Server and its operating method

Abstract

According to embodiments disclosed herein, the server includes a communication circuit, a memory, and a processor operationally coupled to the communication circuit and the memory, wherein the processor can acquire time-series data relating to a plurality of battery-related factors for each user, generate feature data showing the relationship between at least two of the plurality of factors that are expected to be correlated with each other based on the respective time-series data, classify the feature data into a plurality of clusters, and define a plurality of patterns based on the characteristics of each cluster.

Description

[Technical Field]

[0001] The present invention claims the benefit of priority based on Korean Patent Application No. 10-2023-0114896 filed on August 30, 2023, and all contents disclosed in the documents of said Korean patent application are incorporated as a part of the present specification. Embodiments disclosed in the present document relate to a server and an operating method thereof. [Background Art]

[0002] In recent years, research and development on secondary batteries have been actively conducted. Here, a secondary battery is a battery that can be charged and discharged, and is meant to include both conventional Ni / Cd batteries, Ni / MH batteries, and the like, as well as modern lithium-ion batteries. Among secondary batteries, lithium-ion batteries have the advantage of far higher energy density compared to conventional Ni / Cd batteries, Ni / MH batteries, and the like. In addition, since lithium-ion batteries can be manufactured to be small and lightweight, they are used as power sources for mobile devices. In recent years, their application range has been expanded to power sources for electric vehicles, and they have attracted attention as next-generation energy storage media.

[0003] When such a battery is installed in a vehicle, individual differences may occur in the performance, lifespan, safety, etc., of the battery depending on the driving tendencies of the vehicle driver, so it is common to collect and analyze battery data. However, the amount of data collected for each vehicle is enormous, and the battery usage patterns differ for each vehicle user, so there has been a problem that it is difficult to structure the collected data. [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] One object of the embodiments disclosed in the present document is to provide a server and an operating method thereof, which can structure enormous data and define user types considering complex factors. One objective of the embodiments disclosed in this document is to provide a server and a method of operating the same that can extract key factors related to battery evaluation metrics.

[0005] The technical problems of the embodiments disclosed in this document are not limited to those mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0006] According to embodiments disclosed herein, the server includes a communication circuit, a memory, and a processor operationally coupled to the communication circuit and the memory, wherein the processor can acquire time-series data relating to a plurality of battery-related factors for each user, generate feature data showing the relationship between at least two of the plurality of factors that are expected to be correlated with each other based on the respective time-series data, classify the feature data into a plurality of clusters, and define a plurality of patterns based on the characteristics of each cluster.

[0007] According to the embodiment, the processor can generate the feature data based on the joint probability density function (Joint PDF) of the at least two factors.

[0008] According to the embodiment, the processor can calculate a joint probability mass function (Joint PMF) for at least two factors from the time series data, apply a kernel function (KDE) to the joint probability mass function to calculate the joint probability density function, and generate the feature data that shows the joint probability density of the at least two factors. According to one embodiment, the feature data may include 2D contour image data showing the joint probability density of the at least two factors.

[0009] According to the embodiment, the processor can classify the feature data into the plurality of clusters based on the relationship between the at least two factors derived from the feature data and the distribution of each of the at least two factors.

[0010] According to the embodiment, the processor can generate representative feature data by fusing the feature data contained in each cluster for each of the clusters, and define the plurality of patterns based on the relationship between the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

[0011] According to one embodiment, the processor can determine multiple types for classifying users based on the defined multiple patterns. According to the embodiment, the processor can analyze the relationship between the evaluation index of the battery according to the plurality of types and extract the main factors related to the evaluation index from among the plurality of factors.

[0012] According to the embodiment, the plurality of factors may include at least some of the following: charge start SOC, charge DOD, charge C-rate, charge start temperature, charge maximum temperature, charge start time, charge start day of the week, driving start time, driving distance, driving start temperature, driving maximum temperature, driving DOC, driving speed distribution, discharge time, and discharge end day of the week.

[0013] According to the embodiment, the processor can acquire the time-series data from an OBD (On-Board Device) installed in each user's vehicle.

[0014] According to embodiments disclosed herein, the server operation method may include the steps of: acquiring time-series data relating to a plurality of battery-related factors for each user; generating feature data based on the respective time-series data showing the relationships between at least two of the plurality of factors that are expected to be correlated with each other; and classifying the feature data into a plurality of clusters and defining a plurality of patterns based on the characteristics of each cluster.

[0015] According to the embodiment, the step of generating the feature data may include: calculating a joint probability mass function (Joint PMF) for the at least two factors from the time series data; applying a kernel function (KDE) to the joint probability mass function to calculate a joint probability density function (Joint PDF) for the at least two factors; and generating the feature data showing the joint probability density of the at least two factors.

[0016] According to the embodiment, the step of defining the plurality of patterns may include: classifying the feature data into the plurality of clusters based on the relationships of the at least two factors derived from the feature data and the distribution of each of the at least two factors; for each of the clusters, fusing the feature data contained in each cluster to generate representative feature data; and defining the plurality of patterns based on the relationships of the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

[0017] According to one embodiment, the server's operation method may further include the step of determining a plurality of types for classifying users based on the plurality of defined patterns. [Effects of the Invention]

[0018] A server according to an embodiment disclosed in the present document and an operation method thereof can structure unstructured data and define patterns and types in consideration of complex factors.

[0019] In addition, a server according to an embodiment disclosed in the present document and an operation method thereof can extract main factors related to battery evaluation indicators. In addition, various effects that can be directly or indirectly ascertained can be provided by the present document. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] [Figure 1] It is a diagram showing a data analysis system according to an embodiment disclosed in the present document. [Figure 2] It is a diagram showing an example of feature data generation according to an embodiment disclosed in the present document. [Figure 3] It is a diagram showing examples of a plurality of patterns according to an embodiment disclosed in the present document. [Figure 4] It is a block diagram showing a configuration of a server according to an embodiment disclosed in the present document. [Figure 5] It is a flowchart for explaining an operation method of a server according to an embodiment disclosed in the present document. [Figure 6] It is a flowchart for explaining a process of generating feature data according to an embodiment disclosed in the present document. [Figure 7] It is a flowchart for explaining a process of defining a plurality of patterns according to an embodiment disclosed in the present document. DESCRIPTION OF THE EMBODIMENTS

[0021] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that the present invention includes various modifications, equivalents, and / or alternatives of the embodiments of the present invention.

[0022] In this text, the singular form of a noun corresponding to an item may include one or more of the item unless the context clearly indicates otherwise. In this text, each phrase such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B, or C,” “at least one of A, B, and C,” and “at least one of A, B, or C” may include any one of the items listed together in the phrase, or any possible combination thereof. Terms such as “first,” “second,” “first,” or “second” may be used merely to distinguish one component from other components and not to limit the component in any other respect (e.g., importance or order). When one (e.g., the first) component is referred to as being "connected" or "linked" to another (e.g., the second) component, with or without the terms "functionally" or "communically," this means that the first component may be connected to the other component directly (e.g., by wire), wirelessly, or via the third component.

[0023] Each component (e.g., module or program) described herein may include one or more individuals. According to various embodiments, one or more components or operations of the component may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components identical or similar to those performed by the components of the multiple components before the integration. According to various embodiments, operations performed by modules, programs, or other components may be performed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be performed in a different order, omitted, or one or more other operations may be added.

[0024] The terms "module" or "...part" as used in this document may include units implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component configured as a whole, or the smallest unit or part of such component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an ASIC (application-specific integrated circuit).

[0025] Various embodiments of this document may be implemented as software (e.g., a program or application) containing one or more instruction words stored in a machine-readable storage medium (e.g., memory). For example, the machine's processor may call and execute at least one instruction from the one or more instruction words stored in the storage medium. This allows the machine to operate to perform at least one function according to the one or more instruction words called. The one or more instruction words may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily on the storage medium.

[0026] Figure 1 shows a data analysis system according to one embodiment disclosed in this document. Referring to Figure 1, the data analysis system may include a vehicle 10, a server 20, and electronic equipment 30.

[0027] The data analysis system can structure the vast amount of unstructured time-series data collected from each user's vehicle and define representative patterns from the structured data to define its characteristics. Furthermore, the data processing system can combine multiple patterns defined from the structured data to determine representative types that allow for user classification.

[0028] Vehicle 10 may be an electric vehicle or a hybrid vehicle equipped with a battery. The battery may be a battery pack or a battery module, and may include at least one battery cell and a battery management system (BMS) for monitoring and managing the battery status.

[0029] According to the embodiment, the vehicle 10 may be equipped with an OBD (On-Board Device) device 11 for collecting battery data, and the server 20 may acquire battery data from the OBD device 11. The battery data may comprehensively include, but is not limited to, data related to the state of the battery (e.g., SOC, SOH, current, voltage, etc.), data related to battery charging (e.g., charging time, temperature during charging, charging completion time, charging current distribution, etc.), and data related to the vehicle in which the battery is installed (e.g., driving time, driving distance, speed, acceleration, etc.). The OBD device 11 may receive battery data from a battery management system or acquire battery data directly.

[0030] Server 20 can acquire time-series data on multiple factors related to the battery and define multiple patterns. For example, Server 20 can receive time-series data on multiple factors from the vehicle's OBD device 11. As an example, Server 20 can acquire time-series data on the battery's charging start SoC (State of Charge) and charging DoD (Depth of Discharge).

[0031] Server 20 can manage the acquired time-series data on a per-user basis or on a per-vehicle basis. For example, Server 20 can store and manage time-series data based on a unique ID assigned to each vehicle.

[0032] According to the embodiment, the multiple factors may include at least some of the following: charge start SOC, charge DoD, charge C-rate, charge start temperature, charge maximum temperature, charge start time, charge start day of the week, driving start time, driving distance, driving start temperature, driving maximum temperature, driving DoD, driving speed distribution, discharge time, and discharge end day of the week. The multiple factors may not be limited to these and may include any elements that can affect the state of the battery, such as the duration of the end of operation state and ambient temperature. For example, the multiple factors may include factors that can represent each section by separating the charging and discharging sections from time-series data.

[0033] Server 20 can generate feature data from time-series data relating to at least two factors. For example, the at least two factors can be selected from among multiple factors that are expected to be correlated with each other. As an example, the at least two factors can be selected from among multiple factors that are expected to be correlated with each other, namely the charging start SoC and charging DoD. In one embodiment, Server 20 can generate feature data by selecting two factors from among multiple factors in order to visualize the feature data and clarify the differences between patterns.

[0034] According to the embodiment, the server 20 can generate feature data based on the joint probability density function (Joint PDF) of at least two factors. For example, the server 20 can generate feature data by representing the joint probability density function graphically. If the server 20 generates feature data based on only one of several factors, the pattern definition may be inaccurate and distorted because the factors are not independent of each other. Therefore, the server 20 can generate feature data based on the joint probability density function so as to take into account at least two factors that are not independent, i.e., are expected to be correlated. An example of a specific method by which the server 20 generates feature data will be described later with reference to Figure 2.

[0035] According to the embodiment, the feature data may include 2D contour image data showing the joint probability densities of at least two factors. 2D contour image data may mean image data in which the joint probability densities are represented by contour data.

[0036] Server 20 can classify feature data into multiple clusters. For example, Server 20 can analyze the characteristics of the feature data and classify feature data with similar characteristics into the same cluster. The characteristics of the feature data may include, for example, the trends and distribution of the data values ​​included in the feature data.

[0037] According to the embodiment, the server 20 can classify the feature data into multiple clusters based on the relationships between at least two factors derived from the feature data and the distributions of at least two of those factors. That is, the characteristics of each feature data can be analyzed based on the relationships between at least two factors and the distributions of those two factors.

[0038] Server 20 can define multiple patterns based on the characteristics of the classified clusters. These multiple patterns may be representative of data features related to at least two factors.

[0039] According to the embodiment, the server 20 can generate representative feature data for each cluster by fusing the feature data contained in each cluster. Here, fusing feature data may mean summing up the data values ​​of each feature data. That is, the feature data may be data with the same dimension, and the server 20 can sum up the data values ​​of each feature data. For example, the server 20 can generate representative feature data by representing the contour of the data from the summed data.

[0040] According to the embodiment, the server 20 can define multiple patterns based on the relationships between at least two factors derived from representative feature data and the distributions of at least two of those factors. By generating representative feature data from the feature data included in the cluster and defining multiple patterns accordingly, the server 20 can more clearly define the tendencies and representative characteristics shown by each pattern.

[0041] In this way, the server 20 can define multiple patterns for the selected factors. If the pair of factors selected from the multiple factors is different, the multiple patterns can also be defined to be different. That is, the server 20 can define patterns that are different from each other depending on the pair of factors selected. For example, the pattern defined according to the charging start SoC-charging DoD and the pattern defined according to the charging DoD-charging C-rate can be different from each other.

[0042] According to the embodiment, the server 20 can determine multiple types for classifying users based on a set of defined patterns. The server 20 can determine multiple types by combining patterns defined according to pairs of different factors. For example, the server 20 can determine multiple types by combining a first set of patterns defined according to the charging start SoC-charging DoD and a second set of patterns defined according to the charging start time-charging start day of the week.

[0043] Multiple user types can be represented, for example, by combinations of characters that capture user tendencies. For instance, Server 20 can represent user types using combinations of characters, similar to the MBTI (Myers-Briggs Type Indicator) which indicates individual personality types, to show user vehicle usage tendencies. Of course, Server 20 can also represent user types using various methods, including not only character combinations but also numerical grades, graphs, symbols, and shapes.

[0044] For example, server 20 can classify user types into "Preparation" or "Margin" based on a first set of patterns defined according to the charging start SoC-charging DoD. Alternatively, server 20 can classify user types into "Regularity" or "Instant" based on a second set of patterns defined according to the charging start time-charging start day of the week. Server 20 can combine these to classify user types into four categories. The types and number of user types described above are merely examples and are not limited thereto.

[0045] According to the embodiment, the server 20 can analyze the relationship between battery evaluation metrics for multiple types. For example, the server 20 can analyze the relationship between battery evaluation metrics and the behavior of a particular type. Battery evaluation metrics may include battery life (e.g., SOH, RUL), frequency of abnormal behavior, average power consumption, etc.

[0046] According to the embodiment, the server 20 can extract key factors related to the evaluation indicator from among multiple factors. The server 20 can analyze the evaluation indicator according to the user type and identify types that show a high correlation with the evaluation indicator. For example, if a particular evaluation indicator shows a high correlation with a type according to a pattern defined from the charging start SoC-charging DoD, the server 20 can estimate the key factors related to that evaluation indicator in the charging start SoC and charging DoD.

[0047] According to one embodiment, the server 20 can classify users according to a predetermined set of types. For example, the server 20 can provide the user type classification results to the user via the electronic device 30.

[0048] The electronic device 30 may be a user terminal carried by the user. The electronic device 30 may include various forms of devices capable of performing data communication. For example, the electronic device 30 may include, but is not limited to, the aforementioned devices, portable devices such as smartphones or tablets, computer devices such as desktops or laptops, multimedia devices, cameras, wearable devices, and VR (virtual reality) devices. For example, the electronic device 30 may include a server or gateway capable of transmitting data packets via an application. The user can confirm their classified type via the electronic device 30.

[0049] Figure 2 shows an example of feature data generation according to one embodiment disclosed in this document. Referring to Figure 2, the server 20 can generate feature data from time-series data.

[0050] The server 20 can acquire time-series data relating to multiple factors. For example, the server 20 can acquire time-series data from the OBD device 11 installed in the vehicle 10. As an example, the time-series data relating to multiple factors may be data acquired during multiple charge-discharge cycles. The time-series data 210 shown in Figure 2 exemplifies the time-series data relating to the charge start SoC and the charge DoD among the multiple factors.

[0051] According to the embodiment, the server 20 can calculate a joint probability mass function (Joint PMF) 220 for at least two factors using time-series data relating to at least two factors. For example, if the server 20 generates feature data for two factors, the joint probability mass function 220 may have the x-axis representing the first factor and the y-axis representing the second factor, with the data at each coordinate representing the data value of the first factor, the data value of the second factor, and the joint probability mass.

[0052] According to the embodiment, the server 20 can calculate the joint probability density function 230 by applying a kernel function (KDE) to the calculated joint probability mass function 220. Since the joint probability mass function 220 has statistically distorted values ​​due to discontinuous values, and the analysis may differ depending on the density of the data, the server 20 can apply a kernel function to calculate the joint probability density function 230 for continuous domains.

[0053] According to the embodiment, the server 20 can generate feature data 240 that shows the calculated joint probability density. In the embodiment, the feature data may include 2D contour image data that shows the joint probability density of at least two factors. For example, if the server 20 generates feature data 240 for two factors, the x-axis of the feature data 240 may show the first factor, the y-axis may show the second factor, and the data for each coordinate may show the data value of the first factor, the data value of the second factor, and the joint probability density. As an example, in the feature data 240 of Figure 2, the joint probability density at a particular coordinate can be represented by color. That is, in the feature data 240, the darker the color of the coordinate, the higher the probability density.

[0054] According to the embodiment, the server 20 can analyze feature data. For example, by analyzing the feature data 240 shown in Figure 2, it can be determined that the user has a low charging start SoC, a wide distribution of charging DoDs, and a tendency for a low percentage of full charge based on the relationship between charging start SoC and charging DoD. The server 20 can analyze the characteristics of the feature data and classify the feature data into multiple clusters.

[0055] Figure 3 shows examples of multiple patterns according to one embodiment disclosed in this document. Referring to Figure 3, server 20 can define multiple patterns from the cluster's representative feature data.

[0056] Server 20 can merge the feature data belonging to each cluster to generate representative feature data. In Figure 3, each graph included in each pattern area represents representative feature data.

[0057] Server 20 can classify representative feature data and define multiple patterns based on the relationship between at least two factors and the distribution of at least two of those factors. For example, as shown in Figure 3, Server 20 can define multiple patterns (P1 to P13) depending on the distribution of each factor derived from the representative feature data (charging start region, degree of distribution spread) and the relationship between the factors (presence or absence of full charge). For example, the P13 pattern may indicate a high user charging start SoC, a low degree of distribution spread for charging DoD, and a tendency towards full charge.

[0058] Figure 4 is a block diagram showing the configuration of a server according to one embodiment disclosed in this document. Referring to Figure 4, a server 400 according to one embodiment (for example, server 20 in Figure 1) may include a first communication circuit 410, a first processor 420, and a first memory 430.

[0059] The first communication circuit 410 can support the establishment of a wired or wireless connection between the server 400 and external electronic devices (e.g., a vehicle, electronic equipment), and the execution of communication over the established connection. According to one embodiment, the first communication circuit 410 includes a wireless communication circuit (e.g., a cellular communication circuit, a near-field wireless communication circuit, or a GNSS (global navigation satellite system) communication circuit) or a wired communication circuit (e.g., a LAN (local area network) communication circuit, or a power line communication circuit), and can communicate with external electronic devices via a near-field communication network such as Bluetooth®, WiFi Direct, or IrDA (infrared data association), or a far-field communication network such as a cellular network, the Internet, or a computer network, using the applicable communication circuit. The various first communication circuits 410 described above can be implemented on a single chip or on separate chips. According to one embodiment, the first communication circuit 410 of the server 400 can communicate with the electronic equipment 30 and the vehicle 10 in Figure 1.

[0060] The first processor 420 can control the overall operation of the server 400. In various embodiments, the first processor 420 may include one processor core or multiple processor cores. For example, the processor 420 may include a multi-core such as a dual-core, quad-core, or hexa-core. According to embodiments, the processor 420 may further include cache memory located internally or externally. According to embodiments, the first processor 420 may be configured with one or more processors. For example, the first processor 420 may include at least one of an application processor, a communication processor, or a GPU (graphical processing unit).

[0061] All or part of the first processor 420 can be electrically or operationally coupled with or connected to other components within the server 400 (e.g., the first communication circuit 410 or the first memory 430). The first processor 420 can receive instructions from other components, parse received instructions, and perform calculations or process data according to the parsed instructions. The first processor 420 can parse and process messages, data, instructions, or signals received from the first communication circuit 410 and the first memory 430. The first processor 420 can generate new messages, data, instructions, or signals based on received messages, data, instructions, or signals. The first processor 420 can provide the processed or generated messages, data, instructions, or signals to the first communication circuit 410 or the first memory 430.

[0062] The first processor 420 can process data or signals generated or generated by a program. For example, the first processor 420 can request instructions, data, or signals from the first memory 430 to execute or control a program. The first processor 420 can record (or store) or update instructions, data, or signals in the first memory 430 to execute or control a program. According to one embodiment, the first processor 420 can define multiple patterns from time-series data stored in the first memory 430.

[0063] The first memory 430 can store instruction words, control instruction code, control data, or user data that control the server. For example, the first memory 430 can contain at least one of the following: an application program, an OS (operating system), middleware, or a device driver. The first memory 430 can contain one or more of the following: volatile memory or non-volatile memory. Volatile memory can include DRAM (dynamic random access memory), SRAM (static RAM), SDRAM (synchronous DRAM), PRAM (phase-change RAM), MRAM (magnetic RAM), RRAM (resistive RAM), FeRAM (ferroelectric RAM), etc. Non-volatile memory can include ROM (read-only memory), PROM (programmable ROM), EPROM (electrically programmable ROM), EEPROM (electrically erasable programmable ROM), flash memory, etc. The first memory 430 may further include a non-volatile medium such as an HDD (hard disk drive), SSD (solid state disk), eMMC (embedded multimedia card), or UFS (universal flash storage). According to one embodiment, the first memory 430 can store time-series data acquired from the user's vehicle.

[0064] Figure 5 is a flowchart illustrating the operation method of a server according to one embodiment disclosed in this document. The embodiment shown in Figure 5 is only one embodiment, and the order of steps in various embodiments of the present invention may differ from that shown in Figure 5, some of the steps shown in Figure 5 may be omitted, the order of the steps may be changed, or steps may be merged.

[0065] Referring to Figure 5, the server operation method may include the steps of: acquiring time-series data on multiple battery-related factors for each user (S100); generating feature data showing the relationship between at least two factors that are expected to be correlated with each other, based on the respective time-series data (S200); classifying the feature data into multiple clusters and defining multiple patterns based on the characteristics of each cluster (S300); and determining multiple types for classifying users based on the defined multiple patterns (S400).

[0066] In step S100, the server 20 can acquire time-series data for each user regarding multiple battery-related factors. For example, the server 20 can acquire time-series data for each user from the OBD device 11 installed in the vehicle 10.

[0067] In step S200, the server 20 can generate feature data that shows the relationship between at least two factors that are expected to be correlated with each other, based on the respective time series data. For example, the server 20 can select at least two factors from among the multiple factors and generate feature data based on the joint probability density function of at least two factors.

[0068] In step S300, the server 20 can classify the feature data into multiple clusters and define multiple patterns based on the characteristics of each cluster. For example, the server 20 can classify the feature data into multiple clusters based on the relationships between at least two factors derived from the feature data and the distributions of at least two of those factors.

[0069] In step S400, the server 20 can determine multiple types for classifying users based on multiple defined patterns. For example, the server 20 can determine multiple types by combining multiple patterns defined according to selected combinations of factors.

[0070] Figure 6 is a flowchart illustrating the process of generating feature data according to one embodiment disclosed in this document. Referring to Figure 6, the server 20 can generate feature data that shows the relationship between at least two factors.

[0071] In step S210, the server 20 can calculate a joint probability mass function (Joint PMF) for at least two factors from the time series data. For example, the time series data can be acquired during multiple charge-discharge cycles.

[0072] In step S220, the server 20 can apply a kernel function (KDE) to the joint probability mass function to calculate the joint probability density function (Joint PDF) of at least two factors.

[0073] In step S230, the server 20 can generate the feature data that shows the joint probability density of at least two factors. For example, the feature data may include 2D contour image data.

[0074] Figure 7 is a flowchart illustrating the process of defining multiple patterns according to one embodiment disclosed in this document. Referring to Figure 7, the server 20 can define multiple patterns from the feature data.

[0075] In step S310, the server 20 can classify the feature data into multiple clusters based on the relationships between at least two factors derived from the feature data and the distribution of at least two of those factors.

[0076] In step S320, the server 20 can generate representative feature data for each cluster by fusing the feature data contained in each cluster.

[0077] In step S330, the server 20 can define multiple patterns based on the relationships between at least two factors derived from representative feature data and the distributions of at least two of those factors.

[0078] Although all components constituting the embodiments disclosed in this document have been described as operating either as a single unit or in combination, the embodiments disclosed in this document are not necessarily limited to such embodiments. That is, within the scope of the purpose of the embodiments disclosed in this document, all components may operate in combination of one or more units.

[0079] Furthermore, terms such as “includes,” “constitutes,” or “possesses,” as described above, mean that they may contain the component in question, and not exclude other components, unless otherwise specified. All terms, including technical or scientific terms, have the same meaning as those generally understood by a person of ordinary skill in the art to which the embodiments disclosed herein belong, unless otherwise specified. Commonly used terms, such as those defined in dictionaries, should be interpreted to be consistent with their meaning in the context of the relevant technology, and not to be interpreted in an ideal or overly formal sense unless explicitly defined herein.

[0080] The above description is merely illustrative of the technical concept disclosed herein, and any person with ordinary skill in the art to which the embodiments disclosed herein belong can make various modifications and variations without departing from the essential characteristics of the embodiments disclosed herein. Therefore, the embodiments disclosed herein are for illustrative purposes only, not to limit the technical concept of the embodiments disclosed herein, and the scope of the technical concept disclosed herein is not limited by such embodiments. The scope of protection of the technical concept disclosed herein shall be interpreted according to the claims described below, and all technical concepts within an equivalent scope should be interpreted as being included in the scope of rights of this document.

Claims

1. Communication circuit and Memory and A processor that is operationally connected to the communication circuit and the memory, Includes, The aforementioned processor, For each user, we obtain time-series data on multiple battery-related factors. Based on each time-series data, feature data is generated that shows the relationship between at least two of the multiple factors that are expected to be correlated with each other. A server that classifies the aforementioned feature data into multiple clusters and defines multiple patterns based on the characteristics of each cluster.

2. The aforementioned processor, The server according to claim 1, which generates the feature data based on the joint probability density functions of the at least two factors.

3. The aforementioned processor, The joint probability mass function for at least two factors is calculated from the aforementioned time series data. The kernel function is applied to the aforementioned joint probability mass function to calculate the aforementioned joint probability density function. The server according to claim 2, which generates the feature data showing the joint probability density of at least two of the factors.

4. The aforementioned feature data is The server according to claim 3, comprising 2D contour image data showing the joint probability density of at least two of the factors.

5. The aforementioned processor, The server according to claim 1, which classifies the feature data into a plurality of clusters based on the relationship between the at least two factors derived from the feature data and the distribution of each of the at least two factors.

6. The aforementioned processor, For each of the aforementioned clusters, representative feature data is generated by fusing the feature data contained in each cluster. A server according to any one of claims 1 to 5, which defines the plurality of patterns based on the relationship between the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

7. The aforementioned processor, A server according to any one of claims 1 to 5, which determines a plurality of types for classifying users based on the plurality of patterns defined above.

8. The aforementioned processor, The server according to claim 7, which analyzes the relationship between the evaluation index of the battery according to the plurality of types and extracts the main factors related to the evaluation index from among the plurality of factors.

9. The aforementioned multiple factors are, A server according to any one of claims 1 to 5, comprising at least a portion of the following: charging start SOC, charging DOD, charging C-rate, charging start temperature, charging maximum temperature, charging start time, charging start day of the week, driving start time, driving distance, driving start temperature, driving maximum temperature, driving DOC, driving speed distribution, discharge time, and discharge end day of the week.

10. The aforementioned processor, A server according to any one of claims 1 to 5, which acquires the time-series data from an OBD installed in the vehicle of each of the aforementioned users.

11. The steps include: obtaining time-series data on multiple battery-related factors for each user; The steps include generating feature data that shows the relationship between at least two of the multiple factors that are expected to be correlated with each other, based on each time-series data, The steps include classifying the aforementioned feature data into multiple clusters and defining multiple patterns based on the characteristics of each cluster, The server's operating method, including its operation.

12. The step of generating the aforementioned feature data is: A step of calculating a joint probability mass function for at least two factors from the time series data, The steps include applying a kernel function to the aforementioned joint probability mass function to calculate the joint probability density function of the at least two factors, A method for operating a server according to claim 11, comprising the step of generating feature data that shows the joint probability density of at least two of the factors.

13. The step of defining the aforementioned multiple patterns is: A step of classifying the feature data into the plurality of clusters based on the relationship between the at least two factors derived from the feature data and the distribution of each of the at least two factors, For each of the aforementioned clusters, the step of fusing the feature data contained in each cluster to generate representative feature data, A method for operating a server according to claim 11 or 12, comprising the step of defining the plurality of patterns based on the relationships between the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

14. A method for operating a server according to claim 11 or 12, further comprising the step of determining a plurality of types for classifying users based on the plurality of patterns defined above.

Images