CN117421659A

CN117421659A - Charging station monitoring management method, system, terminal equipment and storage medium

Info

Publication number: CN117421659A
Application number: CN202311473537.5A
Authority: CN
Inventors: 常加忠; 王璠; 李仁强; 陈江伐
Original assignee: Henan Longxiang New Energy Technology Co ltd
Current assignee: Henan Longxiang New Energy Technology Co ltd
Priority date: 2023-11-07
Filing date: 2023-11-07
Publication date: 2024-01-19

Abstract

The application relates to the technical field of charging stations, in particular to a charging station monitoring management method, a charging station monitoring management system, terminal equipment and a storage medium. If the target monitoring set is a user side monitoring set, analyzing various user monitoring data in the user side monitoring set according to a preset user data monitoring standard, and generating a corresponding user behavior analysis result; establishing a corresponding user behavior prediction classification model, and outputting a corresponding user behavior optimization management strategy; if the target monitoring set is a server monitoring set, judging whether the equipment monitoring data in the server monitoring set accords with the corresponding preset operation monitoring standard or not; aiming at the abnormal monitoring data, acquiring a corresponding target abnormal event and a similar abnormal event set corresponding to the target abnormal event; and generating a repair order corresponding to the target abnormal event as a device repair management strategy according to the similar abnormal event set repair strategy and the repair coefficient. According to the technical scheme, the monitoring management effect of the charging station can be improved.

Description

Charging station monitoring management method, system, terminal equipment and storage medium

Technical Field

The application relates to the technical field of charging stations, in particular to a charging station monitoring management method, a charging station monitoring management system, terminal equipment and a storage medium.

Background

Charging station monitoring management refers to a system for monitoring and managing charging stations in real time. The charging pile, the power distribution system, the charging equipment and the like are monitored and controlled by installing the monitoring equipment and the software, so that safe operation and efficient management of the charging station are ensured.

Among them, charging station monitoring management generally includes the following aspects, real-time monitoring: through installing the sensor and the monitoring equipment, each index of the charging station is monitored in real time, wherein the indexes comprise current, voltage, temperature, electric energy consumption and the like; remote control: the remote control equipment can remotely regulate and control the start and stop of the charging pile, the electric quantity control, the charging speed and the like; fault early warning: the system can pre-warn the fault of the charging equipment by analyzing historical data and real-time monitoring data; and (3) safety management: the charging station monitoring management system can also carry out safety management on the charging station, including monitoring and verifying the safety performance of the charging equipment, so as to ensure the safety and reliability of the charging process.

In practical application, the charging station monitoring management system generates a large amount of monitoring data, including various types of data such as charging pile state, charging record, electric energy consumption, user information and the like, and the utilization rate of the monitoring data is low due to lack of unified data management and analysis tools, so that the monitoring management effect of the charging station is poor.

Disclosure of Invention

In order to improve the monitoring management effect of a charging station, the application provides a charging station monitoring management method, a charging station monitoring management system, terminal equipment and a storage medium.

In a first aspect, the present application provides a charging station monitoring management method, including the steps of:

acquiring charging station monitoring data, and dividing the charging station monitoring data into corresponding target monitoring sets according to preset monitoring data classification standards;

if the target monitoring set is a user side monitoring set, analyzing various user monitoring data in the user side monitoring set according to a preset user data monitoring standard, and generating a corresponding user behavior analysis result;

establishing a corresponding user behavior prediction classification model according to the user behavior analysis result, and outputting a corresponding user behavior optimization management strategy;

Performing optimization management on the target user according to the user behavior optimization management strategy;

if the target monitoring set is a server monitoring set, judging whether the equipment monitoring data in the server monitoring set accords with a corresponding preset operation monitoring standard or not;

if the equipment monitoring data in the server monitoring set does not accord with the corresponding preset operation monitoring standard, acquiring corresponding abnormal monitoring data, and matching corresponding target abnormal events and similar abnormal event sets corresponding to the target abnormal events from a preset abnormal event library according to the abnormal characteristics of the abnormal monitoring data;

obtaining a repair coefficient of each abnormal event in the abnormal event set corresponding to a repair strategy, and combining the repair strategy and the repair coefficient to generate a repair order corresponding to the target abnormal event as an equipment repair management strategy;

and carrying out repair management on the target abnormal event according to the equipment repair management strategy.

By adopting the technical scheme, the data are divided into the corresponding target monitoring sets according to the preset monitoring data classification standards, the monitoring data can be classified, managed and analyzed according to different categories, so that the situation that analysis and management are not in place due to excessively complicated monitoring data is reduced, if the target monitoring sets are user side monitoring sets, a corresponding user behavior prediction classification model is built according to various monitoring data of the user and behavior analysis results, and a user behavior optimization management strategy is output, further, on the basis of knowing the behavior mode and habit of the user, the corresponding user behavior optimization management strategy is adopted to optimize the charging experience of the user, if the target monitoring sets are server side monitoring sets, the corresponding target abnormal event and the similar abnormal event sets are matched from the preset abnormal event library, and the repair strategy and the repair coefficient are combined, so that the repair order of the target abnormal event is generated as a device repair management strategy, the repair efficiency of the current target abnormal event can be effectively improved, and the influence of the device fault on the operation of the charging station can be reduced to the greatest extent. The method comprises the steps of classifying a large amount of monitoring data generated by the charging station into sets according to a user side and a server side, and configuring corresponding data analysis processing rules according to actual monitoring management requirements of the specific classification target monitoring sets, so that the utilization rate of the monitoring data is improved, and the monitoring management effect of the charging station is improved.

Optionally, if the target monitoring set is a user monitoring set, analyzing various user monitoring data in the user monitoring set according to a preset user data monitoring standard, and generating a corresponding user behavior analysis result includes the following steps:

extracting target behavior characteristics corresponding to various types of user monitoring data in the user side monitoring set according to the preset user data monitoring standard;

establishing a corresponding user behavior analysis model according to the target behavior characteristics, and outputting a corresponding user behavior mode;

and carrying out predictive analysis on the user behavior mode according to a preset user behavior prediction rule, and generating a corresponding user behavior trend as the user behavior analysis result.

Through adopting above-mentioned technical scheme, charging station manager can be according to user behavior analysis result, adjusts service strategy, equipment configuration, the charging stake overall arrangement etc. of charging station to provide better user experience, thereby improved charging station's efficiency and operation management level.

Optionally, establishing a corresponding user behavior prediction classification model according to the user behavior analysis result, and outputting a corresponding user behavior optimization management policy, where the method includes the following steps:

Matching the corresponding user behavior prediction classification model according to the classification task corresponding to the user behavior analysis result;

performing predictive analysis on the user behavior analysis result according to the user behavior predictive classification model to generate a corresponding behavior classification prediction result;

and formulating a corresponding user behavior optimization management strategy according to the behavior classification prediction result.

By adopting the technical scheme, the user behavior prediction classification model is established, the corresponding optimization management strategy is formulated, the user management effect of the charging station can be improved, personalized service is provided, resource allocation is optimized, the operation efficiency of the charging station is improved, and therefore the monitoring management effect of the charging station is improved.

Optionally, the step of formulating the corresponding user behavior optimization management policy according to the behavior classification prediction result includes the following steps:

acquiring behavior prediction characteristics of the corresponding target user according to the behavior classification prediction result;

classifying the behavior prediction features according to a preset clustering algorithm, and dividing the corresponding target users into corresponding similar feature user groups according to classification results;

and analyzing the classification characteristics corresponding to the similar characteristic user groups according to a preset optimization rule, and formulating the corresponding user behavior optimization management strategy.

By adopting the technical scheme, users are divided into different characteristic groups according to cluster analysis, different management strategies can be formulated for the users in different groups, the management refinement degree is improved, and therefore the monitoring management effect of the charging station is improved.

Optionally, after judging whether the device monitoring data in the server monitoring set meets the corresponding preset operation monitoring standard if the target monitoring set is the server monitoring set, the method further includes the following steps:

if the equipment monitoring data in the server monitoring set accords with the corresponding preset operation monitoring standard, acquiring the load condition of the corresponding target charging pile according to the equipment monitoring data;

establishing a corresponding energy demand prediction model according to a history monitoring record corresponding to the equipment monitoring data, and outputting a corresponding energy demand prediction;

and formulating a resource optimization strategy corresponding to the target charging pile by combining the load condition and the energy prediction demand.

By adopting the technical scheme, the corresponding resource optimization strategy is formulated by combining the load condition and the energy prediction requirement of the target charging pile, so that the reasonable allocation and allocation of the corresponding charging station resources can be realized, and the monitoring management effect of the charging station is improved.

Optionally, after performing repair management on the target abnormal event according to the device repair management policy, the method further includes the following steps:

importing the equipment repairing management strategy into a preset automatic repairing decision model, and outputting a repairing record corresponding to the target abnormal event;

performing time sequence analysis on the repair record, and acquiring corresponding time sequence characteristics;

fitting is carried out according to the time sequence characteristics of a preset fitting algorithm, a corresponding time sequence fitting model is generated, and the predicted trend distribution corresponding to the target abnormal event is output.

By adopting the technical scheme, according to the time sequence fitting model, the trend distribution and the periodicity of the target abnormal event can be predicted, further measures can be taken in advance, the repair time and the cost are reduced, and the monitoring management effect of the charging station is improved.

Optionally, after importing the device repair management policy into a preset automatic repair decision model and outputting a repair record corresponding to the target abnormal event, the method further includes the following steps:

acquiring a maintenance team corresponding to the target abnormal event in the repair record;

evaluating maintenance performance indexes of the maintenance team to generate corresponding efficiency indexes;

Analyzing the efficiency index according to a preset maintenance efficiency standard, obtaining a corresponding efficiency difference, and generating an optimization guiding strategy corresponding to the maintenance team according to the efficiency difference.

By adopting the technical scheme, the defects of a maintenance team can be found by evaluating the maintenance performance index and the analysis efficiency difference, and a corresponding optimization strategy is provided to improve the maintenance efficiency, so that the monitoring management effect of the charging station is improved.

In a second aspect, the present application provides a charging station monitoring management system, comprising:

the monitoring module is used for acquiring the charging station monitoring data and dividing the charging station monitoring data into corresponding target monitoring sets according to a preset monitoring data classification standard;

the user behavior analysis module is used for analyzing various user monitoring data in the user side monitoring set according to preset user data monitoring standards and generating corresponding user behavior analysis results if the target monitoring set is the user side monitoring set;

the user behavior optimization module is used for establishing a corresponding user behavior prediction classification model according to the user behavior analysis result and outputting a corresponding user behavior optimization management strategy;

The user side management module is used for carrying out optimization management on the target user according to the user behavior optimization management strategy;

the server-side data analysis module is used for judging whether the equipment monitoring data in the server-side monitoring set accords with the corresponding preset operation monitoring standard or not if the target monitoring set is the server-side monitoring set;

the same-kind abnormal matching module is used for acquiring corresponding abnormal monitoring data and matching corresponding target abnormal events and a same-kind abnormal event set corresponding to the target abnormal events from a preset abnormal event library according to the abnormal characteristics of the abnormal monitoring data if the equipment monitoring data in the server monitoring set do not accord with the corresponding preset operation monitoring standard;

the abnormal repair ordering module is used for acquiring the repair coefficient of each abnormal event corresponding to the repair strategy in the abnormal event set, and combining the repair strategy and the repair coefficient to generate repair ordering corresponding to the target abnormal event as an equipment repair management strategy;

and the server management module is used for carrying out repair management on the target abnormal event according to the equipment repair management strategy.

By adopting the technical scheme, the data are divided into the corresponding target monitoring sets according to the preset monitoring data classification standard in the monitoring module, the monitoring data can be classified, managed and analyzed according to different categories, so that the situation that analysis and management are not in place due to excessively complicated monitoring data is reduced, if the target monitoring sets are user side monitoring sets, a corresponding user behavior prediction classification model is built according to various monitoring data and behavior analysis results of a user through the user behavior optimization module, a user behavior optimization management strategy is output, and further, on the basis of knowing the behavior mode and habit of the user, the corresponding user behavior optimization management strategy is adopted to optimize the charging experience of the user, if the target monitoring sets are abnormal monitoring data which do not meet the preset operation monitoring standard, the corresponding target abnormal events and the similar abnormal event sets are matched from the preset abnormal event library through the similar abnormal matching module, and the repair ordering module is combined with the repair strategy and the repair coefficient, so that the repair ordering of the target abnormal events is generated as the equipment repair management strategy, and the repair ordering of the current target abnormal events can be effectively improved, and further, the influence of equipment faults on the operation can be reduced to the maximum degree. The method comprises the steps of classifying a large amount of monitoring data generated by the charging station into sets according to a user side and a server side, and configuring corresponding data analysis processing rules according to actual monitoring management requirements of the specific classification target monitoring sets, so that the utilization rate of the monitoring data is improved, and the monitoring management effect of the charging station is improved.

In a third aspect, the present application provides a terminal device, which adopts the following technical scheme:

the terminal equipment comprises a memory and a processor, wherein the memory stores computer instructions capable of running on the processor, and the charging station monitoring and management method is adopted when the processor loads and executes the computer instructions.

By adopting the technical scheme, the charging station monitoring management method generates the computer instruction, stores the computer instruction in the memory and loads and executes the computer instruction by the processor, so that the terminal equipment is manufactured according to the memory and the processor, and is convenient to use.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

a computer readable storage medium having stored therein computer instructions which, when loaded and executed by a processor, employ a charging station monitoring management method as described above.

By adopting the technical scheme, the charging station monitoring management method generates the computer instruction, stores the computer instruction in the computer readable storage medium to be loaded and executed by the processor, and facilitates the reading and storage of the computer instruction through the computer readable storage medium.

In summary, the present application includes at least one of the following beneficial technical effects: according to the method, data are divided into corresponding target monitoring sets according to preset monitoring data classification standards, the monitoring data can be classified, managed and analyzed according to different categories, so that the situation that analysis and management are not in place due to excessive complexity of the monitoring data is reduced, if the target monitoring sets are user side monitoring sets, a corresponding user behavior prediction classification model is built according to various monitoring data of users and behavior analysis results, and a user behavior optimization management strategy is output, further, on the basis of knowing the behavior mode and habit of the users, the corresponding user behavior optimization management strategy is adopted to optimize charging experience of the users, if the target monitoring sets are server side monitoring sets, corresponding target abnormal events and similar abnormal event sets are matched from a preset abnormal event base according to abnormal monitoring data which does not meet the preset operation monitoring standards, and the repairing strategies and the repairing coefficients are combined, so that repairing sequences of the target abnormal events are generated to serve as equipment repairing management strategies, and repairing efficiency of the current target abnormal events can be effectively improved, and influences of equipment faults on an operation charging station can be reduced to the greatest extent. The method comprises the steps of classifying a large amount of monitoring data generated by the charging station into sets according to a user side and a server side, and configuring corresponding data analysis processing rules according to actual monitoring management requirements of the specific classification target monitoring sets, so that the utilization rate of the monitoring data is improved, and the monitoring management effect of the charging station is improved.

Drawings

Fig. 1 is a schematic flow chart of steps S101 to S108 in a charging station monitoring and managing method of the present application.

Fig. 2 is a schematic flow chart of steps S201 to S203 in the charging station monitoring and managing method of the present application.

Fig. 3 is a schematic flow chart of steps S301 to S303 in the charging station monitoring and managing method of the present application.

Fig. 4 is a schematic flow chart of steps S401 to S403 in the charging station monitoring and managing method of the present application.

Fig. 5 is a schematic flow chart of steps S501 to S503 in a charging station monitoring and managing method of the present application.

Fig. 6 is a schematic flow chart of steps S601 to S603 in the charging station monitoring and managing method of the present application.

Fig. 7 is a schematic flow chart of steps S701 to S703 in a charging station monitoring and managing method of the present application.

Fig. 8 is a schematic block diagram of a charging station monitoring management system according to the present application.

Reference numerals illustrate:

1. a monitoring module; 2. a user behavior analysis module; 3. a user behavior optimization module; 4. a user side management module; 5. the server-side data analysis module; 6. the same kind of abnormal matching module; 7. an abnormality repair ordering module; 8. and the server management module.

Detailed Description

The present application is described in further detail below in conjunction with figures 1-8.

The embodiment of the application discloses a charging station monitoring and managing method, as shown in fig. 1, comprising the following steps:

s101, acquiring charging station monitoring data, and dividing the charging station monitoring data into corresponding target monitoring sets according to preset monitoring data classification standards;

s102, if the target monitoring set is a user terminal monitoring set, analyzing various user monitoring data in the user terminal monitoring set according to a preset user data monitoring standard, and generating a corresponding user behavior analysis result;

s103, building a corresponding user behavior prediction classification model according to a user behavior analysis result, and outputting a corresponding user behavior optimization management strategy;

s104, optimizing and managing the target user according to the user behavior optimizing and managing strategy;

s105, if the target monitoring set is a server monitoring set, judging whether equipment monitoring data in the server monitoring set accords with corresponding preset operation monitoring standards;

s106, if the equipment monitoring data in the server monitoring set do not accord with the corresponding preset operation monitoring standard, acquiring corresponding abnormal monitoring data, and matching corresponding target abnormal events and similar abnormal event sets corresponding to the target abnormal events from a preset abnormal event library according to the abnormal characteristics of the abnormal monitoring data;

S107, acquiring a repair coefficient of each abnormal event in the abnormal event set corresponding to the repair strategy, and combining the repair strategy and the repair coefficient to generate a repair order of the corresponding target abnormal event as an equipment repair management strategy;

s108, repairing and managing the target abnormal event according to the equipment repairing and managing strategy.

In step S101, charging station monitoring data refers to a process of acquiring various monitoring data from the charging station, and these data may include various parameters such as an operation state of the charging post, a charging speed, a charging power, a charging current, and the like. The manner in which such data is acquired may be by sensors, monitoring devices, and the like.

The preset monitoring data classification standard refers to a preset standard for classifying the charging station monitoring data according to a certain rule. This criterion may be set according to the characteristics of the charging station, the operating requirements, etc., for example, classified according to the model of the charging pile, the charging power, the geographical location, etc.

Secondly, dividing the charging station monitoring data into corresponding target monitoring sets is a process of grouping the acquired charging station monitoring data according to a preset classification standard. Each target monitoring set represents a class of charging station monitoring data having similar characteristics or attributes. The purpose is to facilitate analysis and processing of different types of monitoring data.

In step S102, the user side monitoring set refers to a data set for monitoring and recording user behavior and operation in the charging station system or product. These data are primarily used to analyze and understand the behavior patterns, preferences, and feedback of the user when using the product or service, thereby helping to optimize the user experience, improve product functionality, and promote user satisfaction.

For example, the client monitoring set includes: user behavior data, namely operation behavior data such as charging browsing pages, clicking links, submitting forms and the like of a user; user interaction data, namely recording interaction operation between a user and a charging station product or service; user equipment information.

The preset user data monitoring standard refers to a predetermined standard or standard for monitoring and recording user data when a user side monitoring set is set, and the standard prescribes requirements of which user data to collect, how to collect, store and process the data, confidentiality and security of the data, and the like. The preset user data monitoring criteria are set to ensure accuracy, consistency and comparability of the user data for subsequent analysis and utilization of the data, and are typically set according to business requirements and analysis purposes.

For example, the user side monitoring set includes user access data and user interaction data. Analyzing access data such as a browsing page, a clicking link and the like of a user according to a preset user data monitoring standard, and obtaining a user behavior analysis result of an access path of the user; and analyzing the user interaction data according to a preset user data monitoring standard, and calculating a user behavior analysis result of the stay time of the user on each page.

In steps S103 to S104, the user behavior prediction classification model predicts the future behavior of the user using a machine learning or statistical model based on the current behavior analysis result and the historical behavior data of the user. The method can divide users into different behavior categories, such as purchasing electric quantity on a charging station client operation platform, browsing charging unit price of a charging station, clicking various preferential activities initiated by the charging station, and the like, so as to take corresponding optimized management strategies for the users in the different categories.

Specifically, the process of establishing the user behavior prediction classification model may be divided into the following steps: and (3) data acquisition: collecting behavior data of a user, including a current behavior analysis result of the user and historical behavior data, wherein the historical behavior data can come from a historical record browsed and accessed by the user in a charging station client; feature selection and extraction: appropriate features are selected from the behavioral data to describe the user's behavior and characteristics, which may include user's basic information (e.g., age, gender, geographic location, etc.), user's behavioral records (e.g., browsing records, purchasing records, etc.), and other features related to the user's behavior, and the different behavioral features are classified into corresponding feature classification sets.

Secondly, dividing the various feature classification sets into corresponding training sets and test sets, wherein the training sets are used for training and parameter adjustment of the model, and the test sets are used for evaluating the performance and generalization capability of the model; according to the characteristics of the charging station user behavior analysis requirements and data, a proper classification model is selected for training, such as logistic regression, decision trees, random forests, support vector machines, neural networks and the like, and the selected model is utilized for training through the data of the training set, so that the model can learn the mode and rule in the data.

Further, the performance and accuracy of the model are evaluated by using the test set, and the evaluation indexes can comprise accuracy, precision, recall, F1 value and the like, and parameters of the model are adjusted or other models are selected for optimization according to the evaluation result so as to obtain better prediction performance; after the model is trained and optimized, the model can be applied to an actual scene, behavior prediction is carried out according to the characteristic data of the user, and a user behavior optimization management strategy of a corresponding personalized recommendation or marketing mode is formulated according to a prediction result so as to meet the requirements of the user and improve the user experience. And then carrying out optimization management on the target user according to the user behavior optimization management strategy.

For example, the user behavior optimization management policy is to provide personalized recommended content for the user according to the behavior data and preferences of the user. By analyzing behavior data such as browsing records, purchasing records and the like of the user on the charging station client operation platform, the user's interest, hobbies and demands can be known, and then products or services meeting the personalized demands can be recommended to the user.

In step S105, the server monitoring set refers to a set for monitoring and managing the charging station system. Charging stations refer to facilities for charging electric vehicles, while a server monitoring set is a set of indices, states, and behaviors for monitoring and managing charging station systems.

The device monitoring data refers to data for monitoring and recording states and performance indexes of various charging station devices in the server monitoring set. Specifically, in the server monitoring set, the device monitoring data may include, but is not limited to, the following: the connection state, namely, whether the equipment is normally connected to a server system or not, comprises information such as the on-line state, connection quality and the like of the equipment; the health state is the normal working state of the equipment, and comprises whether the equipment operates normally, whether hardware and software of the equipment fail or not, and the like; the running state, namely, the current working condition of the equipment is represented, and the running state comprises information such as running time, running speed and running mode of the equipment; the energy consumption monitoring, namely the energy consumption monitoring of the equipment, refers to monitoring the energy use condition of the equipment, and comprises the power consumption, the energy efficiency and the like of the equipment. By monitoring the energy consumption condition of the equipment, the energy consumption of the equipment can be optimized, and the energy consumption cost is reduced.

Secondly, the preset operation monitoring standard refers to a standard or index which is preset in a server monitoring set and used for monitoring the operation state of equipment or a system. These criteria or metrics may be used to determine whether the device or system is functioning properly and meeting expected operating requirements. For example, the preset operation monitoring standard is a charging station performance index, and is used for measuring indexes such as a charging speed, a charging power, a charging efficiency and the like in terms of working efficiency, processing capacity, response speed and the like of a charging station device or system. By setting reasonable performance indexes, whether the performance of the equipment or the system meets the expected requirement can be evaluated.

In step S106, if the device monitoring data in the server monitoring set does not meet the preset operation monitoring standard, in order to improve the abnormal monitoring effect of the charging station, the monitoring data related to the device is obtained from the server monitoring set. The monitoring data include sensor data, log records, performance statistics, etc. of the charging station equipment, and are used for describing information of the running state, performance indexes, health states, etc. of the equipment.

And secondly, analyzing and processing the obtained abnormality monitoring data, and extracting the characteristics related to the abnormality of the equipment. These features may be outliers, outlier trends, outlier distributions, etc. of the data that are used to describe the characteristics of the device anomalies.

And further, matching the extracted abnormal characteristics with the abnormal characteristics in a preset abnormal event library. The known abnormal characteristics and the corresponding abnormal event information are stored in a preset abnormal event library, and a target abnormal event matched with the target abnormal characteristics can be found through matching. And then, according to the target abnormal event obtained by matching, acquiring a similar abnormal event set similar to or related to the target abnormal event from a preset abnormal event library again. These same kind of anomalies may provide similar anomalies, solutions, troubleshooting steps, etc. information for assisting in processing the target anomalies.

It should be noted that, the homogeneous abnormal event set refers to a set of abnormal events having similarity or correlation with the target abnormal event. These anomalies have some similarity or relevance to the target anomalies in terms of nature, cause, impact, solution, etc.

For example, there are a plurality of charging posts in the charging station, each of which is equipped with a monitoring device for collecting and monitoring operation data of the charging post. According to preset operation monitoring standards, the monitoring data should include parameters such as current, voltage, temperature and the like of the charging pile, and the parameters need to be kept within a certain range. If the monitoring data does not meet the preset operation monitoring standard, namely, the current or voltage of a certain charging pile exceeds a preset range, the abnormal monitoring data is identified. For this anomaly monitoring data, a corresponding target anomaly event needs to be matched from a preset anomaly event library.

For another example, according to the characteristics of the anomaly monitoring data, it may be matched that the target anomaly event is "charging pile current overload". At this time, according to the target abnormal event, other related abnormal events such as "abnormal voltage of the charging pile caused by overload of the charging pile current", "excessive temperature of the charging pile caused by overload of the charging pile current" and the like may be further obtained from the similar abnormal event set.

In steps S107 to S108, the repair policy corresponding to each abnormal event is collected from the abnormal event set. The repair policy may include troubleshooting steps for specific exceptions, problem-solving methods, code modifications or configuration adjustments, and the like. The repair strategy of each abnormal event is evaluated to obtain a corresponding repair coefficient, wherein the repair coefficient is an index for evaluating and measuring the repair strategy, and the repair coefficient can be evaluated according to factors such as the effect, complexity, feasibility and the like of the repair strategy and can be represented by numbers, grades or other forms.

Further, according to the repair strategy of each abnormal event and the repair coefficient of the repair strategy, the repair strategies in the abnormal event set are ordered. The repair coefficients of the repair strategies may be ordered from high to low or low to high to determine the repair strategy with the optimal repair coefficients. Wherein, the higher the repair coefficient is, the better the repair effect of the corresponding repair strategy is.

The repair ranking can rank the abnormal events in the abnormal event set according to the repair coefficients of the abnormal events. The abnormal events with higher repairing coefficients are arranged in front, so that the repairing strategies for the abnormal events are more effective, simpler or feasible and can be processed preferentially. And then, preferentially selecting the repairing strategy arranged in front to repair and manage the target abnormal event corresponding to the charging station. For example, repair management is to perform overall management and repair for a target abnormal event, including discovering an abnormality, formulating a repair scheme, performing repair, verifying a repair effect, and the like.

Second, according to the repair order, the device manager can handle the abnormal event according to the priority. Firstly, processing an abnormal event with a higher repair coefficient, and performing fault investigation and repair according to a corresponding repair strategy. This can improve the efficiency and accuracy of fault handling.

It should be noted that, the repair order is generated according to the repair policy and the repair coefficient in the abnormal event set, and the repair order may also change with the changes of the repair policy and the repair coefficient. Therefore, the repair order should be dynamically updated to reflect the latest repair strategy and repair coefficients in time.

According to the charging station monitoring management method provided by the embodiment, the data are divided into the corresponding target monitoring sets according to the preset monitoring data classification standards, the monitoring data can be classified, managed and analyzed according to different categories, so that the situation that analysis and management are not in place due to excessively complicated monitoring data is reduced, if the target monitoring sets are the user side monitoring sets, the corresponding user behavior prediction classification model is built according to various monitoring data of the user and behavior analysis results, and the user behavior optimization management strategy is output, further, on the basis of knowing the behavior mode and habit of the user, the corresponding user behavior optimization management strategy is adopted to optimize the charging experience of the user, if the target monitoring sets are the server side monitoring sets, the corresponding target abnormal event and the similar abnormal event sets are matched from the preset abnormal event library, and the repair strategy and the repair coefficient are combined, so that the repair sequence of the target abnormal event is used as the equipment repair management strategy, and further, the effect of the current target abnormal event on the operation of the charging station can be effectively improved to the greatest extent. The method comprises the steps of classifying a large amount of monitoring data generated by the charging station into sets according to a user side and a server side, and configuring corresponding data analysis processing rules according to actual monitoring management requirements of the specific classification target monitoring sets, so that the utilization rate of the monitoring data is improved, and the monitoring management effect of the charging station is improved.

In one implementation manner of the present embodiment, as shown in fig. 2, step S102, if the target monitoring set is a user monitoring set, analyzes various types of user monitoring data in the user monitoring set according to a preset user data monitoring standard, and generates a corresponding user behavior analysis result, where the step includes the following steps:

s201, extracting target behavior characteristics corresponding to various user monitoring data in a user side monitoring set according to a preset user data monitoring standard;

s202, establishing a corresponding user behavior analysis model according to target behavior characteristics, and outputting a corresponding user behavior mode;

s203, carrying out predictive analysis on the user behavior mode according to a preset user behavior prediction rule, and generating a corresponding user behavior trend as a user behavior analysis result.

In step S201, the target behavior feature refers to a user behavior feature that meets the preset user data monitoring standard, and may be used to determine whether the user behavior meets the expectations or whether there is an abnormality or risk.

For example, various user monitoring data in the user monitoring set include the frequency of logging in the charging station client platform by the user, the access duration and the page browsing amount, and the user activity is measured according to the data indexes. If the activity of the user in a period of time is higher than the preset user data monitoring standard, the user can be regarded as a target behavior feature, and the user is interested in the platform and participates in the platform more.

In step S202, the user behavior analysis model is a mathematical model or algorithm for analyzing and understanding the user behavior pattern. Based on the target behavior characteristics of a user, the behavior rules and preferences of the user under a specific environment are revealed through technologies such as data mining, machine learning, statistical analysis and the like, and then the corresponding user behavior mode of the target user is obtained based on the behavior rules and preferences.

Where user behavior patterns refer to a series of repetitive or regular behavior patterns and preferences exhibited by a user under a particular environment. Through analysis of the user behavior patterns, personalized services can be provided for the user and user experience can be optimized.

In step S203, the user behavior prediction rule is a series of rules or patterns derived from historical user behavior data and related algorithm models for predicting a possible future behavior trend of the user. For example, charging modes of interest to the user may be predicted based on a record of the user's past selection of a particular charging peg type within the charging station.

And secondly, analyzing and calculating the user behavior mode by applying the user behavior prediction rule to obtain possible behavior trend of the user in the future. May be implemented by techniques such as data mining, machine learning, or artificial intelligence.

Further, the user behavior trend is a possible behavior pattern or behavior pattern of the user in the future, which is obtained according to the prediction analysis result. For example, if the predictive analysis shows that a user may select a fast-fill mode in the near future, then the user's fast-fill mode is the predicted user behavior trend.

According to the charging station monitoring management method provided by the embodiment, a charging station manager can adjust the service strategy, the equipment configuration, the charging pile layout and the like of the charging station according to the user behavior analysis result so as to provide better user experience, thereby improving the efficiency and the operation management level of the charging station.

In one implementation manner of the present embodiment, as shown in fig. 3, step S103 includes the following steps of:

s301, matching corresponding user behavior prediction classification models according to classification tasks corresponding to user behavior analysis results;

s302, carrying out predictive analysis on a user behavior analysis result according to a user behavior predictive classification model to generate a corresponding behavior classification prediction result;

s303, formulating a corresponding user behavior optimization management strategy according to the behavior classification prediction result.

In step S301, the user behavior analysis result may include a plurality of categories, such as different user behavior categories of purchase, browsing, searching, and the like. The classification task is to classify each user behavior instance in the user behavior analysis result into a corresponding class so as to better understand the user behavior mode and conduct personalized recommendation and other works.

Second, the user behavior prediction classification model is a machine learning model or statistical model for predicting the user's possible behavior classes in the future based on the user behavior characteristics and historical data. Common classification models include decision trees, logistic regression, support vector machines, naive bayes, and the like.

According to the classification task of the user behavior analysis result, a proper user behavior prediction classification model can be selected for matching. For example, if the classification task is to divide the user's purchasing behavior into different commodity categories, a multi-classification model such as a naive Bayesian classifier or a support vector machine classifier may be used to make predictions. The proper user behavior prediction classification model is selected, so that the accuracy and effect of user behavior prediction can be improved, and better charging user behavior monitoring management can be provided for the charging station.

In steps S302 to S303, the behavior classification prediction result is a result of classification prediction for each user behavior instance, that is, each user behavior instance is classified into a corresponding behavior class. For example, for a behavior analysis result in which a charging user selects to purchase a different charging unit price, the behavior classification prediction result includes information such as a charging unit price category that the user may purchase in the future or a cycle frequency of purchase.

According to the behavior classification prediction result, a user behavior optimization management strategy aiming at different behavior categories can be formulated. For example, for users of the purchase behavior category, policies such as personalized recommendation, promotion, etc. can be adopted to promote the purchase conversion; for users of the browsing behavior categories, the interface design of the website or application may be optimized, policies such as providing more relevant information, etc., to increase user residence time and conversion rate.

According to the charging station monitoring management method provided by the embodiment, the user behavior prediction classification model is established, the corresponding optimization management strategy is formulated, the user management effect of the charging station can be improved, personalized service is provided, resource allocation is optimized, the operation efficiency of the charging station is improved, and therefore the monitoring management effect of the charging station is improved.

In one implementation manner of the present embodiment, as shown in fig. 4, step S303, namely, formulating a corresponding user behavior optimization management policy according to the behavior classification prediction result, includes the following steps:

s401, according to a behavior classification prediction result, obtaining behavior prediction characteristics of a corresponding target user;

s402, classifying behavior prediction features according to a preset clustering algorithm, and dividing corresponding target users into corresponding similar feature user groups according to classification results;

s403, analyzing the classification characteristics corresponding to the similar characteristic user groups according to a preset optimization rule, and formulating a corresponding user behavior optimization management strategy.

In step S401, the behavior prediction feature refers to a feature or index used by the user behavior prediction classification model when predicting the user behavior class. By acquiring the behavior prediction features, the behavior pattern and behavior trend of the target user can be better understood.

Where the target user refers to a specific group of users that need to be analyzed and predicted. According to the behavior classification prediction result, the target users can be classified into different behavior categories, and then the behavior prediction characteristics are acquired for each behavior category.

Second, the behavior prediction features include historical behavior data of the user, personal information of the user, preferences of the user, and the like. By analyzing these features, the behavior patterns and behavior trends of the target user can be more accurately obtained, thereby better predicting their future behavior.

Specifically, the obtaining of the corresponding behavior prediction features of the target user may be roughly divided into the following steps: according to the behavior classification prediction result of the target user, a proper machine learning algorithm is used for training a model, the process of training the model comprises dividing a data set into a training set and a testing set, training the model by utilizing the training set, and then using the testing set for model verification and evaluation, wherein the trained model can be used for performing behavior prediction on the target user to obtain behavior prediction characteristics. And evaluating and optimizing the behavior prediction characteristics, evaluating indexes such as accuracy, stability and the like of the prediction result, and optimizing the model and the characteristics according to the evaluation result.

In steps S402 to S403, the preset clustering algorithm refers to a clustering algorithm selected in advance according to the specific category of the behavior prediction feature. Such as K-means, hierarchical clustering, DBSCAN, etc.

Before classifying the behavior prediction features by using a preset clustering algorithm, setting corresponding parameters, such as the number of clusters or a density threshold value, for the selected clustering algorithm. And then clustering the behavior prediction features by using a selected clustering algorithm, and dividing the target users into different similar feature user groups.

And secondly, the preset optimization rule refers to a preset optimization analysis strategy aiming at the corresponding classification characteristics of the user groups with different types of characteristics. Classifying a feature refers to classifying users with similar features into the same cluster in a cluster analysis, and assigning a representative feature or attribute to the cluster to describe the feature or characteristic of the cluster.

For example, the preset optimization rule uses an optimization rule of a hierarchical clustering algorithm that constructs a hierarchical clustering result by merging or partitioning clusters. Specifically, the aggregation hierarchical clustering is implemented by calculating the similarity between two clusters, and selecting the two clusters with the highest similarity for merging until the preset clustering number is reached. The split hierarchical clustering is to select the data points with the least similarity to divide by calculating the similarity of the data points in the clusters until the preset clustering number is reached. The goal of the optimization is to maximize the similarity of data points within the same cluster while minimizing the similarity between different clusters.

It should be noted that the categorizing features may be specific numerical features, such as average consumption amount, purchase frequency, and the like; or may be discrete category features such as purchase preferences, user interests, etc. By analyzing the features of the users within a cluster, representative features of the cluster can be found, thereby better understanding and describing the features of the cluster.

Further, according to the characteristics of the different user groups, personalized recommendation strategies can be formulated. For example, for a population of users who purchase high price charge unit price for a long period of time, the relevant latest charge technology and its corresponding price update range may be recommended.

According to the charging station monitoring management method provided by the embodiment, users are divided into different characteristic groups according to cluster analysis, different management strategies can be formulated for the users in different groups, the management refinement degree is improved, and therefore the monitoring management effect of the charging station is improved.

In one implementation manner of this embodiment, as shown in fig. 5, in step S105, if the target monitoring set is the server monitoring set, after determining whether the device monitoring data in the server monitoring set meets the corresponding preset operation monitoring standard, the method further includes the following steps:

s501, if the equipment monitoring data in the server monitoring set accords with the corresponding preset operation monitoring standard, acquiring the load condition of the corresponding target charging pile according to the equipment monitoring data;

s502, establishing a corresponding energy demand prediction model according to a history monitoring record corresponding to equipment monitoring data, and outputting a corresponding energy demand prediction;

S503, combining the load condition and the energy prediction requirement, and formulating a resource optimization strategy corresponding to the target charging pile.

In step S501, when the device monitoring data of the charging station meets the preset operation monitoring standard, it is indicated that the device is operating normally and the data is accurate and reliable, and in order to deepen the monitoring management of the corresponding charging pile device in the charging station, the load condition of the corresponding target charging pile is further obtained according to the device monitoring data. The load condition refers to the current load condition of the target charging pile, and comprises information such as the use state, the charging speed, the current, the voltage and the like of the target charging pile.

In step S502, the energy demand prediction model is a model that analyzes and predicts future energy demands using charging station history monitoring data. By analyzing the history monitoring records, rules and trends of the energy demands of the charging station can be found and applied to future predictions.

For example, first, charging station history monitoring record data is collected, including time stamps, charging demand data and other characteristic data related thereto, such as weather data, season data, and the like. These data may be collected from the aspects of charging piles, charging records, grid loads, etc.

And secondly, analyzing and characteristic engineering is carried out on the historical monitoring data. Through the analysis of the historical charging demand data, the change condition and influence factors of the charging demand can be known. At the same time, other characteristic data, such as weather data, may also be utilized to construct a characteristic representative of the change in charging demand. If weather factors are considered, the characteristics such as average temperature, rainfall and the like can be extracted as factors influencing the charging requirement.

Furthermore, a suitable predictive model, such as a time series model, is selected. The time series model may capture periodic and trending changes in the charging demand based on the time characteristics of the historical charging demand data. Common time series models include ARIMA model, SARIMA model, and the like. By training the training set and optimizing parameters, an accurate charging demand prediction model can be obtained.

Further, the trained model is evaluated using the validation set. The accuracy and reliability of the model is evaluated by comparing the prediction result with the actual observed value, calculating a prediction error index such as Root Mean Square Error (RMSE), mean Absolute Error (MAE), etc. And predicting the future energy demand by using the trained model to obtain the energy prediction demand of the corresponding charging station. The prediction results can help a decision maker to know the future charging demand condition, prepare for energy supply in advance, and reasonably arrange charging resources so as to meet the future charging demand.

In step S503, according to the load condition and the energy prediction requirement, the resource optimization strategy for the target charging pile is formulated, which can help to improve the utilization rate and the operation efficiency of the charging pile, and can ensure the reasonable distribution of the charging resources.

For example, dynamic pricing strategies are employed to adjust charging prices based on the load conditions and energy forecast demands of the charging piles. When the load is higher or the energy demand is larger, the charging price can be moderately increased so as to encourage users to reasonably use charging resources; when the load is lower or the energy demand is smaller, the charging price can be moderately reduced so as to increase the utilization rate of the charging pile.

For another example, intelligent scheduling strategies are employed to optimize the resource allocation of the charging piles based on the energy forecast demand. By comprehensively considering factors such as charging requirements, distance between charging piles, availability of the charging piles and the like, the execution sequence of charging tasks and the distribution of the charging piles are reasonably arranged, so that the utilization rate of the charging piles and the satisfaction degree of users are maximized.

For another example, according to the energy prediction requirement, the capacity and the number of the energy storage devices are reasonably configured by combining the characteristics of the energy storage devices of the charging station so as to meet the energy requirement in the peak period. The energy storage equipment can charge when the load is lower, then release energy when the load is higher, balance load peak valley difference, improve the utilization ratio and the energy utilization efficiency of charging stake.

According to the charging station monitoring management method provided by the embodiment, the corresponding resource optimization strategy is formulated by combining the load condition and the energy prediction requirement of the target charging pile, so that reasonable allocation and allocation of corresponding charging station resources can be realized, and the monitoring management effect of the charging station is improved.

In one implementation manner of the present embodiment, as shown in fig. 6, after step S108, that is, performing repair management on the target abnormal event according to the device repair management policy, the method further includes the following steps:

s601, importing an equipment repair management strategy into a preset automatic repair decision model, and outputting a repair record corresponding to a target abnormal event;

s602, carrying out time sequence analysis on the repair record and acquiring corresponding time sequence characteristics;

s603, fitting is carried out according to the time sequence characteristics of a preset fitting algorithm, a corresponding time sequence fitting model is generated, and the predicted trend distribution of the corresponding target abnormal event is output.

In step S601, the preset automated repair decision model is a repair decision model based on the device repair management policy and related data. The model automatically generates a repair decision according to factors such as the type, severity, influence range and the like of the equipment abnormal event and by combining an equipment repair management strategy. The model can be trained and optimized in a machine learning algorithm, expert experience and other modes so as to improve the accuracy and efficiency of decision making.

And after repairing the target abnormal event based on a preset automatic repairing decision model, a corresponding repairing record is generated. Repair records include, but are not limited to, repair time, repair measures, repair personnel, repair results, and the like. The purpose of the repair record is to record the repair process and result of the abnormal event and provide reference for subsequent equipment maintenance and fault analysis.

In steps S602 to S603, the time series analysis refers to a method of performing statistics and analysis on time series data. In this scheme, a time series analysis method such as a time series chart, an autocorrelation chart, a moving average, etc. may be applied to the repair record to identify and analyze the repair trend and the periodic variation of the target abnormal event.

The time sequence features refer to some feature indexes in the time sequence data, and are used for describing and representing the change rule of the data. Common timing characteristics include trending, seasonal, periodic, abrupt, and the like. By carrying out time sequence analysis on the repair records, corresponding time sequence characteristics can be extracted for subsequent fitting and prediction.

Next, the preset fitting algorithm refers to that a specific fitting algorithm is preselected when performing time series fitting. And carrying out fitting calculation on the time sequence characteristics according to the preset fitting algorithm, and selecting a proper time sequence fitting model to carry out modeling and prediction. Common time series fitting models include ARIMA models, exponential smoothing models, neural network models, and the like.

Further, based on the generated time series fitting model, future trend distribution of the target abnormal event can be predicted. The predicted outcome may include indicators of the number of abnormal events, repair time, repair costs, etc. over a future time period. Through predicting trend distribution, the development trend of the target abnormal event can be better known, and corresponding decisions and plans can be made.

According to the charging station monitoring management method provided by the embodiment, the trend distribution and the periodicity of the target abnormal event can be predicted according to the time sequence fitting model, so that measures can be taken in advance, the repair time and the cost are reduced, and the monitoring management effect of the charging station is improved.

In one implementation manner of the present embodiment, as shown in fig. 7, after step S601, the device repair management policy is imported into a preset automatic repair decision model, and a repair record corresponding to the target abnormal event is output, the method further includes the following steps:

s701, acquiring a maintenance team corresponding to a target abnormal event in a repair record;

s702, evaluating maintenance performance indexes of a maintenance team to generate corresponding efficiency indexes;

s703, analyzing the efficiency index according to a preset maintenance efficiency standard, obtaining a corresponding efficiency difference, and generating an optimization guidance strategy of a corresponding maintenance team according to the efficiency difference.

In steps S701 to S702, the target abnormal event is screened out from the whole dataset through data screening and screening according to the characteristics of the target abnormal event, and screening can be performed based on time, equipment, fault type and other conditions. And then, correlating the screened target abnormal event with the information of the maintenance team. The matching can be performed according to the information of maintenance personnel, maintenance teams, maintenance work orders and the like in the record.

Second, related information of the maintenance team, such as team name, number of people, expertise, etc., is extracted from the associated data. Specifically, the evaluation of the maintenance performance index of the maintenance team may be performed by: determining performance indexes, namely determining proper performance indexes according to responsibilities and targets of maintenance teams, wherein the common maintenance performance indexes comprise maintenance time, maintenance cost, work order completion rate, fault rate improvement and the like; data collection, i.e., collecting data related to performance indicators, such as maintenance records, work order information, maintenance time, maintenance costs, etc., may be obtained from sources such as maintenance records, work order systems, maintenance logs, etc.

Secondly, data processing and calculation, namely cleaning and arranging the collected data, and then calculating performance indexes, such as average maintenance time, maintenance cost ratio, work order completion rate and the like; performance evaluation and comparison, namely, performance of maintenance teams is evaluated and compared according to the calculated performance indexes, the performance indexes can be compared with set targets, and performance and efficiency levels of teams are evaluated; and generating an efficiency index, namely generating a corresponding efficiency index according to the performance evaluation result, wherein the efficiency index is the comprehensive evaluation of the performance index, and the efficiency index can be calculated by means of weighted average or normalization and the like so as to reflect the overall efficiency level of the maintenance team.

In step S703, the preset maintenance efficiency standard refers to a standard or index for measuring the efficiency of the maintenance team, which is preset in the maintenance work of the charging station. It is formulated based on industry experience, corporate requirements, or other reference criteria to measure and evaluate the efficiency level of a maintenance team in completing a maintenance task.

The preset maintenance efficiency criteria may include various aspects of indicators such as time limits for maintenance work, equipment availability requirements, maintenance cost control, etc. These metrics are determined based on the nature and requirements of the maintenance task and are intended to provide a clear target and metric for the maintenance team.

For example, a preset maintenance efficiency standard may require that the maintenance team have an average repair time of no more than 2 hours when handling the fault, or that the maintenance team complete the maintenance work within 24 hours after the equipment fault occurs. In addition, the preset maintenance efficiency criteria may also require maintenance teams to control costs during maintenance, such as limiting spare part procurement costs or reducing unnecessary human waste.

And secondly, comparing the efficiency index of the maintenance team with a preset standard to determine the efficiency difference of the maintenance team. The efficiency difference may be quantified by calculating the difference between the performance indicators and the preset criteria. And then carrying out deep analysis on the efficiency difference to find out main factors influencing the efficiency of the maintenance team. Possible reasons include skill level of personnel, equipment, unreasonable workflow, poor coordination of communications, etc.

Further, according to the analysis result of the efficiency difference, a targeted optimization guiding strategy is formulated. These policies may include: updating tool equipment, namely updating and improving tool equipment of a maintenance team as required, and improving maintenance efficiency and quality; optimizing the workflow, namely analyzing the bottleneck and unnecessary links in the workflow, optimizing and improving the workflow, and improving the working efficiency.

Furthermore, corresponding action plans can be formulated according to the optimization guidance strategy, and effective implementation of the action plans can be ensured. Meanwhile, a monitoring mechanism can be established, the effect of the improvement measures can be tracked and evaluated, and corresponding adjustment and optimization can be timely made.

According to the charging station monitoring management method provided by the embodiment, the maintenance performance index and the analysis efficiency difference are evaluated, the defects of a maintenance team can be found, and a corresponding optimization strategy is provided to improve the maintenance efficiency, so that the monitoring management effect of the charging station is improved.

The embodiment of the application discloses a charging station monitoring management system, as shown in fig. 8, includes:

the monitoring module 1 is used for acquiring charging station monitoring data and dividing the charging station monitoring data into corresponding target monitoring sets according to preset monitoring data classification standards;

The user behavior analysis module 2 is used for analyzing various user monitoring data in the user side monitoring set according to a preset user data monitoring standard and generating a corresponding user behavior analysis result if the target monitoring set is the user side monitoring set;

the user behavior optimization module 3 is used for establishing a corresponding user behavior prediction classification model according to the user behavior analysis result and outputting a corresponding user behavior optimization management strategy;

the user side management module 4 is used for carrying out optimization management on the target user according to the user behavior optimization management strategy;

the server-side data analysis module 5 is used for judging whether the equipment monitoring data in the server-side monitoring set accords with the corresponding preset operation monitoring standard if the target monitoring set is the server-side monitoring set;

the similar abnormal matching module 6 is used for acquiring corresponding abnormal monitoring data if the equipment monitoring data in the server monitoring set does not accord with the corresponding preset operation monitoring standard, and matching corresponding target abnormal events and similar abnormal event sets corresponding to the target abnormal events from a preset abnormal event library according to the abnormal characteristics of the abnormal monitoring data;

The abnormal repair ordering module 7 is used for acquiring the repair coefficient of each abnormal event in the abnormal event set corresponding to the repair strategy, and generating the repair ordering of the corresponding target abnormal event as the equipment repair management strategy by combining the repair strategy and the repair coefficient;

and the server management module 8 is used for carrying out repair management on the target abnormal event according to the equipment repair management strategy.

According to the charging station monitoring management system provided by the embodiment, the data is divided into the corresponding target monitoring sets according to the preset monitoring data classification standard in the monitoring module 1, the monitoring data can be classified, managed and analyzed according to different categories, so that the situation that analysis and management are not in place due to excessive complexity of the monitoring data is reduced, if the target monitoring sets are user side monitoring sets, the corresponding user behavior prediction classification model is built according to various monitoring data of the user and behavior analysis results through the user behavior optimization module 3, the user behavior optimization management strategy is output, the corresponding user behavior optimization management strategy is adopted on the basis of knowing the behavior mode and habit of the user, the charging experience of the user is optimized, if the target monitoring sets are abnormal monitoring data which does not meet the preset operation monitoring standard, the corresponding target abnormal event and the similar abnormal event sets are matched from the preset abnormal event base through the similar abnormal matching module 6, the repair ordering module 7 is combined with the repair strategy and the repair coefficient, the repair ordering of the target abnormal event is generated as the equipment repair management strategy, and the current target abnormal event repair efficiency is effectively improved, and the influence on the charging station operation is reduced to the maximum degree. The method comprises the steps of classifying a large amount of monitoring data generated by the charging station into sets according to a user side and a server side, and configuring corresponding data analysis processing rules according to actual monitoring management requirements of the specific classification target monitoring sets, so that the utilization rate of the monitoring data is improved, and the monitoring management effect of the charging station is improved.

It should be noted that, the charging station monitoring management system provided in the embodiment of the present application further includes each module and/or the corresponding sub-module corresponding to the logic function or the logic step of any one of the charging station monitoring management methods, so that the same effects as each logic function or logic step are achieved, and detailed descriptions thereof are omitted herein.

The embodiment of the application also discloses a terminal device, which comprises a memory, a processor and computer instructions stored in the memory and capable of running on the processor, wherein when the processor executes the computer instructions, any charging station monitoring and management method in the embodiment is adopted.

The terminal device may be a computer device such as a desktop computer, a notebook computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory, for example, the terminal device may further include an input/output device, a network access device, a bus, and the like.

The processor may be a Central Processing Unit (CPU), or of course, according to actual use, other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), ready-made programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and the general purpose processor may be a microprocessor or any conventional processor, etc., which is not limited in this application.

The memory may be an internal storage unit of the terminal device, for example, a hard disk or a memory of the terminal device, or may be an external storage device of the terminal device, for example, a plug-in hard disk, a Smart Memory Card (SMC), a secure digital card (SD), or a flash memory card (FC) provided on the terminal device, or the like, and may be a combination of the internal storage unit of the terminal device and the external storage device, where the memory is used to store computer instructions and other instructions and data required by the terminal device, and the memory may be used to temporarily store data that has been output or is to be output, which is not limited in this application.

Any charging station monitoring management method in the embodiment is stored in a memory of the terminal device through the terminal device, and is loaded and executed on a processor of the terminal device, so that the charging station monitoring management method is convenient to use.

The embodiment of the application also discloses a computer readable storage medium, and the computer readable storage medium stores computer instructions, wherein when the computer instructions are executed by a processor, any charging station monitoring and management method in the embodiment is adopted.

The computer instructions may be stored in a computer readable medium, where the computer instructions include computer instruction codes, where the computer instruction codes may be in a source code form, an object code form, an executable file form, or some middleware form, etc., and the computer readable medium includes any entity or device capable of carrying the computer instruction codes, a recording medium, a usb disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, etc., where the computer readable medium includes but is not limited to the above components.

Any one of the charging station monitoring management methods in the above embodiments is stored in the computer readable storage medium through the present computer readable storage medium, and is loaded and executed on a processor, so as to facilitate storage and application of the method.

The foregoing are all preferred embodiments of the present application, and are not intended to limit the scope of the present application in any way, therefore: all equivalent changes in structure, shape and principle of this application should be covered in the protection scope of this application.

Claims

1. The charging station monitoring and managing method is characterized by comprising the following steps of:

2. The charging station monitoring management method according to claim 1, wherein if the target monitoring set is a user monitoring set, analyzing various user monitoring data in the user monitoring set according to a preset user data monitoring standard, and generating a corresponding user behavior analysis result comprises the following steps:

3. The charging station monitoring and management method according to claim 1, wherein establishing a corresponding user behavior prediction classification model according to the user behavior analysis result, and outputting a corresponding user behavior optimization management policy comprises the following steps:

4. A charging station monitoring management method according to claim 3, wherein formulating the corresponding user behavior optimization management policy according to the behavior classification prediction result comprises the steps of:

5. The charging station monitoring management method according to claim 1, further comprising the steps of, if the target monitoring set is a server monitoring set, determining whether the device monitoring data in the server monitoring set meets a corresponding preset operation monitoring standard:

6. The charging station monitoring and management method according to claim 1, further comprising the steps of, after performing repair management on the target abnormal event according to the device repair management policy:

7. The charging station monitoring and management method according to claim 6, further comprising the steps of, after importing the device repair management policy into a preset automated repair decision model and outputting a repair record corresponding to the target abnormal event:

8. A charging station monitoring management system, comprising:

the monitoring module (1) is used for acquiring charging station monitoring data and dividing the charging station monitoring data into corresponding target monitoring sets according to preset monitoring data classification standards;

the user behavior analysis module (2) is used for analyzing various user monitoring data in the user side monitoring set according to a preset user data monitoring standard and generating a corresponding user behavior analysis result if the target monitoring set is the user side monitoring set;

the user behavior optimization module (3) is used for establishing a corresponding user behavior prediction classification model according to the user behavior analysis result and outputting a corresponding user behavior optimization management strategy;

the user side management module (4) is used for carrying out optimization management on the target user according to the user behavior optimization management strategy;

The server-side data analysis module (5), if the target monitoring set is a server-side monitoring set, the server-side data analysis module (5) is used for judging whether the equipment monitoring data in the server-side monitoring set accords with the corresponding preset operation monitoring standard;

the same-type abnormal matching module (6) is used for acquiring corresponding abnormal monitoring data and matching corresponding target abnormal events and a same-type abnormal event set corresponding to the target abnormal events from a preset abnormal event library according to the abnormal characteristics of the abnormal monitoring data if the equipment monitoring data in the server monitoring set do not accord with the corresponding preset operation monitoring standard;

the abnormal repair ordering module (7) is used for acquiring the repair coefficient of each abnormal event corresponding to the repair strategy in the abnormal event set, and generating the repair ordering corresponding to the target abnormal event as an equipment repair management strategy by combining the repair strategy and the repair coefficient;

and the server management module (8) is used for carrying out repair management on the target abnormal event according to the equipment repair management strategy.

9. A terminal device comprising a memory and a processor, wherein the memory has stored therein computer instructions executable on the processor, and wherein the processor, when loaded and executing the computer instructions, employs a charging station monitoring management method according to any one of claims 1 to 7.

10. A computer readable storage medium having stored therein computer instructions, wherein the computer instructions, when loaded and executed by a processor, employ a charging station monitoring management method according to any one of claims 1 to 7.