Service strategy determination method and device for charging station, equipment and storage medium

By obtaining and optimizing the initial service strategy of the charging station, based on historical data and real-time information, the problem that the charging station is difficult to predict future charging needs is solved, and more accurate service strategy configuration and user experience improvement are achieved.

CN118917965APending Publication Date: 2024-11-08BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410939989.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing charging station service strategy is difficult to effectively predict future charging needs based on historical data and real-time information, resulting in poor user charging experience.

Method used

By obtaining multiple initial service policies, the charging amount data related to the target site is determined based on the historical data sequence and initial service policies, and the optimization algorithm is used to optimize these strategies to obtain the target service strategy to determine the time-sharing of the future period. Unit cost of providing charging services.

Benefits of technology

The accuracy and user experience of charging station service strategies have been improved, and the operational efficiency of charging stations has been improved by predicting future charging needs and optimizing service configuration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917965A_ABST
    Figure CN118917965A_ABST
Patent Text Reader

Abstract

The invention provides a service strategy determination method and device for a charging station, equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of Internet of Things, deep learning, large models and the like. According to the specific implementation scheme, in response to a service strategy determination request, multiple initial service strategies are obtained, and the initial service strategies are used for determining the initial unit cost of a target station for providing a charging service in a time-sharing manner in a future period; based on the initial service strategy and the historical data sequence of the target station, determining charging amount data related to the initial service strategy, the charging amount data related to the initial service strategy representing the time-sharing charging amount of the target station in the future period under the initial service strategy; and based on the charging amount data related to the plurality of initial service strategies, the plurality of initial service strategies are optimized to obtain a target service strategy, and the target service strategy is used for determining the unit cost of the target station for providing the charging service in the future time period in a time-sharing manner.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of Internet of Things, deep learning, large models and other technical fields, and more specifically to a method, device, equipment and storage medium for determining a service strategy for a charging station. Background Art

[0002] With the continuous development of Internet of Things and artificial intelligence technologies, intelligent and networked charging facilities have gradually become popular in charging stations. These facilities can be remotely monitored and maintained through the Internet to improve operational efficiency. The popularity of intelligent charging facilities in charging stations also provides a hardware infrastructure foundation for the intelligent adjustment of charging station service strategies. Reasonable service strategies can guide users' charging choices and improve their charging experience. Summary of the invention

[0003] The present disclosure provides a method, device, equipment and storage medium for determining a service strategy for a charging station.

[0004] According to one aspect of the present disclosure, a method for determining a service strategy for a charging station is provided, comprising: in response to a service strategy determination request, obtaining a plurality of initial service strategies, the initial service strategies being used to determine an initial unit cost for a target station to provide charging services in a time-sharing manner in a future time period; determining charging quantity data related to the initial service strategy based on the initial service strategy and a historical data sequence of the target station, the charging quantity data related to the initial service strategy representing the time-sharing charging quantity of the target station in the future time period under the initial service strategy; and optimizing the plurality of initial service strategies based on the charging quantity data related to each of the plurality of initial service strategies to obtain a target service strategy, the target service strategy being used to determine a unit cost for the target station to provide charging services in a time-sharing manner in the future time period.

[0005] According to another aspect of the present disclosure, a service strategy determination device for a charging station is provided, including: a first acquisition module, for acquiring a plurality of initial service strategies in response to a service strategy determination request, the initial service strategies being used to determine an initial unit cost of a target station providing charging services in a time-sharing manner in a future time period; a first determination module, for determining charging quantity data related to the initial service strategy based on the initial service strategy and a historical data sequence of the target station, the charging quantity data related to the initial service strategy representing the time-sharing charging quantity of the target station in the future time period under the initial service strategy; and a first optimization module, for optimizing the plurality of initial service strategies based on the charging quantity data related to each of the plurality of initial service strategies to obtain a target service strategy, the target service strategy being used to determine a unit cost of the target station providing charging services in a time-sharing manner in the future time period.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method as described above.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described above when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 An exemplary system architecture to which the method and device for determining a service strategy for a charging station according to an embodiment of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart of a method for determining a service strategy for a charging station according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A schematic diagram schematically shows a data link of a charging station according to an embodiment of the present disclosure;

[0014] Figure 4 A schematic diagram schematically shows the correlation of the historical data sequence of the target station according to an embodiment of the present disclosure;

[0015] Figure 5A A schematic diagram schematically shows the sub-data sequences of the target feature item A and the target feature item B before normalization;

[0016] Figure 5B A schematic diagram schematically shows the sub-data sequences of each of the target feature item A and the target feature item B after normalization;

[0017] Figure 6 A schematic diagram of a converter network according to an embodiment of the present disclosure is schematically shown;

[0018] Figure 7 A schematic diagram schematically shows a method for predicting charging amount data according to an embodiment of the present disclosure;

[0019] Figure 8 A schematic diagram schematically shows charging amount data according to an embodiment of the present disclosure;

[0020] Fig. 9 A block diagram schematically shows a device for determining a service strategy for a charging station according to an embodiment of the present disclosure; and

[0021] Fig.10 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0022] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] The embodiments of the present disclosure provide a method, device, equipment and storage medium for determining the service strategy of a charging station, which can predict future charging needs based on the historical data and real-time information of the charging station, provide support for the service decision of the charging station, and improve the charging experience of users at the charging station. Specifically, the method for determining the service strategy of the charging station includes: in response to a service strategy determination request, obtaining multiple initial service strategies, the initial service strategies are used to determine the initial unit cost of the target station providing charging services in a time-sharing manner in a future period; based on the initial service strategy and the historical data sequence of the target station, determining the charging amount data related to the initial service strategy, the charging amount data related to the initial service strategy represents the time-sharing charging amount of the target station in the future period under the initial service strategy; and based on the charging amount data related to each of the multiple initial service strategies, optimizing the multiple initial service strategies to obtain the target service strategy, the target service strategy is used to determine the unit cost of the target station providing charging services in a time-sharing manner in the future period.

[0024] Figure 1 An exemplary system architecture to which the method and device for determining a service strategy for a charging station according to an embodiment of the present disclosure can be applied is schematically shown.

[0025] It should be noted that Figure 1The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the method and apparatus for determining a service strategy for a charging station can be applied may include a terminal device, but the terminal device may implement the method and apparatus for determining a service strategy for a charging station provided by the embodiments of the present disclosure without interacting with a server.

[0026] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, a network 103 and a server 104. The network 103 is used to provide a medium for a communication link between the terminal devices 101, 102 and the server 104. The network 103 may include various connection types, such as wired and / or wireless communication links, etc.

[0027] The terminal devices 101 and 102 may include various information receiving terminals in the charging station, such as charging piles, sensors, etc.

[0028] The server 104 may be a server that provides various services.

[0029] It should be noted that the service strategy determination method for the charging station provided in the embodiment of the present disclosure can generally be executed by the server 104. Accordingly, the service strategy determination device for the charging station provided in the embodiment of the present disclosure can generally be set in the server 104.

[0030] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0031] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0032] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0033] Figure 2 The flowchart of the method for determining the service strategy of a charging station according to an embodiment of the present disclosure is schematically shown.

[0034] like Figure 2 As shown, the method includes operations S210 to S230.

[0035] In operation S210, a plurality of initial service policies are acquired in response to a service policy determination request.

[0036] In operation S220 , based on the initial service strategy and the historical data sequence of the target site, charging amount data related to the initial service strategy is determined.

[0037] In operation S230 , the plurality of initial service strategies are optimized based on the charge amount data associated with each of the plurality of initial service strategies to obtain a target service strategy.

[0038] The service policy determination request may be generated by a timed trigger of the server device, or may be generated by the server device after receiving a user operation instruction, which is not limited here. The service policy determination request may at least include station information, based on which the target station for which the service policy needs to be re-determined may be determined. The target station may refer to any controlled charging station, which is not limited here.

[0039] The initial service strategy can be used to determine the initial unit cost of the target station to provide charging services in the future time period. The future time period can be expressed as the effective period of the service strategy. The length of the future time period can be, for example, one day, one week, etc., which is not limited here. The method for determining the future time period is not limited here, for example, it can be determined based on user operation instructions, or it can be determined based on the default duration and the current system time. The time-sharing division method of the future time period can, for example, follow the time-sharing division method of the electricity price, and divide the time period of a day into sharp, peak, flat, valley and other time periods, or the time period of a day can be evenly divided, such as dividing 0:00-3:00 into one time period, and dividing 3:00-6:00 into one time period, etc.

[0040] For example, the length of the future period is one day, and the time period division method is to divide the time period of one day into peak, peak, flat and valley periods. The initial service strategy A can be as shown in Table 1, that is, the initial service strategy A can indicate that the unit cost of the target station providing services during the peak period of the future day is b1, the unit cost of providing services during the peak period of the future day is b2, the unit cost of providing services during the flat period of the future day is b3, and the unit cost of providing services during the valley period of the future day is b4.

[0041] Table 1

[0042] Time tip peak flat valley Unit cost of providing charging services b1 b2 b3 b4

[0043] The historical data sequence of the target station may include the operating data of the target station during the historical period, such as charging power, unit cost of electricity, unit cost of service fee, etc., other data associated with the target station, such as weather conditions in the area where the target station is located, outdoor temperature, outdoor humidity, etc., and data of other objective factors, such as date, etc. The historical period may refer to any period before the service strategy determines the request trigger, which is not limited here. The historical data sequence of the target station can be collected by the charging facilities and other sensor equipment in the target station, which will not be elaborated here.

[0044] The historical data sequence and the initial service strategy can be used as the input of the model and input into the time series model. The model can be a trained model, and the output of the model can be the charging amount data related to the initial service strategy. The time series model can be, for example, RNN (Recurrent Neural Networks), LSTM (Long Short-Term Memory), transformer (converter network), etc., which are not limited here.

[0045] The charging amount data related to the initial service strategy may represent the time-sharing predicted charging amount of the target station in the future period under the initial service strategy. For example, the charging amount data related to the initial service strategy A may be represented as the predicted charging amount of the target station in the peak, peak, flat and valley periods in the future day when the unit costs of providing services at the target station in the peak, peak, flat and valley periods in the future day are b1, b2, b3 and b4 respectively.

[0046] Optimizing multiple initial service strategies can be achieved using various swarm intelligence algorithms, such as particle swarm optimization, genetic algorithm, etc., which are not limited here.

[0047] The target service strategy can be used to determine the unit cost of the target station providing time-sharing charging services in the future period.

[0048] According to the embodiments of the present disclosure, the time-sharing predicted charging amount under each initial service strategy can be determined respectively, and the service strategy can be optimized by using the time-sharing predicted charging amount as a parameter of the objective function used in optimization, so as to more accurately configure the service strategy of the charging station, so that the charging power station can provide users with more reasonable services to enhance the user's charging experience.

[0049] Reference below Figure 3 to Figure 6 , combined with specific embodiments Figure 2 The method shown is further explained.

[0050] The control system of the charging station can be used to control multiple charging stations, and use the service strategy determination method of the charging station as described above to configure the service strategy of each charging station. The control system of the charging station can be configured in a cloud service end or a server in a local computer room. The charging facilities included in each charging station can be used as an IoT device. During the operation of the charging station, the sensors configured in each charging device can collect data in different time periods and send the collected data to the control system of the charging station through the message middleware.

[0051] Figure 3 A schematic diagram of a data link of a charging station according to an embodiment of the present disclosure is schematically shown.

[0052] like Figure 3 As shown, the sensor 301 can be set on any charging facility in the charging station. When the charging station is in operation, the sensor 301 can collect corresponding types of data according to its function. For example, if the sensor is a temperature sensor, the sensor can collect temperature data in time division; if the sensor is a humidity sensor, the sensor can collect humidity data in time division, etc.

[0053] The gateway device 302 can also be set in the charging station. The gateway device 302 can be an industrial computer, an edge gateway, etc., which is not limited here. The gateway device 302 can be used to manage the metadata of the sensor 301 and process the data that needs to be sent. The gateway device 302 can use a high-performance non-blocking communication framework to receive the data sent by the sensor 301, and can establish a communication link with the sensor 301 through HTTP (Hyper Text Transfer Protocol) communication, TCP (Transmission Control Protocol) communication, etc., to achieve interaction with the sensor 301.

[0054] In order to reduce data loss, a message middleware 304 may be configured between the gateway device 302 and the control system 303. The gateway device 302 may package the data from the sensor 301 into a fixed format and push it to the message middleware 304. The control system 303 may consume data from the message middleware 304 and cache it in a related database. Using the message middleware, batch push of data may be achieved to improve the real-time performance and availability of the control system.

[0055] Correspondingly, the historical data sequence of the target station is extracted from the database of the control system 303. The historical data sequence may originate from the sensors of the charging equipment in the target station, be collected by the sensors in the target station, and be sent to the control system through the gateway device and the message queue, and be stored by the control system, which will not be elaborated here.

[0056] For each charging station, feature selection can be performed based on the characteristics of the charging station to determine the feature items suitable for evaluating the predicted charging amount of the charging station. For example, for charging stations in areas with relatively constant temperatures, such as charging stations in tropical areas, the temperature changes less, and the temperature-related data has less impact on the prediction accuracy of the charging amount. For charging stations in areas with large day and night temperature changes, in addition to affecting user behavior, temperature changes will also affect the operating status of the charging facilities, such as affecting the output power of the facilities. Therefore, for charging stations in this area, the outside temperature is a feature item suitable for evaluating the predicted charging amount of the charging station.

[0057] According to an embodiment of the present disclosure, the historical data sequence may include a historical charging amount data sequence of the target station, and the historical data sequence may include sub-data sequences corresponding to each of the plurality of characteristic items. The historical charging amount data sequence may correspond to the charging amount characteristic item.

[0058] Optionally, multiple feature items may be screened to obtain a target feature item, and the sub-data sequence corresponding to the target feature item may be used for subsequent model inference.

[0059] According to an embodiment of the present disclosure, a target feature item may be determined from a plurality of feature items based on a correlation coefficient between a historical charge amount data series and each of a plurality of sub-data series.

[0060] Alternatively, the correlation coefficient may be used to evaluate the degree of association between the charge amount characteristic item and the plurality of characteristic items.

[0061] According to an embodiment of the present disclosure, determining a target feature item from multiple feature items based on the correlation coefficient between the historical charge amount data sequence and each of the multiple sub-data sequences may include the following operations:

[0062] Perform linear correlation calculations on the historical charge capacity data sequence and multiple sub-data sequences respectively to obtain correlation coefficients between the historical charge capacity data sequence and each of the multiple sub-data sequences; and, when the correlation coefficient between the historical charge capacity data sequence and the sub-data sequence is greater than a first preset value or less than a second preset value, determine that the feature item corresponding to the sub-data sequence is the target feature item, wherein the first preset value>0>second preset value.

[0063] The correlation coefficient can be obtained using various correlation coefficient calculation methods. For example, the Pearson correlation coefficient can be used to evaluate the correlation between each two feature items, as shown in formula (1):

[0064]

[0065] In formula (1), x and y can represent the sub-data sequences corresponding to the two feature items respectively, σ x and σ y can represent the standard deviation of x and y respectively, cov(x, y) can represent the covariance between x and y, μ x and μ y can represent the mean of x and y respectively.

[0066] Figure 4 A schematic diagram showing the correlation of historical data sequences of a target station according to an embodiment of the present disclosure is shown schematically.

[0067] like Figure 4 As shown, multiple feature items related to the target station may include charging amount, unit cost of electricity price, unit cost of service, date, outdoor temperature, and outdoor humidity. For example, the first preset value can be set to 0.8 and the second preset value can be set to -0.5. It can be seen from the figure that the charging amount of the station is positively correlated with the unit cost of electricity price and the unit cost of service, while the outdoor temperature and outdoor humidity are negatively correlated with the charging amount of the station. Therefore, the unit cost of electricity price, the unit cost of service, the outdoor temperature and the outdoor humidity can all be used as target feature items of the target station. The sub-data sequence corresponding to the target feature item can be used to determine the time-sharing predicted charging amount in the future period.

[0068] According to an embodiment of the present disclosure, by screening the historical data series of the target station based on the correlation between the feature items, and then using the screened data to predict the time-sharing charging amount, the interference of noise information can be effectively reduced and the accuracy of the prediction can be improved.

[0069] Optionally, for the original historical data sequence, or the sub-data sequence corresponding to the target feature item obtained by screening, these data can be preprocessed to enhance the robustness of the data. The preprocessing method may include data merging, outlier processing, missing value processing, normalization processing, etc., which will not be described in detail here.

[0070] Taking data normalization as an example, the dimension of the data elements in the sub-data sequence corresponding to the target feature item A can be 1×10 4 , the dimension of the data elements in the sub-data sequence corresponding to the target feature item B can be 1×10 1 .

[0071] Figure 5A A schematic diagram schematically shows the sub-data sequences of the target feature item A and the target feature item B before normalization.

[0072] like Figure 5AAs shown, before normalization, the change trend of the data elements in the sub-data sequence 501 corresponding to the target feature item A can be reflected. However, the change amount of the data elements in the sub-data sequence 502 corresponding to the target feature item B is much smaller than the dimension of the data elements in the sub-data sequence 501 corresponding to the target feature item A, so that the data elements in the sub-data sequence 502 corresponding to the target feature item B are almost unchanged. When the sub-data sequence 502 corresponding to the target feature item B is used for model training or inference, the sub-data sequence 502 corresponding to the target feature item B has almost no contribution to the training or inference results.

[0073] Figure 5B A schematic diagram schematically shows the sub-data sequences of each of the target feature item A and the target feature item B after normalization.

[0074] like Figure 5B As shown, by normalizing the sub-data sequence 501 corresponding to the target feature item A and the sub-data sequence 502 corresponding to the target feature item B, a normalized sub-data sequence 503 corresponding to the target feature item A and a normalized sub-data sequence 504 corresponding to the target feature item B are obtained. The relative relationship of the original data can be retained and the influence of the dimension can be eliminated, thereby improving the training or reasoning effect of the model.

[0075] Optionally, the converter network may be used to predict charging amount data related to the initial service strategy based on the initial service strategy and the historical data sequence of the target site.

[0076] According to an embodiment of the present disclosure, based on the initial service strategy and the historical data sequence of the target station, determining the charging amount data related to the initial service strategy may include the following operations:

[0077] Obtain a historical observation data sequence of the target station, wherein the historical observation data sequence is determined from the historical data sequence of the target station based on the target characteristic item; determine a predictable data sequence of the target station in a future time period based on the initial service strategy, the target characteristic item and the preset characteristic item; and input the historical observation data sequence and the predictable data sequence into a converter network to obtain charging amount data related to the initial service strategy.

[0078] The historical observation data sequence may include a sub-data sequence corresponding to the target feature item in the historical data sequence. For all service strategies, the historical observation data sequence may be fixed.

[0079] The preset feature item may represent a data item whose state is constant in a future period. For example, the preset feature item may include holiday information in a future period.

[0080] Different from the determination method of the historical observation data sequence, the sub-data sequence corresponding to the target feature item in the predictable data sequence can be obtained from other data sources. For example, the temperature data and humidity data for the future period can be obtained from the meteorological forecast data published by the meteorological department where the target station is located. For another example, the unit price of electricity in the future period can be obtained from the electricity price data published by the power department where the target station is located. For another example, the charging amount data for the future period can be obtained based on the time-sharing predicted charging amount represented by the initial service strategy.

[0081] As an optional implementation, after constructing the historical observation data sequence and the predictable data sequence, the charge amount data can be directly predicted using the converter network.

[0082] According to an embodiment of the present disclosure, inputting a historical observation data sequence and a predictable data sequence into a converter network to obtain charging amount data related to an initial service strategy may include the following operations:

[0083] Input the historical observation data sequence into the encoder to obtain the first output feature; input the predictable data sequence into the decoder to obtain the second output feature; concatenate the first output feature and the second output feature to obtain a fusion feature; and perform time series prediction based on the fusion feature to obtain charging amount data related to the initial service strategy.

[0084] Figure 6 A schematic diagram of a converter network according to an embodiment of the present disclosure is schematically shown.

[0085] like Figure 6 As shown, the encoder of the converter network can be composed of a first attention layer 601 and a first feedforward network layer 602. Similarly, the decoder of the converter network can be composed of a second attention layer 603 and a second feedforward network layer 604. The outputs of the encoder and the decoder can both be input into a linear layer 605, which predicts the data.

[0086] The number of layers of the attention structure used in the first attention layer 601 and the second attention layer 603 may be different, which is not limited here.

[0087] The historical observation data sequence can be sequentially input into the first attention layer 601, and the predictable data sequence can be synchronously input into the second attention layer 603, so that the linear layer 605 sequentially outputs the charge amount data.

[0088] Optionally, the first attention layer 601, the first feedforward network layer 602, the second attention layer 603, the second feedforward network layer 604 and the linear layer 605 may all include a normalization structure, which may be, for example, a RevIN normalization layer. In the training process of the converter network, by using the normalization structure, the model can ignore the problem of data drift and reduce the loss of non-stationary information by training the time series data in two stages, namely, normalization and denormalization. Moreover, the use of the normalization structure does not bring about additional hardware resource consumption, thereby effectively improving the performance of the converter network.

[0089] For example, in the charging data prediction scenario of a charging station, if a holiday occurs and a time series prediction model is used, the prediction results will be subject to large errors due to the inconsistent distribution of the training set and the test set. However, if the RevIN normalization layer is added to the time series prediction model, the negative impact of inconsistent data set distribution can be reduced, thereby improving the performance of the model.

[0090] As another optional implementation, the historical observation data sequence and the predictable data sequence may be encoded respectively, and the encoded data may be used to predict the charging capacity data.

[0091] According to an embodiment of the present disclosure, inputting a historical observation data sequence and a predictable data sequence into a converter network to obtain charging amount data related to an initial service strategy may include the following operations:

[0092] Based on the timestamp information of the data elements respectively included in the historical observation data sequence and the predictable data sequence, the historical observation data sequence and the predictable data sequence are position encoded to obtain a first feature sequence and a second feature sequence; and the first feature sequence and the second feature sequence are input into the converter network to obtain the charging amount data related to the initial service strategy.

[0093] The method of position encoding of the data sequence is not limited here. For example, the position of the data element in the data sequence can be encoded using trigonometric functions, etc. In the actual production process, the acquisition time intervals between adjacent data elements in the data sequence may be different. Therefore, in order to better reflect the timing information of the data elements in the data sequence, the position encoding of the data element can be performed according to the timestamp information of the data element.

[0094] According to an embodiment of the present disclosure, position encoding the historical observation data sequence based on the timestamp information of the data elements included in the historical observation data sequence to obtain the first feature sequence may include the following operations:

[0095] Determine sub-elements corresponding to multiple time granularities from timestamp information of data elements included in the historical observation data sequence; perform feature encoding on the sub-elements corresponding to the multiple time granularities respectively to obtain multiple sub-features; perform feature fusion on the multiple sub-features to obtain position codes of the data elements; and, encode the multiple data elements using the respective position codes of the multiple data elements included in the historical observation data sequence to obtain a first feature sequence.

[0096] The multiple time granularities may include time granularities such as "year", "month", "day", "hour", "minute", and "second". Each time granularity may correspond to an encoder, and the encoders corresponding to the multiple time granularities may be used to perform feature encoding on the sub-elements corresponding to the multiple time granularities to obtain multiple sub-features.

[0097] Methods for fusing multiple sub-features may include, but are not limited to, high-dimensional splicing, wide-dimensional splicing, channel-dimensional splicing, fusion using matrix operations, fusion using neural networks, etc., which are not limited here.

[0098] The data element is encoded using position coding, which may be performed by adding the position coding to the field of the data element, or by loading the position coding information into the field of the data element in a certain manner, which is not limited here.

[0099] For example, for data element C, the collection time of data element C, that is, the timestamp information of data element C can be expressed as C1 month C2 day C3 hour C4 minute C5 second C6 millisecond, and the encoders corresponding to the multiple time granularities can include encoder D1 corresponding to "month", encoder D2 corresponding to "day", encoder D3 corresponding to "hour", encoder D4 corresponding to "minute", encoder D5 corresponding to "second" and encoder D6 corresponding to "millisecond". Encoder D1 can be used to encode C1 to obtain sub-feature E1; encoder D2 can be used to encode C2 to obtain sub-feature E2; encoder D3 can be used to encode C3 to obtain sub-feature E3; encoder D4 can be used to encode C4 to obtain sub-feature E4; encoder D5 can be used to encode C5 to obtain sub-feature E5; encoder D6 can be used to encode C6 to obtain sub-feature E6. Sub-feature E1, sub-feature E2, sub-feature E3, sub-feature E4, sub-feature E5 and sub-feature E6 are superimposed to obtain a position code E, which can then be used to perform position coding on the data element C.

[0100] In the case of adopting the position encoding method, the historical observation data sequence and the predictable data sequence are input into the converter network to obtain the charging amount data related to the initial service strategy, which may include the following operations:

[0101] Input the first feature sequence into the encoder to obtain the first output feature; input the second feature sequence into the decoder to obtain the second output feature; concatenate the first output feature and the second output feature to obtain a fusion feature; and perform time series prediction based on the fusion feature to obtain charging amount data related to the initial service strategy.

[0102] The structure of the converter network can be as follows Figure 6 As shown, the first feature sequence can be sequentially input into the first attention layer 601, and the second feature sequence can be synchronously input into the second attention layer 603, so that the linear layer 605 sequentially outputs the charge amount data.

[0103] As another optional implementation, other types of encoding methods may be used to encode the historical observation data sequence and the predictable data sequence respectively, and use the encoded data to predict the charging capacity data.

[0104] According to an embodiment of the present disclosure, the static covariates of the target station may be acquired, and the historical observation data sequence and the predictable data sequence may be context-encoded using the static covariates to obtain the third feature sequence and the fourth feature sequence.

[0105] The static covariate may be represented as fixed information of the target station. For example, the static covariate may be determined based on the geographical location information of the target station, that is, the static covariate may be represented as the geographical location information of the target station, such as longitude and latitude information.

[0106] The context encoding of the data sequence is performed using the static covariate, that is, the static covariate is added to the context of the data element in the data sequence, which is not limited here.

[0107] In the case of adopting the context encoding method, the historical observation data sequence and the predictable data sequence are input into the converter network to obtain the charging amount data related to the initial service strategy, which may include the following operations:

[0108] The third feature sequence is input into the encoder to obtain the first output feature; the fourth feature sequence is input into the decoder to obtain the second output feature; the first output feature and the second output feature are concatenated to obtain a fusion feature; and time series prediction is performed based on the fusion feature to obtain charging amount data related to the initial service strategy.

[0109] Optionally, the data sequence may be encoded in other ways besides position encoding and context encoding, and the encoded data sequence may be used to predict the charge capacity data.

[0110] As an optional implementation, multiple encoding methods may be combined for encoding.

[0111] Figure 7 A schematic diagram of a charging amount data prediction method according to an embodiment of the present disclosure is schematically shown.

[0112] like Figure 7 As shown, for the historical observation data sequence 701, position encoding can be performed based on the timestamp information 702 of each data element in the historical observation data sequence 701 to obtain a first feature sequence 703, and then the first feature sequence 703 is context-encoded using the static covariate 704 to obtain a third feature sequence 705. For the predictable data sequence 706, position encoding can be performed based on the timestamp information 702 of each data element in the predictable data sequence 706 to obtain a second feature sequence 707, and then the second feature sequence 707 is context-encoded using the static covariate 704 to obtain a fourth feature sequence 708. The third feature sequence 705 and the fourth feature sequence 708 can be respectively input into the converter network 709 to obtain the charge amount data 710.

[0113] Figure 8 The figure schematically shows charging amount data according to an embodiment of the present disclosure.

[0114] like Figure 8 As shown, a historical observation data sequence can be constructed based on the charging amount data before time T and other observation data before time T, a predictable data sequence can be constructed in combination with future weather conditions, holiday conditions, etc., and the charging amount data after time T can be predicted based on the historical observation data sequence and the predictable data sequence.

[0115] After determining the charging amount data associated with each initial service strategy, a swarm intelligence algorithm may be used to optimize the multiple initial service strategies based on the charging amount data to determine a final target service strategy.

[0116] Taking the particle swarm algorithm as an example, the decision variable of the particle swarm algorithm can be determined as the unit cost of the time-sharing service of the target station in the future period. The constraints can be determined in combination with the actual status of the target station and historical data. For example, the constraints can include the charging capacity constraint determined based on the equipment status of the target station, the range constraint of the unit cost of the charging service provided by the target station, etc. For example, the determined constraints can be shown in formulas (2) and (3):

[0117] pi ,min ≤p i ≤pi ,max (2)

[0118] 0≤C i ≤C max (3)

[0119] In formulas (2) and (3), p i represents the unit cost of service in period i, p i,min represents the minimum value of the service unit cost set in period i, p i,max represents the maximum value of the service unit cost set in period i, C i represents the predicted charge capacity in period i, C max Indicates the maximum charging capacity of the target station.

[0120] The objective function may be a function related to the unit cost of the time-sharing service and the time-sharing predicted charging amount. For example, the objective function may be as shown in formula (4):

[0121]

[0122] In formula (4), It can represent the electricity price in period j, It can represent the weight of the target station profit in period j, It can represent the weight of the target station’s revenue in period j.

[0123] According to an embodiment of the present disclosure, based on the charging amount data related to each of the multiple initial service strategies, optimizing the multiple initial service strategies to obtain the target service strategy may include the following operations:

[0124] Based on the charging amount data related to each of the multiple initial service strategies, the fitness of each of the multiple initial service strategies is determined; based on the fitness and constraints of each of the multiple initial service strategies, the multiple initial service strategies are optimized to obtain multiple updated service strategies and a global optimal service strategy; and in response to meeting the termination condition, the global optimal service strategy is determined as the target service strategy.

[0125] When applying the particle swarm algorithm for optimization, the initial position information of each particle can be used to represent the initial service strategy. The fitness of each particle can be calculated using formula (4), and then the particle can be updated by population evolution, including updating the particle position and particle speed.

[0126] Optionally, for multiple particles corresponding to multiple initial service strategies, the particle position of the particle can be represented by the initial service strategy, and the particle speed of the particle can be generated by random generation. In the initialization state, for the multiple particles, the individual best position of each particle can be represented as the current position of the particle, and then the individual best position of the particle can be represented as the best position among all the positions experienced by the particle. The global best position of the particle group can be determined based on the individual best positions of the multiple particles, which will not be described in detail here. The particle speed can be updated as shown in formula (5):

[0127] v i (t+1)=w·v i (t)+c1·rand1·(pbest i -x i )+c2·rand2·(gbest-x i ) (5)

[0128] In formula (5), v i (t) can represent the current velocity of particle i, v i (t+1) can represent the speed of particle i in the next step; c1 and c2 can be represented as acceleration factors, which can be used as hyperparameters and pre-set by the user; pbest i It can represent the individual optimal position of particle i; x i It can represent the current position of particle i; gbest can represent the global best position of the particle swarm; rand1 and rand2 can be represented as random numbers with a value range of [0, 1]; w represents the inertia weight.

[0129] The inertia weight can be used as a hyperparameter and preset by the user, or it can be adaptively adjusted with the number of iterations, as shown in formula (6):

[0130]

[0131] In formula (6), w max and w min They represent the maximum and minimum values ​​of the set inertia weight, t represents the number of current iterations, and t max Indicates the maximum number of iterations. Adjusting the inertia weight according to the number of iterations or the progress of the algorithm can enhance the convergence speed and global search capability of the algorithm.

[0132] Based on the adjusted particle velocity, the particle position can be updated as shown in formula (7):

[0133] x i (t+1)=x i (t)+vi (t+1) (7)

[0134] In formula (7), x i (t) can represent the current position of particle i, x i (t+1) can represent the position of particle i in the next step. The position of particle i in the next step can be represented as the updated service strategy.

[0135] According to an embodiment of the present disclosure, in response to the termination condition not being met, the charging amount data related to the updated service strategy can be determined based on the updated service strategy and the historical data sequence of the target site; and the updated service strategy and the global optimal service strategy can continue to be optimized based on the charging amount data related to the updated service strategy.

[0136] The termination condition can be set by the user. For example, the termination condition can be set to stop the iterative optimization when the number of iterations reaches a threshold, and determine the global optimal position of the particle swarm obtained in the end. It is represented as the target service strategy. Optionally, the termination condition can also be set as a reinitialization condition. For example, if the global optimal position is not updated after a certain number of iterations, the particle swarm is reinitialized. By setting the termination condition, the algorithm's global search capability for the solution space can be increased, avoiding the situation where the algorithm falls into the local optimal solution.

[0137] Fig. 9 A block diagram of a device for determining a service strategy for a charging station according to an embodiment of the present disclosure is schematically shown.

[0138] like Fig. 9 As shown, the service strategy determination device 900 for a charging station may include a first acquisition module 910 , a first determination module 920 and a first optimization module 930 .

[0139] The first acquisition module 910 is used to obtain multiple initial service strategies in response to a service strategy determination request, where the initial service strategies are used to determine an initial unit cost of the target station providing a charging service in a future time period.

[0140] The first determination module 920 is used to determine the charging amount data related to the initial service strategy based on the initial service strategy and the historical data sequence of the target station. The charging amount data related to the initial service strategy represents the time-sharing charging amount of the target station in the future period under the initial service strategy.

[0141] The first optimization module 930 is used to optimize multiple initial service strategies based on the charging amount data related to each of the multiple initial service strategies to obtain a target service strategy, which is used to determine the unit cost of the target station providing time-sharing charging services in the future period.

[0142] According to an embodiment of the present disclosure, the first determination module 920 includes a first determination submodule, a second determination submodule, and a third determination submodule.

[0143] The first determination submodule is used to obtain a historical observation data sequence of a target station, wherein the historical observation data sequence is determined from a historical data sequence of the target station based on a target feature item.

[0144] The second determination submodule is used to determine the predictable data sequence of the target station in the future time period based on the initial service strategy, the target characteristic item and the preset characteristic item.

[0145] The third determination submodule is used to input the historical observation data sequence and the predictable data sequence into the converter network to obtain the charging amount data related to the initial service strategy.

[0146] According to an embodiment of the present disclosure, the third determining submodule includes a first determining unit and a second determining unit.

[0147] The first determination unit is used to position encode the historical observation data sequence and the predictable data sequence based on the timestamp information of the data elements respectively included in the historical observation data sequence and the predictable data sequence to obtain the first feature sequence and the second feature sequence.

[0148] The second determining unit is used to input the first feature sequence and the second feature sequence into the converter network to obtain charging amount data related to the initial service strategy.

[0149] According to an embodiment of the present disclosure, a converter network includes an encoder and a decoder.

[0150] According to an embodiment of the present disclosure, the second determining unit includes a first determining subunit, a second determining subunit, a third determining subunit, and a fourth determining subunit.

[0151] The first determining subunit is used to input the first feature sequence into the encoder to obtain the first output feature.

[0152] The second determining subunit is used to input the second feature sequence into the decoder to obtain a second output feature.

[0153] The third determination subunit is used to concatenate the first output feature and the second output feature to obtain a fusion feature.

[0154] The fourth determination subunit is used to perform time series prediction based on the fusion features to obtain charging amount data related to the initial service strategy.

[0155] According to an embodiment of the present disclosure, the first determining unit includes a fifth determining subunit, a sixth determining subunit, a seventh determining subunit, and an eighth determining subunit.

[0156] The fifth determining subunit is used to determine the sub-elements corresponding to the multiple time granularities from the timestamp information of the data elements included in the historical observation data sequence.

[0157] The sixth determination subunit is used to perform feature encoding on the sub-elements corresponding to the multiple time granularities respectively to obtain multiple sub-features.

[0158] The seventh determination subunit is used to perform feature fusion on multiple sub-features to obtain a position code of the data element.

[0159] The eighth determination subunit is used to encode the multiple data elements by using the position codes of the multiple data elements included in the historical observation data sequence to obtain a first feature sequence.

[0160] According to an embodiment of the present disclosure, the device 900 for determining a service strategy of a charging station further includes a second acquisition module and an encoding module.

[0161] The second acquisition module is used to acquire the static covariate of the target station, wherein the static covariate is determined based on the geographical location information of the target station.

[0162] The encoding module is used to use static covariates to contextually encode the historical observation data sequence and the predictable data sequence respectively to obtain the third feature sequence and the fourth feature sequence.

[0163] According to an embodiment of the present disclosure, the second determining unit includes a ninth determining subunit.

[0164] The ninth determination subunit is used to input the third characteristic sequence and the fourth characteristic sequence into the converter network to obtain charging amount data related to the initial service strategy.

[0165] According to an embodiment of the present disclosure, the historical data sequence includes a historical charging amount data sequence of the target station, and the historical data sequence includes sub-data sequences corresponding to each of the plurality of characteristic items.

[0166] According to an embodiment of the present disclosure, the service strategy determination device 900 of the charging station further includes a second determination module.

[0167] The second determination module is used to determine a target characteristic item from multiple characteristic items based on the correlation coefficient between the historical charging amount data sequence and each of the multiple sub-data sequences.

[0168] According to an embodiment of the present disclosure, the second determining module includes a fourth determining submodule and a fifth determining submodule.

[0169] The fourth determination submodule is used to perform linear correlation calculations on the historical charge amount data sequence and the multiple sub-data sequences respectively, to obtain correlation coefficients between the historical charge amount data sequence and the multiple sub-data sequences.

[0170] The fifth determination submodule is used to determine that the feature item corresponding to the sub-data sequence is the target feature item when the correlation coefficient between the historical charging amount data sequence and the sub-data sequence is greater than a first preset value or less than a second preset value, wherein the first preset value>0>second preset value.

[0171] According to an embodiment of the present disclosure, the first optimization module 930 includes a first optimization submodule, a second optimization submodule, and a third optimization submodule.

[0172] The first optimization submodule is used to determine the fitness of each of the multiple initial service strategies based on the charging amount data related to each of the multiple initial service strategies.

[0173] The second optimization submodule is used to optimize the multiple initial service strategies based on their respective fitness and constraint conditions to obtain multiple updated service strategies and a global optimal service strategy.

[0174] The third optimization submodule is used to determine the global best service strategy as the target service strategy in response to meeting the termination condition.

[0175] According to an embodiment of the present disclosure, the constraint condition includes at least one of the following: a charging capacity constraint determined based on equipment conditions of the target station, and a range constraint on the unit cost of the charging service provided by the target station.

[0176] According to an embodiment of the present disclosure, the service strategy determination device 900 of the charging station further includes a third determination module and a second optimization module.

[0177] The third determination module is used to determine the charging amount data related to the updated service strategy based on the updated service strategy and the historical data sequence of the target station in response to the termination condition not being met.

[0178] The second optimization module is used to continue optimizing the updated service strategy and the global optimal service strategy based on the charging amount data related to the updated service strategy.

[0179] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0180] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0181] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method as described above.

[0182] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method as described above.

[0183] Fig.10 A schematic block diagram of an example electronic device that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0184] like Fig.10 As shown, the electronic device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0185] A number of components in the device 1000 are connected to an input / output (I / O) interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0186] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as a service policy determination method for a charging station. For example, in some embodiments, the service policy determination method for a charging station may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the service policy determination method for the charging station described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the service strategy determination method for the charging station in any other appropriate manner (for example, by means of firmware).

[0187] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0189] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0191] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0192] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0193] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0194] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining a service strategy of a charging station, comprising: In response to the service strategy determination request, a plurality of initial service strategies are obtained, wherein the initial service strategies are used to determine an initial unit cost of the target station providing a time-sharing charging service in a future period; Based on the initial service strategy and the historical data sequence of the target station, determining charging amount data related to the initial service strategy, wherein the charging amount data related to the initial service strategy represents the time-sharing charging amount of the target station in the future period under the initial service strategy; as well as Based on the charging amount data associated with each of the multiple initial service strategies, the multiple initial service strategies are optimized to obtain a target service strategy, and the target service strategy is used to determine the unit cost of the target site providing time-sharing charging services in the future period.

2. The method according to claim 1, wherein: The determining, based on the initial service strategy and the historical data sequence of the target station, the charging amount data related to the initial service strategy includes: Acquire a historical observation data sequence of the target station, wherein the historical observation data sequence is determined from the historical data sequence of the target station based on a target feature item; Determining a predictable data sequence of the target station in the future period based on the initial service strategy, the target feature item and the preset feature item; and The historical observation data sequence and the predictable data sequence are input into a converter network to obtain charging quantity data related to the initial service strategy.

3. The method according to claim 2, wherein: The step of inputting the historical observation data sequence and the predictable data sequence into a converter network to obtain charging amount data related to the initial service strategy includes: Based on the timestamp information of the data elements respectively included in the historical observation data sequence and the predictable data sequence, position encoding is performed on the historical observation data sequence and the predictable data sequence to obtain a first feature sequence and a second feature sequence; and The first feature sequence and the second feature sequence are input into the converter network to obtain charging amount data related to the initial service strategy.

4. The method according to claim 3, wherein: The converter network includes an encoder and a decoder; The step of inputting the first feature sequence and the second feature sequence into the converter network to obtain charging amount data related to the initial service strategy includes: Inputting the first feature sequence into the encoder to obtain a first output feature; Inputting the second feature sequence into the decoder to obtain a second output feature; concatenating the first output feature and the second output feature to obtain a fused feature; and Time series prediction is performed based on the fusion features to obtain charging amount data related to the initial service strategy.

5. The method according to claim 3, wherein: Based on the timestamp information of the data elements included in the historical observation data sequence, the historical observation data sequence is position-encoded to obtain a first feature sequence, including: Determine, from the timestamp information of the data elements included in the historical observation data sequence, the sub-elements corresponding to the multiple time granularities respectively; Feature encoding is performed on the sub-elements corresponding to the multiple time granularities respectively to obtain multiple sub-features; Performing feature fusion on the multiple sub-features to obtain a position code of the data element; and The plurality of data elements included in the historical observation data sequence are encoded using their respective position codes to obtain the first feature sequence.

6. The method according to claim 3, further comprising: Acquiring a static covariate of the target station, wherein the static covariate is determined based on geographic location information of the target station; and Using the static covariate to respectively perform context encoding on the historical observation data sequence and the predictable data sequence to obtain a third feature sequence and a fourth feature sequence; The step of inputting the first feature sequence and the second feature sequence into the converter network to obtain charging amount data related to the initial service strategy includes: The third feature sequence and the fourth feature sequence are input into the converter network to obtain charging amount data related to the initial service strategy.

7. The method according to claim 2, wherein: The historical data sequence includes a historical charging amount data sequence of the target station, and the historical data sequence includes sub-data sequences corresponding to each of a plurality of characteristic items; The method further comprises: The target feature item is determined from the plurality of feature items based on the correlation coefficient between the historical charge amount data series and each of the plurality of sub-data series.

8. The method according to claim 7, wherein: The determining the target feature item from the plurality of feature items based on the correlation coefficient between the historical charge amount data sequence and each of the plurality of sub-data sequences comprises: Calculate the linear correlation between the historical charge amount data sequence and the plurality of sub-data sequences respectively, and obtain the correlation coefficient between the historical charge amount data sequence and the plurality of sub-data sequences; and When the correlation coefficient between the historical charge amount data sequence and the sub-data sequence is greater than a first preset value or less than a second preset value, the characteristic item corresponding to the sub-data sequence is determined to be the target characteristic item, wherein the first preset value>0>the second preset value.

9. The method according to claim 1, wherein: Based on the charging amount data related to each of the multiple initial service strategies, the multiple initial service strategies are optimized to obtain a target service strategy, including: determining, based on the charge amount data associated with each of the plurality of initial service strategies, a fitness level of each of the plurality of initial service strategies; Based on the fitness and constraint conditions of each of the multiple initial service strategies, the multiple initial service strategies are optimized to obtain multiple updated service strategies and a global optimal service strategy; and In response to satisfying a termination condition, determining the global best service policy as the target service policy.

10. The method according to claim 9, wherein: The constraint condition includes at least one of the following: The target station provides a range constraint on the unit cost of a charging service based on a charging capacity constraint determined based on the equipment status of the target station.

11. The method according to claim 9, further comprising: In response to not satisfying the termination condition, determining charging amount data related to the updated service strategy based on the updated service strategy and the historical data sequence of the target station; as well as The updated service strategy and the global optimal service strategy are continuously optimized based on the charge amount data related to the updated service strategy.

12. A device for determining a service strategy of a charging station, comprising: A first acquisition module is used to obtain a plurality of initial service strategies in response to a service strategy determination request, wherein the initial service strategies are used to determine an initial unit cost of a target station providing a charging service in a future time period in time sharing; A first determination module is used to determine the charging amount data related to the initial service strategy based on the initial service strategy and the historical data sequence of the target station, wherein the charging amount data related to the initial service strategy represents the time-sharing charging amount of the target station in the future period under the initial service strategy; as well as The first optimization module is used to optimize the multiple initial service strategies based on the charging amount data related to each of the multiple initial service strategies to obtain a target service strategy, and the target service strategy is used to determine the unit cost of the target site to provide time-sharing charging services in the future period.

13. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 11.