Charging station data analysis method, device, equipment, medium and program product

Abstract

The invention relates to a charging station data analysis method, device and equipment, a medium and a program product. The method comprises the following steps: firstly, acquiring target data including data of a charging station in a preset period and data of different business dimensions of the charging station, determining initial statistical data according to the target data, then determining to-be-concerned data in the target data according to the initial statistical data, and determining the to-be-concerned data in the target data according to the contribution degree of the to-be-concerned data. And determining a first data analysis result of the charging station. By adopting the method, the data analysis result of the charging station can be automatically determined through the target data of the charging station, manual analysis processing is not needed, and the efficiency is higher.

Description

Technical Field

[0001] The present application relates to the technical field of charging stations, and in particular, to a method, device, equipment, medium, and program product for analyzing charging station data. Background Art

[0002] With the development of new energy technologies and the continuous promotion of the concepts of environmental protection and low-carbon life, the market share of new energy vehicles has been increasing year by year. Compared with traditional vehicles, new energy vehicles are cleaner and more environmentally friendly, and have a broader development future. As the infrastructure for new energy vehicles, charging stations play an important role in promoting the popularization and development of new energy vehicles. As an emerging industry, in order to achieve intelligent management of charging stations, it is necessary to perform data analysis on the data of charging stations.

[0003] However, currently, the data analysis of charging stations is generally carried out by staff analyzing historical data, with low efficiency. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, equipment, medium, and program product for analyzing charging station data with higher efficiency.

[0005] In a first aspect, the present application provides a method for analyzing charging station data, including: obtaining target data, where the target data includes data within a preset period of the charging station and data in different business dimensions of the charging station; determining initial statistical data based on the target data; determining data to be concerned in the target data according to the initial statistical data; and determining a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

[0006] In one embodiment, determining the data to be concerned in the target data according to the initial statistical data includes: calculating the difference data between the initial statistical data and the historical statistical data; and determining the data to be concerned in the target data according to the fluctuation value of the difference data.

[0007] In one embodiment, the method further includes: obtaining associated data of the charging station; determining the association relationship between the associated data and the total order resources of the charging station; and determining a second data analysis result of the charging station according to the association relationship.

[0008] In one embodiment, the method further includes: performing linear fitting on the initial statistical data of the charging station to determine a linear fitting result; and determining a third data analysis result of the charging station according to the linear fitting result.

[0009] In one embodiment, the method further includes: calculating the standard deviation of the initial statistical data of the charging station to determine a standard deviation calculation result; and determining a fourth data analysis result of the charging station according to the standard deviation calculation result.

[0010] In one embodiment, the method further includes: obtaining operation data of a charging station; determining a fifth data analysis result of the charging station according to the operation data, and presenting the fifth data analysis result through an analysis report.

[0011] In one embodiment, the method further includes: obtaining a text request for the charging station input by a client; performing word segmentation processing on the text request to generate word vectors; determining data content corresponding to the text request according to the word vectors and a preset metadata mapping table; determining a text request result according to the data content, and returning the text request result to the client.

[0012] In one embodiment, the method further includes: determining whether there is abnormal data according to initial statistical data; if there is abnormal data, outputting a warning message.

[0013] In a second aspect, the present application further provides a charging station data analysis device, including:

[0014] An obtaining module, configured to obtain target data, where the target data includes data within a preset period of the charging station and data of different service dimensions of the charging station;

[0015] A first determining module, configured to determine initial statistical data according to the target data;

[0016] A second determining module, configured to determine data to be concerned in the target data according to the initial statistical data;

[0017] A third determining module, configured to determine a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

[0018] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the charging station data analysis method according to any one of the first aspects is implemented.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the charging station data analysis method according to any one of the first aspects is implemented.

[0020] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the charging station data analysis method according to any one of the first aspects is implemented.

[0021] The above-mentioned charging station data analysis method, device, equipment, medium, and program product. First, obtain target data including data within a preset period of the charging station and data in different business dimensions of the charging station, determine initial statistical data based on the target data, then, based on the initial statistical data, determine the data to be concerned in the target data, and determine the first data analysis result of the charging station according to the contribution degree of the data to be concerned. In this way, by obtaining the target data and then determining the initial statistical data, further determining the data to be concerned through the initial statistical data, calculating the contribution degree of the data to be concerned, and determining the first data analysis result of the charging station, it is possible to automatically determine the data analysis result of the charging station through the target data of the charging station, without the need for manual analysis and processing, and the efficiency is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of the charging station data analysis method in one embodiment;

[0024] Figure 2 It is a data processing flowchart of the charging station data analysis method in another embodiment;

[0025] Figure 3 It is a flowchart of the charging station data analysis method in another embodiment;

[0026] Figure 4 It is a flowchart for determining the data to be concerned in another embodiment;

[0027] Figure 5 It is a flowchart of the charging station data analysis method in another embodiment;

[0028] Figure 6 It is a flowchart of the charging station data analysis method in another embodiment;

[0029] Figure 7 It is a flowchart of the charging station data analysis method in another embodiment;

[0030] Figure 8 It is a flowchart of the charging station data analysis method in another embodiment;

[0031] Figure 9 It is a flowchart of the charging station data analysis method in another embodiment;

[0032] Figure 10 Flow chart for text request processing in another embodiment;

[0033] Figure 11 Schematic flow diagram of the charging station data analysis method in another embodiment;

[0034] Figure 12 Flow chart for abnormal data monitoring of the charging station in another embodiment;

[0035] Figure 13 Schematic diagram of the result of contribution degree calculation in another embodiment;

[0036] Figure 14 Structural block diagram of the charging station data analysis device in one embodiment;

[0037] Figure 15 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0038] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0039] In an exemplary embodiment, a charging station data analysis method is provided. Taking the application of this method to a server as an example for illustration, it can be understood that this method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0040] Step 101, obtain target data.

[0041] Among them, the target data includes the data of the charging station within a preset period and the data of different business dimensions of the charging station. The preset period can be a period set according to actual needs, which can be every day or every week, etc. In the embodiment of the present application, the data of the charging station within the preset period is obtained through the RDS (Relational Database Service) data table, the HIVE (data warehouse tool) dimension data table and the COOPER table document, the data of different business dimensions of the charging station is obtained through the HIVE fine-grained dimension data table, and the business rules are obtained through the HIVE business report. Optionally, the target data is obtained through a scheduled task or by listening to the Binlog (log file) event corresponding to the database.

[0042] Step 102, determine the initial statistical data according to the target data.

[0043] Optionally, the initial statistical data can be various statistical values of the target data, including the maximum value, the minimum value, or the average value, and can also include the summary data of the target data and the trend of the target data, etc. To improve the timeliness of data analysis, when determining the initial statistical data based on the target data, the overall market data can be quickly generated first, that is, the core indicator data is quickly output, and then, according to the business scenario used, the initial statistical data corresponding to the business is generated.

[0044] Step 103: Determine the data to be concerned about in the target data according to the initial statistical data.

[0045] In this embodiment, after obtaining the initial statistical data, the data to be concerned about in the target data is determined by performing logical processing on the initial statistical data. Optionally, the initial statistical data can be logically processed according to a preset time period such as daily, and through logical processing, the data to be concerned about in the target data is determined, where the data to be concerned about can be the data with abnormal index analysis in the target data determined during the logical processing process.

[0046] Step 104: Determine the first data analysis result of the charging station according to the contribution degree of the data to be concerned about.

[0047] Among them, in attribution analysis, it is usually necessary to determine the contribution degree of each factor, so as to determine the importance of different factors to the whole, so as to facilitate decision-making according to the analysis result. Therefore, after determining the data to be concerned about, calculate the contribution degree of the data to be concerned about. The contribution degree can be the contribution degree of the data to be concerned about to the total order resources of the charging station, or the contribution degree of the data to be concerned about to the superior index. Determine the first data analysis result of the charging station according to the contribution degree. Optionally, the first data analysis result can be recorded in the database.

[0048] Optionally, the process of obtaining the target data and determining the initial statistical data according to the target data is as Figure 2As shown in the figure. Obtain data within the preset period of the charging station from the RDS data table, the HIVE dimension data table, and the COOPER form document. Obtain data of different business dimensions of the charging station from the HIVE fine-grained dimension data table. Obtain business rules from the HIVE business report. Use the scheduled task or monitor the corresponding Binlog event of the database as the data source to collect daily data of the business. In the data processing part, process through HIVE, summarize and output through SPARK / FLINK (distributed computing framework), and summarize through HIVE. First, quickly calculate the core index data, namely the maximum and minimum values, the average value, the summary value, and the trend data. Then, match the summarized data with the dimension data to generate corresponding wide table data. Finally, according to the used business scenario, split the corresponding processing scenario item by item according to the business scenario, and obtain the business maximum and minimum values, the business summary value, the business average value, and the business trend data through the HIVE business. In the data output part, store the above data in databases such as RDS and CLICKHOUSE (analytical database). The stored data can be used for subsequent anomaly monitoring. In this way, the core data can be output quickly, while the fine-grained data needs to be statistically output for a long time. This can be applied to different clients respectively. For example, when the user needs to quickly view the core data, the user can view the core data through the APP side, and the analysis results of the specific fine-grained business data can be queried through the WEB side.

[0049] In this embodiment, first, obtain target data including data within the preset period of the charging station and data of different business dimensions of the charging station, determine the initial statistical data according to the target data, then, according to the initial statistical data, determine the data to be concerned in the target data, and determine the first data analysis result of the charging station according to the contribution degree of the data to be concerned. In this way, by obtaining the target data and then determining the initial statistical data, further determining the data to be concerned through the initial statistical data, calculating the contribution degree of the data to be concerned, and determining the first data analysis result of the charging station, it is possible to automatically determine the data analysis result of the charging station through the target data of the charging station without manual analysis and processing, and the efficiency is higher.

[0050] In one embodiment, the step of determining the data to be concerned in the target data in step 103 is as Figure 3 shown and includes:

[0051] Step 301, calculate the difference data between the initial statistical data and the historical statistical data.

[0052] Among them, the target data may include multiple index values, determine the initial statistical data corresponding to each index value, and the difference data may be the year-on-year value or the month-on-month value of the initial statistical data corresponding to each index data and the historical statistical data.

[0053] Step 302: determine the data to be paid attention to in the target data according to the fluctuation value of the difference data.

[0054] Determine the data to be concerned among the multiple indicator values ​​of the target data according to the fluctuation value of the difference data. The data to be concerned may be indicator data whose fluctuation value exceeds a preset threshold, such as 10%. Optionally, the process of determining the data to be concerned is as follows: Figure 4 shown.

[0055] Analyze the initial statistical data through scheduled tasks. First, obtain the list of indicators to be monitored, obtain the data of the previous day, the same day of the previous week, and the same day of the previous two weeks in the indicator list, and then calculate the difference data such as the previous day's month-on-month, week-on-week, and week-on-week, to determine whether the indicator data in the indicator list has been analyzed. If the analysis is completed and the watch list is empty, the analysis ends. If the analysis is completed and the watch list is not empty, calculate the contribution of the indicator to the total order resource volume and the contribution to the superior indicator, and then record the contribution in the database to end.

[0056] If the indicator data analysis is not completed, determine whether the current indicator fluctuation value to be analyzed exceeds 10%. If not, return to continue to determine whether the indicator data analysis is completed. If exceeded, record the indicator name in the watch list, that is, determine it as the data to be watched, and continue to return to determine whether the indicator data analysis is completed.

[0057] In one embodiment, the data analysis of the charging station may also include a logistic regression method, such as Figure 5 As shown, the method also includes:

[0058] Step 501, obtaining the associated data of the charging station.

[0059] Among them, the associated data is data that is associated with the total order resource volume of the charging station, such as whether there are shopping malls, convenience stores, restaurants, fast-gun stations, or slow-gun stations around the charging station. These data all have a certain impact on the total order resource volume of the charging station.

[0060] Step 502: Determine the association relationship between the associated data and the total resource quantity of the order of the charging station.

[0061] Optionally, the total order resource quantity may be the total order amount. In order to determine the correlation between the associated data and the total order resource quantity of the charging station, the associated data may be used as an independent variable and the total order amount as a dependent variable. The correlation between the total order amount and the associated data may be determined through the Imperial Capital Descent Algorithm.

[0062] Step 503: Determine a second data analysis result of the charging station according to the association relationship.

[0063] According to the association relationship, the second data analysis result of the charging station is determined. The second analysis result is the analysis result of the association relationship with the total order amount determined according to the label of the charging station, that is, the associated data, so that decision-making guidance can be provided for each charging station according to the label.

[0064] In one embodiment, the data analysis of the charging station may further include the method of linear regression. For example, Figure 6 As shown, the method further includes:

[0065] Step 601, perform linear fitting on the initial statistical data of the charging station to determine the linear fitting result.

[0066] In this embodiment, using linear regression, for some charging stations in short-term operation, through linear fitting, the initial statistical data of newly built charging stations, such as those with a construction time less than 6 months, are linearly fitted. Then, by comparing the fitting coefficient with the deviation value, that is, the difference, of the actual operation situation of the charging station, the linear fitting result is obtained.

[0067] Step 602, determine the third data analysis result of the charging station according to the linear fitting result.

[0068] According to the linear fitting result, the third data analysis result of the charging station is determined. According to the third data analysis result, the operation status of the charging station can be judged, and key monitoring is carried out on the charging stations with too large deviation values determined by the third data analysis result, and the operation merchants of the relevant charging stations are reminded to handle them.

[0069] In one embodiment, the data analysis of the charging station may further include the method of standard deviation analysis. For example, Figure 7 As shown, the method further includes:

[0070] Step 701, calculate the standard deviation of the initial statistical data of the charging station to determine the standard deviation calculation result.

[0071] Optionally, when some charging stations have been in operation for a long time, such as more than 6 months, it can be considered that the charging station is a relatively mature station, and the standard deviation of the initial statistical data of the charging station is calculated to determine the standard deviation calculation result.

[0072] Step 702, determine the fourth data analysis result of the charging station according to the standard deviation calculation result.

[0073] Optionally, by calculating the standard deviation of the initial statistical data of different charging stations, the corresponding standard deviation calculation results are obtained, so as to determine the fourth data analysis result. For example, when the average order price in a certain area is determined to be 0.5 and the standard deviation is 0.1, taking 0.1 / 2 = 0.05, that is, within one standard deviation range, the charging stations with the standard deviation calculation results within the average value of 0.45 - 0.55 are determined to be relatively normal, and the charging stations with the standard deviation calculation results exceeding the standard deviation range may have certain problems.

[0074] In this embodiment, the charging stations with too high or too low standard deviation are determined through the fourth data analysis result, and combined with other data analysis results to be used for determining the decision guidance of the charging stations.

[0075] In one embodiment, the data analysis of the charging stations may further include the prediction of the operation conditions of the charging stations, such as Figure 8 as shown, the method further includes:

[0076] Step 801, obtain the operation data of the charging station.

[0077] For the convenience of the merchants operating the charging stations to make decisions on the operation conditions of the charging stations, the operation conditions of the charging stations can be predicted through the operation data. Optionally, the operation data may include the various incomes and expenditures of the charging stations. For example, the expenditures include investment and construction costs, electricity costs, site rents, and power losses, etc., and the incomes include electricity revenues, service revenues, and subsidy revenues, etc.

[0078] Step 802, determine the fifth data analysis result of the charging station according to the operation data, and display the fifth data analysis result through an analysis report.

[0079] Among them, the fifth data analysis result may be the payback period of the charging station. According to the operation data and the existing algorithm models in the charging industry, the payback period of the charging station can be predicted, and then the operation data and the fifth data analysis result can be regularly displayed in the form of an analysis report.

[0080] In an alternative implementation manner, the calculation method of the fifth data analysis result is as follows:

[0081] 1. Payback period calculation

[0082] Investment payback period (month) = n + (the investment amount not yet recovered at the end of the nth month / the net cash flow in the (n + 1)th month)

[0083] The investment amount not yet recovered at the end of the nth month = investment and construction cost - sum (net cash flow from the 1st month to the nth month)

[0084] 2. Expenditure

[0085] Outflow = Investment and construction cost + Electricity cost + Platform commission + Site rent + Power loss + Marketing expenditure + Operating cost

[0086] a. Investment and construction cost = Charging pile cost + Engineering cost = Cost per single gun of template configuration * Number of guns + Engineering cost (The investment and construction cost is one-time and included in M0; the charging pile cost is included every 5 years)

[0087] b. Electricity cost = Charging volume (kWh / day / gun) * Number of days in a month * Electricity price (yuan / kWh) * Utilization seasonal coefficient * Equipment efficiency

[0088] c. Platform commission = Charging volume (kWh / day / gun) * Number of days in a month * Service fee (yuan / kWh) * Platform commission ratio * Utilization seasonal coefficient * Equipment efficiency

[0089] d. Site rent = Monthly rent agreed in the lease contract

[0090] e. Marketing expenditure = (Electricity revenue + Service fee revenue) * Marketing expenditure rate

[0091] f. Operating cost = Insurance + IT cost + Materials + Maintenance cost + Labor

[0092] g. Power loss = Electricity cost * Power loss ratio

[0093] 3. Revenue

[0094] Revenue = Electricity revenue + Service fee revenue + Subsidy revenue + Asset disposal

[0095] a. Electricity revenue = Charging volume (kWh / day / gun) * Number of days in a month * Electricity price (yuan / kWh) * Utilization seasonal coefficient * Equipment efficiency

[0096] b. Service fee revenue = Charging volume (kWh / day / gun) * Number of days in a month * Service fee (yuan / kWh) * Utilization seasonal coefficient * Equipment efficiency

[0097] c. Subsidy revenue = Construction subsidy + Charging volume (kWh / day / gun) * Number of days in a month * Operating subsidy (yuan / kWh) * Utilization seasonal coefficient * Equipment efficiency

[0098] d. Charging pile disposal = Investment and construction cost of charging pile * (1 - Depreciation rate of charging pile * Number of operating months)

[0099] In the embodiment of the present application, as Figure 9 shown, the method further includes:

[0100] Step 901, obtaining a text request for the charging station input by the client.

[0101] Among them, the user can input a text request through the client to obtain the data analysis data of the charging station required by the user.

[0102] Step 902: Perform word segmentation on the text request to generate word vectors.

[0103] Step 903: Determine the data content corresponding to the text request according to the word vectors and the preset metadata mapping table.

[0104] Among them, the metadata mapping table is a pre-configured keyword. By matching the word vectors with the metadata mapping table, the specific data to be obtained for the text request input by the user can be determined.

[0105] Step 904: Determine the text request result according to the data content and return the text request result to the client.

[0106] After determining the data content corresponding to the text request, perform statistical processing on the data content, calculate the statistical data, and then calculate the contribution degree and regression processing according to the statistical data, so as to generate the corresponding data analysis result. Determine the text request result according to the data analysis result, and then return it to the client.

[0107] Optionally, the processing flow of the text request can be as Figure 10 shown. The user inputs a text request, performs semantic decomposition on the text request, analyzes relevant phrases, and judges whether the analysis is completed. If not, vectorize the current phrase until all phrases are analyzed. After all phrases are analyzed, query the phrase and metadata mapping table for matching, determine the metadata, determine the data content corresponding to the text request, and then calculate relevant statistical data such as year-on-year and month-on-month, variance, and extreme values, calculate the contribution degree and regression data, perform data analysis attribution, and then generate the text request result, and output the text request result corresponding to the text request to the client.

[0108] In one embodiment, by performing data analysis on the data of the charging station, abnormal monitoring of the charging station can also be performed, as Figure 11 shown, including:

[0109] Step 1101: Determine whether there is abnormal data according to the initial statistical data.

[0110] Optionally, it can be determined whether there is abnormal data with abnormal fluctuations in the initial statistical data by setting a threshold or through an intelligent regression model.

[0111] Step 1102: If there is abnormal data, output a warning message.

[0112] If it is detected that there is abnormal data, output a warning message to remind the user to process it in time. Optionally, in order to realize the real-time monitoring of the initial statistical data and discover risks as early as possible, mainly through the streaming data processing method, the data changes per minute can be detected, and the real-time performance is higher. Optionally, the streaming data processing flow is as Figure 12As shown in the figure. In the data collection part, order data is collected through KAFKA (an open-source stream processing platform) and DDMQ (a distributed message middleware), and business data is collected by means of scheduled tasks or by listening to the corresponding Binlog events in the database as the data source. Dimension data is obtained through ELASTICSEARCH (a search data analysis engine), RDS, and HBASE (an open-source database). In the data processing part, the data is aggregated by Source, and after being calculated by FLINK (a distributed computing framework), the aggregated output is output. SINK (an atomic queue) performs streaming data processing and then outputs statistical data such as maximum and minimum values, mean values, aggregated values, and trend data, which are saved in the database. At the same time, the message data output by SINK can also be processed together with the dimension data through FLINK and SINK to generate corresponding statistical data such as business maximum and minimum values, business mean values, business aggregated values, and business trend data, which are saved in the database. In the data output part, that is, the corresponding database where the above statistical data is saved, it can include RDS, KAFKA, DDMQ, CLICKHOUSE, ELASTICSEARCH, Woater (a unified index monitoring platform), etc.

[0113] In an embodiment of the present application, a charging station data analysis system is further provided. By obtaining the target data of the charging station, multiple data analysis results of the charging station are determined to achieve attribution analysis, and abnormal data is captured for abnormal monitoring, so that the operation decision of the charging station can be determined according to each data analysis result. During the data analysis process of the target data, a shortest real-time link of core data is provided, and through the streaming data processing method, the data analysis result can be obtained in a short time, and the real-time performance is higher.

[0114] Attribution analysis is performed through multiple data analysis results. Optionally, the random forest algorithm can be used, and the above-mentioned contribution degree calculation, logistic regression, linear regression, and standard deviation calculation are used as different decision trees to form a decision forest for decision-making. Among them, the contribution degree algorithm is used as the benchmark, and the others are used as auxiliary, and their respective corresponding data analysis results are output to assist the merchants of the charging station in making decisions.

[0115] For ease of understanding, an example is given using contribution calculation. The contribution algorithm can use two methods: multiplication and addition. Among them, the addition-based contribution is essentially the ratio of the change amount. Therefore, the calculation method for the addition-based contribution is: sub-index contribution = sub-index change degree / main-index change degree. For example, if the new value of the sub-index is 120, the old value of the sub-index is 100, the new value of the main-index is 250, and the old value of the main-index is 200, then the addition-based contribution of this sub-index is (120 - 100) / (250 - 200) = 20 / 50 = 0.4 = 40%. The calculation method for the multiplication-based contribution is lg(sub-index new value / sub-index comparison value) / lg(main-index new value / main-index comparison value). For example, if the new value of the sub-index is 120, the old value of the sub-index is 100, the new value of the main-index is 250, and the old value of the main-index is 200, then the multiplication-based contribution of this sub-index is lg(120 / 100) / lg(250 / 200) ~= 0.19897784671578994 ~= 19.89778%

[0116] The total order resource amount, that is, the total order amount, is the most concerned indicator data for the charging station. By splitting the total order amount as follows, it can be determined that the contribution of the average electricity cost per order and the service fee can be calculated by the addition method.

[0117] Total order amount = average degree per order * unit price per degree * number of orders

[0118] = average charging duration per order * average charging power * number of orders * unit price per degree

[0119] = average charging duration per order * average charging power * number of users * average number of orders per user * unit price per degree

[0120] = average charging duration per order * average charging power * number of users * average number of orders per user * (unit price per degree of electricity + unit price per degree of service fee)

[0121] = (average service fee per order + average electricity cost per order) * order volume

[0122] For example, taking the data of a certain charging station as an example, the contribution calculation is as follows Figure 13As shown in the figure. The data at the beginning and middle of the year of the charging station are presented. It can be seen that the order amount value has approximately increased by 86481.03 / 41694.32 = 2.07 times. However, the growth of specific service fees, electricity fees, and charging volume does not match. Therefore, we use the above contribution algorithm: total order amount = (average service fee per order + average electricity fee per order) * number of orders. According to the calculation, the contributions of the number of orders and the average service fee per order to the total order amount show a positive correlation, which are 119.89% and 11.74% respectively. But the contribution of the average electricity fee per order to the order amount is -38.25%. Since the electricity fee is a cost item with zero profit for merchants (the electricity income needs to be fully paid to the power supply department), but they have to bear the relevant power losses. If the electricity volume increases, the power losses will increase accordingly, that is, an increase in the number of orders may have a negative impact. Thus, the data analysis results of the charging station can be determined, providing guidance for data decision-making for the merchants of the charging station.

[0123] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0124] Based on the same inventive concept, an embodiment of the present application also provides a charging station data analysis device for implementing the above-mentioned charging station data analysis method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the following charging station data analysis device can refer to the limitations on the charging station data analysis method in the above text, and will not be repeated here.

[0125] In an exemplary embodiment, as Figure 14 shown, a charging station data analysis device 1400 is provided, including: an acquisition module 1401, a first determination module 1402, a second determination module 1403, and a third determination module 1404, where:

[0126] The acquisition module 1401 is configured to acquire target data, where the target data includes data within a preset period of the charging station and data of different business dimensions of the charging station;

[0127] The first determination module 1402 is configured to determine initial statistical data according to target data;

[0128] The second determination module 1403 is configured to determine data to be concerned in the target data according to the initial statistical data;

[0129] The third determination module 1404 is configured to determine a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

[0130] In one embodiment, the second determination module 1403 is specifically configured to calculate difference data between the initial statistical data and historical statistical data; and determine the data to be concerned in the target data according to the fluctuation value of the difference data.

[0131] In one embodiment, the apparatus further includes a fourth determination module, configured to obtain associated data of the charging station; determine an association relationship between the associated data and the total order resources of the charging station; and determine a second data analysis result of the charging station according to the association relationship.

[0132] In one embodiment, the apparatus further includes a fifth determination module, configured to perform linear fitting on the initial statistical data of the charging station to determine a linear fitting result; and determine a third data analysis result of the charging station according to the linear fitting result.

[0133] In one embodiment, the apparatus further includes a sixth determination module, configured to calculate a standard deviation of the initial statistical data of the charging station to determine a standard deviation calculation result; and determine a fourth data analysis result of the charging station according to the standard deviation calculation result.

[0134] In one embodiment, the apparatus further includes a seventh determination module, configured to obtain operation data of the charging station; determine a fifth data analysis result of the charging station according to the operation data, and display the fifth data analysis result through an analysis report.

[0135] In one embodiment, the apparatus further includes a request processing module, configured to obtain a text request for the charging station input by a client; perform word segmentation processing on the text request to generate word vectors; determine data content corresponding to the text request according to the word vectors and a preset metadata mapping table; determine a text request result according to the data content, and return the text request result to the client.

[0136] In one embodiment, the apparatus further includes an output module, configured to determine whether there is abnormal data according to the initial statistical data; and output a warning message if there is abnormal data.

[0137] Each module in the above-mentioned charging station data analysis device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0138] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 15 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the target data of the charging station. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a charging station data analysis method.

[0139] Those skilled in the art can understand that Figure 15 the structure shown in

[0140] merely represents a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0141] In an embodiment, when the processor executes the computer program, it also implements the following steps: calculating the difference data between the initial statistical data and the historical statistical data; determining the data to be concerned in the target data according to the fluctuation value of the difference data.

[0142] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the associated data of the charging station; determining the association relationship between the associated data and the total order resources of the charging station; and determining the second data analysis result of the charging station according to the association relationship.

[0143] In one embodiment, when the processor executes the computer program, the following steps are further implemented: performing linear fitting on the initial statistical data of the charging station to determine the linear fitting result; and determining the third data analysis result of the charging station according to the linear fitting result.

[0144] In one embodiment, when the processor executes the computer program, the following steps are further implemented: calculating the standard deviation of the initial statistical data of the charging station to determine the standard deviation calculation result; and determining the fourth data analysis result of the charging station according to the standard deviation calculation result.

[0145] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the operation data of the charging station; determining the fifth data analysis result of the charging station according to the operation data, and displaying the fifth data analysis result through an analysis report.

[0146] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the text request for the charging station input by the client; performing word segmentation processing on the text request to generate word vectors; determining the data content corresponding to the text request according to the word vectors and the preset metadata mapping table; determining the text request result according to the data content, and returning the text request result to the client.

[0147] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determining whether there is abnormal data according to the initial statistical data; and if there is abnormal data, outputting a warning message.

[0148] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining target data, where the target data includes the data of the charging station within a preset period and the data of different business dimensions of the charging station; determining the initial statistical data according to the target data; determining the data to be concerned in the target data according to the initial statistical data; and determining the first data analysis result of the charging station according to the contribution degree of the data to be concerned.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: calculating the difference data between the initial statistical data and the historical statistical data; and determining the data to be concerned in the target data according to the fluctuation value of the difference data.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining associated data of a charging station; determining an association relationship between the associated data and the total order resources of the charging station; and determining a second data analysis result of the charging station according to the association relationship.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: performing linear fitting on the initial statistical data of the charging station to determine a linear fitting result; and determining a third data analysis result of the charging station according to the linear fitting result.

[0152] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: calculating a standard deviation of the initial statistical data of the charging station to determine a standard deviation calculation result; and determining a fourth data analysis result of the charging station according to the standard deviation calculation result.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining operation data of the charging station; determining a fifth data analysis result of the charging station according to the operation data, and presenting the fifth data analysis result through an analysis report.

[0154] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining a text request for the charging station input by a client; performing word segmentation on the text request to generate word vectors; determining data content corresponding to the text request according to the word vectors and a preset metadata mapping table; determining a text request result according to the data content, and returning the text request result to the client.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining whether there is abnormal data according to the initial statistical data; and if there is abnormal data, outputting a warning message.

[0156] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps:

[0157] Obtaining target data, where the target data includes data of the charging station within a preset period and data of different business dimensions of the charging station; determining initial statistical data according to the target data; determining data to be concerned in the target data according to the initial statistical data; and determining a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: calculating difference data between the initial statistical data and historical statistical data; and determining data to be concerned in the target data according to the fluctuation value of the difference data.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining associated data of the charging station; determining the association relationship between the associated data and the total order resource amount of the charging station; and determining a second data analysis result of the charging station according to the association relationship.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: performing linear fitting on the initial statistical data of the charging station to determine a linear fitting result; and determining a third data analysis result of the charging station according to the linear fitting result.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: calculating the standard deviation of the initial statistical data of the charging station to determine a standard deviation calculation result; and determining a fourth data analysis result of the charging station according to the standard deviation calculation result.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the operation data of the charging station; determining a fifth data analysis result of the charging station according to the operation data, and displaying the fifth data analysis result through an analysis report.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining a text request for the charging station input by a client; performing word segmentation on the text request to generate word vectors; determining the data content corresponding to the text request according to the word vectors and a preset metadata mapping table; determining a text request result according to the data content, and returning the text request result to the client.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining whether there is abnormal data according to the initial statistical data; and if there is abnormal data, outputting a warning message.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0166] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0167] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0168] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for analyzing charging station data, characterized in that, the method includes: Obtaining target data, where the target data includes data within a preset period of the charging station and data of different business dimensions of the charging station; Determining initial statistical data according to the target data; Determining the data to be concerned in the target data according to the initial statistical data; Determining a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

2. The method according to claim 1, characterized in that, the determining the data to be concerned in the target data according to the initial statistical data includes: Calculating the difference data between the initial statistical data and the historical statistical data; Determining the data to be concerned in the target data according to the fluctuation value of the difference data.

3. The method according to claim 1, characterized in that, the method further includes: Obtaining the associated data of the charging station; Determining the association relationship between the associated data and the total order resources of the charging station; Determining a second data analysis result of the charging station according to the association relationship.

4. The method according to claim 1, characterized in that, the method further includes: Performing linear fitting on the initial statistical data of the charging station to determine a linear fitting result; Determining a third data analysis result of the charging station according to the linear fitting result.

5. The method according to claim 1, characterized in that, the method further includes: Calculating the standard deviation of the initial statistical data of the charging station to determine a standard deviation calculation result; Determining a fourth data analysis result of the charging station according to the standard deviation calculation result.

6. The method according to claim 1, characterized in that, the method further includes: Obtaining the operation data of the charging station; Determining a fifth data analysis result of the charging station according to the operation data, and displaying the fifth data analysis result through an analysis report.

7. The method according to claim 1, characterized in that, the method further includes: Obtaining a text request for the charging station input by the client; Performing word segmentation on the text request to generate word vectors; Determining the data content corresponding to the text request according to the word vectors and a preset metadata mapping table; Determining a text request result according to the data content and returning the text request result to the client.

8. The method according to claim 1, characterized in that, the method further includes: Determining whether there is abnormal data according to the initial statistical data; If there is the abnormal data, outputting a warning message.

9. A charging station data analysis device, characterized in that, the device includes: An obtaining module, configured to obtain target data, where the target data includes data within a preset period of the charging station and data of different business dimensions of the charging station; A first determining module, configured to determine initial statistical data according to the target data; A second determining module, configured to determine the data to be concerned in the target data according to the initial statistical data; A third determining module, configured to determine a first data analysis result of the charging station according to the contribution degree of the data to be concerned.

10. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images