A method, device and electronic device for controlling the upload of hydrogen filling station filling information

Abstract

The embodiments of this specification disclose a method, device and electronic device for controlling the upload of refueling information at a hydrogen refueling station. The method includes determining the probability of network recovery within a preset time period. Based on the probability of network recovery within the preset time period, an information reporting mode is determined, and the information reporting mode includes a first mode of postponing the centralized reporting until a preset time period has passed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode of continuous reporting based on the reporting interval corresponding to the network recovery probability. Based on the information reporting mode, the refueling information stored locally at the hydrogen refueling station is reported. In the embodiments of this specification, after the hydrogen refueling machine fails to upload to the server through the Internet, the temporarily locally stored refueling information is re-uploaded, and the local reporting mode can be dynamically switched according to the predicted probability of network recovery in the future, so as to report the refueling information in a timely manner while maximizing the utilization of network and system resources.

Description

Technical Field

[0001] The embodiments of this specification belong to the field of local storage information upload control, and particularly relate to a method, device, and electronic device for controlling the upload of hydrogen station refueling information. Background Art

[0002] Hydrogen refueling stations are locations that supply hydrogen to fuel cell vehicles. When a vehicle enters a station to refuel, it generates refueling information containing interaction data. To prevent this refueling information from occupying limited local memory for a long time, it is uploaded to the cloud for storage and management. If a hydrogen refueling station experiences a network outage, it will typically continue to attempt to report refueling information at fixed intervals until a successful report is received. This approach generates continuous reporting requests, which consumes system resources and is inefficient. Summary of the Invention

[0003] The embodiments of the present disclosure provide a method, device, and electronic device for controlling the upload of hydrogen station refueling information, aiming to solve one or more of the above-mentioned problems and other potential problems.

[0004] According to the first aspect of the present disclosure, a method for uploading and controlling refueling information of a hydrogen refueling station is provided, the method comprising determining the probability of network recovery within a preset duration based on the network interruption time and signal strength at the current moment. The method further comprises determining an information reporting mode based on the network recovery probability within the preset duration, the information reporting mode comprising a first mode of postponing centralized reporting until a preset duration has elapsed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode of continuously reporting based on the reporting interval corresponding to the network recovery probability. In addition, the method further comprises reporting the refueling information stored locally at the hydrogen refueling station based on the information reporting mode.

[0005] According to the second aspect of the present disclosure, a device for uploading refueling information of a hydrogen refueling station is provided, and the device includes a recovery probability determination module, which is configured to determine the probability of network recovery within a preset time period based on the network interruption time and signal strength at the current moment. The device also includes a reporting mode determination module, which is configured to determine the information reporting mode based on the network recovery probability within a preset time period, and the information reporting mode includes a first mode of postponing the centralized reporting until a preset time period has passed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode of continuously reporting based on the reporting interval corresponding to the network recovery probability. In addition, the device also includes a refueling information reporting module, which is configured to report the refueling information stored locally at the hydrogen refueling station based on the information reporting mode.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising one or more processors and a memory associated with the one or more processors, wherein the memory is used to store program instructions. When the program instructions are read and executed by the one or more processors, the method provided according to the first scheme is executed.

[0007] According to a fourth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method provided according to the first aspect is implemented.

[0008] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram illustrating an example environment in which various embodiments of the present disclosure may be implemented;

[0011] Figure 2 A schematic diagram showing a flow chart of a method for controlling the upload of hydrogen filling information at a hydrogen filling station according to some embodiments of the present disclosure;

[0012] Figure 3 A schematic diagram showing a process flow of processing various information reporting modes in some embodiments of the present disclosure;

[0013] Figure 4 A schematic diagram showing a process flow of batch division of filling information according to some embodiments of the present disclosure;

[0014] Figure 5 A flowchart illustrating a training process of a prediction model according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic diagram showing the structure of a control device for uploading refueling information of a hydrogen refueling station according to some embodiments of the present disclosure is shown;

[0016] Figure 7 A schematic block diagram of an electronic device according to some embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0018] The terms "including" and "having," and any variations thereof, in this specification, claims, and drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus. Depending on the context, the word "if," as used herein, may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0019] As previously mentioned, after a hydrogen vehicle is refueled at a hydrogen refueling station, the station generates refueling information based on the refueling process. This refueling information may include the date of hydrogen refueling, the vehicle's license plate number, the cylinder registration number, the amount of hydrogen consumed, the transaction amount, the inspector's identity, the refueler's identity, the invoice QR code, and the invoice receipt. This refueling information needs to be promptly uploaded to a cloud server for storage to record, manage, and archive each refueling event, preventing the loss of some refueling information at the station due to force majeure. Furthermore, the local memory of a hydrogen refueling station is generally limited. By promptly uploading refueling information to the cloud server, the local system can operate effectively and stably. In practice, the network at a hydrogen refueling station may experience certain fluctuations, resulting in occasional network disconnections. This can prevent the refueling information from being uploaded immediately, forcing it to be stored locally at the station for a long time. Currently, the solution to this problem is to continuously attempt to report the refueling information at regular intervals after a network disconnection until the refueling information is successfully reported upon network recovery. This method will frequently occupy the system resources of the hydrogen refueling station to continuously try to report data, resulting in a heavy network load. It may also cause secondary network paralysis due to intensive retries and even affect the stable operation of the local system of the hydrogen refueling station.

[0020] To address this issue, the disclosed embodiments propose a control scheme for uploading hydrogen station refueling information. In this embodiment, the probability of network recovery within a certain period of time is estimated based on network parameters at the time of the network interruption (such as network interruption duration and signal strength). Based on the estimated network recovery probability, different information reporting modes are selected to implement the reporting strategy for the interruption, and locally stored refueling information is reported according to the corresponding reporting strategy.

[0021] Through the above method, the present application can estimate the probability of network recovery in the future based on the network interruption time and signal strength at the moment of network interruption, and select an information reporting mode that can maximize resource utilization based on the estimated network recovery probability to report the locally stored refill information. In this way, the information reporting mode can be determined more accurately based on the network interruption situation that occurred recently, and under the selected information reporting mode, the refill information can be reported as early as possible, more efficiently, and accurately, thereby reducing the number of invalid reporting attempts and further reducing the system load caused by the reporting.

[0022] Figure 1 1 shows a schematic diagram of an example environment 100 in which various embodiments of the present disclosure may be implemented. Figure 1 As shown, environment 100 may include a terminal 110, a hydrogen refueling machine 120, and a cloud 130. Terminal 110 may be any device with computing or processing capabilities. For example, terminal 110 may include, but is not limited to, a mobile phone, a tablet computer, a desktop computer, a server, etc. After receiving a refueling instruction from terminal 110, hydrogen refueling machine 120 will perform a refueling operation on the currently connected hydrogen refueling vehicle according to the refueling instruction. During the refueling operation, it will generate corresponding refueling information 115 and send it to terminal 110 for local storage. If refueling information 115 is locally stored, terminal 110 will upload it to cloud 130 and delete the locally stored refueling information 115 after successful upload to the cloud to conserve local resources. If terminal 110 detects a network interruption between the terminal 110 and cloud 130, resulting in a failure to upload refueling information 115, terminal 110 will estimate the network recovery probability 113 based on the network interruption time 111 and signal strength 112. Next, the terminal 110 selects an information reporting mode 114 according to the network recovery probability 113 , and reports the refill information 115 according to the selected information reporting mode 114 , so as to attempt to report the refill information 115 to the cloud 130 .

[0023] Figure 2 1 shows a flow chart of a method 200 for controlling the upload of hydrogen filling station filling information according to some embodiments of the present disclosure. The method 200 may be executed by the terminal 110, for example. Figure 2As shown, at block 202, method 200 may determine the probability of network recovery within a preset duration based on the current network outage time and signal strength. In this embodiment, when a network outage occurs, the terminal may first obtain the current network outage time and network signal strength, and then estimate the probability of network recovery within a preset duration (e.g., 10 minutes) based on the network outage time and signal strength. The network outage time may be the time when the refill information fails to be reported, or the time when the network outage is detected, and the network signal strength data collected at that time may be used as the signal strength. As an example, a prediction model, such as a Long Short-Term Memory (LSTM) model, may be pre-trained based on historical data of network outages. The obtained network outage time and signal strength are input into the prediction model to obtain the network recovery probability output by the prediction model. As another example, a mapping relationship between network outage time, signal strength, and network recovery probability may be pre-set based on historical data and human experience. The corresponding network recovery probability may be obtained by querying this mapping relationship. Among them, in order to avoid the excessive amount of data, which makes the construction of the prediction model or mapping relationship too difficult or complicated, the network interruption time can be accurate to only minutes, and the signal strength can be divided into intensity levels according to intervals. For example, the length of an interval is 5dBm, and the signal strength in the same interval is regarded as the intensity level corresponding to the interval, and the preset signal strength corresponding to the intensity level is used as the actual signal strength. For example, assuming that the signal strength at this time is 84dBm, which belongs to the interval of 81dBm to 85dBm, and the interval uses the middle value of 83dBm as the preset signal strength, then when actually training is performed, the signal strength at this time will be considered to be 83dBm. In other embodiments, if the amount of data used for training is not large, or in order to further improve the accuracy of the model, the network interruption event can be accurate to seconds, for example, and the signal strength is not divided by intervals but the original value is directly used.

[0024] At block 204, method 200 may determine an information reporting mode based on the probability of network recovery within a preset duration. The information reporting modes include a first mode in which centralized reporting is postponed until a preset duration has elapsed, a second mode in which batch reporting is performed using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode in which continuous reporting is performed based on the reporting interval corresponding to the network recovery probability. In this embodiment, three probability intervals may be pre-divided, and an information reporting mode may be set for each probability interval. The corresponding mode is then selected as the current information reporting mode based on the probability interval corresponding to the network recovery probability. The relationship between different probability intervals and different modes can be configured based on actual needs. For example, if the probability of network recovery is high, it can be assumed that there is a high probability that the network has recovered at the corresponding time after the preset duration. In this case, the first mode may be configured to attempt to uniformly report data after the preset duration, i.e., at the time when the network is deemed to have recovered with a high probability, thereby reducing the number of unnecessary reporting attempts within the preset duration and conserving system resources. If the probability of network recovery is low, it can be assumed that even after a preset period of time, there's no guarantee that the network will recover. This means that waiting for the preset period before reporting uniformly is not very meaningful. Instead, it will cause more unuploadable annotation information to accumulate during this period, occupying system memory. Furthermore, due to limited system resources and the continuous generation of annotation information, reporting cannot be completely abandoned simply because of a poor network. Otherwise, if the accumulated annotation information exceeds the local storage capacity, some of the annotation information will be lost. Therefore, a third mode can be set to determine the reporting interval based on the probability of network recovery (for example, the lower the probability of network recovery, the longer the reporting interval, to reduce resource usage when the probability of recovery is particularly low). Attempts to report annotation information are then made continuously based on this reporting interval. While still using some system resources, multiple reporting attempts are made to consume as much redundant and accumulated annotation information as possible, thus avoiding the continuous accumulation of annotation information and the long-term resource consumption. If the probability of network recovery is too low (for example, below 10%), no reporting mode can be used, and a system alarm can be issued directly to alert personnel to manually repair the network. If the probability of network recovery is medium, a second mode can be set to report the accumulated filling information in batches using an exponential backoff algorithm. The specific value of the initial reporting interval used by the exponential backoff algorithm can be dynamically adjusted based on the actual network recovery probability to balance the success rate and resource consumption. In the second mode, the filling information can be divided into batches based on the time period of data storage, the order of data storage, and a fixed amount of data as a batch. In addition, if the number of successfully uploaded filling information is less than the preset number during two consecutive rounds of reporting attempts, a system alarm will be issued.

[0025] At block 206, method 200 may report the refueling information stored locally at the hydrogen refueling station based on the information reporting mode. In this embodiment, after the information reporting mode is determined, the locally stored refueling information will be reported using the information reporting mode within a preset duration. Once the refueling information is successfully reported, the corresponding refueling information will be deleted locally. If the refueling information is still not successfully reported after the preset duration, the next round of reporting processing will be performed. At this time, the time after the preset duration can be used as the new network interruption time, and the network recovery probability can be re-estimated based on the signal strength at that time. The corresponding mode will be selected for the next round of reporting based on the newly obtained network recovery probability.

[0026] In this way, the selected information reporting model can be switched according to the determined network recovery probability to adjust the reporting strategy of the replenishment information, maximize the utilization of network and system resources, and ensure that the replenishment information can be reported as early, efficiently and accurately as possible while minimizing the number of invalid reporting attempts.

[0027] Figure 3 A flowchart illustrating a process 300 for processing various information reporting modes in some embodiments of the present disclosure is provided. In process 300, based on the current network outage duration 311 and signal strength 312, a probability 320 of network recovery within a preset duration is determined, and a probability range 330 corresponding to the network recovery probability 320 is determined. If probability range 330 falls within a preset high probability range (e.g., above 80%), first mode 340 is selected as the current information reporting mode. In block 350, a preset duration is waited for, and after the preset duration, the network is deemed to have recovered with a high probability, and all locally stored addition information is reported. If probability range 330 falls within a preset low probability range (e.g., between 10% and 30%), third mode 342 is selected as the current information reporting mode. In block 370, each addition information is reported sequentially according to the reporting interval corresponding to the network recovery probability (e.g., 30 seconds). This means that the next addition information is reported only after the previous addition information has been successfully reported.

[0028] If probability range 330 is within the preset medium probability range (e.g., between 30% and 80%), second mode 341 is selected as the current information reporting mode. In second mode 341, the probability difference 360 ​​between the obtained network recovery probability and a preset probability (e.g., a reference value arbitrarily selected within the medium probability range, such as 50%) is first calculated. Different probability differences 360 can be pre-set with different initial reporting intervals, and probability difference 360 ​​can be negative. A larger probability difference 360 ​​indicates a greater probability of network recovery after the preset duration. Consequently, frequent retries within the preset duration are unnecessary. Instead, attempts can be made later, when the network is more likely to recover. Consequently, the initial reporting interval in the exponential backoff algorithm is increased. Furthermore, the backoff factor 362 in the exponential backoff algorithm can be set based on signal strength 312. Since the network recovery probability is only an estimate, in this embodiment, under the same network recovery probability, a greater signal strength 312 indicates a more stable network signal and a higher likelihood of faster recovery within a preset timeframe. To minimize system load, a smaller backoff factor can be set to shorten the interval between retries after a failed report, allowing redundant information to be reported as soon as possible. After the information is divided into batches, the information for each batch is reported according to batch priority. In block 363, the current batch to be reported is determined, and the information is reported according to the current reporting interval 361, which can initially be the initial reporting interval. After a report is submitted, block 380 determines whether the report was successful. If the report failed, the current reporting interval 361 is multiplied by the backoff factor 362 to obtain a new current reporting interval 361, which is then used for the next report. Each time a reporting failure is multiplied by the current reporting interval 361, the backoff factor 362 is re-determined based on the signal strength reacquired at the time of the multiplication, enabling dynamic adjustment of the backoff factor 362 and, consequently, the current reporting interval 361. In block 390, if the reporting is successful, the current reporting interval 361 is restored to its initial state, and the next batch of refill information is reported. Furthermore, if the cumulative reporting interval exceeds a preset duration, the reporting process is halted, the network recovery probability 320 is re-determined based on the network outage time 311 and signal strength 312, and the information reporting mode is re-selected for the next round of reporting.

[0029] Figure 4A flow chart of the batch division process 400 of the annotation information of some embodiments of the present disclosure is shown. In the process 400, the annotation information 410 can be classified to obtain core data 420 and non-core data 430. Next, based on the current network bandwidth, it will be determined whether the current network bandwidth is small (that is, whether it is less than the preset bandwidth). If the bandwidth is small, in order to avoid the situation where the system is stuck and paralyzed due to exceeding the bandwidth even if the network is restored, and then the reporting of the information fails, the data will be compressed at this time. The core data 420 is more important and will be compressed losslessly, while the non-core data 430 will be compressed losslessly. If the bandwidth is sufficient, the core data 420 will not be compressed, and only the non-core data 430 will be compressed losslessly. When the annotation information is divided into batches, the uncompressed core data 421 can be divided into the first batch 440, the compressed core data 422 can be divided into the second batch 441, the uncompressed non-core data 432 can be divided into the third batch 442, and the compressed non-core data 431 can be divided into the fourth batch 443 according to the order of batch priority from high to low.

[0030] Figure 5A flowchart illustrating a training process 500 for a prediction model according to some embodiments of the present disclosure is provided. In process 500, each historical interruption data 510 includes a historical network interruption time 511, a historical recovery duration 512, and a historical signal strength 513. By comparing the historical recovery duration 512 with a preset duration 514, it is possible to determine whether the historical interruption data 510 had network recovery within the preset duration. A label is then assigned to each historical interruption data 510 based on the comparison result. Subsequently, all historical interruption data 510 with the same historical network interruption time 511 and historical signal strength 513 are grouped together as a set, and each set is processed separately. For any set, the percentage of historical interruption data 510 with a label representing network recovery relative to all historical interruption data 510 in the set is determined, thereby determining the historical network recovery probability 520-2 for the historical interruption data 510 under the combination 520-1 of the historical network interruption time 511 and historical signal strength 513. After determining the historical network recovery probabilities 520-2 corresponding to all combinations 520-1, a training set 520 can be constructed and used to train the prediction model 530. During the training process, the generator 531 of the prediction model 530 can generate a predicted network recovery probability 532 based on the combination 520-1. The generator loss 533 is used to perform a loss judgment on the predicted network recovery probability 532. The loss judgment can be judged using a comparative loss function. The generator loss 533 can be a large value, and the generator loss 533 can then be backpropagated to the generator 531 to guide the optimization of the parameters of the generator 531. This training process can be performed iteratively until the generator 531 is able to generate a more accurate predicted network recovery probability 532. After the training process is completed, the prediction model 530 can output the network recovery probability 540 within a preset time period.

[0031] As an example, assume there are 500 historical outage data points for training. All historical outage data points with the same historical network outage duration and historical signal strength are grouped together, for example, into 10 groups, each containing multiple historical outage data points. For any group, assume the preset duration is 10 minutes, a group contains 50 historical outage data points, and 30 of the historical outage data points corresponding to the group have a recovery duration of less than 10 minutes (i.e., the number of historical outage data points labeled as network recovery within the preset duration is 30). If the ratio of historical outage data points labeled as network recovery within the preset duration to all historical outage data points in the group is calculated to be 30 / 50, then the historical network recovery probability for this group is 60%. The trained prediction model is not used to predict a specific recovery time (the predicted recovery time is based on an ideal recovery time, which often differs from the actual recovery time and is difficult to use as a benchmark). Instead, it is used to predict the probability of network recovery within the preset duration, so that different information reporting modes can be selected based on different probabilities. In this way, you do not need to pay attention to the specific time when the network is restored. You only need to adjust the reporting strategy according to different information reporting models to report the recharge information as early as possible in a way that minimizes system resource usage.

[0032] Figure 6 The following is a schematic diagram showing the structure of the upload control device 600 for hydrogen filling station filling information of some embodiments of the present disclosure. The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Figure 6 As shown, the device 600 includes a recovery probability determination module 601, which is configured to determine the network recovery probability within a preset time period based on the network interruption time and signal strength at the current moment. The device 600 also includes a reporting mode determination module 602, which is configured to determine the information reporting mode based on the network recovery probability within a preset time period. The information reporting mode includes a first mode of postponing the centralized reporting until a preset time period has passed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode of continuously reporting based on the reporting interval corresponding to the network recovery probability. In addition, the device 600 also includes a refueling information reporting module 603, which is configured to report the refueling information stored locally at the hydrogen refueling station based on the information reporting mode.

[0033] The reporting mode determination module 602 includes a first determination unit configured to determine the information reporting mode as the first mode in response to a probability range corresponding to the network recovery probability within a preset duration being within a preset high probability range. The reporting mode determination module 602 also includes a second determination unit configured to determine the information reporting mode as the second mode in response to a probability range corresponding to the network recovery probability within a preset duration being within a preset medium probability range. The reporting mode determination module 602 also includes a third determination unit configured to determine the information reporting mode as the third mode in response to a probability range corresponding to the network recovery probability within a preset duration being within a preset low probability range.

[0034] The refill information reporting module 603 includes a fourth determination unit configured to, in response to the second mode, determine an initial reporting interval based on a probability difference between a network recovery probability within a preset duration and a preset probability, where the probability difference is positively correlated with the initial reporting interval. The refill information reporting module 603 also includes a fifth determination unit configured to determine a backoff factor based on signal strength, where the signal strength is negatively correlated with the backoff factor. The refill information reporting module 603 also includes a batch reporting unit configured to divide each refill information into batches and report the refill information in batches based on an exponential backoff algorithm.

[0035] The device 600 also includes a batch division module, which is configured to classify the annotation information based on data priority, and the classified data categories include core data and non-core data. The device 600 also includes a first compression module, which is configured to perform lossless compression on the core data and lossy compression on the non-core data in response to the current network bandwidth being less than the preset bandwidth. The device 600 also includes a second compression module, which is configured to perform lossless compression on the non-core data in response to the current network bandwidth being not less than the preset bandwidth. The batch reporting unit includes a batch division element, which is configured to divide the annotation information into a first batch corresponding to the uncompressed core data, a second batch corresponding to the compressed core data, a third batch corresponding to the uncompressed non-core data, and a fourth batch corresponding to the compressed non-core data in order of batch priority from high to low.

[0036] The batch reporting unit also includes a first response element configured to report the batch's filling information based on the current reporting interval in response to the currently reported batch, until the batch reporting is successful or the cumulative reporting interval exceeds a preset duration. The current reporting interval is initially defined as the initial reporting interval. The batch reporting unit also includes a second response element configured to determine a backoff factor based on the current signal strength in response to a batch reporting failure, and use the product of the backoff factor and the current reporting interval as the new current reporting interval. The batch reporting unit also includes a third response element configured to report the next batch in response to a successful batch reporting.

[0037] In apparatus 600, the probability of network recovery within a preset duration is obtained based on the prediction model. Apparatus 600 also includes a training set construction module configured to determine a training set from historical outage data. The training set includes a combination of historical network outage duration and historical signal strength, and the historical network recovery probability corresponding to the combination. Apparatus 600 also includes a training module configured to train the prediction model based on the combination and the historical network recovery probability.

[0038] The training set construction module includes a label setting unit, which is configured to set labels for historical interruption data based on the comparison results of the recovery time and the preset time. Each historical interruption data includes the historical network interruption time, the historical recovery time and the historical signal strength. The label is used to indicate whether the historical interruption data restored the network within the preset time. The training set construction module includes a proportion calculation unit, which is configured to determine the historical network recovery probability corresponding to the combination of historical network interruption time and historical signal strength based on the proportion of historical interruption data characterized by the label as restoring the network within the preset time for each historical interruption data with the same historical network interruption time and historical signal strength. The training set construction module includes a training set construction unit, which is configured to construct a training set based on the combination and the historical network recovery probability.

[0039] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0040] Figure 71 shows a block diagram of an electronic device 700 that can implement various embodiments of the present disclosure. Figure 7 As shown, electronic device 700 includes a processor 710, a disk drive 720, an input / output interface 730, a network interface 740, and a memory 750. The processor 710, disk drive 720, input / output interface 730, network interface 740, and memory 750 can be communicatively connected via a communication bus 760.

[0041] The processor 710 may be implemented as a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and may be used to execute relevant programs to implement the technical solutions provided in this application.

[0042] The memory 750 can be implemented in the form of ROM (Read Only Memory), RAM (Read Access Memory), static memory, dynamic storage devices, etc. The memory 750 can store an operating system 751 for controlling the operation of the electronic device 700 and a basic input and output system (BIOS) 752 for controlling the low-level operations of the electronic device 700. In addition, a web browser 753, a data storage management system 754, etc. can also be stored. In short, when the technical solutions provided in this application are implemented through software or firmware, the relevant program code is stored in the memory 750 and is called and executed by the processor 710.

[0043] The input / output interface 730 is used to connect to an input / output module to enable information input and output. The input / output module can be configured as a component within the device (not shown) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc. Output devices may include a display, speaker, vibrator, indicator light, etc.

[0044] The network interface 740 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via wired means (e.g., USB, network cable, etc.) or wireless means (e.g., mobile network, Wi-Fi, Bluetooth, etc.).

[0045] The bus 760 comprises a pathway for transmitting information between the various components of the device (eg, the processor 710 , the disk drive 720 , the input / output interface 730 , the network interface 740 , and the memory 750 ).

[0046] It should be noted that although the above device only shows the processor 710, disk drive 720, input / output interface 730, network interface 740, memory 750, bus 760, etc., in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will understand that the above device may only include the components necessary to implement the method of the present application, and does not necessarily include all the components shown in the figure.

[0047] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0048] In the context of this 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, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations be performed to achieve the desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented in multiple implementations individually or in any suitable subcombination.

[0049] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for controlling the upload of hydrogen filling station filling information, characterized in that: The method comprises: Determine the probability of network recovery within a preset time period based on the current network outage duration and signal strength; Determining an information reporting mode based on the network recovery probability within the preset time period, the information reporting mode including a first mode of postponing centralized reporting until a preset time period has passed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts the initial reporting interval based on the network recovery probability, and a third mode of continuous reporting based on a reporting interval corresponding to the network recovery probability; and Based on the information reporting mode, the refueling information stored locally at the hydrogen refueling station is reported, including: In response to the second mode, determining an initial reporting interval based on a probability difference between the network recovery probability within the preset time period and a preset probability, wherein the probability difference is positively correlated with the initial reporting interval; determining a backoff factor based on the signal strength, the signal strength being negatively correlated with the backoff factor; and After the filling information is divided into batches, the filling information is reported in batches based on an exponential backoff algorithm, including: In response to a currently reported batch, reporting the filling information of the batch based on a current reporting interval until the batch is successfully reported or the cumulative reporting interval is greater than the preset time length, the current reporting interval being the initial reporting interval in an initial state; In response to a batch reporting failure, determining the backoff factor based on the signal strength at the current moment, and taking the product of the backoff factor and the current reporting interval as the new current reporting interval; and In response to the batch reporting being successful, the next batch is reported.

2. The method according to claim 1, characterized in that The determining of the information reporting mode based on the network recovery probability within the preset time period includes: In response to the probability range corresponding to the network recovery probability within the preset time period being a preset high probability range, determining the information reporting mode to be the first mode; In response to the probability range corresponding to the network recovery probability within the preset time period being a preset medium probability range, determining the information reporting mode to be the second mode; and In response to the probability range corresponding to the network recovery probability within the preset time period being a preset low probability range, the information reporting mode is determined to be the third mode.

3. The method according to claim 1, characterized in that The method further comprises: Classifying the annotation information based on data priority, wherein the classified data categories include core data and non-core data; In response to a current network bandwidth being less than a preset bandwidth, performing lossless compression on the core data and lossy compression on the non-core data; and In response to the current network bandwidth being not less than the preset bandwidth, performing lossless compression on the non-core data; The batch division of each filling information includes: According to the order of batch priority from high to low, each of the annotation information is divided into a first batch corresponding to the uncompressed core data, a second batch corresponding to the compressed core data, a third batch corresponding to the uncompressed non-core data, and a fourth batch corresponding to the compressed non-core data.

4. The method according to claim 1, wherein The network recovery probability within the preset time period is obtained based on a prediction model; The method further comprises: Determining a training set from historical outage data, the training set including a combination of historical network outage time and historical signal strength, and a historical network restoration probability corresponding to the combination; and The prediction model is trained based on the combination and the historical network recovery probability.

5. The method according to claim 4, characterized in that Determining a training set from historical interruption data includes: Based on the comparison result of the recovery time and the preset time, a label is set for the historical interruption data. Each historical interruption data includes the historical network interruption time, the historical recovery time and the historical signal strength. The label is used to indicate whether the historical interruption data is restored to the network within the preset time. Determining, for each of the historical interruption data having the same historical network interruption time and historical signal strength, a historical network recovery probability corresponding to the combination of the historical network interruption time and the historical signal strength based on a proportion of the historical interruption data characterized by the label as having network recovery within a preset time period; and A training set is constructed based on the combination and the historical network recovery probability.

6. A device for uploading hydrogen filling information at a hydrogen filling station, characterized in that: The device comprises: A recovery probability determination module is configured to determine the network recovery probability within a preset time period based on the current network interruption time and signal strength; a reporting mode determination module configured to determine an information reporting mode based on the network recovery probability within the preset time period, the information reporting modes including a first mode of postponing centralized reporting until a preset time period has passed, a second mode of reporting in batches using an exponential backoff algorithm that dynamically adjusts an initial reporting interval based on the network recovery probability, and a third mode of continuous reporting based on a reporting interval corresponding to the network recovery probability; and a refueling information reporting module configured to report the refueling information stored locally at the hydrogen refueling station based on the information reporting mode; The filling information reporting module includes: a fourth determining unit configured to determine, in response to the second mode, an initial reporting interval based on a probability difference between a network recovery probability within a preset time period and a preset probability, wherein the probability difference is positively correlated with the initial reporting interval; a fifth determining unit configured to determine a backoff factor based on signal strength, wherein the signal strength is negatively correlated with the backoff factor; A batch reporting unit is configured to divide each filling information into batches and report the filling information in batches based on an exponential backoff algorithm; the batch reporting unit includes: A first response element is configured to respond to a currently reported batch and report the filling information of the batch based on a current reporting interval until the batch is successfully reported or the cumulative reporting interval exceeds a preset time period, and the current reporting interval is initially an initial reporting interval; a second response element configured to, in response to a batch reporting failure, determine a backoff factor based on a current signal strength, and use a product of the backoff factor and a current reporting interval as a new current reporting interval; The third response element is configured to report the next batch in response to the batch reporting being successful.

7. An electronic device comprising: one or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the steps of the method according to any one of claims 1 to 5 are executed.

8. Computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images