CN117853264A - 3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium - Google Patents
3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium Download PDFInfo
- Publication number
- CN117853264A CN117853264A CN202311151204.0A CN202311151204A CN117853264A CN 117853264 A CN117853264 A CN 117853264A CN 202311151204 A CN202311151204 A CN 202311151204A CN 117853264 A CN117853264 A CN 117853264A
- Authority
- CN
- China
- Prior art keywords
- site
- data
- score
- station
- power exchange
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000003066 decision tree Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000002131 composite material Substances 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013480 data collection Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 description 8
- 238000003745 diagnosis Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a 3D city insight and pushing method, a device and a storage medium of a two-wheel vehicle battery exchange station, and the method, the device and the storage medium are used for collecting operation data and Internet of things data of the two-wheel vehicle battery exchange station; analyzing and calculating the data to obtain operation characteristic data of the power exchange station, and reflecting the problem characteristics of the power exchange station according to the operation characteristic data; acquiring the running condition, problem distribution and influence range of each power conversion station in an intuitive manner through the 3D city model display of the operation characteristic data and problem state of the power conversion station; extracting features according to operation feature data of the power exchange station and the reflected problems, calculating risk scores of all stations, and determining priority ranking of risk stations according to the obtained risk scores; and sending early warning notification for processing related site problems to the corresponding site responsible person according to the priority order of the sites. The invention has the functions of real-time insight, risk early warning, intelligent sorting and instant pushing aiming at the power exchange station, and improves the operation management level and decision making capability of the station.
Description
Technical Field
The invention belongs to the technical field of two-wheel vehicle power exchange, and particularly relates to a 3D city insight and pushing method and device of a two-wheel vehicle power exchange station and a storage medium.
Background
At present, the power exchange industry of the two-wheel vehicle is rapidly developed, but a plurality of problems still face in the operation and management process. And the application of new technologies such as big data and artificial intelligence provides new possibilities for solving the problems. Therefore, the technical scheme aims to provide a system based on big data and a rule engine, and the system is combined with a 3D city insight and pushing system so as to improve operation management and decision making processes of the two-wheel vehicle battery replacement industry.
Disclosure of Invention
The invention aims to: in order to overcome the defects in the prior art, the invention provides the 3D city insight and pushing method, the device and the storage medium of the two-wheel vehicle power exchange station, which have the functions of real-time insight, risk early warning, intelligent sequencing and instant pushing aiming at the power exchange station, and improve the operation management level and decision making capability of the station.
The technical scheme is as follows: in order to achieve the above object, the 3D city insight and pushing method of the two-wheel vehicle battery exchange station of the present invention includes:
collecting operation data and Internet of things data of a two-wheel vehicle power exchange station, wherein the operation data and Internet of things data comprise station data, power exchange cabinet data of the station and battery data of the power exchange cabinet;
analyzing and calculating the collected data based on a rule engine algorithm of the power exchange station to obtain operation characteristic data of the power exchange station, and reflecting problem characteristics of the power exchange station according to the operation characteristic data so as to perform early warning and processing on problems existing in the operation process of the station;
transmitting the operation characteristic data of the power exchange station and the problem state corresponding to the reflected problem characteristic to a 3D platform through an interface, and acquiring the operation condition, problem distribution and influence range of each power exchange station in an intuitive mode through the 3D city model display of the operation characteristic data and the problem state of the power exchange station;
carrying out algorithm feature extraction according to operation feature data of the power exchange station and the reflected problems, carrying out risk score calculation on each station, and determining priority ranking of risk stations according to the obtained risk score;
and sending early warning notification for processing related site problems to the corresponding site responsible person according to the priority order of the sites.
Further, the operation characteristic data of the power exchange station comprises the number of offline cabinets, the number of unavailable batteries, the ratio of available batteries, the number of idle and to-be-recovered batteries in a recent cabinet, the recent average electric quantity lack, the number of times of restarting the recent power exchange cabinet, the ineffective power exchange duty ratio, the recent average power exchange duration, the customer complaint amount and the today abnormal battery rate.
Further, the steps of calculating and sequencing the site problem risk score are as follows:
s1: feature importance analysis was performed using the XGboost model: the importance scores of the features of the site are calculated through gain in a tree model, the XGboost model comprises N decision trees, each decision tree is used for predicting the comprehensive score of the site problem, and the average gain of each feature in the decision tree is calculated as the importance score, as follows:
s1.1: for each feature of each decision tree, calculating the gain of the feature, and setting the gain of the feature i on the j-th decision tree as g (i, j);
s1.2: for each feature i, summing its gains in all decision trees to obtain a total gain:
s1.3: the total gain for each feature is divided by the total gain for all features to obtain a relative importance score fi (i) for the feature:
wherein: m represents the total number of site features;
s2: correlation of problem indicators with features: analyzing the importance and historical data of the features, determining the relevance of each problem index and the site integrated score, helping to understand the influence of each problem index on the site integrated score, and measuring the relevance between each problem index and the site integrated score by using pearson correlation coefficients:
wherein: x is x i The value of the problem index i is indicated,mean value, y of the problem index i i A value representing a site composite score,means for representing a site composite score;
and obtaining the degree of correlation between the problem index and the site integrated score by calculating the pearson correlation coefficient of each problem index and the site integrated score:
if the correlation coefficient is close to 1 or-1, the problem index has linear correlation to the site composite score;
if the correlation coefficient is close to 0, the problem index has no linear correlation to the site composite score;
s3: weight distribution: the feature importance score fi (i) and the association coefficient r of the problem index and the feature are calculated based on the XGboost model, so that weights of different indexes are obtained to reflect the contribution degree of each index to the problem of the site;
s4: calculating a comprehensive score of the problem: according to the calculated weight and the historical data of the problem index, calculating a problem comprehensive score of each site representing the risk level of the site, wherein the problem comprehensive score is as follows:
s4.1: for each problem index i, normalize the original value to [0,1]Within range i nom ：
Wherein: i is a problem index of the site, min_value i And max_value i The minimum value and the maximum value of the problem index i are respectively;
s4.2: multiplying the normalized problem index by a corresponding weight W i And adding to obtain the comprehensive score of the problems of the sites:
S f ＝w1*1 nom +w2*2 nom +...+w i *i nom
s5: and (5) sequencing the sites: according to the comprehensive question score S f Sequencing stations from high to low to obtain a station list with the risk degree from high to low;
s6: real-time application: the site problem risk score calculation and ranking model is embedded into the real-time data stream to calculate the site problem comprehensive score in real time, thereby providing real-time site risk ranking.
Further, the step of sending the early warning notification to the site responsible person is as follows:
step one: the analyzed site data is sent to a message center in a JDBC mode;
step two: after receiving the data generated by the message center, judging whether an early warning short message needs to be sent or not according to the site priority strategy;
step three: aiming at a website conforming to the early warning rule, the pushing system acquires corresponding responsible person information through website information, and selects a corresponding short message template according to priority to push to the responsible person;
step four: aiming at the stations without early warning, the pushing system does not process.
The device is used for realizing a 3D city insight and pushing method of a two-wheel vehicle battery exchange station, and comprises the following steps:
and a data collection module: the method comprises the steps of collecting operation data and Internet of things data of a power conversion station;
and a data processing module: the system is used for carrying out feature engineering processing, analysis and calculation on the collected data;
and the data execution module is used for: and pushing the early warning notice.
The storage medium stores an executable program, and the executable program is executed by the processor to realize the 3D city insight and pushing method of the two-wheel vehicle battery exchange station.
The beneficial effects are that: the invention has real-time insight, risk early warning, intelligent sorting and instant pushing functions aiming at the power exchange site, wherein: through the real-time data collection and analysis of the system, a decision maker can know the operation state and problem condition of a site in real time and take measures to deal with in time; the rule engine can pre-warn the possible problems in operation according to preset rules and algorithms, so that a decision maker can be helped to adjust the operation strategy in time, and the risk is reduced; through calculation and sequencing of the algorithm engine, reasonable problem priority can be provided for decision makers, so that the decision makers can be helped to more effectively process problems and allocate resources; through the short message pushing of the message center, the site responsible person can be timely notified and reminded of related problems, so that the site responsible person can quickly take actions, and the site operation efficiency is improved.
Drawings
FIG. 1 is a schematic overall flow diagram of the present invention;
FIG. 2 is a schematic diagram of a data collection flow;
FIG. 3 is a schematic flow chart of the operation data and problem state obtained by calculation being transmitted to a 3D platform through an interface to realize display and map modeling;
FIG. 4 is a 3D site diagnosis schematic diagram of the problem synthesis score;
FIG. 5 is a 3D site diagnosis schematic diagram of average power deficiency;
FIG. 6 is a 3D diagnostic schematic of average power-on duration;
fig. 7 is a schematic diagram of an early warning notification pushing flow.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
As shown in fig. 1, the 3D city insight and pushing method of the two-wheel vehicle power exchange station comprises the following steps:
and collecting operation data and Internet of things data of a two-wheel vehicle power exchange station, wherein the operation data and Internet of things data comprise station data, power exchange cabinet data of the station and battery data of the power exchange cabinet.
As shown in fig. 2, the data collection steps are as follows:
step one: business side dimension information is extracted and updated to a data mart through Mysql JDBC every day in an offline mode, for example: information such as a site;
step two: the dimension information is accessed through the Flink Table API and updated to Redis, so that dimension information sharing is realized, and service complexity and cost are reduced;
step three: service side change data (including battery change in a cabinet, user power change orders and the like) are captured through binlog, and real-time updating and writing of the data marts are realized through association with Redis cache data.
And analyzing and calculating the collected data based on a rule engine algorithm of the power exchange station to obtain operation characteristic data of the power exchange station, and reflecting problem characteristics of the power exchange station according to the operation characteristic data so as to perform early warning and processing on problems existing in the operation process of the station.
The operation characteristic data of the power exchange station comprise the number of offline cabinets, the number of unavailable batteries, the proportion of available batteries, the number of idle and to-be-recovered batteries in a recent cabinet, the recent average power shortage quantity, the number of restarting the recent power exchange cabinet, the ineffective power exchange duty ratio, the recent average power exchange duration, the customer complaint quantity of users and the today abnormal battery rate, and the specific calculation mode is as follows:
1) Number of off-line cabinets: get a battery cabinet C i ，i∈(1，..., n), the last heartbeat report of the battery-changing cabinet is defined ast last Defined as the last time reported, the threshold value is defined as Z threshold When t now -t last ≥Z threshold Defining that the electric cabinet is offline;
the number of the off-line electric cabinets today is calculated as:
2) Number of unavailable batteries: unusable battery definitionForbidden battery is defined as +.>The uncharged cell is defined as->i represents the cabinet number;
the battery charge is defined as Q, and the number of unusable batteries in the cabinet is calculated as:
3) Available battery proportion alpha total-available : the number of rentals of a cabinet is defined asThe number of batteries in the cabinet is defined asThe number of all unavailable batteries in the cabinet is defined as +.>i represents the cabinet number;
the battery proportions available today are calculated as:
4) The number of idle and recovered batteries in the recent cabinet: defining the average number of people who change electricity of each electricity changing cabinet recently ast represents the number of days in which the average value is continuously calculated, and the fluctuation of the number of recent battery changers is defined as +.>The available battery in the cabinet is proportioned as above and defined as alpha total-available The number of batteries in the cabinet is beta;
when (when)When the battery in the cabinet needs to be recovered;
when (when)When the battery in the cabinet is needed to be distributed;
the recovery and distribution amounts were calculated as:
5) Recent average lack of electricity: define the power take-out asThe number of times of removal is defined as +.> i represents each power-on time, and t represents the number of days in the near future;
the recent average electricity deficiency is calculated as:
6) The number of restarting of the recent power change cabinet: defining the restarting times of the cabinet ast is the number of days to be continuously calculated, and the number of recent restarting is calculated as follows:
7) Ineffective power-change duty ratio: the user power-on and power-off interval is defined as deltat=t put -t take The effective power change is defined as S valid ＝S Δt＞180s The invalid commutation duty cycle is calculated as:
100-S valid /S total *100％
8) Average recent power change time period: defining the code scanning time of each power conversion of a user as t scan The power-changing and power-taking time is t take The extraction time interval is Δt=t take -t scan The number of times of removal is defined as T i I epsilon (1, …, n), i represents power taking each time;
the recent average power change time length is calculated as:
9) Recent customer complaints: defining the customer complaint quantity of the user as F t T e (1., n), t is the number of days to be calculated continuously, and the recent customer complaint is calculated as:
Count F t
10 Today abnormal battery rate: define the last internal personnel circulation time t of the battery move Battery no-flow days define Δt=t now -t move The out-of-cabinet battery is defined asThe total battery is defined as +.>i e (1, n), i represents the cabinet number；
The abnormal battery rate today is calculated as:
the operation characteristic data of the power exchange station obtained through calculation and the problem state corresponding to the reflected problem characteristic are transmitted to the 3D platform through an interface, the operation condition, the problem distribution and the influence range of each power exchange station are obtained in an intuitive mode through the operation characteristic data of the power exchange station and the 3D city model display of the problem state, as shown in fig. 4, 5 and 6, each columnar graph in the graph represents a station with a risk problem, the higher the height of the columnar graph is, the higher the score of each problem is, the higher the risk degree of each columnar graph is, and of course, different colors can be rendered for each columnar graph according to the risk degree to distinguish more intuitively.
As shown in fig. 3, the following is provided in the software operation interface:
1. drop-down list box for providing selected city, region and business person, operation mode and inquiry button
2. Initiating a joint query: selecting specific cities, areas and business responsible persons through a drop-down list box on the page, clicking a query button, and triggering joint query operation;
3. joint query results: displaying asset information, asset risk, operation overview, user experience and site diagnosis and analysis report information obtained by joint query in a form of a table or a chart on a page;
4. selecting a diagnosis index: providing options for selecting different diagnosis indexes on a page, scoring comprehensive problems, offline battery changing cabinets, unavailable battery numbers, unavailable battery duty ratio and the like;
5. initiating a site query: triggering the operation of inquiring the specific index through the option of selecting the diagnostic index on the page;
6. site query results: the queried distribution and use of cabinets and batteries under each site are displayed in a 3D model of a page (using echartis) in offline and online conditions, and the running condition, problem distribution and possible influence range of each site are highlighted;
7. data statistics: the data statistics options are provided on the page, and data summarization and analysis can be performed according to different dimensions, so that a user is helped to know the overall operation condition and problem condition.
And carrying out algorithm feature extraction according to the operation feature data of the power exchange station and the reflected problems, carrying out risk score calculation on each station, and determining the priority order of the risk stations according to the obtained risk score.
S1: feature importance analysis was performed using the XGboost model: the importance scores of the features of the site are calculated through gain in a tree model, the XGboost model comprises N decision trees, each decision tree is used for predicting the comprehensive score of the site problem, and the average gain of each feature in the decision tree is calculated as the importance score, as follows:
s1.1: for each feature of each decision tree, calculating the gain of the feature, and setting the gain of the feature i on the j-th decision tree as g (i, j);
s1.2: for each feature i, summing its gains in all decision trees to obtain a total gain:
s1.3: the total gain for each feature is divided by the total gain for all features to obtain a relative importance score fi (i) for the feature:
wherein: m represents the total number of site features;
s2: correlation of problem indicators with features: analyzing the importance and historical data of the features, determining the relevance of each problem index and the site integrated score, helping to understand the influence of each problem index on the site integrated score, and measuring the relevance between each problem index and the site integrated score by using pearson correlation coefficients:
wherein: x is x i The value of the problem index i is indicated,mean value, y of the problem index i i A value representing a site composite score,means for representing a site composite score;
and obtaining the degree of correlation between the problem index and the site integrated score by calculating the pearson correlation coefficient of each problem index and the site integrated score:
if the correlation coefficient is close to 1 or-1, the problem index has linear correlation to the site composite score;
if the correlation coefficient is close to 0, the problem index has no linear correlation to the site composite score;
s3: weight distribution: the feature importance score fi (i) and the association coefficient r of the problem index and the feature are calculated based on the XGboost model, so that weights of different indexes are obtained to reflect the contribution degree of each index to the problem of the site;
s4: calculating a comprehensive score of the problem: according to the calculated weight and the historical data of the problem index, calculating a problem comprehensive score of each site representing the risk level of the site, wherein the problem comprehensive score is as follows:
s4.1: for each problem index i, normalize the original value to [0,1]Within range i nom ：
Wherein: i is a problem index of the site, min_value i And max_value i The minimum value and the maximum value of the problem index i are respectively;
s4.2: the problem of normalization is referred to asMultiplying by corresponding weights W i And adding to obtain the comprehensive score of the problems of the sites:
S f ＝w1*1 nom +w2*2 nom +…+w i *i nom
s5: and (5) sequencing the sites: according to the comprehensive question score S f Sequencing stations from high to low to obtain a station list with the risk degree from high to low;
s6: real-time application: the site problem risk score calculation and ranking model is embedded into the real-time data stream to calculate the site problem comprehensive score in real time, thereby providing real-time site risk ranking.
And sending early warning notification for processing related site problems to the corresponding site responsible person according to the priority order of the sites.
As shown in fig. 7, the steps for sending the early warning notification to the site responsible person are as follows:
step one: the analyzed site data is sent to a message center in a JDBC mode;
step two: after receiving the data generated by the message center, judging whether an early warning short message needs to be sent or not according to the site priority strategy;
step three: aiming at a website conforming to the early warning rule, the pushing system acquires corresponding responsible person information through website information, and selects a corresponding short message template according to priority to push to the responsible person;
step four: aiming at the stations without early warning, the pushing system does not process.
The device is used for realizing a 3D city insight and pushing method of a two-wheel vehicle battery exchange station, and comprises the following steps:
and a data collection module: the method comprises the steps of collecting operation data and Internet of things data of a power conversion station;
and a data processing module: the system is used for carrying out feature engineering processing, analysis and calculation on the collected data;
and the data execution module is used for: and pushing the early warning notice.
The storage medium stores an executable program, and the executable program is executed by the processor to realize the 3D city insight and pushing method of the two-wheel vehicle battery exchange station.
The invention has the following advantages:
(1) Real-time insight: through the real-time data collection and analysis of the system, a decision maker can know the operation state and problem condition of a site in real time and take measures to deal with in time;
(2) Risk early warning: the rule engine can pre-warn the possible problems in operation according to preset rules and algorithms, so that a decision maker can be helped to adjust the operation strategy in time, and the risk is reduced;
(3) Intelligent sequencing: through calculation and sequencing of the algorithm engine, reasonable problem priority can be provided for decision makers, so that the decision makers can be helped to more effectively process problems and allocate resources;
(4) Instant pushing: through the short message pushing of the message center, the site responsible person can be timely notified and reminded of related problems, so that the site responsible person can quickly take actions, and the site operation efficiency is improved.
In conclusion, the 3D urban insight and pushing scheme provided by the invention has the effects of providing real-time insight, risk early warning, intelligent sorting and instant pushing in the two-wheel vehicle power conversion industry, and has important significance in improving the operation management level and decision making capability.
The foregoing is only a preferred embodiment of the invention, it being noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (6)
1. The 3D city insight and pushing method of the two-wheel vehicle power exchange station is characterized by comprising the following steps of: comprising the following steps:
collecting operation data and Internet of things data of a two-wheel vehicle power exchange station, wherein the operation data and Internet of things data comprise station data, power exchange cabinet data of the station and battery data of the power exchange cabinet;
analyzing and calculating the collected data based on a rule engine algorithm of the power exchange station to obtain operation characteristic data of the power exchange station, and reflecting problem characteristics of the power exchange station according to the operation characteristic data so as to perform early warning and processing on problems existing in the operation process of the station;
transmitting the operation characteristic data of the power exchange station and the problem state corresponding to the reflected problem characteristic to a 3D platform through an interface, and acquiring the operation condition, problem distribution and influence range of each power exchange station in an intuitive mode through the 3D city model display of the operation characteristic data and the problem state of the power exchange station;
carrying out algorithm feature extraction according to operation feature data of the power exchange station and the reflected problems, carrying out risk score calculation on each station, and determining priority ranking of risk stations according to the obtained risk score;
and sending early warning notification for processing related site problems to the corresponding site responsible person according to the priority order of the sites.
2. The 3D city insight and pushing method of a two-wheeled vehicle battery exchange station of claim 1, wherein: the operation characteristic data of the power exchange station comprises the number of offline cabinets, the number of unavailable batteries, the proportion of available batteries, the number of idle and to-be-recovered batteries in a recent cabinet, the recent average power shortage quantity, the number of restarting the recent power exchange cabinet, the ineffective power exchange duty ratio, the recent average power exchange duration, the customer complaint quantity of users and the today abnormal battery rate.
3. The 3D city insight and pushing method of a two-wheeled vehicle battery exchange station of claim 1, wherein: the steps of calculating and sequencing the site problem risk score are as follows:
s1: feature importance analysis was performed using the XGboost model: the importance scores of the features of the site are calculated through gain in a tree model, the XGboost model comprises N decision trees, each decision tree is used for predicting the comprehensive score of the site problem, and the average gain of each feature in the decision tree is calculated as the importance score, as follows:
s1.1: for each feature of each decision tree, calculating the gain of the feature, and setting the gain of the feature i on the j-th decision tree as g (i, j);
s1.2: for each feature i, summing its gains in all decision trees to obtain a total gain:
s1.3: the total gain for each feature is divided by the total gain for all features to obtain a relative importance score fi (i) for the feature:
wherein: m represents the total number of site features;
s2: correlation of problem indicators with features: analyzing the importance and historical data of the features, determining the relevance of each problem index and the site integrated score, helping to understand the influence of each problem index on the site integrated score, and measuring the relevance between each problem index and the site integrated score by using pearson correlation coefficients:
wherein: x is x i The value of the problem index i is indicated,mean value, y of the problem index i i Value representing site composite score,/->Means for representing a site composite score;
and obtaining the degree of correlation between the problem index and the site integrated score by calculating the pearson correlation coefficient of each problem index and the site integrated score:
if the correlation coefficient is close to 1 or-1, the problem index has linear correlation to the site composite score;
if the correlation coefficient is close to 0, the problem index has no linear correlation to the site composite score;
s3: weight distribution: the feature importance score fi (i) and the association coefficient r of the problem index and the feature are calculated based on the XGboost model, so that weights of different indexes are obtained to reflect the contribution degree of each index to the problem of the site;
s4: calculating a comprehensive score of the problem: according to the calculated weight and the historical data of the problem index, calculating a problem comprehensive score of each site representing the risk level of the site, wherein the problem comprehensive score is as follows:
s4.1: for each problem index i, normalize the original value to [0,1]Within range i nom ：
Wherein: i is a problem index of the site, min_value i And max_value i The minimum value and the maximum value of the problem index i are respectively;
s4.2: multiplying the normalized problem index by the corresponding weight w i And adding to obtain the comprehensive score of the problems of the sites:
S f ＝w1*1 nom +w2*2 nom +…+w i *i nom
s5: and (5) sequencing the sites: according to the comprehensive question score S f Sequencing stations from high to low to obtain a station list with the risk degree from high to low;
s6: real-time application: the site problem risk score calculation and ranking model is embedded into the real-time data stream to calculate the site problem comprehensive score in real time, thereby providing real-time site risk ranking.
4. The 3D city insight and pushing method of a two-wheeled vehicle battery exchange station of claim 1, wherein: the step of sending the early warning notice to the site responsible person is as follows:
step one: the analyzed site data is sent to a message center in a JDBC mode;
step two: after receiving the data generated by the message center, judging whether an early warning short message needs to be sent or not according to the site priority strategy;
step three: aiming at a website conforming to the early warning rule, the pushing system acquires corresponding responsible person information through website information, and selects a corresponding short message template according to priority to push to the responsible person;
step four: aiming at the stations without early warning, the pushing system does not process.
5. The device is used for realizing the 3D city insight and pushing method of the two-wheel vehicle power exchange station according to any one of claims 1 to 4, and is characterized in that: comprising the following steps:
and a data collection module: the method comprises the steps of collecting operation data and Internet of things data of a power conversion station;
and a data processing module: the system is used for carrying out feature engineering processing, analysis and calculation on the collected data;
and the data execution module is used for: and pushing the early warning notice.
6. A storage medium, characterized in that: an executable program is stored in the electric power station, and the executable program is executed by a processor to realize the 3D city insight and pushing method of the two-wheel vehicle power station according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311151204.0A CN117853264A (en) | 2023-09-07 | 2023-09-07 | 3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311151204.0A CN117853264A (en) | 2023-09-07 | 2023-09-07 | 3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117853264A true CN117853264A (en) | 2024-04-09 |
Family
ID=90546578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311151204.0A Pending CN117853264A (en) | 2023-09-07 | 2023-09-07 | 3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117853264A (en) |
-
2023
- 2023-09-07 CN CN202311151204.0A patent/CN117853264A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103577883A (en) | Grid-load intelligent interaction method and device | |
| CN111080101A (en) | AHP-based multi-dimensional evaluation method for service efficiency of power supply channel | |
| CN111461521A (en) | Residential housing vacancy rate analysis method based on electric power big data | |
| WO2023065760A1 (en) | Method and apparatus for predicting quantity of scrapped global traction batteries | |
| CN116011827B (en) | Power failure monitoring analysis and early warning system and method for key cells | |
| CN111552686B (en) | Power data quality assessment method and device | |
| CN115271415A (en) | Intelligent community service management system | |
| CN115600824A (en) | Early warning method and device for carbon emission, storage medium and electronic equipment | |
| CN115099444A (en) | Hospital reservation background service system | |
| CN114819680A (en) | Enterprise health degree evaluation model construction method and system and storage medium | |
| CN106997371A (en) | The construction method of single user wisdom collection of illustrative plates | |
| CN117853264A (en) | 3D city insight and pushing method and device of two-wheel vehicle battery replacement station and storage medium | |
| CN116881535A (en) | Public opinion comprehensive supervision system with timely early warning function | |
| CN113157521A (en) | Monitoring method and monitoring system for whole life cycle of block chain | |
| CN116993227A (en) | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence | |
| CN112052283A (en) | Information consultation service platform based on big data analysis and collection | |
| CN117056591A (en) | Intelligent electric power payment channel recommendation method and system based on dynamic prediction | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| CN201266951Y (en) | Equipment for implementing automatic collection and automatic diagnosis of river health data | |
| CN114639484A (en) | System and method for analyzing community population mobility condition based on electric power big data | |
| CN115203545A (en) | Health maintenance service intelligent matching method and system based on deep learning and knowledge graph | |
| CN114077977A (en) | Building intelligent management method and system based on big data and readable storage medium | |
| Mao et al. | Elevator fault diagnosis and maintenance method based on Internet of Things | |
| CN114912846B (en) | Comprehensive energy customer value mining energy efficiency evaluation method and device for online learning | |
| CN115963408B (en) | Energy storage power station single battery fault early warning system and method |
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 |