Charging station battery life prediction method based on soft bus and related device

Abstract

The invention provides a charging station battery life prediction method based on a soft bus and a related device, and the method comprises the steps: obtaining the charging data and working data of a target vehicle on a plurality of charging devices through a control soft bus module, then processing the charging data according to a time sequence, and obtaining the working data of the target vehicle; the method comprises the following steps of: determining equipment computing resources of a computing module of each piece of charging equipment according to working data, then dividing a charging data sequence according to a computing task division rule, and allocating a plurality of division tasks to the computing module on each piece of charging equipment according to a preset computing resource allocation rule, the method comprises the steps of obtaining a plurality of calculation tasks, inputting elements in a charging data sequence in the plurality of calculation tasks into a preset battery life prediction model to obtain a plurality of prediction results, and finally optimizing the battery predicted life based on a preset attenuation factor to obtain a target prediction result. Therefore, the battery life prediction precision and efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent power distribution, in particular to a charging station battery life prediction method based on a soft bus and related devices. BACKGROUND

[0002] At present, the electric vehicle industry is experiencing rapid development. As of June 2025, the total number of new energy vehicles in China has reached 36.89 million, accounting for more than 10% of the total number of vehicles, of which pure electric vehicles account for more than 69%. The number of new registrations in the first half of the year increased by 27.86% compared with the same period last year, and the penetration rate was close to 45%, marking a shift from policy-driven to endogenous growth. Behind this explosive growth is the continuous iteration of battery technology as the core support, but the large-scale application has also exposed key pain points: the lack of accuracy in predicting the life of power batteries leads to rising operational costs, and traditional methods rely on laboratory environment simulation, which is difficult to adapt to complex and variable actual working conditions such as temperature fluctuations, charging and discharging cycles, etc., directly affecting user experience and asset preservation rate. Vehicle power battery life prediction based on charging piles has become a hot topic and is evolving towards standardization. Currently, the prediction of battery life by charging piles relies on fixed algorithms or artificial intelligence models based on historical data. However, users do not charge at the same charging pile every time, so user vehicle data is scattered in each charging pile in the field station; due to the limitations of single charging pile data, the prediction accuracy of battery life is greatly reduced.

[0003] Therefore, how to improve the prediction accuracy and efficiency of power battery life through the charging conditions of the battery station needs to be solved. SUMMARY

[0004] The embodiments of the present application provide a charging station battery life prediction method based on a soft bus and related devices, which improves the accuracy and efficiency of battery life prediction.

[0005] In a first aspect, the embodiments of the present application provide a charging station battery life prediction method based on a soft bus, applied to a control module of a local area network, wherein the local area network is composed of a plurality of charging devices interconnected through physical communication links; each charging device in the plurality of charging devices is provided with a computing module and a soft bus module, the soft bus module realizes signaling interaction between charging devices through the physical communication links based on a soft bus protocol, and the method comprises: controlling the soft bus module to obtain charging data of a target vehicle on the plurality of charging devices, and to obtain working data of the plurality of charging devices; processing the charging data in chronological order to obtain a charging data sequence; determine device computing resources of a computing module of each of the plurality of charging devices according to the working data, to obtain computing resource data; divide the charging data sequence according to a preset computing task division rule, to obtain a plurality of divided computing tasks; allocate the plurality of divided tasks to the computing module on each of the plurality of charging devices according to a preset computing resource allocation rule, to obtain a plurality of computing tasks; each of the plurality of computing tasks includes at least one element in the charging data sequence; input the element in the charging data sequence in the plurality of computing tasks into a preset battery life prediction model, to obtain a plurality of prediction results; determine a life prediction weight based on a preset decay factor, a preset life prediction weight calculation formula, and the charging data sequence, to obtain a plurality of life prediction weights; perform weighted calculation on the plurality of prediction results according to the plurality of life prediction weights, to obtain a target prediction result.

[0006] In a second aspect, an embodiment of the present application provides a charging station battery life prediction device based on a soft bus, which is applied to a control module of a local area network. The local area network is composed of a plurality of charging devices interconnected through physical communication links. Each of the plurality of charging devices is provided with a computing module and a soft bus module. The soft bus module realizes signaling interaction between the charging devices through the physical communication links based on a soft bus protocol. The device comprises: An acquisition unit is configured to control the soft bus module to acquire charging data of a target vehicle on the plurality of charging devices, and to acquire working data of the plurality of charging devices. A determination unit is configured to process the charging data in chronological order to obtain a charging data sequence, and to determine device computing resources of a computing module of each of the plurality of charging devices according to the working data, to obtain computing resource data. A control unit is configured to divide the charging data sequence according to a preset computing task division rule, to obtain a plurality of divided computing tasks; and to allocate the plurality of divided tasks to the computing module on each of the plurality of charging devices according to a preset computing resource allocation rule, to obtain a plurality of computing tasks. Each of the plurality of computing tasks includes at least one element in the charging data sequence. The computing unit is configured to input elements in the charging data sequence in the plurality of computing tasks into a preset battery life prediction model to obtain a plurality of prediction results; determine a life prediction weight based on a preset attenuation factor, a preset life prediction weight calculation formula, and the charging data sequence to obtain a plurality of life prediction weights; and perform weighted calculation on the plurality of prediction results according to the plurality of life prediction weights to obtain a target prediction result.

[0007] In a third aspect, an embodiment of the present application provides a charging device, including a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of the embodiments of the present application.

[0008] In a fourth aspect, an embodiment of the present application provides a soft bus-based charging station battery life prediction system, wherein the soft bus-based charging station battery life prediction system is configured to perform the steps in any method of the first aspect of the embodiments of the present application.

[0009] In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of the embodiments of the present application.

[0010] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer readable storage medium storing a computer program. The computer program is operable to cause a computer to perform some or all of the steps described in any method of the first aspect of the embodiments of the present application. The computer program product can be a software installation package.

[0011] By implementing the embodiments of the present application, the following beneficial effects are achieved: The embodiment of the application provides a charging station battery life prediction method based on a soft bus and a related device, the method is applied to a control module of a local area network, the local area network is composed of a plurality of charging devices interconnected through physical communication links, each charging device in the plurality of charging devices is provided with a computing module and a soft bus module, the soft bus module realizes signaling interaction between the charging devices through the physical communication links based on a soft bus protocol, and the method comprises the following steps: controlling the soft bus module to acquire charging data of a target vehicle on the plurality of charging devices and to acquire working data of the plurality of charging devices, processing the charging data in chronological order to obtain a charging data sequence, determining device computing resources of the computing module of each device in the plurality of charging devices according to the working data to obtain computing resource data, dividing the charging data sequence according to a preset computing task division rule to obtain a plurality of division computing tasks, and distributing the plurality of division tasks to the computing module on each charging device in the plurality of charging devices according to a preset computing resource distribution rule to obtain a plurality of computing tasks, wherein each computing task in the plurality of computing tasks comprises at least one element in the charging data sequence, the elements in the charging data sequence in the plurality of computing tasks are input into a preset battery life prediction model to obtain a plurality of prediction results, a life prediction weight is determined based on a preset attenuation factor, a preset life prediction weight calculation formula and the charging data sequence to obtain a plurality of life prediction weights, and the plurality of prediction results are weighted and calculated according to the plurality of life prediction weights to obtain a target prediction result. In this way, on the one hand, based on the soft bus technology, the charging historical data of each charging device in the charging station is integrated to realize data sharing, thereby improving the battery life prediction accuracy; on the other hand, through the self-organizing network capability and distributed computing power distribution and scheduling of the soft bus, the prediction tasks are reasonably distributed to idle devices, the resource occupation of a single device is reduced, and the prediction efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0013] Figure 1 It is an architecture diagram of a vehicle battery life prediction system based on a soft bus provided by the embodiment of the application. Figure 2 It is a structural schematic diagram of a charging device provided by the embodiment of the application. Figure 3 It is a flowchart of a charging station battery life prediction method based on a soft bus provided by the embodiment of the application. Figure 4is a soft bus-based charging station networking structure schematic diagram provided by an embodiment of the present application; Figure 5 is a soft bus network structure schematic diagram provided by an embodiment of the present application; Figure 6 is a soft bus-based active networking flow schematic diagram provided by an embodiment of the present application; Figure 7 is a soft bus-based passive networking flow schematic diagram provided by an embodiment of the present application; Figure 8 is a soft bus-based historical sequence management flow schematic diagram provided by an embodiment of the present application; Figure 9 is a soft bus-based charging station battery life prediction device functional module composition block diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0015] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0016] The "connection" appearing in the embodiments of the present application refers to various connection modes such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not make any limitation on this. In this document, "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0017] The related terms involved in the present application will be explained first as follows: Soft bus: It is a software architecture and communication protocol stack that runs on local area network devices. It builds a distributed collaborative framework on top of existing physical network connections, which supports automatic device discovery, service identification, standardized data exchange and resource sharing. It is a key software foundation for realizing cross-device data and computing power integration.

[0018] In the electric vehicle sector, the accuracy of power battery life prediction directly impacts the user experience. Existing charging station prediction methods rely solely on single-charge data or localized historical data from individual charging stations. Since users charge at different stations, the data is scattered across various charging points, leading to a significant decrease in prediction accuracy. Furthermore, the data limitations of individual charging stations prevent prediction algorithms from fully utilizing global data, and centralized computing deployment can result in excessive equipment resource consumption, affecting system response and stability.

[0019] To address the aforementioned problems, this application provides a method and related apparatus for predicting the battery life of a charging station based on a soft bus. This method is applied to a control module of a local area network (LAN). The LAN consists of multiple charging devices interconnected via physical communication links. Each charging device is equipped with a computing module and a soft bus module. The soft bus module uses a soft bus protocol to enable signaling interaction between the charging devices via the physical communication links. The method includes: controlling the soft bus module to acquire charging data of a target vehicle on multiple charging devices, and acquiring working data from multiple charging devices; processing the charging data in chronological order to obtain a charging data sequence; and determining the computing resources of the computing module of each charging device based on the working data to obtain computing resources. The source data is divided into multiple computational tasks according to a preset computational task partitioning rule. These tasks are then allocated to the computational modules of each of the multiple charging devices according to a preset computational resource allocation rule. Each computational task includes at least one element from the charging data sequence. The elements from the charging data sequence in these multiple computational tasks are input into a preset battery life prediction model, resulting in multiple prediction results. Based on a preset attenuation factor, a preset life prediction weight calculation formula, and the charging data sequence, life prediction weights are determined, resulting in multiple life prediction weights. Finally, the multiple prediction results are weighted and calculated to obtain the target prediction result. This improves the accuracy and efficiency of battery life prediction.

[0020] The following is combined Figure 1 The system architecture of a vehicle battery life prediction method based on a soft bus, as described in the embodiments of this application, is explained. Figure 1Figure 1 is a schematic diagram of a vehicle battery life prediction system based on a soft bus according to an embodiment of the present application. The vehicle battery life prediction system based on a soft bus 100 comprises a soft bus module 110, a prediction algorithm 120 and a bottom interface 130.

[0021] The soft bus module 110 is configured to implement network management, communication protocol processing and unified management of charging history sequences among multiple charging devices in a charging station. The soft bus module 110 comprises a network management unit 111, a protocol framework unit 112 and a history sequence management unit 113. The network management unit 111 is configured to perform network identification, online state detection, device topology confirmation and logical grouping management on the charging devices. In one possible embodiment, the network management unit 111 can complete device online detection based on the heartbeat frame mechanism of the soft bus protocol, and trigger topology update operations when new devices are detected to join or devices are detected to be offline, thereby ensuring real-time mastery of the state of the devices by the system. The protocol framework unit 112 is configured to perform soft bus protocol analysis, data calibration, message routing and synchronization control on the physical communication link, to ensure that the charging devices share a unified communication format and interaction logic. The protocol framework unit 112 can support multiple underlying communication methods (such as Ethernet, serial link or CAN link), and shield the communication differences between different devices through the protocol layer, so that the vehicle battery life prediction system based on a soft bus 100 can implement consistent data exchange processes in a heterogeneous device environment. Preferably, the protocol framework unit 112 can use a reliable transmission mechanism to perform segmented transmission of large-scale historical charging data across devices, thereby improving transmission stability. The history sequence management unit 113 is configured to collect, time-align, format and store the charging data of the target vehicle from different charging devices, to provide a structured data basis for subsequent task division and prediction model input. In one possible embodiment, the history sequence management unit 113 can perform time sequence reconstruction of cross-device data based on a unified timestamp system, so that continuous and complete charging history sequences can be generated, thereby effectively solving the problem of scattered data caused by charging of the vehicle at different charging piles. For a clearer description, the details of the protocol framework unit 112 are described below. The protocol framework in the protocol framework unit 112 formulates a standard communication protocol and soft bus function requirements for the application scenario. The main communication content of the soft bus module 110 includes two types of data, namely data and files, and also needs to meet certain protocol compatibility. Based on these requirements, a standard protocol based on JSON format and oriented to event objects is constructed.

[0022] The protocol frame format is shown in Table 1 as follows: Table 1 Protocol frame format framework

[0023] Wherein, the service identification is composed of 1 byte service identification string length and service standard string, used for expressing the function object of current content service; for example, the service identification string of current battery life prediction function is "BATREM_PREDICT"; the operation instruction is used for indicating the instruction set of current frame, including: probe login (0x01), back connection login (0x02), data transmission (0x10), file transmission (0x20); the multi-frame identification is composed of 2 byte packet quantity and 2 byte packet serial number, used for indicating whether the current frame is multi-frame transmission; when the packet quantity is 0 or 1, indicating single packet transmission; when the packet quantity is greater than 1, it is multi-packet transmission, at this time, packet processing is needed after all packet receiving is completed; the data field is the target data content of transmission, composed of 2 byte data length and several byte data content; wherein, in order to ensure transmission reliability, the maximum length of data content is 2048 bytes, for large data transmission, the form of multi-packet is adopted. According to the difference of operation instruction, the data and content are different, see the following table 2, table 3 and table 4: Table 2 Login frame data field

[0024] Table 3 Data transmission frame data field

[0025] Table 4 File transmission frame data field

[0026] Based on the above communication protocol framework and the current function scene, define the data transmission frame, including: HeartBeat (HeartBeat), VirtDir (VirtDir). Among them, HeartBeat is used for connection state management. When the server has not received the HeartBeat frame of a connected device for a long time, it is considered that the communication has been interrupted; At this time, the connection will be disconnected, and the event transmitter will be logged out of the connection with the device. VirtDir is used to expose the file list in the current device and service sandbox directory. The sandbox directory is a virtual folder based on the file sharing function of the soft bus framework; In the current device, it is actually a JSON format file (.json). In the content of the sandbox JSON file, the key name is the service name, and the key value is a string array. Each string member is the absolute path of the file to be exposed. When the sandbox file content changes or the two devices complete the networking association, a VirtDir frame broadcast will be triggered. The historical sequence management unit is realized based on the above VirtDir frame and file transmission frame. In the current vehicle battery life prediction service, the single charging historical sequence file name rule is specified as: start time + vehicle unique identification code (VIN code). Because the charging start needs to be started remotely through the cloud platform, it can be considered that the charging pile device has completed the platform time, and the vehicle VIN code has uniqueness; Therefore, each charging historical sequence file has uniqueness, and the time period does not overlap.

[0027] Among them, the prediction algorithm 120 is used to perform model calculation required for vehicle battery life prediction, and the prediction algorithm 120 includes a distributed computing unit 121 and an algorithm unit 122. The distributed computing unit 121 is used to distribute the computing task among multiple computing nodes according to the evaluation result, realize parallel processing, and improve the computing efficiency of the life prediction. In one possible embodiment, the distributed computing unit 121 can combine device computing power, task queue length, and current workload to dynamically schedule prediction tasks to fully utilize the available resources of the station. The algorithm unit 122 is used to load the preset battery life prediction model, and performs prediction reasoning based on the serialized charging data, and finally outputs the prediction result. Preferably, the algorithm unit 122 can use a life prediction method based on a recurrent neural network or a time series degradation model, and obtain the remaining life estimate value of the vehicle battery by comprehensively analyzing the charging mode, temperature change trend and battery degradation speed.

[0028] The underlying interface 130 provides basic communication and data interaction capabilities for the soft bus module 110 and the prediction algorithm 120. The underlying interface 130 includes a network interface 131, a file interface 132, and an algorithm model interface 133. The network interface 131 connects to the physical communication link, providing a low-level data transmission channel to the soft bus module; the file interface 132 interacts with the local storage system to read or write historical data files, task files, and serialized data; and the algorithm model interface 133 loads, calls, and updates model files used for lifetime prediction, providing a model runtime environment for the algorithm unit 122.

[0029] As can be seen, the soft bus module 110 enables unified data aggregation and management among charging devices, the prediction algorithm 120 enables efficient battery life prediction calculation, and the underlying interface 130 provides stable communication and data support. The vehicle battery life prediction system 100 based on the soft bus can effectively solve the problems of scattered charging data and non-shareable computing power in a multi-device collaborative environment, thereby significantly improving the accuracy and efficiency of vehicle battery life prediction.

[0030] The following is combined Figure 2 The charging device in the embodiments of this application will be described. Figure 2 This is a schematic diagram of the structure of a charging device provided in an embodiment of this application, such as... Figure 2 As shown, the charging device includes one or more processors 210, a memory 220, a communication interface 230, and one or more programs 221. The processor 210 is communicatively connected to the memory 220 and the communication interface 230 via an internal communication bus.

[0031] The one or more programs 221 are stored in the memory 220 and configured to be executed by the processor 210. The one or more programs 221 include instructions for performing any step in the above method embodiments.

[0032] The processor 210 can be a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logical blocks, units, and circuits described in connection with the disclosure. The processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication unit can be a communication interface, a transceiver, a transceiver circuit, and the like, and the storage unit can be a memory.

[0033] The memory 220 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0034] It can be understood that the charging device 200 can include more or fewer structural elements than the above structural block diagram, for example, including a power module, a physical button, a Wi-Fi module, a speaker, a Bluetooth module, a sensor, a display module, etc., which are not limited herein. It can be understood that the charging device can be equipped with, for example, Figure 1 The architecture of the soft bus-based charging station battery life prediction system.

[0035] After understanding the software and hardware architecture of the present application, the following will be combined with Figure 3 A soft bus-based charging station battery life prediction method in an embodiment of the present application is described, Figure 3 is a flowchart of a soft bus-based charging station battery life prediction method provided by an embodiment of the present application, applied to a control module of a local area network, the local area network being composed of a plurality of charging devices interconnected through physical communication links; each charging device in the plurality of charging devices is provided with a computing module and a soft bus module, the soft bus module realizing signaling interaction between the charging devices through the physical communication links based on a soft bus protocol, specifically including the following steps: Step S310, controlling the soft bus module to acquire charging data of a target vehicle on the plurality of charging devices, and to acquire working data of the plurality of charging devices.

[0036] Wherein, the plurality of charging devices constitute a local area network through physical communication links, each charging device is internally deployed with a soft bus module, and performs device state synchronization, data transmission and task issuing operations based on a soft bus protocol. The physical communication link can be CAN, Ethernet, 485 bus or other media that can support the soft bus protocol, which is not limited herein. The soft bus module is a protocol / software framework running on the physical link, which can realize cross-device data sharing without relying on a central server, so that each charging device has self-organizing and self-coordinating network capabilities. When the control module needs to collect charging data of a target vehicle, it can interact with the soft bus module to trigger the soft bus to broadcast a data request instruction within the local area network, and each charging device judges whether there is charging history record or current charging process data matching the target vehicle according to the received instruction, and returns the corresponding data. The charging data of the target vehicle is measured in real time by a monitoring unit in the charging device and uploaded to the soft bus module by an internal controller of the charging device, and is distributed or synchronized in the local area network after being formatted by the soft bus module. After receiving the charging data uploaded from different charging devices, the control module can collect according to the time label and vehicle identification, thereby forming a complete cross-device charging history sequence.

[0037] The working data indicates the current running state and available computing power state of each charging device, including: CPU occupancy rate, memory occupancy rate, task queue length, current load power, device online state, communication link quality, and soft bus heartbeat frame response time, etc. The soft bus protocol specifies a unified device state reporting mechanism, each charging device periodically sends a heartbeat frame carrying part of the working data fields above, for the control module to evaluate the device health and schedulability. In addition, before the control module initiates a task, it can also obtain higher precision real-time working data from the soft bus module through instruction query mode to ensure the accuracy of subsequent computing task division and allocation.

[0038] Specifically, first, a broadcast query mechanism defined by the soft bus protocol is used to send a target vehicle data request instruction to all charging devices. After receiving the request, each charging device soft bus module returns the charging log, real-time monitoring data and historical charging sequence corresponding to the target vehicle stored locally to the control module. At the same time, the soft bus module synchronously carries the current working data of the device within the request response period, so that the control module can obtain the data state information of the entire station range at one time. In order to ensure the reliability and consistency of data transmission, the soft bus protocol supports a timestamp-based data synchronization mechanism to ensure that the data uploaded by each device can be correctly reorganized into a unified time scale.

[0039] For ease of understanding, please refer to Figure 4 , Figure 4 is a soft bus-based charging station networking structure provided by the embodiment. As can be seen, the networking structure interconnects multiple charging devices through a local area network, and establishes data interaction between each charging device and the corresponding power storage battery through a CAN communication link, realizing cross-device charging data collection and distributed execution of prediction tasks. Specifically, the local area network uses a switch as the network core device, and the switch is connected to multiple charging devices through physical communication links, forming a typical star or tree network structure. Multiple charging devices are connected to the switch, thereby realizing network reachability between each other and unified operation of the soft bus protocol. In the embodiment, each charging device not only bears the function of providing charging service for external vehicles or energy storage systems, but also carries a soft bus module for performing device heartbeat detection, service discovery, data synchronization and computing task reception, etc. A communication link is established between the CAN interface and the power storage battery, and the CAN communication link is used to obtain real-time running data of the power storage battery during the charging process, such as voltage, current, SOC, temperature, alarm information, and charging strategy parameters reported by the BMS, etc. These data are uploaded to the local area network through the data acquisition unit inside the charging device, and are uniformly managed through the soft bus, providing a basic data source for subsequent charging data serialization processing and battery life prediction calculation. Through the soft bus protocol, the control module can periodically query the real-time working data of each charging device, and the data state information of the entire station range can be obtained at one time, thereby ensuring the accuracy of subsequent computing task division and allocation. Figure 4With the illustrated hardware networking mode, the embodiment of the present application can realize soft bus cooperation among multiple charging devices in the same local area network, so that the power storage battery charging data collected by different charging devices can be uniformly gathered, sorted and distributed for calculation processing. The networking structure not only solves the problem of data dispersion caused by charging of vehicles at different charging devices, but also provides a unified data channel and computing power sharing basis for realizing a high-precision battery life prediction model.

[0040] It can be seen that by controlling the soft bus module to perform the above data collection, not only can the data island limitation of a single charging pile be broken through, but also complete charging history data of a target vehicle across devices can be gathered, and the running load information of all station devices can be synchronously obtained, thereby providing accurate basis for subsequent distributed calculation task division and scheduling, and further improving the prediction efficiency and system stability.

[0041] In step S320, the charging data is processed in chronological order to obtain a charging data sequence.

[0042] The charging data refers to charging event records of a target vehicle generated at different times and different charging locations, which are gathered from multiple charging devices through a soft bus module, and include historical charging data and charging process data currently being executed. Each piece of charging data is usually stored in the corresponding charging device in the form of an independent record, and contains charging start time, end time, steady-state voltage, current, real-time SOC (state of charge), battery temperature, alarm flag, and key parameters reported by a vehicle battery management system (BMS) during the charging process. Under the background of continuous expansion of charging stations, the target vehicle may repeatedly switch between different charging devices, so these charging data are spatially dispersed and may have inconsistent sampling intervals in time, and must be integrated into continuous time sequences that can be used as model inputs through unified time sequence processing.

[0043] Specifically, first, the time dimension of each data record is collated, that is, the time label carried in the data record is analyzed, including the charging start time, end time and sampling timestamp. With the support of the SoftBus protocol, the internal clock of each charging device can be kept consistent through the network time synchronization mechanism, thereby avoiding data disorder caused by clock offset. On this basis, the control module aggregates data from different devices according to charging events, and eliminates incomplete sampling segments or abnormal time points, such as data missing segments caused by communication interruption. Then, the control module sorts all charging records according to the charging start time as the primary key to build a preliminary time-ordered list. After sorting, to meet the requirement of time continuity of the battery life prediction model, the control module further interpolates and formats the data according to the preset sampling period. For example, when the sampling frequency of a charging device is higher than that of other devices or local data discontinuity occurs, linear interpolation, spline interpolation or model-driven estimation can be used to complete the time series, so that all data meet the unified time granularity. Finally, the control module organizes the sorted data into continuous charging data sequences according to the time sequence, and each data sequence reflects the complete charging history of the target vehicle from multiple charging devices across devices and time periods.

[0044] It can be seen that, by processing the charging data in time sequence, the charging data originally scattered in different charging devices and different charging events can be sorted into time series with unified format, unified time reference and continuous analysis, so that the charging data has consistency, availability and model compatibility. In actual station application, time series processing can effectively solve the problems of data island and inconsistent sampling of multiple devices, and is the key to realizing high-precision battery life prediction.

[0045] In one possible embodiment, the charging data includes historical charging data and charging time data, and the charging data is processed in time sequence to obtain a charging data sequence, specifically including the following steps: 321. Extracting each charging event of the target vehicle from the historical charging data to obtain a plurality of charging event data; 322. Determining the start time corresponding to each charging event data in the plurality of charging event data according to the charging time data to obtain a plurality of charging start times; 323. Sorting the plurality of charging start times in chronological order to obtain a charging start time sequence; 324. Determining the charging event data corresponding to each charging start time in the charging start time sequence to obtain the charging data sequence.

[0046] The historical charging data refers to the vehicle charging process record files stored on different charging devices in the charging station local area network, which are found and integrated by the soft bus history sequence management unit. Each file is uniquely identified by the "start time + vehicle VIN code" in the file name, and records the time series data of battery voltage, current, temperature, etc. in a charging session, so it corresponds to an independent charging event. The charging time data is the timestamp string in the file name or the metadata record in the file header, which is used to accurately identify the starting time of each charging event.

[0047] Specifically, the prediction task initiator broadcasts a query request containing the target vehicle VIN code to the network through the soft bus. After receiving the virtual directory frame, the history sequence management unit of each charging device will report the list of charging sequence files in its local "sandbox directory" that meet the naming rules (i.e. the file name contains the VIN code). The host can extract all related charging event files distributed in multiple devices in the station by summarizing these lists, forming a preliminary multiple charging event data set. Then, the host assigns a machine-readable charging start time to each charging event data object by analyzing the file naming (e.g. "20231027143000" in the file name represents the start time of 14:30:00 on October 27, 2023) or reading the standardized timestamp recorded in the file. The host performs a time sequence sorting algorithm (such as ascending order) on all extracted charging start times, generating a linear charging start time sequence arranged in chronological order. This sequence objectively depicts the charging behavior timeline of the target vehicle in the charging station, clearly defining the time intervals and sequence of each charging event. Then, the host generates a time sequence based on the established "charging event data-charging start time" mapping relationship, reorganizes the charging event data into an ordered data structure list, i.e. the final charging data sequence.

[0048] As can be seen, through the collaborative discovery of the soft bus and the standardized timestamp analysis, the multiple charging records physically dispersed and temporally dispersed are intelligently reconstructed into a logically coherent and time-sequential clear standardized data sequence, providing important and structured data input for subsequent application of prediction optimization algorithms based on time decay weight, thereby improving prediction accuracy and efficiency.

[0049] In step S330, the device computing resources of the computing module of each device in the plurality of charging devices are determined according to the working data, and computing resource data is obtained.

[0050] The operational data is collected in real time by the monitoring unit inside each charging device and reported to the control module via the soft bus module at preset intervals, serving as the basis for assessing the device's current ability to participate in distributed computing. Because the hardware configurations, actual loads, and operating frequencies of the multiple charging devices differ, their available computing resources vary significantly. Therefore, it is necessary to uniformly parse and quantify the operational data reported from the soft bus to generate computing resource data for task allocation decisions.

[0051] Specifically, after acquiring the operating data of each charging device, the control module first analyzes the computing resource utilization rate from the data, such as CPU utilization, memory utilization, available storage space, and the number of device interrupt events. Computing resource utilization rate represents the current level of computing resource consumption by the device and is the most basic parameter for determining whether the device has the capability to participate in computing. Next, the control module analyzes the device task queue length, which reflects the number of tasks currently queued for processing and can be used to determine the device's responsiveness in future periods. After extracting the multi-dimensional parameters, the control module normalizes and maps the various operating data according to a preset resource evaluation model. The resource evaluation model can be a multi-factor weighted model, a threshold-based segmented evaluation model, or a fitted model trained based on historical operating data. Taking a weighted model as an example, the control module can assign different weights to CPU utilization, task queue length, device temperature change rate, and load power, and calculate the current computing power availability of the device using a formula. For example, a charging device will have a higher computing power score when its CPU utilization is low and its task queue length is short; conversely, its computing power score will be appropriately reduced when the device temperature is high or it is under high charging load to avoid allocating too many computing tasks to the device. Finally, the control module binds the calculated computing power availability with the device identifier to generate corresponding computing resource data.

[0052] It is evident that by analyzing and modeling the working data, the raw equipment operating status information can be transformed into quantitative indicators representing the equipment's computing power, thus providing a basis for subsequent task allocation and resource scheduling. In charging stations, equipment load fluctuates rapidly with changes in vehicle charging behavior. Without real-time updates to computing resources, it will be difficult to guarantee the execution efficiency and stability of distributed prediction tasks.

[0053] In one possible embodiment, determining the device computing resources of the computing module of each of the plurality of charging devices based on the working data to obtain computing resource data specifically includes the following steps: 331. Based on the working data, determine the computing resource utilization rate and task queue length of the computing module of each of the multiple charging devices, and obtain multiple computing resource utilization rates and multiple task queue lengths; 332. determining, according to the plurality of computing resource occupancies, a computing resource capability of a computing module of each of the plurality of charging devices, to obtain a capability resource; 333. determining, according to the plurality of task queue lengths, a load parameter of each of the plurality of charging devices, to obtain a load parameter; 334. determining, based on a preset mapping relationship between the load parameter and a required computing resource, a required computing resource corresponding to the load parameter, to obtain a computing resource requirement; 335. determining, according to the computing resource requirement and the capability resource, a computing resource of a computing module of each of the plurality of charging devices, to obtain the computing resource data.

[0054] The working data is derived from a HeartBeat frame periodically broadcast in the soft bus protocol. The data frame is not only used to maintain the online state of the connection, but also encapsulates real-time running state parameters of the charging device in the data field, including a central processing unit occupancy (UsingCPU), a neural network processing unit occupancy (UsingNPU), and a memory occupancy (UsingRAM). In addition, for a device supporting advanced task management, the length of a task queue (i.e., the number of currently queued computing tasks waiting for execution) maintained by a local task scheduler can also be transmitted as part of the working data through a self-defined state reporting mechanism.

[0055] Specifically, the host of the prediction task extracts the calculation resource occupancy rate (such as CPU occupancy rate 70%) for indicating the instantaneous load of the calculation module and the task queue length (such as 2 tasks in the queue are waiting) indirectly reflecting the current busy degree of the device from the above heartbeat frame and status report from each charging device by continuously listening and analyzing. By a preset conversion model, the "occupancy rate" is associated with the "remaining available theoretical computing power". For example, if the occupancy rate of an NPU with a nominal computing power of 10 TOPS is 60%, the current remaining available computing power can be estimated to be about 4 TOPS. The calculation method is to make the occupancy rate data from different performance heterogeneous charging devices have unified comparability. A longer task queue length may indicate that the device will soon enter a busy state even if the current CPU occupancy rate is not high. The preset mapping relationship is essentially an empirical or experimental data-based prediction model. The model can estimate the computing resources (for example, at least 10% of the CPU is idle and 200MB of available memory is required) required by the device to stably and timely process a new task according to a given load parameter, and then compare the calculated current actual remaining computing power of the device with the computing resource requirement of the new task. If the actual remaining resource is continuously and stably greater than the required resource, the device is determined to be "available" or "idle", and the remaining resource amount is taken as a part of the final calculation resource data.

[0056] It can be seen that the method provided in the embodiment ensures that the task scheduler can accurately identify the devices that truly have sufficient and stable idle resources, thereby maximizing the avoidance of improper task allocation, calculation delay or device overload caused by resource misjudgment, and providing an important resource perception and evaluation basis for realizing efficient and stable distributed parallel computing.

[0057] In step S340, the charging data sequence is divided according to a preset calculation task division rule to obtain a plurality of divided calculation tasks.

[0058] The calculation task division rule is used to decompose the charging data sequence processed in time sequence into a plurality of independently executable calculation tasks according to appropriate data granularity, so that each task can be run in parallel on the calculation modules of different charging devices, thereby improving the overall prediction efficiency of the system. The task division rule is usually set according to the structural characteristics of the charging data sequence, the file data volume, the sequence time span, and the requirements of the calculation model on the input data, and is also combined with the computing power difference of each charging device in the station to avoid delay diffusion caused by centralized allocation of data to devices with low computing power. Preferably, the task division rule can be formed according to the number of charging record files, the file size, the time interval between different charging events and other information.

[0059] Specifically, the process begins by parsing the generated charging data sequence, which contains multiple charging record files. Each file typically corresponds to complete data for the target vehicle during a single charging session, including charging start time, end time, voltage and current curves, SOC change records, temperature curves, and operating parameters reported by the BMS. Next, the control module labels each record file according to its source device to identify the original distribution of the charging data. After parsing the charging record files, the control module splits the file set according to task partitioning rules. For example, in sequences with large amounts of data, files can be prioritized based on data volume, allocating larger files to devices with more computing power. In cases where data volume differences are small but there are many source devices, charging sequences within different time intervals can be divided into independent tasks based on time period partitioning. Furthermore, task partitioning rules can incorporate preset device load constraints, such as avoiding scheduling multiple large tasks to the same device simultaneously, thus ensuring overall scheduling balance. To ensure that the partitioned tasks can be computed independently, the control module also performs consistency checks on the data within each partitioned task, ensuring its structural integrity, temporal continuity, and compliance with preset model input formats. Finally, each task is encapsulated into an independent task unit, along with necessary task tags and metadata, such as task number, data source device, and data volume range, to facilitate subsequent task scheduling.

[0060] It is evident that by using a task partitioning mechanism, large-scale, cross-device charging history data can be broken down into multiple sub-tasks suitable for distributed computing, greatly reducing the computational load on individual devices while improving the parallel processing capability of the entire system, thereby enhancing the efficiency of predicting the lifespan of electric vehicle power batteries.

[0061] In one possible embodiment, dividing the charging data sequence according to a preset computational task partitioning rule to obtain multiple partitioning computational tasks specifically includes the following steps: 341. Extract the charging record file of the target vehicle from the charging data sequence to obtain multiple charging record files; 342. Determine the source device of each of the multiple charging record files to obtain the multiple file device sources; 343. Select the charging record file corresponding to the target file device source from the plurality of file device sources to obtain the target charging record file; the target file device source is any one of the plurality of file device sources; 344. Select the charging record files other than the target charging record file from the plurality of charging record files to obtain a charging record file set; 345、determining the data volume of each charging record file in the charging record file set, to obtain a plurality of file data volumes; 346、determining the computing resource occupation parameters corresponding to the plurality of charging devices according to the computing resource data, to obtain a plurality of computing resource occupation parameters; 347、dividing the charging record file set according to the computing task division rule, the plurality of computing resource occupation parameters and the plurality of file data volumes, to obtain the plurality of divided computing tasks.

[0062] Wherein, the input is a charging data sequence after time sequence processing, which is essentially a list of all historical charging record files of the target vehicle sorted by charging start time. Extracting charging record files is a direct data access operation, because each element of the sequence is an independent data file corresponding to a charging event. When the charging pile device exposes its local files to the network through the virtual directory frame (VirtDir), the frame not only contains a list of file paths, but also implies the unique identification of the sending device. Therefore, when the host establishes an index for each charging record file, it can simultaneously associate and record the physical storage location, i.e. the source device. The target device source usually refers to the "host" device that initiates the battery life prediction request; the selected charging record file set contains all historical files stored on other remote devices that need to be scheduled across the network. The computing task division rule is a manifestation of the regularization of the scheduling strategy, mainly including: the near-first rule, which preferentially allocates files to the local device (target device source) where they are stored for calculation; the load balancing and matching rule, which, for files that must be allocated remotely, performs double matching based on their data volume (large files first) and the computing resource occupation parameters of the device (high idle degree devices first); the resource guarantee rule, which ensures that the device allocated for the target file has sufficient remaining resources to meet the minimum memory and computing power threshold required to run the prediction model. The charging device iteratively traverses and matches the charging record file set according to these rules, and finally divides and maps the entire file set to different available computing devices, forming a clear "file-target computing device" pairing, i.e. a plurality of divided computing tasks. Each divided computing task represents "performing battery life prediction algorithm on a specified charging record file or files on a specified device".

[0063] It can be seen that the intelligent task division mechanism is the key scheduling layer for efficient and stable distributed computing. It decomposes the data sequence into independent file computing tasks, and optimally matches them by fusing multi-dimensional rules of data location (proximity), data characteristics (file size) and system real-time state (resource idle degree), thereby minimizing unnecessary data network transmission, reducing communication overhead and delay, and thus improving the efficiency of the subsequent charging module in predicting the life of the power battery.

[0064] In one possible embodiment, the step of dividing the charging record file set according to the computing task partitioning rules, the plurality of computing resource occupancy parameters, and the plurality of file data volumes to obtain the plurality of partitioned computing tasks specifically includes the following steps: 3471. Sort the multiple computing resource occupancy parameters in descending order to obtain a resource occupancy parameter sequence; 3472. Sort the multiple file data volumes in ascending order to obtain a file data volume sequence; 3473. Based on the computation task partitioning rules and the resource occupancy parameter sequence, each charging record file in the file data volume sequence is partitioned to obtain the multiple partitioning computation tasks.

[0065] The process of sorting multiple resource usage parameters in descending order essentially prioritizes the real-time computing power supply capabilities of all available charging devices within the local area network. A higher value for a resource usage parameter indicates more abundant remaining computing resources for that charging device. The resource usage parameter sequence generated by sorting the parameters in descending order effectively constructs a global device idleness ranking sequence, with the device at the top of the sequence considered the ideal executor of the current computing task. Sorting multiple file data volumes in ascending order assesses and ranks the workload of the charging data record file set to be computed. The file data volume is directly related to the basic computation cycles and memory usage required by the prediction model to process that file. Sorting the file data volume sequence in ascending order indicates that smaller files with relatively light computational loads are placed first, while larger, more computationally intensive files are placed later. Based on preset computing task partitioning rules, the two ordered sequences are collaboratively matched.

[0066] Specifically, the host maintains the above two sequences and follows the following iterative process: first, according to the principle of nearest calculation priority, for any charging record file, check whether the stored source device is in the current "resource occupation parameter sequence" and ranks first (i.e. higher idle degree itself). If so, directly divide the file into a calculation task performed locally by the source device, and remove the file from the file sequence, while adjusting the position of the device in the resource sequence according to the amount of new tasks it undertakes. Then, for files that cannot be executed locally or have insufficient local device resources, perform a sorting-based cross-device matching. At this time, the scheduler adopts a "try small files first, match large files to strong machines" strategy, which starts from the head of the "file data volume sequence" (i.e. the smallest file) and attempts to assign it to the currently most idle device at the head of the "resource occupation parameter sequence". After completing a match, the file is removed from the file sequence, and the resource parameters of the assigned device are updated and reinserted into the sorted sequence (usually with a lower rank) to reflect its new load. Then, the next smallest file is used to match the updated, currently most idle device, and the iteration continues. In this way, small tasks can be quickly distributed and completed, while large files have a higher probability of matching to strong devices that remain relatively idle during the iteration process, thus achieving balanced distribution of load globally and shortening the overall task completion time.

[0067] As can be seen, by quantifying device resources and file load into sortable sequences and designing matching iteration rules, the complex distributed scheduling problem is converted into an efficient deterministic algorithm, which minimizes the total completion time of all predicted subtasks while ensuring that individual devices are not overloaded, thereby achieving the technical effect of improving prediction efficiency at the system level.

[0068] In step S350, the plurality of divided tasks are distributed to the computing module on each of the plurality of charging devices according to a preset computing resource distribution rule, to obtain a plurality of computing tasks; each computing task in the plurality of computing tasks includes at least one element in the charging data sequence.

[0069] Among them, the computing resource distribution rule refers to the strategy set of the control module for optimal scheduling of divided tasks according to the current computing resource data, load state, online state and task execution ability of each charging device. This rule not only needs to consider the instantaneous available computing power of each device, but also needs to consider factors such as CPU occupancy rate, task queue length, soft bus heartbeat response delay, device temperature, and rectification load degree, to ensure the stability and consistency of task execution in a distributed structure.

[0070] Specifically, after completing task division, the control module first matches the task amount (such as the number of files contained, file size, time span, etc.) of each divided task with the obtained device computing resource data. The control module can map the task amount to a computing requirement level and map the device computing power to a computing power level based on a pre-established resource mapping model, and then match the two through a computing resource allocation rule. In the matching process, the control module can also combine the online detection results of the soft bus module to ensure that tasks are only assigned to charging devices that are in normal communication and have stable soft bus heartbeat frame responses. Then, the control module issues corresponding computing instructions to the target charging device through the soft bus protocol, and the instructions contain the input data index or data content corresponding to the divided task. The charging device computing module enters a computing execution state after receiving the task, forming the final multiple computing tasks. Each computing task contains at least one element in the charging data sequence, such as an independent charging record file or a charging data segment within a certain time interval, to ensure the independent computability of the task. After each device executes the task, it can return the corresponding computing intermediate result or final prediction result through the soft bus for subsequent weighted calculation and result fusion.

[0071] As can be seen, through the computing resource allocation mechanism, efficient and dynamic distributed task scheduling can be achieved among multiple charging devices, fully utilizing global computing power resources while avoiding performance degradation caused by excessive device load, ensuring that each divided task is assigned to the most suitable device for processing, effectively improving computing execution efficiency, and improving the overall scalability and stability of the system.

[0072] Step S360, inputting the elements in the charging data sequence in the multiple computing tasks into a preset battery life prediction model to obtain multiple prediction results.

[0073] The real-time computing resource state refers to the dynamic load parameters of each charging device periodically broadcast in the local area network through the HeartBeat in the soft bus protocol, mainly including CPU usage (UsingCPU), NPU usage (UsingNPU), and memory usage (UsingRAM). These parameters are collected by the local monitoring unit of each device and packaged into the data field of the HeartBeat frame, broadcast or respond to queries through the soft bus, so that any device in the network that serves as a prediction task initiator (host) can have real-time access to the global computing power resource distribution map. The multiple historical charging data files refer to single charging process data record files uniquely identified by the naming rule (start time + vehicle VIN code) and stored in the local or shared directory of each charging device. Each file is a complete, time-continuous data sequence unit and is the smallest computing granularity for life prediction.

[0074] Wherein, due to the huge amount of time slice data, and the large amount of computing resources required by the time series based large model algorithm; If the CPU resource is high for a long time, it may seriously affect the response of other interrupts of the system, leading to unpredictable problems. In order to solve this problem, relying on the parameter and file sharing ability of the soft bus, a distributed computing unit is constructed, and the prediction calculation of different time slice sequence files is dispersed in each idle device of the station. The algorithm unit relies on the sequence based AI prediction model, or the prediction algorithm based on historical sequence, which is based on the existing ready model; However, the existing model or algorithm often needs fixed sampling period, continuous data for time series. In the current application scenario, the data of single charging meets this requirement, but when extended to all data in the whole station, the sequence is discontinuous, so an optimization algorithm needs to be constructed. In the heartbeat frame defined in the foregoing protocol framework, in addition to including HeartBeatCount, it also includes device CPU utilization (UsingCPU), NPU utilization (UsingNPU), memory utilization (UsingRAM) and other device resource utilization parameters. These parameters are updated into the device parameters of the corresponding device connection list in the networking unit in real time; In this way, any device in the soft bus can know the device situation of the station system in real time. In addition, CompReq, CompReqAck and CompResult frames are added. Among them, CompReq: event title "CompReq", parameters include UserID and OrderFile; CompReqAck: event title "CompReqAck", parameters include ReqAck and FileReason; When the request is passed, FileReason value is 0; CompResult: event title "CompResult", parameter includes BatLifeResult. When the user clicks the battery life prediction service on the billing interface of the charging pile, the prediction process is triggered. The current device will act as the host, according to the vehicle unique identification code (VIN code) of the user of this charging, in the above prediction sequence container, find the corresponding sequence file, and arrange according to the file size, form the target file table; Then according to the resource occupation situation of the device list in the networking unit (when AI model operation, depend on NPU unit, prefer to sort according to NPU occupation situation; When the system does not exist NPU unit, or for the algorithm operation depending on CPU, prefer to sort according to CPU occupation situation; Finally, check the memory occupation, ensure that the remaining memory can meet the minimum value required by the budget), form the device idle table.

[0075] Specifically, first, the host device initiating the prediction task retrieves and collects relevant historical charging data files distributed in all networked devices according to the VIN code of the target vehicle through the query interface provided by the history sequence management unit of the soft bus, and forms a list of files to be calculated. At the same time, the host parses the continuously received heartbeat frames and maintains a real-time updated list of device idle states (i.e., "device idle table"). The devices in the list are sorted according to the remaining key resources. For AI prediction models relying on NPU acceleration, the NPU idle rate is sorted first; for algorithms using only CPU, the CPU idle rate is sorted; at the same time, the remaining memory of the device is checked to see if it meets the minimum requirement for model running. In the allocation process, a multi-round matching process is performed, which is based on the principle of proximity priority and load balancing. Specifically, a certain historical charging data file is preferentially allocated to the local device where it is stored for calculation to reduce network transmission overhead. If the local device is insufficient in resources, the file is allocated to a remote idle device with the most abundant computing resources and meeting the memory requirement according to the "device idle state list". For computing tasks with large data volume (large file size), higher idle devices are preferentially matched to avoid forming new performance bottlenecks. The final output of this allocation decision is to generate a mapping relationship that clearly indicates which specific charging device with sufficient idle resources should be responsible for calculating each historical charging data file. The allocation instruction is sent to the target device through the computing power request frame (CompReq) defined in the soft bus protocol, and the target device confirms it with the computing power request response frame (CompReqAck). Finally, each allocated device independently and in parallel calls the locally deployed battery life prediction model to process the allocated files, starting the distributed computing process.

[0076] As can be seen, the global resource view constructed by the soft bus converts the huge prediction calculation task from the traditional centralized processing mode relying on a single central server into a parallel processing mode across multiple idle devices. This not only significantly shortens the overall calculation time and improves the response efficiency of the prediction service, but more importantly, it disperses the computing load to multiple nodes of the network, effectively avoiding the problem of response delay or even system instability caused by long-time high-intensity operation of a single device, thereby improving the prediction accuracy (by integrating multiple data sources) while ensuring the robustness and service reliability of the entire charging station operation system.

[0077] In step S370, the life prediction weight is determined based on a preset attenuation factor, a preset life prediction weight calculation formula, and the charging data sequence, and a plurality of life prediction weights are obtained.

[0078] wherein, the life prediction weight is determined according to the charging start time stamp corresponding to each sequence, which is uniquely determined when the data file is generated, thereby giving each historical charging data and its corresponding initial prediction result a clear time attribute. The preset decay factor (λ) ) is an empirical constant used to control the rate of weight decay over time, and its default value can be 0.05 and can be adjusted according to the characteristics of different battery chemical systems. The preset life prediction weight calculation formula is:

[0079] wherein, is the weight value, is the decay factor, is the time difference (sequence start time to current time difference, unit: day). Specifically, first, for each initial prediction result, the charging module or its coordination module parses the start time stamp of the charging from the metadata or file name of the corresponding historical charging data file. Then, calculate the time difference t between the time stamp and the current system time. Then, put t and the preset decay factor λ into the above exponential decay formula to calculate the original decay value of the prediction result. After obtaining the original decay values corresponding to all prediction results, sum all the original decay values and normalize each original decay value (i.e. divide by the sum). Finally, the normalized weight corresponding to each prediction result is obtained, and the weight of the recent data will be much higher than that of the early data after normalization.

[0080] It should be noted that the way to obtain the time stamp, the unit of the time difference, and the specific value of the decay factor can be adaptively configured according to the actual data record format and the battery decay model. The core of the present application is to introduce a weight distribution mechanism based on time exponential decay to realize effective fusion and value evaluation of multi-source historical data.

[0081] It can be seen that the existing methods are limited to single or short-term continuous data, and cannot effectively utilize the fragmented historical data left by users at different times and different charging piles. The embodiment of the present application introduces a time decay factor and a normalized weight calculation formula to construct a mathematical model for quantitatively evaluating the time value of historical data. Thus, the limitation of single data source is broken at the data level, and the accuracy, robustness and timeliness of the life prediction result are significantly improved.

[0082] In one possible embodiment, the life prediction weight is determined based on the preset decay factor, the preset life prediction weight calculation formula, and the charging data sequence, and a plurality of life prediction weights are obtained, specifically including the following steps: 371、According to the last charging data in the charging data of the target vehicle, first charging data is obtained; 372、The first charging start time in the first charging data is determined; 373、The charging start time corresponding to the plurality of charging devices in the charging data sequence is determined, and a plurality of charging start times are obtained; 374、Each charging start time in the plurality of charging start times is subtracted from the first charging start time, and a plurality of time difference values are obtained; 375、According to the life prediction weight calculation formula, the plurality of time difference values and the attenuation factor are calculated, and the plurality of life prediction weights are obtained.

[0083] Wherein, the charging data sequence is a list of historical charging record files of the target vehicle which has been organized in chronological order. The last charging data is the charging record file with the latest time stamp selected from the time sequence as the first charging data. By analyzing the metadata of the first charging data to obtain its accurate starting time, and analyzing all other charging record files in the sequence in parallel, a series of charging start times are extracted, thereby completely depicting the time distribution of historical charging behavior. Then, the operation of is performed, wherein, is usually negative or absolute value, a time difference value relative to the last charging is calculated for each historical charging event. Then, the time difference value is substituted into the preset life prediction weight calculation formula for calculation, and finally a set of normalized life prediction weights with a total sum of 1 is obtained .

[0084] It can be seen that through the quantifiable time sequence data processing flow, the data timeliness in the battery health state evaluation is transformed into a weight parameter that can be embedded in the prediction model. Not only does it solve the modeling problem of non-equidistant and non-continuous historical data sequence caused by the randomness of charging behavior at the algorithm level, but more importantly, it gives higher weight to recent data through an exponential decay mechanism, so that the final fusion prediction result can more sensitively and accurately reflect the current and recent degradation trajectory of the battery, thereby significantly improving the accuracy, robustness and practical guidance value of the life prediction model.

[0085] Step S380, according to the plurality of life prediction weights, the plurality of prediction results are weighted and calculated, and the target prediction result is obtained.

[0086] Wherein, the host collects the operation result frame (CompResult) returned by each distributed computing device through the soft bus, and the frame encapsulates the initial prediction result The host calculates the charging start time stamp corresponding to each task (used to calculate the charging start time stamp corresponding to each task (used to calculate and the calculated weight The host calculates a correction term for each initial prediction result Then, the host multiplies each corrected prediction value with its corresponding weight and sums all the products to obtain a single, fused target prediction result .

[0087] Specifically, after all the sequence predictions are completed, a prediction result table (sequence start time stamp + prediction life) is formed, where the prediction life unit is days. For each prediction result in the table, the weight can be considered to be lower and lower over time. Therefore, a decay factor is introduced, and the prediction result weight formula is:

[0088] The final optimized prediction result value is:

[0089] wherein, is the weight value of the i-th original data; i is the time difference between the i-th original data and the current time; is a decay factor, which can be modified according to experience for different types of batteries, and the default value is 0.05; i is the total number of prediction results; is the prediction result, is the i-th original prediction data. According to this algorithm, the problem of poor prediction accuracy caused by small amount of single charging data and the problem of non-continuous sampling sequence cannot be used can be solved to some extent. i As can be seen, the contribution of recent high-value data is highlighted by exponential decay weighting. Therefore, the final output target prediction result not only fully mines and utilizes the information contained in fragmented historical data, but also significantly improves the accuracy, reliability and practical reference value of the prediction result through a scientific fusion algorithm, thereby realizing more accurate and stable intelligent evaluation of the remaining life of the vehicle battery.

[0090]

[0091] As can be seen, the contribution of recent high-value data is highlighted by exponential decay weighting. Therefore, the final output target prediction result not only fully mines and utilizes the information contained in fragmented historical data, but also significantly improves the accuracy, reliability and practical reference value of the prediction result through a scientific fusion algorithm, thereby realizing more accurate and stable intelligent evaluation of the remaining life of the vehicle battery.

[0092] ​​In a possible embodiment, the soft bus module comprises a networking management unit, a protocol unit and a data management unit, and before the control of the soft bus module to acquire charging data of the target vehicle on the plurality of charging devices and to acquire working data of the plurality of charging devices, the method further comprises the following steps: A1, detecting a plurality of online states of the plurality of charging devices in response to the networking management unit sending an online detection frame to the plurality of charging devices; A2, determining connected charging devices in the plurality of charging devices according to the plurality of online states, to obtain a connected charging device set; A3, performing device identification registration on all charging devices in the connected charging device set, to obtain a plurality of registration identifiers; A4, determining a topology relationship of all charging devices in the connected charging device set according to the plurality of registration identifiers, to obtain a charging device topology relationship; A5, performing link confirmation on the connected charging device set based on the charging device topology relationship, to obtain a communication available state; A6, performing networking on the charging devices in the connected charging device set according to the communication available state, to obtain the local area network system.

[0093] The detection source in the network management unit acts as a dynamic client, initiates a TCP connection attempt to all possible IP addresses in the current network segment, and sends a specific detection login frame (operation instruction 0x01), which encapsulates the service name and device unique code of the detection initiator to identify itself. At the same time, the listening server on each device continuously listens to the preset port and waits to receive such detection frames or connection requests from other devices. When the listening server receives a valid detection login frame, it will be authenticated, and if it passes, a connection will be established. At the same time, the device as the detection source will also receive responses from other devices. Through this combination of active association and passive association, the final set of online and authenticated devices is determined, forming a preliminary set of connected charging devices. Device identification registration refers to the device unique code and corresponding network socket information of each successfully connected device, which is registered in the valid client list maintained by the event emitter. This list is the basis for any subsequent targeted or broadcast communication by the soft bus. The topology relationship is not a physical wiring topology, but a logical communication topology based on the above client list and connection status, i.e., it is clear that which devices have established direct communication session links in the soft bus layer. Finally, the network formation indicates the formal formation of the local area network system in the soft bus logical layer, at which time a distributed collaborative network consisting of multiple charging devices interconnected through standardized soft bus protocols, with device discovery, identity management, and stable link, is ready for subsequent file discovery by the "data management unit" and data exchange by the "protocol unit", providing a stable communication infrastructure for subsequent "data management unit" file discovery and "protocol unit" data exchange.

[0094] For ease of understanding, please refer to Figure 5 , Figure 5 is a soft bus network structure diagram provided by the embodiment. As can be seen, Figure 5 shows the interaction structure of three typical devices A, B, and C under the soft bus system, each device including a listening server and an event emitter, and forming a multi-point interconnection between devices through a local area network communication connection channel, thereby realizing cross-device event publishing and listening mechanism. Specifically, devices A, B, and C are respectively provided with a listening server and an event emitter. The listening server is used to continuously listen to event messages from other charging devices on the soft bus and trigger corresponding processing logic according to the event type; the event emitter is used to broadcast events outside in the format specified by the soft bus protocol after generating events within the charging device. The soft bus service architecture adopts an event-driven mechanism, enabling different devices to realize cross-device synchronization, data sharing, and asynchronous task triggering without establishing fixed communication peer-to-peer relationships. Among them, Figure 5The event interaction path between multiple devices is shown in the form of a dashed line and an arrow. The event transmitter of device A can not only send events to the listening server of device B, but also send events to the listening server of device C; device B can also broadcast its events to device A and device C; device C can send events to device A and device B. Through this many-to-many event propagation mode, a globally reachable event publishing network is formed between devices, realizing the interconnection and intercommunication between distributed devices and decentralized event scheduling. Further, under the soft bus protocol, each event broadcast process includes event identification, event parameters, source device identification, and event priority information, allowing the listening server to process the received events. For example, when the listening server of device B receives an event from device A, it can determine whether to update data, synchronize states, or start corresponding computing tasks according to the event identification. On the other hand, the event transmitter can select the broadcast range according to the soft bus task scheduling strategy when generating events, thereby reducing unnecessary network load and improving event propagation efficiency.

[0095] It can be seen that the event interaction structure between different devices through the soft bus service can enable multiple charging devices to build a flexible distributed interaction system in a local area network environment. Each device can act as both an event source and an event listener, and the propagation of events does not depend on a central node, thereby avoiding single-point failures and improving system reliability.

[0096] For ease of understanding, please refer to Figure 6 , Figure 6is a flowchart of active networking based on soft bus provided by the embodiment of the present application. It can be seen that the soft bus system as a whole is composed of a listening server on the target device side and a probe source and a message transmitter on the source device side, forming a distributed communication system integrating device automatic discovery, bidirectional handshake authentication, connection maintenance and event forwarding. Through the system, multiple devices in the local area network can automatically establish a communication link without manual configuration and realize subsequent data sharing and distribution of operation tasks. Specifically, the listening server runs on the target device side. After the listening server is started, the flowchart "starts", starts to create a server, and then judges "client connection?". If the answer is "N", it indicates that the client is not connected, and the listening server waits for the successful connection of the client. If the answer is "Y", it indicates that the client is successfully connected, and then judges "receive login frame?". If the answer is "N", it enters the judgment link of "waiting for login timeout?". If the judgment result is "N", it continues to wait for the reception of the login frame. If the judgment result is "Y", it returns to the flowchart judgment of "client connection?" until the client is successfully connected. If the judgment of "receive login frame?" is "Y", it further executes the verification of "whether it is a probe login frame?". If the verification result is "N", it is determined as a frame type not required for networking, and the connection is directly disconnected, entering the passive process (and the passive connection process, such as Figure 7If the result is "Y", the "probing frame information authentication" process is started. In the probing frame information authentication stage, a "authentication passed?" judgment is made. If the authentication is not passed (the result is "N"), an authentication failure instruction is returned to the source device, and then a "connection disconnected?" judgment is made. If the authentication is passed (the result is "Y"), an authentication success instruction is returned to the probe source in the source device, and a "client connection?" judgment of the next charging device is made. Then, the state monitoring of "connection disconnected?" is entered. If the judgment is "Y", the "client connection?" judgment is continued to be executed. If the judgment is "N", a "disconnection timeout?" judgment is entered. If it is "N" (disconnection does not timeout), the "connection disconnected?" judgment is re-executed. If it is "Y" (disconnection does not timeout), the connection is disconnected, and the "client connection?" judgment is re-executed until the client connection is completed, thereby completing the active networking response process on the target device side. The source device side completes the networking initiation action in cooperation with the probe source and the message transmitter. The probe source starts the process "start", and then performs the operation of "random probing IP acquisition". After obtaining the IP to be probed in the network segment, a TCP connection is established, and a "connection success?" judgment is made. If it is "N", it indicates that the TCP connection is not established, and the random probing IP acquisition stage is re-executed. If it is "Y", after the connection establishment is completed, a probe login frame is sent to the target device listening server, and then the authentication feedback of the target device is waited for. When the "authentication success?" step is "Y", the probe source transfers the socket to the message transmitter, and then the random probing IP acquisition is performed again to continue the next IP probing and TCP / IP connection establishment. When it is "N", the probe source receives the authentication failure reply or does not receive the reply within the specified time, and then actively disconnects the connection to enter the random probing IP acquisition step to continue the next IP probing. When the message transmitter receives the socket transfer sent by the probe source, that is, the authentication success reply is received, the message transmitter starts the process (socket registration). The message transmitter triggers the "probe source socket transfer?" judgment. If it is "N", it is waited for. If the judgment is "Y", the current communication socket is transferred to the message transmitter, the socket is included in the soft bus communication management system by the message transmitter performing the "socket registration" operation, and thus the active networking process on the source device side is completed. The subsequent data interaction and task cooperation can be carried out based on the registered socket.

[0097] It can be seen that, relying on the active probing of the probe source, the accurate verification of the listening server and the orderly transfer of the socket, the active networking process realizes the automatic networking of the charging station devices in the local area network, and the communication link between the devices can be built without manual intervention. It lays a communication foundation for subsequent charging data sharing and distributed computing scheduling, meets the actual business needs of multi-device cooperation of the charging station, and improves the self-networking capability and operation convenience of the soft bus system.

[0098] For ease of understanding, see Figure 7 , Figure 7is a flowchart of passive networking based on soft bus provided by the embodiment of the present application. It can be seen that the flowchart is mainly composed of a listening server on the target device side and a probe source, a listening server and an event transmitter on the source device side, and the automatic device discovery, reconnection event triggering, bidirectional authentication connection, socket migration and event reporting are realized through the cooperation of the above-mentioned components, forming a local area network soft bus communication framework with high robustness, self-adaptability and distributed coordination capability. Specifically, on the target device side, the listening server enters a continuous listening state after starting and waits for a reconnection probe request from a source device in the local area network. The listening server receives a reconnection frame sent by the probe source on the source device side and judges whether the listening server has received the reconnection probe frame sent by the source device, that is, whether the reconnection probe login frame? is judged as yes (Y) or no (N). When the judgment is no (N), the target device keeps the listening state and continues to wait until the source device initiates a valid probe. When the judgment is yes (Y), it means that the target device successfully receives the probe request from the source device, and the listening server will immediately trigger the login reply process, that is, sending a confirmation response to the source device, so that the source device judges whether the target server replies? and identifies whether the target device is in a connectable state. After the process is executed, the reconnection processing on the target device side is completed. On the source device side, the probe source is responsible for initiating the automatic discovery process. At the beginning, the probe source receives the trigger reconnection login? instruction sent by the listening server after starting, and enters the judgment of whether the reconnection event occurs? When the judgment is no (N), it means that the probe source has not received the reconnection confirmation from the target device, and the probe source will continue to maintain the listening and probing state. When the judgment is yes (Y), it means that the source device detects a valid reconnection event from the target device. At this time, the source device obtains the target IP from the detected event and creates a TCP connection based on the target IP, and then sends a reconnection frame to the target device to complete the first phase handshake operation of the connection. After the above reconnection is completed, the source device judges whether the target server replies? When the judgment is no (N), it means that the target device does not return a valid login response, and the source device terminates the current connection attempt and returns to the reconnection frame sending operation. When the judgment is yes (Y), it means that the target device has correctly responded to the reconnection frame of the source device, and the source device performs the socket migration operation to hand over the temporary communication socket maintained by the probe source to the local event transmitter for the probe source socket migration? judgment, so as to realize long-term stable session maintenance. After the socket migration is completed, the reconnection process on the source device side is completed. At the same time, the listening server and the event transmitter of the source device operate in parallel. The listening server receives the socket migration from the probe source after starting and judges the reconnection authentication result. When the reconnection authentication is successful, the listening server triggers the reconnection login, and the listening server ends this stage to establish a stable communication link.After the event transmitter enters the "start" stage (i.e. starts), it enters the "detect source handover socket?" judgment flow. When the judgment is "no" (N), the event transmitter remains in standby and does not send events. When the judgment is "yes" (Y), the event transmitter performs "socket registration", adds the accessed socket to the soft bus event management system, and is responsible for subsequent data event reporting, heartbeat maintenance and state synchronization by the event transmitter.

[0099] It can be seen that through the multi-level linkage mechanism of target device listening, source device detection, bidirectional back connection confirmation, socket handover and event registration, the embodiment realizes a passive networking process without manual intervention, so that multiple charging devices in the local area network can automatically discover and establish stable communication connections under the soft bus framework, effectively improving the plug-and-play capability, dynamic expansion capability and network autonomy capability of the system.

[0100] For ease of understanding, please refer to Figure 8 , Figure 8The embodiment provided by the application is a historical sequence management process schematic diagram based on a soft bus. It can be seen that the embodiment mainly includes the processes of soft bus construction, resource adaptation, model deployment, and prediction execution, realizes the management of vehicle charging data and the prediction of vehicle battery life, forms a full-process standardized implementation system from basic environment configuration to prediction function, and includes steps such as local area network deployment, soft bus interaction, virtual directory analysis, sequence container registration, historical sequence archiving, and prediction sequence output, which can ensure the stability of operation in multiple charging device cross-site deployment and distributed computing scenarios, and realize the collaborative optimization of charging data integration and distributed computing power scheduling. Specifically, the soft bus serves as an upper-layer protocol service and is used to broadcast a “virtual directory frame” to multiple charging devices (charging piles). The soft bus first sends a virtual directory frame to all network charging devices. After each charging device receives the virtual directory frame, it analyzes the received virtual directory frame through a built-in “virtual directory analysis VirPraseFunc”. The analysis process is used to identify index information such as a vehicle unique identification code, a data file name, a device identification, and a corresponding sequence start timestamp contained in the virtual directory structure. After the analysis is completed, each charging device generates a “temporary prediction sequence container” based on the analysis result and inputs the temporary prediction sequence container to a “prediction sequence container registration RegisterFunc” on the soft bus side. The prediction sequence container registration RegisterFunc controls the prediction sequence container through “input / output”. The prediction sequence container registration RegisterFunc is actually a prediction sequence container registration function, which is used to index map the temporary containers from different devices and integrate the global input / output, so as to uniformly integrate the historical prediction data of multiple devices and multiple vehicles into a systematic management structure. The vehicle unique identification code (for example, vehicle unique identification code (1) to vehicle unique identification code (N)) is used as a first-level index inside the prediction sequence container, which is used to construct a charging historical sequence management structure centered on the vehicle. In each sequence entry corresponding to a vehicle unique identification code, a “charging historical sequence container” is arranged, which is used to store the charging process data of the vehicle on multiple different devices. Further, inside each charging historical sequence container, the data sources are distinguished according to different device identifications (device identification (a), device identification (b), device identification (c), and device identification (d), etc.). Each device identification includes a “sequence start timestamp”, a “file name”, and a “file size”. The sequence start timestamp is used to identify the start sampling time of the charging sequence generated by the device, which is used to ensure the time continuity management of the historical sequence; the file name corresponds to the specific name of the original charging data file reported by the device; and the file size is used to quickly judge the content size of the file record and whether there is an abnormal truncation.The above fields together constitute the minimum data unit of the historical sequence, enabling the system to be accurately indexed, quickly retrieved, and support subsequent sequence-level prediction calculations.

[0101] It can be seen that, by Figure 8 The historical sequence management mechanism in the soft bus-based historical sequence management process shown in the embodiment realizes the automation process of virtual directory broadcasting, directory resolution, sequence archiving, and container registration under the soft bus framework. The mechanism not only adapts to the distributed deployment structure of multiple devices and multiple vehicles, but also avoids the bottleneck of traditional centralized data management in terms of communication pressure, file storage, and index complexity, providing a stable, unified, and scalable basic data structure for subsequent distributed prediction calculation and battery life modeling.

[0102] The above mainly introduces the scheme of the embodiments of the application from the perspective of the method execution process. It can be understood that, in order to realize the above functions, the charging device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the unit and algorithm steps of each example described in the embodiments provided herein, the application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0103] The embodiments of the application can divide the functional units of the charging device according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the application is illustrative, and is only a logical functional division. Actual implementation can have another division method.

[0104] In the case of dividing each functional module according to each function, Figure 9 is a functional module composition diagram of a soft bus-based charging station battery life prediction device provided by an embodiment of the application. The soft bus-based charging station battery life prediction device 900 includes: The acquisition unit 910 is configured to control the soft bus module to acquire charging data of a target vehicle on the plurality of charging devices, and acquire working data of the plurality of charging devices. The determining unit 920 is configured to process the charging data in chronological order to obtain a charging data sequence, and determine device computing resources of a computing module of each of the plurality of charging devices according to the working data to obtain computing resource data. The control unit 930 is configured to divide the charging data sequence according to a preset computing task division rule to obtain a plurality of divided computing tasks, and allocate the plurality of divided computing tasks to the computing module on each of the plurality of charging devices according to a preset computing resource allocation rule to obtain a plurality of computing tasks, wherein each of the plurality of computing tasks includes at least one element in the charging data sequence. The computing unit 940 is configured to input the elements in the charging data sequence in the plurality of computing tasks into a preset battery life prediction model to obtain a plurality of prediction results, determine a life prediction weight based on a preset attenuation factor, a preset life prediction weight calculation formula and the charging data sequence to obtain a plurality of life prediction weights, and perform weighted calculation on the plurality of prediction results according to the plurality of life prediction weights to obtain a target prediction result.

[0105] In a possible implementation, the charging data includes historical charging data and charging time data, and the determining unit 920, in the aspect of processing the charging data in chronological order to obtain a charging data sequence, is specifically configured to: extract each charging event of the target vehicle from the historical charging data to obtain a plurality of charging event data; determine a start time corresponding to each of the plurality of charging event data according to the charging time data to obtain a plurality of charging start times; sort the plurality of charging start times in chronological order to obtain a charging start time sequence; determine charging event data corresponding to each of the charging start time sequence to obtain the charging data sequence.

[0106] In a possible implementation, the determining unit 920, in the aspect of determining device computing resources of a computing module of each of the plurality of charging devices according to the working data to obtain computing resource data, is specifically configured to: determine a computing resource occupation rate and a task queue length of the computing module of each of the plurality of charging devices according to the working data to obtain a plurality of computing resource occupation rates and a plurality of task queue lengths; determine a computing resource computing power of the computing module of each of the plurality of charging devices according to the plurality of computing resource occupation rates to obtain an algorithm resource; determine a load parameter of each of the plurality of charging devices according to the plurality of task queue lengths, to obtain a load parameter; determine a required computing resource corresponding to the load parameter based on a preset mapping relationship between the load parameter and the computing resource requirement, to obtain a computing resource requirement; determine a computing resource of a computing module of each of the plurality of charging devices according to the computing resource requirement and the computing resource, to obtain the computing resource data.

[0107] In a possible embodiment, the control unit 930 is configured to, in the process of dividing the charging data sequence according to the preset computing task division rule to obtain the plurality of divided computing tasks, specifically configured to: extract charging record files of the target vehicle from the charging data sequence, to obtain a plurality of charging record files; determine a source device of each of the plurality of charging record files, to obtain a plurality of file device sources; select a charging record file corresponding to a target device source from the plurality of file device sources, to obtain a target charging record file; the target device source is any one of the plurality of file device sources; filter out charging record files other than the target charging record file from the plurality of charging record files, to obtain a charging record file set; determine a data amount of each of the charging record file set, to obtain a plurality of file data amounts; determine a computing resource occupation parameter corresponding to the plurality of charging devices according to the computing resource data, to obtain a plurality of computing resource occupation parameters; divide the charging data record file set according to the computing task division rule, the plurality of resource occupation parameters and the plurality of file data amounts, to obtain the plurality of divided computing tasks.

[0108] In a possible embodiment, the control unit 930 is configured to, in the process of dividing the charging data record file set according to the computing task division rule, the plurality of resource occupation parameters and the plurality of file data amounts to obtain the plurality of divided computing tasks, specifically configured to: sort the plurality of resource occupation parameters in descending order, to obtain a resource occupation parameter sequence; sort the plurality of file data amounts in ascending order, to obtain a file data amount sequence; divide each of the charging record files in the file data amount sequence according to the computing task division rule and the resource occupation parameter sequence, to obtain the plurality of divided computing tasks.

[0109] In a possible embodiment, the computing unit 940 is specifically configured to determine the life prediction weights based on the preset attenuation factor, the preset life prediction weight calculation formula and the charging data sequence, and obtain a plurality of life prediction weights, in which the method comprises the following steps: obtain first charging data according to the last charging data of the target vehicle in the charging data; determine a first charging start time in the first charging data; determine charging start times corresponding to the plurality of charging devices in the charging data sequence, and obtain a plurality of charging start times; subtract the first charging start time from each charging start time in the plurality of charging start times to obtain a plurality of time difference values; calculate the plurality of time difference values and the attenuation factor according to the life prediction weight calculation formula to obtain the plurality of life prediction weights.

[0110] In a possible embodiment, the soft bus module comprises a networking management unit, a protocol unit and a data management unit, and the control unit 930 controls the soft bus module to obtain charging data of the target vehicle on the plurality of charging devices and obtain working data of the plurality of charging devices before the process, and the method further comprises the following steps: detect a plurality of online states of the plurality of charging devices in response to the networking management unit sending an online detection frame to the plurality of charging devices; determine connected charging devices in the plurality of charging devices according to the plurality of online states, and obtain a connected charging device set; register device identifiers of all charging devices in the connected charging device set to obtain a plurality of registration identifiers; determine a topology relationship of all charging devices in the connected charging device set according to the plurality of registration identifiers, and obtain a charging device topology relationship; confirm links of the connected charging device set based on the device topology relationship to obtain a communication available state; network the charging devices in the connected charging device set according to the communication available state to obtain the local area network system.

[0111] The embodiments of the present application further provide a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, the computer program causes a computer to execute part or all steps of any method described in the above method embodiments, and the computer comprises a charging device.

[0112] The embodiment of the present application further provides a computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to execute some or all of the steps of any of the methods described in the above method embodiments. The computer program product can be a software installation package, and the computer comprises the charging device.

[0113] It should be noted that, for each of the above embodiments, in order to simply describe, each is expressed as a series of action combinations. Those skilled in the art should know that the present application is not limited to the order of actions described, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions, steps, modules or units involved are not necessarily required in the embodiments of the present application.

[0114] In the above embodiments, the description of each embodiment of the present application has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. The above specific embodiments further specifically describe the purposes, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only a specific embodiment of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical solutions of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

1. A soft bus based charging station battery life prediction method, characterized in that, The application discloses a control module applied to a local area network composed of a plurality of charging devices interconnected through physical communication links; each charging device in the plurality of charging devices is provided with a computing module and a soft bus module; the soft bus module realizes signaling interaction between the charging devices through the physical communication links based on a soft bus protocol; the method comprises the following steps: controlling the soft bus module to acquire charging data of a target vehicle on the plurality of charging devices and to acquire working data of the plurality of charging devices; processing the charging data in chronological order to obtain a charging data sequence; determining device computing resources of the computing module of each device in the plurality of charging devices according to the working data to obtain computing resource data; dividing the charging data sequence according to a preset computing task division rule to obtain a plurality of division computing tasks; allocating the plurality of division computing tasks to the computing module on each charging device in the plurality of charging devices according to a preset computing resource allocation rule to obtain a plurality of computing tasks; each computing task in the plurality of computing tasks comprises at least one element in the charging data sequence; inputting the elements in the charging data sequence in the plurality of computing tasks into a preset battery life prediction model to obtain a plurality of prediction results; determining life prediction weights based on a preset attenuation factor, a preset life prediction weight calculation formula and the charging data sequence to obtain a plurality of life prediction weights; performing weighted calculation on the plurality of prediction results according to the plurality of life prediction weights to obtain a target prediction result.

2. The method of claim 1, wherein, The charging data comprises historical charging data and charging time data; the processing of the charging data in chronological order to obtain a charging data sequence comprises the following steps: extracting each charging event of the target vehicle from the historical charging data to obtain a plurality of charging event data; determining the start time corresponding to each charging event data in the plurality of charging event data according to the charging time data to obtain a plurality of charging start times; sorting the plurality of charging start times in chronological order to obtain a charging start time sequence; determining the charging event data corresponding to each charging start time in the charging start time sequence to obtain the charging data sequence.

3. The method of claim 1, wherein, The determination of the device computing resources of the computing module of each device in the plurality of charging devices according to the working data to obtain the computing resource data comprises the following steps: determining the computing resource occupation rate and the task queue length of the computing module of each device in the plurality of charging devices according to the working data to obtain a plurality of computing resource occupation rates and a plurality of task queue lengths; determining the computing resource computing power of the computing module of each charging device in the plurality of charging devices according to the plurality of computing resource occupation rates to obtain computing power resources; determining the load parameter of each charging device in the plurality of charging devices according to the plurality of task queue lengths to obtain a load parameter; determining the required computing resources corresponding to the load parameter based on the mapping relationship between the load parameter and the computing resource requirement to obtain the computing resource requirement. According to the computing resource requirement and the computing power resource, a computing resource of a computing module of each device in the plurality of charging devices is determined, and the computing resource data is obtained.

4. The method according to any one of claims 1 to 3, characterized in that, The charging data sequence is divided according to the preset computing task division rule, and a plurality of divided computing tasks is obtained. A charging record file of the target vehicle is extracted from the charging data sequence, and a plurality of charging record files is obtained. A source device of each charging record file in the plurality of charging record files is determined, and a plurality of file device sources is obtained. A charging record file corresponding to a target file device source is selected from the plurality of file device sources, and a target charging record file is obtained. The target file device source is any one of the plurality of file device sources. Charging record files except those in the target charging record file are filtered out from the plurality of charging record files, and a charging record file set is obtained. A data amount of each charging record file in the charging record file set is determined, and a plurality of file data amounts is obtained. According to the computing resource data, a computing resource occupation parameter corresponding to the plurality of charging devices is determined, and a plurality of computing resource occupation parameters is obtained. The charging record file set is divided according to the computing task division rule, the plurality of computing resource occupation parameters, and the plurality of file data amounts, and the plurality of divided computing tasks is obtained.

5. The method of claim 4, wherein, The charging record file set is divided according to the computing task division rule, the plurality of computing resource occupation parameters, and the plurality of file data amounts, and the plurality of divided computing tasks is obtained, including: The plurality of computing resource occupation parameters is sorted in descending order, and a resource occupation parameter sequence is obtained. The plurality of file data amounts is sorted in ascending order, and a file data amount sequence is obtained. Each charging record file in the file data amount sequence is divided based on the computing task division rule and the resource occupation parameter sequence, and the plurality of divided computing tasks is obtained.

6. The method of claim 1 or 2, wherein, The plurality of life prediction weights is obtained by determining a life prediction weight based on a preset decay factor, a preset life prediction weight calculation formula, and the charging data sequence, including: The last charging data of the target vehicle in the charging data is determined, and first charging data is obtained. A first charging start time in the first charging data is determined. A charging start time corresponding to the plurality of charging devices in the charging data sequence is determined, and a plurality of charging start times is obtained. Each charging start time in the plurality of charging start times is subtracted from the first charging start time, and a plurality of time difference values is obtained. The plurality of time difference values and the decay factor are calculated according to the life prediction weight calculation formula, and the plurality of life prediction weights is obtained.

7. The method of claim 1 or 2, wherein, The soft bus module includes a networking management unit, a protocol unit, and a data management unit. Before the control of the soft bus module to obtain charging data of the target vehicle on the plurality of charging devices and to obtain working data of the plurality of charging devices, the method further includes: Detecting the multiple charging devices responding to the network management unit sending online detection frames to the multiple charging devices, obtaining multiple online states; According to the multiple online states, determining the connected charging devices in the multiple charging devices, obtaining a connected charging device set; Registering the device identification of all charging devices in the connected charging device set, obtaining multiple registration identifications; According to the multiple registration identifications, determining the topological relationship of all charging devices in the connected charging device set, obtaining a charging device topological relationship; Based on the charging device topological relationship, performing link confirmation on the connected charging device set, obtaining a communication available state; According to the communication available state, performing networking on the charging devices in the connected charging device set, obtaining the local area network system.

8. A soft bus based charging station battery life prediction apparatus, characterized by, The control module applied to the local area network is composed of multiple charging devices interconnected through physical communication links; each charging device in the multiple charging devices is provided with a computing module and a soft bus module; the soft bus module realizes signaling interaction between charging devices based on a soft bus protocol through the physical communication links; the device comprises: An acquisition unit configured to control the soft bus module to acquire charging data of a target vehicle on the multiple charging devices and to acquire working data of the multiple charging devices; A determination unit configured to process the charging data in chronological order to obtain a charging data sequence and to determine device computing resources of the computing module of each device in the multiple charging devices based on the working data to obtain computing resource data; A control unit configured to divide the charging data sequence according to a preset computing task division rule to obtain multiple division computing tasks, and to allocate the multiple division tasks to the computing module on each charging device in the multiple charging devices according to a preset computing resource allocation rule to obtain multiple computing tasks; each computing task in the multiple computing tasks includes at least one element in the charging data sequence; A computing unit configured to input the elements in the charging data sequence in the multiple computing tasks into a preset battery life prediction model to obtain multiple prediction results, to determine life prediction weights based on a preset decay factor, a preset life prediction weight calculation formula and the charging data sequence to obtain multiple life prediction weights, and to perform weighted calculation on the multiple prediction results according to the multiple life prediction weights to obtain a target prediction result.

9. A charging device, characterized by Comprise: a processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in the method of any one of claims 1-7.

10. A soft bus based charging station battery life prediction system, characterized in that, The soft bus-based charging station battery life prediction system performs the method of any one of claims 1-7.

Images