained by training a plurality of groups of historical data sets serving as training samples in a classification learning model.
It should be noted that the classification learning model mentioned in this embodiment is not limited, and is obtained by training a training sample, so that the classification learning model is a supervised classification learning model, for example, a Support Vector Machine (SVM), a k nearest neighbor classification model (KNN), or a C50 decision tree model.
It is understood that there may be one or more classification learning models, and there may be one or more model identification models.
S12: and acquiring an actual charging message.
The actual charging message mentioned in this step is a charging message of the new energy device currently being charged, and it can be understood that charging message data included in the actual charging message is hereinafter referred to as actual charging message data, and the actual charging message data may be the same as or different from the type of the historical charging message data included in the historical charging message.
S13: and outputting actual equipment model data, wherein the actual equipment model data is obtained by the model identification model according to the actual charging message.
In a specific implementation, in the case of acquiring an actual charging packet, if there is only one model identification model, the model may be called, and if there are multiple model identification models, one or more models may be called, where a specific implementation is given below.
It can be understood that, for the accuracy of the model identification model, the actual charging message and the actual device model data may be added to the training sample to train the classification learning model again, so that the model identification model is continuously adjusted and optimized, and the accuracy of the identification result is improved.
It should be noted that the 4 steps mentioned in the embodiment are only for illustrating the steps included in the new energy device identification method, and do not represent that the 4 steps are performed in each identification process, for example, the steps may be performed once for S10 and S11, and the steps may be performed multiple times for S12 and S13.
In the new energy device identification method provided by this embodiment, a plurality of sets of historical data sets including historical charging messages and corresponding historical device model data are input as training samples into a classification learning model for training to obtain a model identification model, and when an actual charging message is obtained, the actual charging message is identified by the model identification model so as to output actual device model data. Therefore, the model of the new energy device can be identified through the actual charging message of the new energy device, the historical charging message is from the real charging process of the electric vehicle, so that the data source is reliable, the accuracy of the identification result can be improved, and in addition, the VIN is not needed, so that the method is suitable for the electric vehicle with the charging message not containing the VIN, and the application range is wider. Finally, the technical scheme does not relate to the improvement of a hardware structure, and effectively reduces the modification cost.
In the above embodiment, the charging message data included in the historical charging message and the actual charging message are not limited, and in fact, the higher the type repetition degree of the charging message data included in the historical charging message and the actual charging message is, the more accurate the obtained identification result is. As a preferred embodiment, the historical charging packet has N historical charging packet data, the actual charging packet has M actual charging packet data, M is less than or equal to N, and M historical charging packet data in the historical charging packet correspond to M actual charging packet data in the actual charging packet. It is understood that both M and N are positive integers. In a specific embodiment, the N historical charging message data may include a required voltage, a minimum voltage of the single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage, and an actual current, and the M actual charging message data may include a required voltage, a minimum voltage of the single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage, and an actual current, where M is equal to N.
On the basis of the above embodiment, the acquisition source of the historical charging packet is not limited, and in this embodiment, the historical charging packet and the corresponding historical device model data are acquired through a historical charging order. The method specifically comprises the following steps:
acquiring a multi-order historical charging order;
and screening a target historical charging order containing VIN from the multi-order historical charging order to obtain a historical charging message and historical equipment model data from the target historical charging order.
Since the new energy device needs to interact with the charging device in the charging process, a charging order, that is, the historical charging order mentioned in this embodiment, is generated. For the charging cloud platform, the historical charging order is the existing data, so that the historical charging message and the equipment model are obtained by using the historical charging order, the operation is rapid, and the cost is low. It should be noted that the more the historical charging orders relate to the more the device models are, the more the historical charging orders of the same device model are, the higher the usability of the training sample is, and the more accurate the recognition result of the model recognition model obtained by training is.
The VIN can uniquely correspond to the device model, but the new energy device cannot send the VIN during charging, so that the historical charging orders do not all include the VIN.
It can be understood that, if the target historical charging order belongs to an abnormal order, the availability of the charging message data contained in the target historical charging order is low, so in order to improve the availability of the training sample, in this embodiment, before inputting the training sample into the classification learning model, the method further includes:
and performing data cleaning on the target historical charging order.
In this embodiment, the method for data cleansing is not limited, and one implementation manner includes the following steps:
removing orders which have the charging duration less than a preset value and are charged by using alternating current from the obtained historical target charging orders;
removing orders with abnormal charging message data from the rest target historical charging orders;
and extracting historical charging message data and historical equipment model data from the rest target historical charging orders to serve as training samples.
Additionally, in other embodiments, data within a particular time range may also be selected, for example, selecting a target historical charging order after 2019. The preset value mentioned above may be 10 minutes.
In order to improve the accuracy of the identification result, in this embodiment, the step of outputting the actual device model data further includes:
respectively acquiring actual equipment model data corresponding to a plurality of actual charging messages in a classification learning model;
actual device model data with the highest frequency of occurrence is selected from the plurality of actual device model data as final actual device model data.
In this embodiment, a plurality of actual charging messages participate in the model identification process, so as to prevent the problem of inaccurate identification result caused by instability of a certain charging message. It can be understood that, in a specific implementation, all actual charging packets may participate in the model identification process, or may participate in the model identification process in stages (a handshake stage, a parameter configuration stage, a charging stage, and a charging end) or N previous charging packets are set. For example, X actual charging messages are acquired within 30 minutes, each actual charging message is input to the model identification model to output one actual device model data, X actual device model data are obtained in total, and the actual device model data with the highest frequency of occurrence is used as a final identification result. By the method, the problem of inaccurate identification results caused by instability of one or more actual charging messages or abnormal data transmission can be avoided.
In the above embodiment, the types of the classification learning models are not limited, and in consideration of the fact that the accuracy of different classification learning models varies under different input parameters, on the basis of the above embodiment, the types of the classification learning models are at least two, and correspondingly, the types of the obtained model identification models are also two. On this basis, respectively acquiring actual device model data corresponding to the multiple actual charging messages in the classification learning model includes:
and respectively acquiring actual equipment model data corresponding to the actual charging messages in the classification learning model.
Taking the types of the model identification models as two examples, if the number of the actual charging messages is 30, inputting the 30 actual charging messages into the two model identification models to obtain 60 actual device model data, and selecting the actual device model data with the largest frequency as a final identification result from the 60 actual device model data.
In one embodiment, the classification learning model is a C50 decision tree model. In order to determine the influence of different charging message data on the recognition result, the influence is preferably calculated by using a chini (Gini) index, and specifically, the historical charging message data includes a required voltage, a minimum voltage of the single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage, and an actual current. It is understood that the above 8 data is only one specific implementation, and in other embodiments, an SOC may also be included.
Fig. 3 is a Gini index distribution diagram provided in the embodiment of the present application. As shown in fig. 3, the horizontal axis represents a Gini index, the vertical axis represents charging packet data, and the influence of each charging packet data on the heterogeneity of the observed value at each node of the classification tree (representing the influence of the variable on the classification effect) is calculated by the Gini index, so as to compare the importance of the charging packet data. The obtained importance ranking is shown in fig. 3, and the importance is the required voltage, the lowest voltage of the single battery, the lowest temperature of the single battery, the highest voltage of the single battery, the highest temperature of the single battery, the required current, the actual voltage, the actual current and the SOC from high to low in sequence.
Further, in order to increase the data processing speed, after the actual charging packet is obtained, only useful charging packet data is extracted, and if the remaining charging packet data is ignored, obtaining the actual charging packet includes:
extracting a required voltage, a lowest voltage of the single battery, a lowest temperature of the single battery, a highest voltage of the single battery, a highest temperature of the single battery, a required current, an actual voltage and an actual current from the actual charging message;
and inputting the required voltage, the lowest voltage of the single battery, the lowest temperature of the single battery, the highest voltage of the single battery, the highest temperature of the single battery, the required current, the actual voltage, the actual current and the SOC into a model identification model to obtain actual equipment model data.
It can be understood that, in the actual charging packet, a problem of missing of a part of packet parameters may occur, and in the actual processing process, if the 8 charging packet data are missing, the corresponding packet parameters may be set as default values.
In this embodiment, the degree of influence of each message parameter on the identification result is calculated through the Gini index, so that in the identification process, if the charging message data is incomplete in the obtained actual charging message, whether the actual charging message can be used as an effective charging message or not can be determined through the actually contained charging message data. Therefore, in other embodiments, after acquiring the actual charging packet, the method further includes:
and judging whether the actual charging message is an effective charging message or not, and if so, inputting the actual charging message into the model identification model to obtain actual equipment model data. The criteria for this determination are: whether the charging message data in the actual charging message includes the predetermined kind of charging message data or not may include: the required voltage, the minimum voltage of the single battery and the minimum temperature of the single battery. And if one actual charging message contains the charging message data of the preset type, the actual charging message is an effective charging message, and if the actual charging message is not completely contained, the actual charging message is an invalid charging message and abnormal prompt information is output.
In the foregoing embodiment, a detailed description is given of a new energy device identification method, and the application also provides an embodiment corresponding to the new energy device identification apparatus. It should be noted that the present application describes the embodiments of the apparatus portion from two perspectives, one is based on the functional module, and the other is based on the hardware structure.
Fig. 4 is a structural diagram of a new energy device identification apparatus according to an embodiment of the present application. As shown in fig. 4, based on the angle of the function module, the new energy device identification apparatus includes:
the first acquisition module 10 is configured to acquire multiple sets of historical data sets, where each historical data set includes a historical charging packet and corresponding historical device model data;
the training module 11 is used for obtaining a model identification model, wherein the model identification model is obtained by training a plurality of groups of historical data sets serving as training samples in a classification learning model;
a second obtaining module 12, configured to obtain an actual charging packet;
and the output module 13 is used for outputting actual equipment model data, and the actual equipment model data is obtained by the model identification model according to the actual charging message.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
According to the new energy device identification apparatus provided by this embodiment, a plurality of sets of historical data sets including historical charging messages and corresponding historical device model data are input into the classification learning model as training samples to be trained to obtain a model identification model, and under the condition that an actual charging message is obtained, the actual charging message is identified through the model identification model, so that actual device model data is output. Therefore, the model of the new energy device can be identified through the actual charging message of the new energy device, the historical charging message is from the real charging process of the electric vehicle, so that the data source is reliable, the accuracy of the identification result can be improved, and in addition, the VIN is not needed, so that the method is suitable for the electric vehicle with the charging message not containing the VIN, and the application range is wider. Finally, the technical scheme does not relate to the improvement of a hardware structure, and effectively reduces the modification cost.
Fig. 5 is a block diagram of another new energy device identification apparatus according to an embodiment of the present application. Based on the angle of the hardware structure, the new energy equipment identification device comprises a memory, a storage device and a control device, wherein the memory is used for storing a computer program;
a processor for implementing the steps of the new energy device identification method as mentioned in the above method embodiments when executing the computer program.
The new energy device identification apparatus provided by this embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, or a desktop computer.
The processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 21 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in a wake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 21 may further include an AI (Artificial Intelligence) processor for processing a calculation operation related to machine learning.
Memory 20 may include one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used for storing a computer program 201, wherein after being loaded and executed by the processor 21, the computer program is capable of implementing relevant steps of the new energy device identification method disclosed in any one of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202, data 203, and the like, and the storage manner may be a transient storage manner or a permanent storage manner. Operating system 202 may include, among others, Windows, Unix, Linux, and the like. Data 203 may include, but is not limited to, historical charge message data, actual charge message data, and the like.
In some embodiments, the new energy device identification apparatus may further include a display 22, an input/output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.
Those skilled in the art will appreciate that the configuration shown in fig. 5 does not constitute a limitation of the new energy device identification apparatus and may include more or less components than those shown.
The new energy equipment identification device provided by the embodiment of the application comprises a memory and a processor, wherein when the processor executes a program stored in the memory, the following method can be realized: the method comprises the steps that multiple sets of historical data sets including historical charging messages and corresponding historical device model data are used as training samples and input into a classification learning model for training to obtain a model identification model, and under the condition that an actual charging message is obtained, the model identification model identifies the actual charging message so as to output actual device model data. Therefore, the model of the new energy device can be identified through the actual charging message of the new energy device, the historical charging message is from the real charging process of the electric vehicle, so that the data source is reliable, the accuracy of the identification result can be improved, and in addition, the VIN is not needed, so that the method is suitable for the electric vehicle with the charging message not containing the VIN, and the application range is wider. Finally, the technical scheme does not relate to the improvement of a hardware structure, and effectively reduces the transformation cost.
Finally, the application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps as set forth in the above-mentioned method embodiments.
It is to be understood that if the method in the above embodiments is implemented in the form of software functional units and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the embodiments of the present application, or all or part of the technical solutions. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The method, the device and the medium for identifying the new energy device provided by the application are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It should also be noted that, in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
Claims (10)
1. A new energy device identification method is characterized by comprising the following steps:
acquiring a plurality of sets of historical data sets, wherein each historical data set comprises a historical charging message and corresponding historical equipment model data;
obtaining a model identification model, wherein the model identification model is obtained by training the multiple groups of historical data sets serving as training samples in a classification learning model;
acquiring an actual charging message;
and outputting actual equipment model data, wherein the actual equipment model data is obtained by the model identification model according to the actual charging message.
2. The new energy device identification method according to claim 1, wherein the historical charging packet has N historical charging packet data, the actual charging packet has M actual charging packet data, M is less than or equal to N, and M historical charging packet data in the historical charging packet corresponds to M actual charging packet data in the actual charging packet.
3. The new energy device identification method according to claim 1, wherein the acquiring of the plurality of sets of historical data comprises:
acquiring a multi-order historical charging order;
and screening out a target historical charging order containing VIN from the plurality of historical charging orders so as to obtain the historical data set from the target historical charging order.
4. The new energy device identification method according to any one of claims 1 to 3, wherein the actual charging message is a plurality of messages, and the step of outputting actual device model data further includes:
respectively acquiring actual equipment model data corresponding to the actual charging messages in the classification learning model;
and selecting the actual equipment model data with the highest frequency of occurrence from the plurality of actual equipment model data as the final actual equipment model data.
5. The new energy device identification method according to claim 4, wherein the classification learning model has at least two types, and the obtaining actual device model data corresponding to the actual charging packets in the classification learning model respectively comprises: and respectively acquiring actual equipment model data corresponding to the actual charging messages in the classification learning model.
6. The new energy device identification method according to claim 1, wherein the classification learning model is a C50 decision tree model.
7. The new energy device identification method according to claim 1, 2, 3 or 6, wherein the historical charging message data comprises a required voltage, a minimum voltage of a single battery, a minimum temperature of the single battery, a maximum voltage of the single battery, a maximum temperature of the single battery, a required current, an actual voltage and an actual current.
8. A new energy device identification apparatus, comprising:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of sets of historical data sets, and each historical data set comprises a historical charging message and corresponding historical equipment model data;
the training module is used for obtaining a model identification model, and the model identification model is obtained by training the multiple groups of historical data sets serving as training samples in a classification learning model;
the second acquisition module is used for acquiring an actual charging message;
and the output module is used for outputting actual equipment model data, and the actual equipment model data is obtained by the model identification model according to the actual charging message.
9. The new energy device identification device is characterized by comprising a memory, a storage unit and a control unit, wherein the memory is used for storing a computer program;
a processor for implementing the steps of the new energy device identification method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the new energy device identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192479.3A CN114970648A (en) | 2021-02-20 | 2021-02-20 | New energy equipment identification method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192479.3A CN114970648A (en) | 2021-02-20 | 2021-02-20 | New energy equipment identification method, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114970648A true CN114970648A (en) | 2022-08-30 |
Family
ID=82954388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110192479.3A Pending CN114970648A (en) | 2021-02-20 | 2021-02-20 | New energy equipment identification method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114970648A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115473856A (en) * | 2022-09-07 | 2022-12-13 | 中国银行股份有限公司 | Message checking method and device |
-
2021
- 2021-02-20 CN CN202110192479.3A patent/CN114970648A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115473856A (en) * | 2022-09-07 | 2022-12-13 | 中国银行股份有限公司 | Message checking method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934955B (en) | Charging mode identification method and device, terminal equipment and storage medium | |
| CN109934473B (en) | Charging health index scoring method and device, terminal equipment and storage medium | |
| CN109948664B (en) | Charging mode identification method and device, terminal equipment and storage medium | |
| CN110704283A (en) | Method, device and medium for uniformly generating alarm information | |
| CN109818396B (en) | Charging method and device for lithium ion battery pack and terminal equipment | |
| CN112886671A (en) | Battery charging state detection method, detection device and charging device | |
| CN111060832B (en) | Electric vehicle battery aging identification method and device, terminal equipment and storage medium | |
| CN111002859A (en) | Method and device for identifying private patch board of charging pile, terminal equipment and storage medium | |
| CN114970648A (en) | New energy equipment identification method, device and medium | |
| CN114954105A (en) | Battery replacement method and device, electronic equipment and storage medium | |
| CN113721161A (en) | Consistency evaluation method and device for lithium ion battery pack | |
| CN112487265A (en) | Data processing method and device, computer storage medium and electronic equipment | |
| CN115499315A (en) | OTA (over the air) upgrading task execution method and device and electronic equipment | |
| CN111055725B (en) | Electric vehicle battery aging identification method and device, terminal equipment and storage medium | |
| CN110532304B (en) | Data processing method and device, computer readable storage medium and electronic device | |
| CN114742297A (en) | Power battery treatment method | |
| CN113097998A (en) | Charging station intelligent control method and device and storage medium | |
| CN114139621A (en) | Method, device, equipment and storage medium for determining model classification performance identification | |
| CN113222401A (en) | Non-invasive load type intelligent identification method, device, server and system | |
| CN111016730B (en) | Battery charging detection method and device and terminal equipment | |
| CN111025043B (en) | Method for identifying charging behavior and terminal equipment | |
| CN111186333B (en) | Electric vehicle charging identification method and device, terminal equipment and storage medium | |
| CN110807589A (en) | Case analysis system of electric power spot market | |
| CN114966405A (en) | Method, device, medium and prompt terminal for detecting charging abnormality of new energy equipment | |
| CN111044813B (en) | Charging mode identification method and device and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |