Battery data processing method, device, computer equipment, storage medium and system

Abstract

This application relates to a battery data processing method, apparatus, computer device, storage medium, and system. The method comprises: in response to a data analysis operation triggered by a power device for at least one charge and discharge management function, obtaining device data reported by the power device through a data reporting channel; invoking a decision analysis model that matches the charge and discharge management function, performing a management decision analysis on the power device based on the device data, and determining device management information for the power device for the charge and discharge management function; and transmitting the device management information to the power device using an information distribution channel that matches the charge and discharge management function. This method can provide efficient and highly accurate charge and discharge decision analysis and management services for power devices.

Description

Technical Field

[0001] The present application relates to the field of battery management technology, and in particular to a battery data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] Power equipment uses batteries as its power source. This energy is utilized by converting the chemical energy stored in the batteries into electrical energy, which is then converted into mechanical energy through devices such as motors. Therefore, battery technology is a key factor in determining the performance and service life of power equipment, such as new energy vehicles. Analyzing and managing charging and discharging decisions for power equipment is an effective means of improving its operational reliability, optimizing the charge and discharge status of its battery cells, and extending its lifespan.

[0003] Currently, charging and discharging decision analysis and management for power equipment is typically performed by configuring a fixed battery management strategy or decision analysis program within the battery's own battery management unit (BMU). However, due to its limited operating resources, the BMU can only handle simple analysis and management tasks and cannot provide efficient and highly accurate charging and discharging decision analysis and management services for power equipment. Summary of the Invention

[0004] Based on this, it is necessary to provide a charging and discharging data processing method, device, computer equipment, computer-readable storage medium and computer program product that can provide efficient and highly accurate charging and discharging decision analysis and management services for power equipment in response to the above technical problems.

[0005] In a first aspect, the present application provides a battery data processing method, the method comprising:

[0006] In response to a data analysis operation triggered by the power equipment for at least one charge and discharge management function, obtaining device data reported by the power equipment through a data reporting channel;

[0007] calling a decision analysis model that matches the charge and discharge management function, performing a management decision analysis on the power equipment according to the equipment data, and determining equipment management information of the power equipment for the charge and discharge management function;

[0008] The device management information is sent to the power device using an information delivery channel that matches the charge and discharge management function.

[0009] In the above-described embodiment, by setting up multiple decision analysis models to match each charge-discharge management function, when the power equipment triggers a data analysis operation for the charge-discharge management function, the decision analysis platform can quickly match and call the corresponding decision analysis model to perform management decision analysis on the power equipment, effectively improving the accuracy and efficiency of equipment management for the power equipment. Furthermore, by setting up separate data reporting channels and information dissemination channels, the data transmission processes of data reporting and information dissemination can be separated, effectively reducing the risk of reduced equipment management efficiency due to transmission interference, channel congestion, etc.

[0010] In some embodiments, calling a decision analysis model that matches the charge and discharge management function, performing a management decision analysis on the power equipment based on the equipment data, and determining the equipment management information of the power equipment for the charge and discharge management function includes:

[0011] Calling a data transmission interface preset by a decision analysis model that matches the charge and discharge management function, and inputting the device data into the decision analysis model;

[0012] receiving an analysis result returned by the decision analysis model after performing a management decision analysis on the power equipment based on the equipment data;

[0013] Based on the analysis result, device management information of the power device for the charge and discharge management function is determined.

[0014] In the above embodiment, by isolating the storage of the decision analysis model from the decision analysis platform and pre-setting a data transmission interface between the decision analysis platform and each decision analysis model, it is possible to effectively improve the operating resources of the decision analysis platform while maintaining the real-time performance of the decision analysis model in performing management decision analysis on the power equipment, thereby improving the accuracy and efficiency of equipment management of the power equipment.

[0015] In some embodiments, there are multiple power devices, and inputting the device data into the decision analysis model includes:

[0016] Perform data comparison on the equipment data of each of the power equipment, and determine the reference equipment data from the equipment data:

[0017] Based on the reference device data, determining data difference information between each of the device data and the reference device data;

[0018] Encoding and compressing the reference device data and each of the data difference information to obtain a composite data packet of the decision analysis model;

[0019] The composite data packet is transmitted to the decision analysis model.

[0020] In the above embodiment, when there are multiple power devices triggering the same charge and discharge management function, by reducing the amount of redundant data, the reference device data and data difference information in the device data of each power device are extracted and encoded and compressed, which can effectively reduce the amount of data in the device data of each power device during the data transmission process, save transmission bandwidth, and achieve high-speed data transmission.

[0021] In some embodiments, using an information delivery channel that matches the charge and discharge management function to send the device management information to the power device includes:

[0022] Determining timeliness requirement information that matches the function identifier of the charge and discharge management function;

[0023] Calling the pre-set mapping relationship between each timeliness requirement and each information delivery channel to determine the target information delivery channel that matches the timeliness requirement information;

[0024] The target information sending channel is used to send the device management information to the power device.

[0025] In the above embodiment, by dividing the corresponding timeliness requirements for each charging and discharging management function and configuring a corresponding information delivery channel for each timeliness requirement, it is possible to achieve efficient management of the power equipment while effectively saving information transmission costs.

[0026] In some embodiments, using the target information delivery channel to send the device management information to the power device includes:

[0027] Based on the charge and discharge management function, determining at least one instruction type required to carry the device management information;

[0028] Extracting instruction information from the device management information according to the instruction type to obtain instruction information corresponding to the instruction type;

[0029] Generate an instruction to be issued corresponding to the instruction type based on the instruction information;

[0030] The target information sending channel is used to send the instruction to be sent to the power equipment.

[0031] In the above embodiment, the instruction type of the equipment management information carrying the charging and discharging management function is determined in advance for each charging and discharging management function. After obtaining the charging and discharging management information, the instruction information of the equipment management information can be quickly extracted according to the instruction type, thereby generating corresponding instructions to be issued, so that the power equipment can quickly respond to the instructions to be issued to perform equipment management tasks, effectively improving the equipment management efficiency of the power equipment.

[0032] In some embodiments, generating the instruction to be issued corresponding to the instruction type based on the instruction information includes:

[0033] Determining an encryption algorithm that matches the power device and an encryption key that matches the instruction type;

[0034] Based on the encryption algorithm and the encryption key, the instruction information is encrypted and compressed to obtain the instruction to be issued corresponding to the instruction type.

[0035] In the above embodiment, by using an encryption algorithm that matches the power equipment and an encryption key that matches the instruction type to encrypt the instruction information, the most appropriate encryption method can be determined for the instruction information from the two dimensions of power equipment and instruction type. While improving the security of instruction information transmission, it can effectively reduce the risk of information decryption failure at the device terminal due to incompatibility of the encryption algorithm.

[0036] In some embodiments, there are multiple instructions to be issued, and each instruction to be issued corresponds to each instruction type one by one;

[0037] The step of using the target information sending channel to send the instruction to be sent to the power equipment includes:

[0038] Calculating the total transmission capacity of the instructions to be issued according to the instruction transmission capacity of each instruction to be issued;

[0039] When the total transmission capacity is less than or equal to a preset capacity threshold, merging and compressing the instructions to be issued to obtain a composite instruction;

[0040] The target information sending channel is used to send the composite instruction to the power equipment.

[0041] In the above embodiment, by comparing the total transmission capacity of each instruction to be issued with a preset capacity threshold, when the total transmission capacity is less than or equal to the preset capacity threshold, the instructions to be issued are merged and compressed into a composite instruction and issued to the power equipment at one time. This not only improves the real-time transmission of instructions, but also significantly reduces the network load and improves transmission efficiency.

[0042] In some embodiments, the method further comprises:

[0043] When the total transmission capacity is greater than the preset capacity threshold, determining the instruction relevance of each of the instructions to be issued according to the instruction type corresponding to each of the instructions to be issued;

[0044] Based on the relevance of each instruction and the preset capacity threshold, dividing each instruction to be issued to obtain at least two instruction sets;

[0045] For each of the instruction sets, merging and compressing the instructions to be issued contained in the instruction set to obtain a sub-compound instruction of the power equipment;

[0046] The target information sending channel is used to send each of the sub-compound instructions to the power equipment in sequence.

[0047] In the above embodiment, when the total transmission capacity exceeds a preset capacity threshold, the instructions to be issued are divided into instruction sets by calculating their relevance. This allows highly relevant instructions to be merged and transmitted first, reducing communication transmission costs, while low-relevance instructions can be processed independently, lowering resource contention. While meeting capacity constraints, the internal relevance of the instructions to be issued in the instruction set is maximized, thereby optimizing transmission efficiency and the reliability of the power equipment's execution.

[0048] In some embodiments, the method further comprises:

[0049] Counting the usage frequencies of each of the pre-configured candidate decision analysis models, and determining theoretical operating resources that match the usage frequencies of each of the models;

[0050] Obtaining actual operating resources of each of the candidate decision analysis models;

[0051] For each of the candidate decision analysis models, determining a resource adjustment value of the candidate decision analysis model according to the theoretical operating resources of the candidate decision analysis model and the actual operating resources;

[0052] The resource partitioning of the candidate decision analysis model is adjusted according to the resource adjustment value.

[0053] In the above embodiment, dynamic resource division is performed on each candidate decision analysis model based on the frequency of use of each model, so that high-frequency use models can be automatically expanded and low-frequency use models can release resources in a timely manner, thereby achieving operational stability and efficiency of the candidate decision analysis models corresponding to the core business.

[0054] In a second aspect, the present application further provides a battery data processing device, the device comprising:

[0055] a response module, configured to obtain device data reported by the power device through a data reporting channel in response to a data analysis operation triggered by the power device for at least one charge and discharge management function;

[0056] a data analysis module, configured to call a decision analysis model matching the charge and discharge management function, perform management decision analysis on the power equipment based on the equipment data, and determine equipment management information of the power equipment for the charge and discharge management function;

[0057] An information sending module is used to send the device management information to the power device using an information sending channel that matches the charge and discharge management function.

[0058] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0059] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0060] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0061] In a sixth aspect, the present application further provides a battery data processing system, the system comprising a decision analysis platform and at least one power device; the decision analysis platform and the power device are pre-established with a data reporting channel and an information sending channel;

[0062] The power equipment reports equipment data to the decision analysis platform through the data reporting channel;

[0063] The decision analysis platform sends equipment management information to the power equipment through the information sending channel;

[0064] The decision analysis platform is used to implement the battery data processing method as described above.

[0065] In the aforementioned battery data processing method, apparatus, computer device, storage medium, and computer program product, a decision analysis platform can, in response to a data analysis operation triggered by a power device for at least one charge-discharge management function, obtain device data reported by the power device via a data reporting channel, invoke a decision analysis model matching the charge-discharge management function, perform a management decision analysis on the power device based on the device data, determine device management information for the power device for the charge-discharge management function, and transmit the device management information to the power device using an information delivery channel matching the charge-discharge management function. The aforementioned battery data processing method, on the one hand, establishes multiple decision analysis models, each matching each charge-discharge management function. When a data analysis operation is triggered by a power device for a charge-discharge management function, the decision analysis platform can quickly match and invoke the corresponding decision analysis model to perform a management decision analysis on the power device, effectively improving the accuracy and efficiency of device management for the power device. On the other hand, by establishing separate data reporting and information delivery channels, the data transmission processes for data reporting and information delivery are separated, effectively reducing the risk of decreased device management efficiency due to transmission interference, channel congestion, and other factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of the structure of a battery data processing system in some embodiments;

[0067] Figure 2 Schematic diagram of the structure of the battery data processing system in some other embodiments;

[0068] Figure 3 is a flowchart of a battery data processing method in some embodiments;

[0069] Figure 4 A schematic diagram of a process for invoking a decision analysis model that matches a charge and discharge management function in some embodiments, performing management decision analysis on a power device based on device data, and determining device management information for the power device for the charge and discharge management function;

[0070] Figure 5 A schematic diagram of a process for inputting device data into a decision analysis model in some embodiments;

[0071] Figure 6 A schematic diagram of a process for sending device management information to a power device using an information delivery channel that matches the charge and discharge management function in some embodiments;

[0072] Figure 7 A flow chart illustrating how to send device management information to a power device using a target information delivery channel in some embodiments;

[0073] Figure 8A schematic diagram of a flow chart of using a target information delivery channel to send a to-be-delivered instruction to a power device in some embodiments;

[0074] Figure 9 Schematic diagram of the flow of battery data processing method in other embodiments;

[0075] Figure 10 Schematic diagram of the flow of battery data processing method in other embodiments;

[0076] Figure 11 A system architecture diagram of a battery data processing system in some embodiments;

[0077] Figure 12 Schematic diagram of the flow of battery data processing method in other embodiments;

[0078] Figure 13 is a structural block diagram of a battery data processing device in some embodiments;

[0079] Figure 14 1 is a diagram of the internal structure of a computer device in some embodiments. DETAILED DESCRIPTION

[0080] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0081] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0082] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least some embodiments of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0083] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0084] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0085] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0086] Power equipment, such as new energy vehicles, uses batteries as its power source, converting the chemical energy stored in the batteries into electrical energy, and then converting the electrical energy into mechanical energy to operate. The battery is considered the core of power equipment, and its operating status directly affects the operation of the power equipment. Managing the charge and discharge of power batteries is an effective way to optimize the charge and discharge status of battery cells in power equipment, extend battery life, and improve equipment performance.

[0087] Currently, charging and discharging decision analysis and management for power equipment is typically performed by configuring a fixed battery management strategy or decision analysis program within the battery's own battery management unit (BMU). However, due to its limited operating resources, the BMU can only handle simple analysis and management tasks and cannot provide efficient and highly accurate charging and discharging decision analysis and management services for power equipment.

[0088] To improve the accuracy of charge-discharge decision analysis and device management efficiency, a decision analysis platform can, in response to a data analysis operation triggered by a power device for at least one charge-discharge management function, obtain device data reported by the power device through a data reporting channel, invoke a decision analysis model that matches the charge-discharge management function, perform management decision analysis on the power device based on the device data, determine device management information for the power device for the charge-discharge management function, and transmit the device management information to the power device using an information distribution channel that matches the charge-discharge management function. The above-mentioned battery data processing method, on the one hand, sets multiple decision analysis models that match each charge-discharge management function. When a data analysis operation is triggered by a power device for a charge-discharge management function, the decision analysis platform can quickly match and invoke the corresponding decision analysis model to perform management decision analysis on the power device, effectively improving the accuracy and efficiency of device management for the power device. On the other hand, by setting up separate data reporting and information distribution channels, the data transmission processes of data reporting and information distribution can be separated, effectively reducing the risk of reduced device management efficiency due to transmission interference, channel congestion, and other factors.

[0089] The battery data processing method provided in the embodiment of the present application can be applied to Figure 1 The battery data processing system 100 shown in FIG. 1 includes a decision analysis platform 101 and at least one power device 102 . The decision analysis platform 101 and the power device 102 are pre-configured with a data reporting channel 103 and an information sending channel 104 .

[0090] The power equipment 102 reports equipment data to the decision analysis platform 101 through the data reporting channel 103 , and the decision analysis platform 101 sends equipment management information to the power equipment 102 through the information sending channel 104 .

[0091] The power equipment 102 can be any battery-powered device, such as new energy vehicles, electric aircraft, and industrial transport vehicles. The power equipment 102 is equipped with its own battery management unit (BMS), which performs functions such as battery data collection, status monitoring, battery protection, balancing management, communication and control, and thermal management. Furthermore, the power equipment 102 is also equipped with corresponding information collection equipment. For example, new energy vehicles are equipped with corresponding onboard sensors, such as environmental sensors, to obtain real-time device operating information during vehicle operation.

[0092] The data reporting channel 103 is a dedicated data transmission path for reporting data generated by the power equipment to the decision analysis platform 101. The information dissemination channel 104 is a dedicated data transmission path for disseminating instruction information generated by the decision analysis platform 101 to the power equipment 102. It will be appreciated that the data reporting channel 103 and the information dissemination channel 104 have opposite data transmission directions. The specific number of data reporting channels 103 and information dissemination channels 104 can be determined based on actual communication conditions.

[0093] Decision analysis platform 101 is an intelligent analysis platform capable of implementing various charge and discharge management functions. By integrating multi-source data and pre-trained algorithm models, it can provide decision analysis services for charge and discharge management issues in various power equipment usage scenarios. It is understood that decision analysis platform 101 can be implemented by a standalone server, a server cluster consisting of multiple servers, or a cloud server.

[0094] In some embodiments, in order to not be limited by operating resources, the decision analysis platform 101 can be a cloud service platform, set up in a cloud server, and the model repository storing pre-trained decision analysis models can be stored in other cloud servers. The decision analysis platform 101 can be communicated with the model repository in other cloud servers through a pre-set communication interface. When the power equipment 102 triggers a data analysis operation for one or more charge and discharge management functions, the corresponding decision analysis model can be quickly matched for the charge and discharge management function from the model repository, and the decision analysis model can be called to perform management decision analysis on the power equipment 102 based on the equipment data.

[0095] In some embodiments, the decision analysis platform 101 can respond to the data analysis operation triggered by the power equipment 102 for at least one charge and discharge management function, obtain the equipment data reported by the power equipment through the data reporting channel, call the decision analysis model matching the charge and discharge management function, perform management decision analysis on the power equipment based on the equipment data, determine the equipment management information of the power equipment for the charge and discharge management function, and use the information distribution channel matching the charge and discharge management function to send the equipment management information to the power equipment.

[0096] In the above-described embodiment, when the power equipment triggers a data analysis operation for the charge and discharge management function, the decision analysis platform in the battery data processing system can quickly match and invoke the corresponding decision analysis model to perform management decision analysis on the power equipment, effectively improving the accuracy and efficiency of power equipment management. Furthermore, by setting up separate data reporting channels and information dissemination channels, the data transmission processes for data reporting and information dissemination can be separated, effectively reducing the risk of reduced equipment management efficiency due to transmission interference, channel congestion, and other factors.

[0097] In some embodiments, as Figure 2 As shown, the power device 102 is provided with a battery management unit 1021, an information acquisition device 1022, and a real-time database module 1024 connected to the battery management unit 1021 and the information acquisition device 1022 via a communication bus 1023, such as a CAN bus. The decision analysis platform 101 is connected to the real-time database module 1024 via a data reporting channel 103 and an information dissemination channel 104, thereby achieving communication with the power device 102.

[0098] The real-time database module 1024 can collect battery pack parameters from the battery management unit 1021, such as single cell voltage / temperature, total voltage, insulation resistance, historical charge and discharge curves, and remaining range. The information collection device 1022 can also obtain the ambient temperature, humidity, altitude, and location information of the power equipment 102.

[0099] In some embodiments, the data flow of data reporting channel 103 is as follows: battery management unit 1021 transparently transmits device data to real-time database module 1024, which then transmits the device data to decision analysis platform 101 via a distributed stream processing platform, such as Kafka. By implementing distributed management of data transmission in data reporting channel 103 through the distributed stream processing platform, the transmission efficiency and stability of device data can be further improved in high-throughput scenarios.

[0100] In some embodiments, the data flow of the information distribution channel 104 is as follows: the decision analysis platform 101 writes the device management information into the real-time database module 1024 through a preset communication protocol, such as the HTTP protocol, and the real-time database module 1024 then transmits the received device management information to the battery management unit 1021.

[0101] In some embodiments, as Figure 3 As shown, a battery data processing method is provided, which is applied to Figure 1 Taking the decision analysis platform 101 in FIG. 1 as an example, the following steps are included:

[0102] S302 : In response to a data analysis operation triggered by the power equipment for at least one charge and discharge management function, obtaining device data reported by the power equipment through a data reporting channel.

[0103] The charge and discharge management function is a platform function that manages the charging and discharging process of power equipment. For example, this function can include charge and discharge strategy recommendation, charge and discharge curve optimization, charge and discharge fault prediction, and charging station recommendation. As you can see, the decision analysis platform is pre-configured with a variety of charge and discharge management functions to match various power equipment usage scenarios.

[0104] The data analysis operation is an operation triggered when the power equipment has a need for data analysis for the charge and discharge management function. It can be understood that the data analysis operation can be an operation directly triggered by the device user of the power equipment for the charge and discharge management function. For example, when the device user has a need for charge and discharge, he can directly log in to the decision analysis platform through the device terminal, select the charging pile recommendation function on the function selection page of the decision analysis platform, and trigger the data analysis operation for the charging pile recommendation function. The data analysis operation can also be indirectly triggered by the device use operation of the power equipment during use. Taking the power equipment as a new energy vehicle as an example, when the new energy vehicle is plugged in for charging, the data analysis operation can be triggered for the charge and discharge management functions such as charge and discharge curve optimization and charge and discharge strategy recommendation. For example, during the driving of the new energy vehicle, if the battery heats up too quickly, the data analysis operation can also be triggered for the charge and discharge fault prediction function.

[0105] Equipment data refers to the data required for decision-making and analysis of charge and discharge management functions. This equipment data can be real-time data generated by power equipment during operation, such as battery usage data, charge and discharge curves, charge and discharge strategies, battery temperature, and environmental information. It can also be historical data recorded by power equipment during its historical operation, such as historical charge and discharge curves, fault repair records, fault alarm records, fault maintenance records, operation logs, and user usage profiles.

[0106] It's understandable that different charging and discharging functions require different device data. For example, the device data required for the charge and discharge strategy recommendation function may include the power device's state of charge information during operation, battery health information, charge and discharge curves, historical charge and discharge curves, and user profile data. The device data required for the charging station recommendation function may include the power device's location, historical charge and discharge habits, and current power level information.

[0107] In some embodiments, the decision analysis platform may obtain device data reported by the power equipment through a data reporting channel in response to a data analysis operation triggered by the power equipment for at least one charge and discharge management function.

[0108] S304 , calling a decision analysis model that matches the charge and discharge management function, performing management decision analysis on the power equipment according to the equipment data, and determining equipment management information of the power equipment for the charge and discharge management function.

[0109] The decision analysis model is a pre-set model tool used to perform dynamic decision analysis on the charging and discharging processes managed by the matching charge and discharge management function. This model can include rule models that encapsulate predefined decision analysis logic, prediction models that predict the charging and discharging process, optimization models that achieve optimal solutions, and deep learning models that train complex decision-making capabilities through machine learning. By invoking the decision analysis model that matches the charge and discharge management function, accurate and rapid management decision analysis can be performed on power equipment, improving the efficiency and accuracy of power equipment management.

[0110] In some of the embodiments, the decision analysis models matching the various charge and discharge management functions can be directly installed in the decision analysis platform, and the decision analysis platform can directly call the various decision analysis models to perform real-time management decision analysis.

[0111] Management decision analysis refers to the process by which a decision analysis model analyzes power equipment based on equipment data according to a pre-set model analysis logic and outputs the analysis results. Equipment management information is the process of converting analysis results into executable management information. By converting analysis results into equipment management information, power equipment can quickly execute the received equipment management information, improving equipment management efficiency.

[0112] In some embodiments, the decision analysis model can determine the charge and discharge management function that needs to be used based on the triggering operation of the power equipment, and then call the decision analysis model that matches the charge and discharge management function, input the equipment data reported by the power equipment into the decision analysis model, perform decision analysis on the power equipment based on the decision analysis model, obtain the analysis results output by the decision analysis model, perform feasibility conversion on the analysis results, and obtain the equipment management information of the power equipment for the charge and discharge function.

[0113] In some of the embodiments, a mapping relationship between each decision analysis model and each charge and discharge management function is pre-set in the decision analysis model. The decision analysis model can search for the mapping relationship based on the determined charge and discharge management function to determine at least one decision analysis model that matches the charge and discharge management function.

[0114] S306: Use an information delivery channel that matches the charge and discharge management function to send the device management information to the power device.

[0115] Among them, there are multiple information sending channels between the decision analysis platform and the power equipment. Different charging and discharging management functions may correspond to different information sending channels. The decision analysis platform needs to determine the information sending channel that matches the charging and discharging management function.

[0116] In some embodiments, the decision analysis platform determines an information delivery channel that matches the charge and discharge management function, and then uses the information delivery channel to send the device management information to the power equipment.

[0117] In some of the embodiments, an information sending channel can be set up for each charging and discharging management function, which can effectively improve the efficiency of information sending and thus improve the equipment management efficiency of the power equipment. Each information sending channel is provided with a functional identifier corresponding to the charging and discharging management function. The decision analysis platform can directly determine the information sending channel that matches the charging and discharging management function from each information sending channel based on the functional identifier of the charging and discharging management function.

[0118] In the aforementioned battery data processing method, the decision analysis platform can, in response to a data analysis operation triggered by a power device for at least one charge-discharge management function, obtain device data reported by the power device via a data reporting channel, invoke a decision analysis model that matches the charge-discharge management function, perform a management decision analysis on the power device based on the device data, determine device management information for the power device for the charge-discharge management function, and transmit the device management information to the power device using an information distribution channel that matches the charge-discharge management function. The aforementioned battery data processing method, on the one hand, establishes multiple decision analysis models that match each charge-discharge management function. When a data analysis operation is triggered by a power device for a charge-discharge management function, the decision analysis platform can quickly match and invoke the corresponding decision analysis model to perform a management decision analysis on the power device, effectively improving the accuracy and efficiency of device management for the power device. On the other hand, by establishing separate data reporting and information distribution channels, the data transmission processes for data reporting and information distribution can be separated, effectively reducing the risk of decreased device management efficiency due to transmission interference, channel congestion, and other factors.

[0119] When conducting management decision analysis, the operating resources of the decision analysis platform will affect the real-time performance of the management decision analysis. In order to further improve the operating resources of the decision analysis platform, in some embodiments, such as Figure 4 As shown, S304, calling a decision analysis model that matches the charge and discharge management function, performing management decision analysis on the power equipment based on the equipment data, and determining the equipment management information of the power equipment for the charge and discharge management function, including:

[0120] S402 , calling a data transmission interface preset in a decision analysis model that matches the charge and discharge management function, and inputting device data into the decision analysis model.

[0121] The data transmission interface is a pre-configured communication channel interface used to provide a data transmission path for the decision analysis platform and the corresponding decision analysis model. It is understandable that the data transmission interface can be an application programming interface (API).

[0122] In order to improve the operating resources of the decision analysis platform, each decision analysis model can be stored in other remote servers. The decision analysis platform can pre-build a data transmission interface with each decision analysis model. When it is necessary to call the decision analysis model to perform management decision analysis on power equipment, there is no need to call the decision analysis model to the decision analysis platform for configuration. Instead, the equipment data required for management decision analysis can be directly input into the decision analysis model through the data transmission interface for processing.

[0123] In some embodiments, after determining the decision analysis model that matches the charge and discharge management function, the decision analysis platform can call a data transmission interface pre-set with the decision analysis model and directly input device data into the decision analysis model through the data transmission interface.

[0124] S404, receiving the analysis result returned by the decision analysis model after performing management decision analysis on the power equipment based on the equipment data.

[0125] The analysis results are the decision analysis conclusions output by the decision analysis model after analyzing the management decisions of the power equipment based on the equipment data. It is understandable that the decision analysis conclusions output by the decision analysis models corresponding to different charge and discharge management functions are different. For example, the analysis results output by the decision analysis model corresponding to the charge and discharge strategy recommendation function are the target charge and discharge strategy, while the analysis results output by the decision analysis model corresponding to the charge and discharge curve optimization function are the optimized charge and discharge curve.

[0126] In some embodiments, the decision analysis model can perform management decision analysis on the power equipment based on the equipment data, output the analysis results, and return the analysis results to the decision analysis platform through the data transmission interface. The decision analysis platform receives the analysis results returned by the decision analysis model through the data transmission interface.

[0127] S406: Determine device management information for the charge and discharge management function of the power device based on the analysis result.

[0128] In some embodiments, the decision analysis platform may determine device management information for the power equipment's charge and discharge management function based on the received analysis results. For example, if the analysis result is an optimized charge and discharge curve, the decision analysis platform may determine the time points and charge and discharge durations of each charge and discharge phase based on the optimized charge and discharge curve, and generate corresponding charge and discharge control instructions based on the time points and charge and discharge durations of each charge and discharge phase. Each charge and discharge instruction is the power equipment's device management information for the charge and discharge management function. Upon receiving each charge and discharge control instruction, the power equipment may perform actual charge and discharge control according to the charge and discharge control instruction.

[0129] In the above embodiment, by isolating the storage of the decision analysis model from the decision analysis platform and pre-setting a data transmission interface between the decision analysis platform and each decision analysis model, it is possible to effectively improve the operating resources of the decision analysis platform while maintaining the real-time performance of the decision analysis model in performing management decision analysis on the power equipment, thereby improving the accuracy and efficiency of equipment management of the power equipment.

[0130] In order to further improve the analysis efficiency of the decision analysis model, in some embodiments, the number of power equipment is multiple. Figure 5 As shown, inputting the device data into the decision analysis model in S402 includes:

[0131] S502 : performing data comparison on the equipment data of each power equipment, and determining reference equipment data from the equipment data.

[0132] The benchmark device data refers to the common data within each power device's device data, i.e., the same data information. When multiple power devices trigger data analysis for the same charge and discharge management function, the device data they report will all be required by the same decision analysis model, so some common data will exist. For example, if the reported device data includes temperature data, and the temperature data reported by each power device is 25°C, 25°C, 26°C, 28°C, and 24°C, then the benchmark device data can be determined to be 25°C.

[0133] In some embodiments, when the decision analysis platform receives data analysis operations triggered by multiple power devices for the same charge and discharge management function, it obtains the device data of each power device, compares the data of each device, and determines the benchmark device data from the data of each device.

[0134] S504: Based on the reference device data, determine data difference information between each device data and the reference device data.

[0135] In some embodiments, the decision analysis platform may compare each device data with the reference device data to determine data difference information between each device data and the reference device data.

[0136] Taking the temperature data reported by each power device as 25°C, 25°C, 26°C, 28°C, and 24°C as an example, and the reference device data is 25°C, the data difference information between each device data and the reference device data is 0, 0, +1, +3, and -4.

[0137] S506 , encoding and compressing the reference device data and the data difference information to obtain a composite data packet of the decision analysis model.

[0138] Encoding compression is a data processing method that compresses data using a compression algorithm to reduce its size. A composite data packet is a data packet created by combining multiple data sets through data compression. As you can see, a composite data packet can contain not only the baseline device data and the difference information between each data set, but also common metadata such as a timestamp and device group identifier.

[0139] In some embodiments, the decision analysis platform may use a preset encoding algorithm, such as a lossless data compression (Huffman) algorithm, to encode and compress the reference device data and each data difference information to obtain a composite data packet of the decision analysis model.

[0140] S508: Transmit the composite data packet to the decision analysis model.

[0141] In some embodiments, the decision analysis platform may transmit the composite data packet to the decision analysis model so that the decision analysis model can perform management decision analysis on each power device based on the device data of each power device carried in the composite data packet.

[0142] In the above embodiment, when there are multiple power devices triggering the same charge and discharge management function, by reducing the amount of redundant data, the reference device data and data difference information in the device data of each power device are extracted and encoded and compressed, which can effectively reduce the amount of data in the device data of each power device during the data transmission process, save transmission bandwidth, and achieve high-speed data transmission.

[0143] In some embodiments, when there are multiple data dimensions in the device data, the decision analysis platform determines, for each data dimension, the benchmark device data and data difference information in each device data under that data dimension, binds each data dimension with its corresponding benchmark device data to obtain a benchmark device data set, and for each power device, binds the device identification of the power device with the data difference information of the power device in each data dimension to obtain a data difference information set of the power device, and finally encodes and compresses the benchmark device data set and the data difference information set of each power device to obtain a composite data packet.

[0144] For example, consider power equipment consisting of devices 1, 2, and 3, with data dimensions including temperature, voltage, and current. For example, the temperatures of devices 1, 2, and 3 are 25°C, 25°C, and 26°C, respectively; the voltages are 300V, 320V, and 300V, respectively; and the currents are 100A, 150A, and 140A, respectively. The temperature reference device data can be determined to be 25°C, the voltage reference device data to be 300V, and the current reference device data to be 140A. These data sets are then combined into a single set, resulting in the reference device data set (temperature reference device data: 25°C, voltage reference device data: 300V, current reference device data: 140A). The data difference information set for device 1 is (device 1, 0°C, 0V, -40A), the data difference information set for device 2 is (device 2, 0°C, 20V, 10A), and the data difference information set for device 3 is (device 3, 1°C, 0V, 0A). The data of (temperature reference device data: 25°C, voltage reference device data: 300V, current reference device data: 140A), (device 1, 0°C, 0V, -40A), (device 2, 0°C, 20V, 10A), and (device 3, 1°C, 0V, 0A) are encoded and compressed to obtain a composite data packet.

[0145] In some embodiments, the decision analysis model includes a data preprocessing sub-model and a data analysis sub-model. The data preprocessing sub-model is configured with decoding rules for decoding a composite data packet to obtain a reference device data set and various data difference information sets. The data preprocessing sub-model is also configured with data recovery rules for recovering the various data difference information sets from the reference device data set into the device data for each power device. After the data preprocessing sub-model recovers the various data difference information sets into the device data for each power device, the data for each device can be sequentially input into the data analysis sub-model to perform management decision analysis on each power device and obtain analysis results for each power device.

[0146] The setting of the information transmission channel between the decision analysis platform and the power equipment has an important impact on the timeliness of sending equipment management information. Figure 6As shown, S306, using the information delivery channel that matches the charge and discharge management function to send the device management information to the power device, including:

[0147] S602: Determine timeliness requirement information that matches the function identifier of the charge and discharge management function.

[0148] Among them, the function identifier is identification information that uniquely identifies the charge and discharge management function, and the charge and discharge management function corresponds to the function identifier one by one.

[0149] Timeliness requirement information is used to characterize the timeliness requirements of the charge and discharge management function, reflecting the specific time sensitivity requirements of the charge and discharge management function. It is understood that the timeliness requirements of the charge and discharge management function are ranked from high to low in terms of time sensitivity, including quasi-real-time, real-time, and batch. Quasi-real-time requirements are the most time-sensitive, real-time requirements are the second most time-sensitive, and batch requirements are the least time-sensitive.

[0150] In some embodiments, the decision analysis platform pre-sets the correspondence between each function identifier and each timeliness requirement information. The correspondence can be searched according to the function identifier of the charge and discharge management function to determine the timeliness requirement information matching the charge and discharge management function.

[0151] S604: Call the pre-set mapping relationship between each timeliness requirement and each information delivery channel to determine the target information delivery channel that matches the timeliness requirement information.

[0152] The mapping between each timeliness requirement and each information distribution channel is pre-set by the designer based on actual conditions. As you can understand, different timeliness requirements correspond to different information distribution channel communication bandwidths and corresponding information transmission speeds. The time sensitivity of the timeliness requirement is directly proportional to the channel bandwidth of the information distribution channel. That is, the higher the time sensitivity of the timeliness requirement, the wider the communication bandwidth of the corresponding information distribution channel and the faster the information transmission speed. Therefore, the communication bandwidth of the information distribution channel corresponding to quasi-real-time is the widest, the communication bandwidth of the information distribution channel corresponding to real-time is the second widest, and the communication bandwidth of the information distribution channel corresponding to batch is the narrowest. The designer divides the bandwidth of each information distribution channel based on actual conditions and matches the corresponding information distribution channel to each timeliness requirement based on its time sensitivity.

[0153] In some embodiments, the decision analysis platform can determine the timeliness requirements of the charging and discharging management function based on the timeliness requirement information, and then call the pre-set mapping relationship between each timeliness requirement and each information delivery channel to find the target information delivery channel that matches the timeliness requirements of the charging and discharging management function.

[0154] S606: Use the target information delivery channel to send the device management information to the power device.

[0155] In some embodiments, after determining the target information delivery channel, the decision analysis platform can use the target information delivery channel to send the equipment management information to the power equipment.

[0156] In the above embodiment, by dividing the corresponding timeliness requirements for each charging and discharging management function and configuring a corresponding information delivery channel for each timeliness requirement, it is possible to achieve efficient management of the power equipment while effectively saving information transmission costs.

[0157] The equipment management of power equipment, especially the equipment management of new energy vehicles, the security of equipment management information is one of the key factors affecting the reliability of power equipment operation. In order to reduce the risk of tampering with information during transmission, in some embodiments, such as Figure 7 As shown, S606, using the target information delivery channel to send the device management information to the power equipment, including:

[0158] S702: Determine at least one instruction type required to carry device management information based on the charge and discharge management function.

[0159] Among them, the instruction type is a type parameter formed by dividing the instructions according to the control object corresponding to the instruction. For example, when optimizing the charge and discharge curve of the power equipment, it is necessary to control and adjust the state of charge, battery health, and charge and discharge voltage of the power equipment battery. Then the instruction types required to carry its equipment management information may include state of charge adjustment instructions, battery health adjustment instructions, and voltage adjustment instructions. It is understandable that different charge and discharge management functions will require different instruction types to carry their equipment management information.

[0160] In some embodiments, the decision analysis platform may determine at least one instruction type required to carry device management information based on the charge and discharge management function.

[0161] In some of the embodiments, the decision analysis platform is pre-set with correspondences between various charge and discharge management functions and various instruction types. The correspondences can be searched according to the charge and discharge management functions, and at least one instruction type corresponding to the charge and discharge management function can be determined, and the instruction type can be determined as the instruction type required for the device management information carrying the charge and discharge management function.

[0162] S704: Extract instruction information from the device management information according to the instruction type to obtain instruction information corresponding to the instruction type.

[0163] In some embodiments, the decision analysis platform may extract instruction information from the device management information based on instruction type, and extract instruction information corresponding to the instruction type from the device management information. For example, if the instruction type is a state of charge adjustment instruction, the decision analysis platform may extract the state of charge adjustment parameters from the device management information and determine the state of charge adjustment parameters as the instruction information for the state of charge adjustment instruction.

[0164] S706: Generate an instruction to be issued corresponding to the instruction type based on the instruction information.

[0165] In some embodiments, the decision analysis platform may compress the instruction information to obtain instructions to be issued corresponding to the instruction type.

[0166] S708: Use the target information sending channel to send the instruction to be sent to the power equipment.

[0167] In some embodiments, the decision analysis platform may use a target information delivery channel to send instructions to be delivered to the power equipment.

[0168] In the above embodiment, the instruction type of the equipment management information carrying the charging and discharging management function is determined in advance for each charging and discharging management function. After obtaining the charging and discharging management information, the instruction information of the equipment management information can be quickly extracted according to the instruction type, thereby generating corresponding instructions to be issued, so that the power equipment can quickly respond to the instructions to be issued to perform equipment management tasks, effectively improving the equipment management efficiency of the power equipment.

[0169] In some embodiments, S706, generating a pending instruction corresponding to the instruction type based on the instruction information, includes determining an encryption algorithm that matches the power device and an encryption key that matches the instruction type. Based on the encryption algorithm and the encryption key, the instruction information is encrypted and compressed to obtain the pending instruction corresponding to the instruction type.

[0170] Among them, the encryption algorithm is the encryption algorithm determined in advance by the decision analysis platform and the power equipment through handshake communication, and is used to encrypt the data transmitted between the decision analysis platform and the power equipment. It is understandable that since different power equipment may have different security requirements or hardware capabilities, the encryption algorithms that can be supported may be different. For example, some power equipment supports national encryption algorithms, while some power equipment can only support international algorithms such as AES and RSA. Therefore, when it is necessary to encrypt and issue instruction information, it is necessary to first determine the encryption algorithm that the power equipment can use. The encryption algorithm that matches the power equipment can be discussed and determined in advance by the decision analysis platform and the power equipment.

[0171] In some embodiments, the decision analysis platform can search for an encryption algorithm that matches the power device based on the device identifier of the power device and the pre-set mapping relationship between each device identifier and each encryption algorithm. Simultaneously, based on the type identifier of the instruction type and the pre-set mapping relationship between each type identifier and each encryption key, the platform can search for an encryption key that matches the instruction type. Subsequently, based on the encryption algorithm and encryption key, the instruction information is encrypted to obtain encrypted information. This encrypted information is then compressed and encapsulated into a complete instruction packet according to the communication protocol, resulting in the instruction to be issued corresponding to the instruction type.

[0172] In the above embodiment, by using an encryption algorithm that matches the power equipment and an encryption key that matches the instruction type to encrypt the instruction information, the most appropriate encryption method can be determined for the instruction information from the two dimensions of power equipment and instruction type. While improving the security of instruction information transmission, it can effectively reduce the risk of information decryption failure at the device terminal due to incompatibility of the encryption algorithm.

[0173] Furthermore, in some embodiments, there are multiple instructions to be issued, and each instruction to be issued corresponds to each instruction type one by one, such as Figure 8 As shown, S708, using the target information sending channel to send the instruction to be sent to the power equipment, including:

[0174] S802: Calculate the total transmission capacity of the instructions to be issued according to the instruction transmission capacity of each instruction to be issued.

[0175] The instruction transmission capacity refers to the amount of transmission data occupied by the instructions to be issued during the data transmission process, and the total transmission capacity refers to the sum of the instruction transmission capacities of all instructions to be issued.

[0176] In some embodiments, the decision analysis platform may obtain the instruction transmission capacity of each instruction to be issued, and sum up the instruction transmission capacity to obtain the total transmission capacity of each instruction to be issued.

[0177] S804: When the total transmission capacity is less than or equal to the preset capacity threshold, the instructions to be sent are combined and compressed to obtain a composite instruction.

[0178] The preset capacity threshold is the maximum single transmission capacity of the target information sending channel, which can represent the single transmission capability of the target information sending channel.

[0179] Merge compression refers to an instruction processing operation that combines multiple instructions to be issued into a single instruction package and compresses it, which can be accomplished through instruction splicing and a preset compression algorithm.

[0180] In some embodiments, the decision analysis platform can compare the total transmission capacity of each instruction to be issued with a preset capacity threshold. When the total transmission capacity is less than or equal to the preset capacity threshold, it means that the target information sending channel can send all the instructions to be issued to the power equipment at one time. At this time, the decision analysis platform can merge and compress the instructions to be issued to obtain a composite instruction.

[0181] In some embodiments, the decision analysis platform may combine and encapsulate the instructions to be issued to obtain a combined instruction package, convert the combined instruction package into a binary stream, and then call a preset compression algorithm to compress it to obtain a composite instruction.

[0182] S806: Use the target information delivery channel to send the composite instruction to the power equipment.

[0183] In some embodiments, after receiving the composite instruction, the decision analysis platform may use the target information distribution channel to send the composite instruction to the power equipment.

[0184] In the above embodiment, by comparing the total transmission capacity of each instruction to be issued with a preset capacity threshold, when the total transmission capacity is less than or equal to the preset capacity threshold, the instructions to be issued are merged and compressed into a composite instruction and issued to the power equipment at one time. This not only improves the real-time transmission of instructions, but also significantly reduces the network load and improves transmission efficiency.

[0185] In other embodiments, Figure 9 As shown, the battery data processing method further includes:

[0186] S902 : When the total transmission capacity is greater than a preset capacity threshold, determine the instruction relevance of each instruction to be issued according to the instruction type corresponding to each instruction to be issued.

[0187] The instruction relevance can represent the degree of association between the pending instructions in terms of execution targets, operation objects, or timing dependencies, and can provide guidance for the combined issuance of the pending instructions. It is understood that the higher the instruction relevance, the closer the connection between the control actions corresponding to the pending instructions, such as the possibility of simultaneous or continuous control.

[0188] In some embodiments, when determining that the total transmission capacity is greater than a preset capacity threshold, the decision analysis platform determines the instruction relevance of each instruction to be issued based on the instruction type corresponding to each instruction to be issued.

[0189] In some embodiments, the decision analysis platform is pre-configured with a correlation analysis logic or a correlation analysis algorithm, which can determine the instruction relevance of each instruction to be issued according to the instruction type of each instruction to be issued.

[0190] In some embodiments, the decision analysis platform is pre-set with instruction relevance information between various instruction types. By searching for instruction relevance information for each instruction type to be issued, the instruction relevance of each instruction to be issued can be determined.

[0191] S904 , dividing the instructions to be issued based on the relevance of the instructions and a preset capacity threshold, to obtain at least two instruction sets.

[0192] In some embodiments, the decision analysis platform may divide each instruction to be issued based on the relevance of each instruction and a preset capacity threshold to obtain at least two instruction sets.

[0193] In some embodiments, the decision analysis platform may sort each instruction to be issued in descending order of relevance to other instructions to be issued, and set an instruction set to be filled with a capacity threshold equal to a preset capacity threshold. The decision analysis platform may then start with the instruction with the highest relevance and gradually add each instruction to be issued to the instruction set to be filled. When the capacity of each instruction to be issued that has been filled in the instruction set to be filled reaches the capacity threshold, or when any unfilled instruction to be issued is added and the capacity exceeds the capacity threshold, the decision analysis platform will return to the step of setting an instruction set to be filled with a capacity threshold equal to the preset capacity threshold, until all instructions to be issued are added to the corresponding instruction set.

[0194] In some of the embodiments, the decision analysis platform can transform the instruction grouping problem into a knapsack problem, determine the number of instruction sets based on the difference between the total transmission capacity of each instruction to be issued and a preset capacity threshold, set the corresponding instruction sets to be filled according to the number, and the capacity threshold of each instruction set to be filled is the preset capacity threshold. Then, for each instruction set to be filled, with the goal of maximizing the sum of the relevance of the instructions in the set within the capacity threshold, solve the instruction grouping problem and obtain the final grouping result, that is, the filled instruction sets.

[0195] S906 , for each instruction set, combining and compressing the instructions to be issued contained in the instruction set to obtain a sub-compound instruction of the power equipment.

[0196] In some embodiments, for each instruction set, the decision analysis platform may combine and compress the instructions to be issued contained in the instruction set to obtain a sub-composite instruction for the power equipment. It is understood that the specific method for combining and compressing the instructions to be issued is substantially the same as described above and will not be repeated here.

[0197] S908: Use the target information delivery channel to send each sub-compound instruction to the power equipment in sequence.

[0198] In some embodiments, the decision analysis platform may use the target information distribution channel to send each sub-compound instruction to the power equipment in sequence.

[0199] In the above embodiment, when the total transmission capacity exceeds a preset capacity threshold, the instructions to be issued are divided into instruction sets by calculating their relevance. This allows highly relevant instructions to be merged and transmitted first, reducing communication transmission costs, while low-relevance instructions can be processed independently, lowering resource contention. While meeting capacity constraints, the internal relevance of the instructions to be issued in the instruction set is maximized, thereby optimizing transmission efficiency and the reliability of the power equipment's execution.

[0200] In order to further optimize the utilization efficiency of computing resources, in some embodiments, such as Figure 10 As shown, the battery data processing method further includes the following steps:

[0201] S1002: Count the usage frequencies of the pre-configured candidate decision analysis models and determine theoretical operating resources that match the usage frequencies of the models.

[0202] Each candidate decision analysis model is a decision analysis model that matches each charge and discharge management function in the decision analysis platform. The model usage frequency of a candidate decision analysis model is the ratio of the number of times the candidate decision analysis model is used within a preset detection cycle to the total number of times all models are used.

[0203] Among them, the theoretical operating resources are the theoretical values ​​of computing resources required to maintain the efficient operation of the candidate decision analysis model under the corresponding model usage frequency.

[0204] In some embodiments, the decision analysis platform can count the total number of times each candidate decision analysis model is used within a preset detection period and the number of times each candidate decision analysis model is used based on the call log of each candidate decision analysis model, and calculate the ratio of each usage number to the total usage number to obtain the model usage frequency of each candidate decision analysis model. Then, based on the usage frequency of each model, determine the theoretical operating resources that match the usage frequency of each model.

[0205] In some of the embodiments, the designer can determine in advance, based on experimental data or empirical data, for each candidate decision analysis model, the theoretical value of computing resources required for the candidate decision analysis model to maintain efficient operation under different model usage frequencies, and bind the candidate decision analysis model, the frequency of use of each model, and the theoretical value of each computing resource corresponding to each model usage frequency to obtain a preset mapping relationship between the frequency of use of each model and the theoretical value of each computing resource. When it is necessary to determine the theoretical operating resources of the candidate decision analysis model, the preset mapping relationship between the frequency of use of each model and the theoretical value of each computing resource corresponding to the candidate decision analysis model can be called, and the preset mapping relationship can be searched based on the model usage frequency of the candidate decision analysis model within the preset detection period to determine the theoretical operating resources corresponding to the candidate decision analysis model.

[0206] In some of the embodiments, a theoretical operating resource calculation function is pre-configured in the decision analysis platform. For each candidate decision analysis model, the decision analysis platform can call the theoretical operating resource calculation function and calculate the theoretical operating resources that match the model usage frequency based on the model usage frequency of the candidate decision analysis model.

[0207] S1004: Obtain actual operating resources of each candidate decision analysis model.

[0208] The actual operating resources are the total computing resources that can be used by the candidate decision analysis model at the current moment.

[0209] In some embodiments, the decision analysis platform may obtain model configuration information of each candidate decision analysis model, and determine actual operating resources of each candidate decision analysis model based on the model configuration information.

[0210] S1006 , for each candidate decision analysis model, determining a resource adjustment value of the candidate decision analysis model according to the theoretical operating resources and actual operating resources of the candidate decision analysis model.

[0211] In some embodiments, for each candidate decision analysis model, the decision analysis platform may compare the theoretical operating resources of the candidate decision analysis model with the actual operating resources of the candidate decision analysis model, and determine the difference between the two as the resource adjustment value of the candidate decision analysis model.

[0212] S1008: Adjust resource partitioning of the candidate decision analysis model according to the resource adjustment value.

[0213] In some embodiments, after determining the resource adjustment value of the candidate decision analysis model, the decision analysis platform may adjust resource partitioning of the candidate decision analysis model according to the resource adjustment value.

[0214] In some embodiments, if each candidate decision analysis model is configured on a decision analysis platform, the decision analysis platform can directly perform resource partitioning adjustments on the candidate decision analysis model according to the resource adjustment value.

[0215] In other embodiments, if each candidate decision analysis model is stored isolated from the decision analysis platform, that is, each candidate decision analysis model is stored on other remote servers and only transmits information with the decision analysis platform through a data transmission interface, the decision analysis platform can generate a model resource adjustment instruction for the candidate decision analysis model based on the resource adjustment value, and send the model resource adjustment instruction to the storage server of the candidate decision analysis model, only instructing the storage server to adjust the resource division of the candidate decision analysis model according to the resource adjustment value.

[0216] In the above embodiment, dynamic resource division is performed on each candidate decision analysis model based on the frequency of use of each model, so that high-frequency use models can be automatically expanded and low-frequency use models can release resources in a timely manner, thereby achieving operational stability and efficiency of the candidate decision analysis models corresponding to the core business.

[0217] In some embodiments, a battery data processing method is provided, which is applied to Figure 2 The battery data processing system shown in FIG is used as an example for explanation, in which the power equipment is a new energy vehicle. In order to more intuitively reflect the data transmission process of the battery data processing system, the battery data processing system can be understood as follows: Figure 11 The three-level architecture shown includes an intelligent decision-making layer, a data collection layer, and a dynamic execution layer.

[0218] The intelligent decision-making layer is a cloud-based service layer consisting of a decision analysis platform and a model repository, used to implement management decision analysis tasks. The intelligent decision-making layer can be connected to the terminal program, allowing users to manually trigger charge and discharge management functions and intuitively view management decision analysis results through the terminal program.

[0219] The data collection layer can be composed of RDB services, which can communicate with the BMU via the CAN bus to collect battery pack parameters such as cell voltage / temperature, total voltage, insulation resistance, etc. It can also collect environmental parameters such as ambient temperature and humidity, altitude, GPS positioning, and vehicle status information such as remaining range and historical charge and discharge curves.

[0220] The dynamic execution layer consists of the BMU and the RDB docking module. The RDB docking module can send the received command signals to the BMU, and the BMU will perform control tasks according to the command signals based on the preset algorithm. For example, when receiving a charging curve optimization instruction, the BMU can combine internal and external parameters to dynamically adjust the charging parameters to achieve safe and efficient charging adjustment of the vehicle battery.

[0221] The data transmission design in the above three-layer architecture is provided with a dual-channel separation mechanism, a timing guarantee mechanism and a data security transmission mechanism.

[0222] The dual-channel separation mechanism includes a downlink command channel and an uplink data channel. The downlink command channel can be understood as: cloud service layer → HTTP protocol → data collection layer → transparent transmission → dynamic execution layer. The uplink data channel can be understood as: dynamic execution layer → transparent transmission → data collection layer → Kafka → cloud service layer (cloud parsing service).

[0223] The timing guarantee mechanism includes the use of a time synchronization server (NTP) to achieve a time error of less than 1ms for each node, and the data packet carries a four-segment timestamp, namely BMU generation time, RDB reception time, Kafka write time, and cloud processing time.

[0224] Secure data transmission media include key exchange security and end-to-end encryption (E2EE). Key exchange security refers to the use of ECDHE or DH algorithms for key exchange, ensuring that historical communications remain confidential even if the key is compromised over time. End-to-end encryption refers to application-layer encryption, such as the AES-GCM algorithm. Keys are generated by both communicating parties and cannot be decrypted by third parties.

[0225] The data collection layer can also be built as a sharded RDB service cluster, using device identification hash values ​​to assign compute nodes and implementing a dual-duplicate prevention mechanism. This dual-duplicate prevention mechanism includes implementing a distributed transaction lock based on Redisson, locking the "device ID + information type + number" key combination. Furthermore, a pre-processing buffer is established to quickly filter out duplicate requests using a Bloom filter.

[0226] like Figure 12 As shown, the method specifically includes the following steps:

[0227] S1201 , in response to a data analysis operation triggered by each vehicle for the same charge and discharge management function, obtaining device data reported by each vehicle through a data reporting channel.

[0228] S1202 , performing data comparison on the equipment data of each vehicle, and determining reference equipment data from the equipment data.

[0229] S1203: Based on the reference device data, determine data difference information between each device data and the reference device data.

[0230] S1204: Encode and compress the reference device data and the data difference information to obtain a composite data packet of the decision analysis model.

[0231] S1205 , calling a data transmission interface preset in a decision analysis model that matches the charge and discharge management function, and inputting the composite data packet into the decision analysis model.

[0232] S1206: For each vehicle, receive the analysis result returned by the decision analysis model after performing management decision analysis on the vehicle.

[0233] S1207: Based on the analysis result, determine the device management information of the vehicle for the charge and discharge management function.

[0234] S1208: Determine timeliness requirement information that matches the function identifier of the charge and discharge management function.

[0235] S1209: Call the pre-set mapping relationship between each timeliness requirement and each information delivery channel to determine the target information delivery channel that matches the timeliness requirement information.

[0236] Among them, timeliness requirements include quasi-real-time, real-time and batch.

[0237] S1210: Determine at least one instruction type required to carry device management information based on the charge and discharge management function.

[0238] S1211 , extracting instruction information from the device management information according to the instruction type to obtain instruction information corresponding to the instruction type.

[0239] S1212: Use the encryption algorithm pre-set with the vehicle to encrypt and compress the instruction information to obtain the instruction to be issued corresponding to the instruction type.

[0240] S1213 , when there are multiple instructions to be issued, the total transmission capacity of each instruction to be issued is calculated according to the instruction transmission capacity of each instruction to be issued.

[0241] S1214, determine whether the total transmission capacity is less than or equal to the preset capacity threshold, if so, execute S1215-S1216, if not, execute S1217.

[0242] The preset capacity threshold may be 512 KB.

[0243] S1215: Combine and compress the instructions to be issued to obtain a composite instruction.

[0244] S1216: Use the target information distribution channel to send the composite instruction to the vehicle.

[0245] S1217 , determining the instruction relevance of each instruction to be issued according to the instruction type corresponding to each instruction to be issued.

[0246] S1218 , dividing each instruction to be issued based on the relevance of each instruction and a preset capacity threshold, to obtain at least two instruction sets.

[0247] S1219: For each instruction set, the instructions to be issued contained in the instruction set are combined and compressed to obtain a sub-compound instruction of the vehicle.

[0248] S1220: Use the target information delivery channel to send each sub-compound instruction to the vehicle in sequence.

[0249] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0250] Based on the same inventive concept, embodiments of the present application also provide a battery data processing device for implementing the aforementioned battery data processing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more battery data processing device embodiments provided below can be found in the aforementioned limitations of the battery data processing method and will not be further elaborated here.

[0251] In some embodiments, as Figure 13 As shown, a battery data processing device 1300 is provided, including: a response module 1301, a data analysis module 1302 and an information sending module 1303, wherein:

[0252] The response module 1301 is configured to obtain device data reported by the power device through a data reporting channel in response to a data analysis operation triggered by the power device for at least one charge and discharge management function.

[0253] The data analysis module 1302 is used to call a decision analysis model that matches the charge and discharge management function, perform management decision analysis on the power equipment based on the equipment data, and determine the equipment management information of the power equipment for the charge and discharge management function.

[0254] The information sending module 1303 is used to send the device management information to the power equipment using an information sending channel that matches the charge and discharge management function.

[0255] In some embodiments, the data analysis module 1302 is used to: call the data transmission interface pre-set by the decision analysis model that matches the charge and discharge management function, and input the equipment data into the decision analysis model; receive the analysis results returned by the decision analysis model after performing management decision analysis on the power equipment based on the equipment data; and determine the equipment management information of the power equipment for the charge and discharge management function based on the analysis results.

[0256] In some embodiments, there are multiple power devices. The data analysis module 1302 is configured to: compare the device data of each power device to determine reference device data from each device data; determine data difference information between each device data and the reference device data based on the reference device data; encode and compress the reference device data and each data difference information to obtain a composite data packet of the decision analysis model; and transmit the composite data packet to the decision analysis model.

[0257] In some embodiments, the information sending module 1303 is used to: determine the timeliness requirement information that matches the functional identifier of the charging and discharging management function; call the pre-set mapping relationship between each timeliness requirement and each information sending channel, and determine the target information sending channel that matches the timeliness requirement information; use the target information sending channel to send the equipment management information to the power equipment.

[0258] In some embodiments, the information sending module 1303 is used to: determine at least one instruction type required to carry device management information based on the charge and discharge management function; extract instruction information from the device management information according to the instruction type to obtain instruction information corresponding to the instruction type; use the encryption algorithm pre-set with the power equipment to encrypt and compress the instruction information to obtain the instruction to be sent corresponding to the instruction type; use the target information sending channel to send the instruction to be sent to the power equipment.

[0259] In some embodiments, there are multiple instructions to be issued, each of which corresponds to a specific instruction type. The information issuing module 1303 is configured to: calculate the total transmission capacity of the instructions to be issued based on the instruction transmission capacity of each instruction to be issued; if the total transmission capacity is less than or equal to a preset capacity threshold, merge and compress the instructions to be issued to obtain a composite instruction; and send the composite instruction to the power equipment using the target information issuing channel.

[0260] In some embodiments, the information sending module 1303 is also used to: when the total transmission capacity is greater than a preset capacity threshold, determine the instruction relevance of each instruction to be sent according to the instruction type corresponding to each instruction to be sent; based on the relevance of each instruction and the preset capacity threshold, divide each instruction to be sent to obtain at least two instruction sets; for each instruction set, merge and compress each instruction to be sent contained in the instruction set to obtain a sub-compound instruction of the power equipment; use the target information sending channel to send each sub-compound instruction to the power equipment in sequence.

[0261] In some embodiments, the battery data processing device 1300 further includes:

[0262] The theoretical operation resource determination module is used to count the model usage frequencies of each pre-configured candidate decision analysis model and determine the theoretical operation resources that match the usage frequencies of each model.

[0263] The actual operation resource acquisition module is used to obtain the actual operation resources of each candidate decision analysis model.

[0264] The resource adjustment value determination module is used to determine the resource adjustment value of each candidate decision analysis model according to the theoretical operating resources and actual operating resources of the candidate decision analysis model.

[0265] The resource partitioning adjustment module is used to adjust the resource partitioning of the candidate decision analysis model according to the resource adjustment value.

[0266] Each module in the battery data processing device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0267] In some embodiments, a computer device is provided. The computer device may be a server integrated with a decision analysis platform. The internal structure diagram thereof may be as follows: Figure 14As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as device data and device management information. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a battery data processing method is implemented.

[0268] Those skilled in the art will understand that Figure 14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0269] In some embodiments, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the specific steps of the above-mentioned battery data processing method embodiment when executing the computer program.

[0270] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the specific steps of the above-mentioned battery data processing method embodiment are implemented.

[0271] In some embodiments, a computer program product is provided, including a computer program, which implements the specific steps of the above-mentioned battery data processing method embodiment when executed by a processor.

[0272] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, storage, and display, etc.) involved in this application are all authorized by the user or have been fully authorized by all parties. Furthermore, the acquisition, storage, processing, and transmission of this data comply with relevant laws and regulations.

[0273] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0274] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0275] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A battery data processing method, characterized in that: The method comprises: In response to a data analysis operation triggered by the power equipment for at least one charge and discharge management function, obtaining device data reported by the power equipment through a data reporting channel; calling a decision analysis model that matches the charge and discharge management function, performing a management decision analysis on the power equipment according to the equipment data, and determining equipment management information of the power equipment for the charge and discharge management function; Using an information delivery channel that matches the charge and discharge management function, the device management information is sent to the power device; The calling of a decision analysis model matching the charge and discharge management function, performing management decision analysis on the power equipment according to the equipment data, and determining equipment management information of the power equipment for the charge and discharge management function includes: Calling a data transmission interface preset by a decision analysis model that matches the charge and discharge management function, and inputting the device data into the decision analysis model; receiving an analysis result returned by the decision analysis model after performing a management decision analysis on the power equipment based on the equipment data; Determining device management information of the power device for the charge and discharge management function based on the analysis result; The using an information delivery channel matching the charge and discharge management function to send the device management information to the power device includes: Determining timeliness requirement information that matches the function identifier of the charge and discharge management function; Invoke the pre-set mapping relationship between each timeliness requirement and each information delivery channel to determine the target information delivery channel that matches the timeliness requirement information; the time sensitivity of the timeliness requirement is positively correlated with the channel bandwidth of the information delivery channel; The target information sending channel is used to send the device management information to the power device.

2. The method according to claim 1, characterized in that There are multiple power devices, and inputting the device data into the decision analysis model includes: Perform data comparison on the equipment data of each of the power equipment, and determine the reference equipment data from the equipment data: Based on the reference device data, determining data difference information between each of the device data and the reference device data; Encoding and compressing the reference device data and each of the data difference information to obtain a composite data packet of the decision analysis model; The composite data packet is transmitted to the decision analysis model.

3. The method according to claim 1, characterized in that The using the target information sending channel to send the device management information to the power device includes: Based on the charge and discharge management function, determining at least one instruction type required to carry the device management information; Extracting instruction information from the device management information according to the instruction type to obtain instruction information corresponding to the instruction type; Generate an instruction to be issued corresponding to the instruction type based on the instruction information; The target information sending channel is used to send the instruction to be sent to the power equipment.

4. The method according to claim 3, characterized in that The generating, based on the instruction information, an instruction to be issued corresponding to the instruction type includes: Determining an encryption algorithm that matches the power device and an encryption key that matches the instruction type; Based on the encryption algorithm and the encryption key, the instruction information is encrypted and compressed to obtain the instruction to be issued corresponding to the instruction type.

5. The method according to claim 3, characterized in that There are multiple instructions to be issued, and each instruction to be issued corresponds to each instruction type one by one; The step of using the target information sending channel to send the instruction to be sent to the power equipment includes: Calculating the total transmission capacity of the instructions to be issued according to the instruction transmission capacity of each instruction to be issued; When the total transmission capacity is less than or equal to a preset capacity threshold, merging and compressing the instructions to be issued to obtain a composite instruction; The target information sending channel is used to send the composite instruction to the power equipment.

6. The method according to claim 5, characterized in that The method further comprises: When the total transmission capacity is greater than the preset capacity threshold, determining the instruction relevance of each of the instructions to be issued according to the instruction type corresponding to each of the instructions to be issued; Based on the relevance of each instruction and the preset capacity threshold, dividing each instruction to be issued to obtain at least two instruction sets; For each of the instruction sets, merging and compressing the instructions to be issued contained in the instruction set to obtain a sub-compound instruction of the power equipment; The target information sending channel is used to send each of the sub-compound instructions to the power equipment in sequence.

7. The method according to any one of claims 1 or 2, characterized in that The method further comprises: Counting the usage frequencies of each of the pre-configured candidate decision analysis models, and determining theoretical operating resources that match the usage frequencies of each of the models; Obtaining actual operating resources of each of the candidate decision analysis models; For each of the candidate decision analysis models, determining a resource adjustment value of the candidate decision analysis model according to the theoretical operating resources of the candidate decision analysis model and the actual operating resources; The resource partitioning of the candidate decision analysis model is adjusted according to the resource adjustment value.

8. A battery data processing device, characterized in that: The device comprises: a response module, configured to obtain device data reported by the power device through a data reporting channel in response to a data analysis operation triggered by the power device for at least one charge and discharge management function; a data analysis module, configured to call a decision analysis model matching the charge and discharge management function, perform management decision analysis on the power equipment based on the equipment data, and determine equipment management information of the power equipment for the charge and discharge management function; An information sending module, configured to send the device management information to the power device using an information sending channel that matches the charge and discharge management function; The data analysis module is specifically configured to call a data transmission interface pre-set by a decision analysis model that matches the charge and discharge management function, input the device data into the decision analysis model; receive an analysis result returned by the decision analysis model after performing a management decision analysis on the power device based on the device data; and determine device management information of the power device for the charge and discharge management function based on the analysis result; The information sending module is specifically used to determine the timeliness requirement information that matches the function identifier of the charging and discharging management function; call the pre-set mapping relationship between each timeliness requirement and each information sending channel to determine the target information sending channel that matches the timeliness requirement information; the time sensitivity of the timeliness requirement is positively correlated with the channel bandwidth of the information sending channel; use the target information sending channel to send the equipment management information to the power equipment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

12. A battery data processing system, characterized in that: The system includes a decision analysis platform and at least one power device; the decision analysis platform and the power device are pre-established with a data reporting channel and an information sending channel; The power equipment reports equipment data to the decision analysis platform through the data reporting channel; The decision analysis platform sends equipment management information to the power equipment through the information sending channel; The decision analysis platform is used to implement the battery data processing method according to any one of claims 1 to 7.

Images