Server and operation method thereof

Abstract

According to an embodiment disclosed in the present document, a server comprises: a communication circuit; a memory; and a processor operatively connected to the communication circuit and the memory, wherein the processor may: acquire, for each user, time-series data regarding a plurality of factors related to a battery; on the basis of the respective pieces of time-series data, generate feature data indicating a relationship between at least two factors expected to have a correlation with each other from among the plurality of factors; and classify the pieces of feature data into a plurality of clusters and define a plurality of patterns that are based on a feature of each cluster.

Description

Server and how it works

[0001] Cross-citation with related applications

[0002] This invention claims the benefit of priority from Korean Patent Application No. 10-2023-0114896, filed on August 30, 2023, and all contents of the document in that Korean Patent Application are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a server and a method of operating the same.

[0005] Recently, research and development on secondary batteries has been actively conducted. Here, secondary batteries are rechargeable and include both conventional Ni / Cd and Ni / MH batteries, as well as recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries have the advantage of having a much higher energy density than conventional Ni / Cd and Ni / MH batteries. Furthermore, lithium-ion batteries can be manufactured in a compact and lightweight form, making them suitable for use as power sources for mobile devices. Recently, their use has expanded to include power sources for electric vehicles, attracting attention as a next-generation energy storage medium.

[0006] When these batteries are installed in vehicles, individual differences in battery performance, lifespan, and safety can occur depending on the driver's preferences, so it's common to collect and analyze battery data. However, the sheer volume of data collected for each vehicle, coupled with the varying battery usage patterns of each vehicle user, makes it difficult to standardize this data.

[0007] One purpose of the embodiments disclosed in this document is to provide a server and its operating method that can define user types by considering complex factors by standardizing a large amount of data.

[0008] One purpose of the embodiments disclosed in this document is to provide a server and its operating method capable of extracting key factors related to the evaluation index of a battery.

[0009] The technical problems of the embodiments disclosed in this document are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the descriptions below.

[0010] According to an embodiment disclosed in the present document, a server includes a communication circuit, a memory, and a processor operatively connected to the communication circuit and the memory, wherein the processor obtains time series data for a plurality of factors related to a battery for each user, generates feature data representing a relationship between at least two factors expected to be correlated among the plurality of factors based on each of the time series data, and classifies the feature data into a plurality of clusters to define a plurality of patterns based on characteristics of each cluster.

[0011] According to an embodiment, the processor can generate the feature data based on a joint probability density function (Joint PDF) of the at least two factors.

[0012] According to an embodiment, the processor may calculate a joint probability mass function (Joint PMF) for the 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 representing the joint probability density of the at least two factors.

[0013] According to an embodiment, the feature data may include 2D contour image data representing a joint probability density of the at least two factors.

[0014] According to an embodiment, the processor can classify the feature data into the plurality of clusters based on the relationship of the at least two factors derived from the feature data and the distribution of each of the at least two factors.

[0015] According to an embodiment, the processor may generate representative feature data by fusing feature data included in each cluster for each of the clusters, and define the plurality of patterns based on the relationship of the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

[0016] According to an embodiment, the processor may determine a plurality of types for classifying users based on the plurality of defined patterns.

[0017] According to an embodiment, the processor may analyze a relationship between the evaluation indicators of the battery according to the plurality of types and extract a main factor related to the evaluation indicator among the plurality of factors.

[0018] According to an embodiment, the plurality of factors may include at least some of a charge start SOC, a charge DOD, a charge C-rate, a charge start temperature, a charge maximum temperature, a charge start time, a charge start day, a driving start time, a driving distance, a driving start temperature, a driving maximum temperature, a driving DOC, a driving speed distribution, a discharge time, and a discharge end day.

[0019] According to an embodiment, the processor can obtain the time series data from an OBD (On Board Device) equipped in each user's vehicle.

[0020] According to an embodiment disclosed in this document, a method of operating a server may include a step of obtaining time series data for a plurality of factors related to a battery for each user, a step of generating feature data representing a relationship between at least two factors expected to be correlated among the plurality of factors based on each of the time series data, and a step of classifying the feature data into a plurality of clusters and defining a plurality of patterns based on characteristics of each cluster.

[0021] According to an embodiment, the step of generating the feature data may include the step of calculating a joint probability mass function (Joint PMF) for the at least two factors from the time series data, the step of calculating a joint probability density function (Joint PDF) of the at least two factors by applying a kernel function (KDE) to the joint probability mass function, and the step of generating the feature data representing the joint probability density of the at least two factors.

[0022] According to an embodiment, the step of defining the plurality of patterns may include the step of classifying the feature data into the plurality of clusters based on the relationship of the at least two factors derived from the feature data and the distribution of each of the at least two factors, the step of generating representative feature data by fusing the feature data included in each cluster for each of the clusters, and the step of defining the plurality of patterns based on the relationship of the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

[0023] According to an embodiment, the method of operating the server may further include a step of determining a plurality of types for classifying users based on the plurality of patterns defined above.

[0024] The server and its operating method according to the embodiments disclosed in this document can define patterns and types that take complex factors into account by formalizing unstructured data.

[0025] In addition, the server and its operating method according to the embodiments disclosed in this document can extract key factors related to the evaluation index of a battery.

[0026] In addition, various effects may be provided, either directly or indirectly, through this document.

[0027] FIG. 1 is a diagram showing a data analysis system according to one embodiment disclosed in this document.

[0028] FIG. 2 is a diagram showing an example of feature data generation according to one embodiment disclosed in this document.

[0029] FIG. 3 is a drawing showing an example of a plurality of patterns according to one embodiment disclosed in this document.

[0030] FIG. 4 is a block diagram showing the configuration of a server according to one embodiment disclosed in this document.

[0031] FIG. 5 is a flowchart for explaining a method of operating a server according to one embodiment disclosed in this document.

[0032] FIG. 6 is a flowchart illustrating a process for generating feature data according to one embodiment disclosed in this document.

[0033] FIG. 7 is a flowchart illustrating a process for defining multiple patterns according to one embodiment disclosed in this document.

[0034] Hereinafter, various embodiments of the present invention will be described with reference to the attached drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that the present invention encompasses various modifications, equivalents, and / or alternatives of the embodiments.

[0035] In this document, the singular form of a noun corresponding to an item may include one or more of said items, unless the context clearly indicates otherwise. In this document, phrases 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 each include any one of the items listed together in that phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish the corresponding element from other corresponding elements, and do not limit the corresponding elements in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as being “coupled” or “connected” to another component (e.g., a second component), with or without the terms “functionally” or “communicatively,” it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0036] Each component (e.g., a module or a program) described in this document may include one or more entities. According to various embodiments, one or more components or operations of the components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0037] The term "module" or "part" used in this document may include a unit 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 an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0038] Various embodiments of the present document may be implemented as software (e.g., a program or an application) including one or more instructions stored in a machine-readable storage medium (e.g., memory). For example, a processor of the device may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the device to operate to perform at least one function according to the at least one instruction called. The one or more instructions 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" only means that the storage medium is a tangible device and does not contain a signal (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 in the storage medium.

[0039] FIG. 1 is a diagram showing a data analysis system according to one embodiment disclosed in this document.

[0040] Referring to FIG. 1, the data analysis system may include a vehicle (10), a server (20), and an electronic device (30).

[0041] The data analysis system can formalize the massive amount of unstructured time-series data collected from each user's vehicle and define patterns representing the characteristics of the data from the structured data. Furthermore, the data processing system can determine representative types by combining multiple patterns defined from the structured data to classify users.

[0042] The vehicle (10) may be an electric vehicle or 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 status of the battery.

[0043] According to an embodiment, a vehicle (10) may be equipped with an OBD (On-Board Device) (11) device for collecting battery data, and a server (20) may obtain battery data from the OBD device (11). The battery data may comprehensively include data on the state of the battery (e.g., SOC, SOH, current, voltage, etc.), data on the charging of the battery (e.g., charging time, temperature during charging, charging end time, charging current distribution, etc.), data on a vehicle equipped with a battery (e.g., driving time, driving distance, speed, acceleration, etc.), and the like, but is not limited to the above-described examples. The OBD device (11) may receive battery data from a battery management system or obtain battery data directly.

[0044] The server (20) can obtain time-series data on multiple factors related to the battery and define multiple patterns. For example, the server (20) can receive data on multiple factors in a time-series manner from the OBD device (11) of the vehicle (10). For example, the server (20) can obtain time-series data on the battery's charging start SoC (State of Charge) and charging DoD (Depth of Discharge).

[0045] The server (20) can manage the acquired time series data by user or by vehicle (10). For example, the server (20) can store and manage the time series data based on a unique ID assigned to each vehicle.

[0046] According to an embodiment, the plurality of factors may include at least some of a charge start SOC, a charge DoD, a charge C-rate, a charge start temperature, a charge maximum temperature, a charge start time, a charge start day of the week, a driving start time, a driving distance, a driving start temperature, a driving maximum temperature, a driving DoD, a driving speed distribution, a discharge time, and a discharge end day of the week. The plurality of factors is not limited thereto, and may include, without limitation, factors that may affect a battery state, such as a driving end state duration, an ambient temperature, and the like. For example, the plurality of factors may separate a charge section and a discharge section from time series data, and include factors that can represent each section.

[0047] The server (20) can generate feature data from time series data for at least two factors. For example, the at least two factors may be selected from among a plurality of factors that are expected to have a correlation with each other. For example, the at least two factors may be selected as charge start SoC - charge DoD, which are expected to have a correlation with each other. In one embodiment, the server (20) can generate feature data by selecting two factors from among a plurality of factors to clearly distinguish between visualization of the feature data and patterns.

[0048] According to an embodiment, the server (20) can generate feature data based on a 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 as a graph. If the server (20) generates feature data based on only one of a plurality of factors, each factor is not independent from each other, and thus the pattern definition result may be inaccurate and distorted. Therefore, the server (20) can generate feature data based on the joint probability density function so as to comprehensively consider at least two factors that are not independent, i.e., are expected to be correlated. An example of a specific method for the server (20) to generate feature data will be described below with reference to FIG. 2.

[0049] According to an embodiment, the feature data may include 2D contour image data representing a joint probability density of at least two factors. The 2D contour image data may refer to image data in which the joint probability density is expressed as contour data.

[0050] The server (20) can classify feature data into multiple clusters. For example, the 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, trends and distributions of data values ​​included in the feature data.

[0051] According to an embodiment, the server (20) can classify feature data into a plurality of clusters based on the relationship between at least two factors derived from the feature data and the distribution of each of the at least two factors. That is, the characteristics of each feature data can be analyzed based on the relationship between at least two factors and the distribution of each of the two factors.

[0052] The server (20) can define multiple patterns based on the characteristics of the classified clusters. The multiple patterns may be patterns that can represent the characteristics of data for at least two factors.

[0053] According to an embodiment, the server (20) may generate representative feature data for each cluster by fusing feature data included in each cluster. Here, fusing feature data may mean expressing the data values ​​of each feature data by adding them up. That is, the feature data may be data having the same size dimension, and the server (20) may sum the data values ​​of each feature data. For example, the server (20) may generate representative feature data by expressing the outline of the data from the summed data.

[0054] According to an embodiment, the server (20) can define multiple patterns based on the relationships between at least two factors derived from representative feature data and the distribution of each of the at least two factors. The server (20) generates representative feature data from the feature data included in the cluster, and by defining multiple patterns therefrom, the tendencies and representative characteristics exhibited by each pattern can be made more distinct.

[0055] In this way, the server (20) can define multiple patterns for the selected factors. If the pairs of factors selected from the multiple factors vary, the multiple patterns can also be defined differently. That is, the server (20) can define different patterns depending on the pairs of selected factors. For example, a pattern defined according to the charge start SoC - charge DoD and a pattern defined according to the charge DoD - charge C-rate can be different from each other.

[0056] According to an embodiment, the server (20) can determine multiple types for classifying users based on a plurality 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.

[0057] Multiple types for classifying users can be expressed, for example, as a combination of characters that can identify the user's tendencies. For example, the server (20) can express user types as a combination of multiple characters to indicate the user's vehicle usage tendencies, similar to the Myers-Briggs Type Indicator (MBTI), which indicates an individual's personality type. It goes without saying that the server (20) can express user types in various ways, such as grades expressed in numbers, graphs, symbols, and shapes, in addition to combinations of characters.

[0058] For example, the server (20) can classify the user type as 'Preparation' or 'Margin' from a first set of patterns defined according to the charging start SoC - charging DoD. In another example, the server (20) can classify the user type as 'Regularity' or 'Instant' from a second set of patterns defined according to the charging start time - charging start day of the week. The server (20) can classify the user type into four types by combining these. The types and number of user types described above are merely examples and are not limited thereto.

[0059] According to an embodiment, the server (20) can analyze the relationship between battery evaluation indicators and battery types according to multiple types. For example, the server (20) can analyze the behavioral correlation between battery evaluation indicators and specific types. Battery evaluation indicators may include battery life (e.g., SOH, RUL), abnormal behavior frequency, average power consumption, etc.

[0060] According to an embodiment, the server (20) can extract key factors related to evaluation indicators from among multiple factors. The server (20) can analyze evaluation indicators according to user types and identify types that exhibit a high correlation with the evaluation indicators. For example, if a specific evaluation indicator is highly correlated with a type defined by a pattern from the charging start SoC - charging DoD, the key factors related to the evaluation indicator can be estimated as the charging start SoC and charging DoD.

[0061] According to an embodiment, the server (20) can classify users according to a plurality of determined types. For example, the server (20) can provide the user type classification results to the user via an electronic device (30).

[0062] The electronic device (30) may be a user terminal carried by a user. The electronic device (30) may include various types of devices capable of performing data communication. For example, the electronic device (30) may include portable devices such as smartphones or tablets, computer devices such as desktops or laptops, multimedia devices, cameras, wearable devices, virtual reality (VR) devices, etc., but is not limited to the aforementioned devices. For example, the electronic device (30) may include a server or gateway capable of transmitting data packets through an application. The user can check his or her classified type through the electronic device (30).

[0063] FIG. 2 is a diagram showing an example of feature data generation according to one embodiment disclosed in this document.

[0064] Referring to FIG. 2, the server (20) can generate feature data from time series data.

[0065] The server (20) can obtain time series data for multiple factors. For example, the server (20) can obtain time series data from the OBD device (11) equipped in the vehicle (10). As an example, the time series data for multiple factors may be data obtained during multiple charge / discharge cycles. The time series data (210) illustrated in FIG. 2 exemplarily represents time series data for the charge start SoC and charge DoD among the multiple factors.

[0066] According to an embodiment, the server (20) can use time series data for at least two factors to produce a joint probability mass function (Joint PMF) (220) for at least two factors. For example, when the server (20) generates feature data for two factors, the joint probability mass function (220) can have the x-axis represent the first factor, the y-axis represent the second factor, and the data of each coordinate can represent the data value of the first factor, the data value of the second factor, and the joint probability mass.

[0067] According to an embodiment, the server (20) can apply a kernel function (KDE) to the calculated joint probability mass function (220) to calculate a joint probability density function (230). Since the joint probability mass function (220) may have statistically distorted values ​​due to discrete values ​​and the analysis may vary depending on the density of data, the server (20) can apply a kernel function to calculate a joint probability density function (230) for a continuous domain.

[0068] According to an embodiment, the server (20) may generate feature data (240) representing the calculated joint probability density. In an embodiment, the feature data may include 2D contour image data representing the joint probability density of at least two factors. For example, when the server (20) generates feature data (240) for two factors, the x-axis of the feature data (240) may represent the first factor, the y-axis may represent the second factor, and the data of each coordinate may represent the data value of the first factor, the data value of the second factor, and the joint probability density. As an example, in FIG. 2, the joint probability density at a specific coordinate in the feature data (240) may be expressed as a color. That is, a darker color of a coordinate in the feature data (240) may indicate a higher probability density.

[0069] According to an embodiment, the server (20) can analyze feature data. For example, by analyzing the feature data (240) illustrated in FIG. 2, it can be determined that the user has a low charging start SoC, a wide distribution of charging DoD, and a tendency for a low charging ratio based on the relationship between the 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.

[0070] FIG. 3 is a drawing showing an example of a plurality of patterns according to one embodiment disclosed in this document.

[0071] Referring to FIG. 3, the server (20) can define multiple patterns from representative feature data of the cluster.

[0072] The server (20) can generate representative feature data by fusing feature data belonging to each cluster. In Fig. 3, each graph included in each pattern area represents representative feature data.

[0073] The server (20) can classify representative feature data based on the relationship of at least two factors and the distribution of each of at least two factors to define a plurality of patterns. For example, as shown in FIG. 3, the server (20) can define a plurality of patterns (P1 to P13) based on the distribution of each factor (charging start area, degree of spread of distribution) derived from the representative feature data and the relationship of the factors (whether or not buffering is present). For example, the P13 pattern may indicate a high user charging start SoC, a low degree of spread of the distribution of the charging DoD, and a tendency to buffer.

[0074] FIG. 4 is a block diagram showing the configuration of a server according to one embodiment disclosed in this document.

[0075] Referring to FIG. 4, a server (400) according to one embodiment (e.g., server (20) of FIG. 1) may include a first communication circuit (410), a first processor (420), and a first memory (430).

[0076] The first communication circuit (410) can support the establishment of a wired or wireless communication connection between the server (400) and an external electronic device (e.g., a vehicle, an electronic device), and the performance of communication through the established connection. According to one embodiment, the first communication circuit (410) includes a wireless communication circuit (e.g., a cellular communication circuit, a short-range 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 an external electronic device through a short-range communication network such as Bluetooth, WiFi direct, or IrDA (infrared data association), or a long-range communication network such as a cellular network, the Internet, or a computer network using a corresponding communication circuit. The various types of first communication circuits (410) described above can be implemented as one chip or can be implemented as separate chips. According to one embodiment, the first communication circuit (410) of the server (400) can communicate with the electronic device (30) and the vehicle (10) of FIG. 1.

[0077] The first processor (420) can control the overall operation of the server (400). In various embodiments, the first processor (420) may include a single processor core or multiple processor cores. For example, the processor (420) may include multi-cores such as 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 graphical processing unit (GPU).

[0078] All or part of the first processor (420) may be electrically or operatively coupled with or connected to other components (e.g., the first communication circuit (410) or the first memory (430)) within the server (400). The first processor (420) may receive commands from other components, interpret the received commands, and perform calculations or process data according to the interpreted commands. The first processor (420) may interpret and process messages, data, commands, or signals received from the first communication circuit (410) and the first memory (430). The first processor (420) may generate new messages, data, commands, or signals based on the received messages, data, commands, or signals. The first processor (420) may provide processed or generated messages, data, commands, or signals to the first communication circuit (410) or the first memory (430).

[0079] The first processor (420) can process data or signals generated or produced by a program. For example, the first processor (420) can request commands, data, or signals from the first memory (430) to execute or control the program. The first processor (420) can record (or store) or update commands, data, or signals in the first memory (430) to execute or control the program. According to one embodiment, the first processor (420) can define multiple patterns from time-series data stored in the first memory (430).

[0080] The first memory (430) may store commands for controlling the server, control command codes, control data, or user data. For example, the first memory (430) may include at least one of an application program, an operating system (OS), middleware, or a device driver. The first memory (430) may include one or more of volatile memory or non-volatile memory. The volatile memory may include dynamic random access memory (DRAM), static RAM (SRAM), synchronous DRAM (SDRAM), phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FeRAM), etc. The non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc. The memory (430) may further include a non-volatile medium such as a hard disk drive (HDD), a solid state disk (SSD), an embedded multi-media card (eMMC), or a universal flash storage (UFS). According to one embodiment, the first memory (430) may store time series data obtained from the users' vehicles.

[0081] FIG. 5 is a flowchart illustrating a method of operating a server according to one embodiment disclosed in this document. The embodiment illustrated in FIG. 5 is merely one embodiment, and the order of steps according to various embodiments of the present invention may differ from that illustrated in FIG. 5. Some steps illustrated in FIG. 5 may be omitted, the order of steps may be changed, or steps may be merged.

[0082] Referring to FIG. 5, the operating method of the server may include a step of obtaining time series data for a plurality of factors related to a battery for each user (S100), a step of generating feature data indicating a relationship between at least two factors expected to have a correlation among the plurality of factors based on each time series data (S200), a step of classifying the feature data into a plurality of clusters and defining a plurality of patterns based on the characteristics of each cluster (S300), and a step of determining a plurality of types for classifying users based on the defined plurality of patterns (S400).

[0083] At step S100, the server (20) can obtain time series data for multiple battery-related factors for each user. For example, the server (20) can obtain time series data for each user from an OBD device (11) equipped in the vehicle (10).

[0084] At step S200, the server (20) can generate feature data representing the relationship between at least two factors expected to be correlated among a plurality of factors based on each time series data. For example, the server (20) can select at least two factors among the plurality of factors and generate feature data based on a joint probability density function of the at least two factors.

[0085] 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 relationship between at least two factors derived from the feature data and the distribution of each of the at least two factors.

[0086] At step S400, the server (20) can determine multiple types for classifying users based on a plurality of defined patterns. For example, the server (20) can determine multiple types by combining multiple patterns defined based on combinations of factors selected from among multiple factors.

[0087] FIG. 6 is a flowchart illustrating a process for generating feature data according to one embodiment disclosed in this document.

[0088] Referring to FIG. 6, the server (20) can generate feature data indicating the relationship between at least two factors.

[0089] At step S210, the server (20) can derive a joint probability mass function (Joint PMF) for at least two factors from time series data. For example, the time series data can be acquired over multiple charge / discharge cycles.

[0090] At step S220, the server (20) can apply a kernel function (KDE) to the joint probability mass function to produce a joint probability density function (Joint PDF) of at least two factors.

[0091] In step S230, the server (20) can generate the feature data representing the joint probability density of at least two factors. For example, the feature data may include 2D contour image data.

[0092] FIG. 7 is a flowchart illustrating a process for defining multiple patterns according to one embodiment disclosed in this document.

[0093] Referring to FIG. 7, the server (20) can define multiple patterns from feature data.

[0094] In step S310, the server (20) can classify the feature data into a plurality of clusters based on the relationship of at least two factors derived from the feature data and the distribution of each of the at least two factors.

[0095] At step S320, the server (20) can generate representative feature data for each cluster by fusing feature data included in each cluster.

[0096] At step S330, the server (20) can define multiple patterns based on the relationship of at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

[0097] Although all components constituting the embodiments disclosed in this document have been described as being combined or operating in combination as one, 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 of the components may be selectively combined and operated one or more times.

[0098] In addition, terms such as "include," "comprise," or "have" described above, unless specifically stated otherwise, mean that the corresponding component can be included, and therefore should be interpreted to include other components rather than excluding other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong, unless otherwise defined. Commonly used terms, such as terms defined in a dictionary, should be interpreted to be consistent with the contextual meaning of the relevant technology, and shall not be interpreted in an idealized or overly formal sense, unless explicitly defined in this document.

[0099] The above description is merely an example of the technical idea disclosed in this document, and those skilled in the art to which the embodiments disclosed in this document pertain may make various modifications and variations without departing from the essential characteristics of the embodiments disclosed in this document. Therefore, the embodiments disclosed in this document are not intended to limit the technical idea of ​​the embodiments disclosed in this document, but to explain it, and the scope of the technical idea disclosed in this document is not limited by these embodiments. The scope of protection of the technical idea disclosed in this document should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of rights of this document.

Claims

1. Communication circuit; memory; and A processor operatively connected to the communication circuit and the memory, the processor comprising: Obtain time series data for multiple battery-related factors for each user, Based on each time series data, feature data representing the relationship between at least two factors among the plurality of factors that are expected to have a correlation with each other is generated, A server that classifies the above feature data into multiple clusters and defines multiple patterns based on the characteristics of each cluster.

2. In paragraph 1, The above processor, A server that generates the feature data based on a joint probability density function (Joint PDF) of at least two factors.

3. In paragraph 2, The above processor, From the above time series data, a joint probability mass function (Joint PMF) for at least two factors is calculated, The joint probability density function is calculated by applying a kernel function (KDE) to the above joint probability mass function, A server that generates the feature data representing the joint probability density of at least two factors.

4. In paragraph 3, The above feature data is, A server comprising 2D contour image data representing a joint probability density of at least two factors.

5. In paragraph 1, The above processor, A server that classifies 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.

6. In paragraph 1, The above processor, For each of the above clusters, representative feature data is generated by fusing the feature data included in each cluster, A server that defines the plurality of patterns based on the relationship of the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

7. In paragraph 1, The above processor, A server that determines multiple types for classifying users based on multiple patterns defined above.

8. In paragraph 7, The above processor, A server that analyzes the relationship between the evaluation indicators of the battery according to the plurality of types and extracts a major factor related to the evaluation indicators among the plurality of factors.

9. In paragraph 1, The above multiple arguments are, A server including 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, driving start time, driving distance, driving start temperature, driving maximum temperature, driving DOC, driving speed distribution, discharge time, and discharge end day.

10. In paragraph 1, The above processor, A server that obtains the time series data from the OBD (On Board Device) equipped in each of the above users' vehicles.

11. A step of obtaining time series data for multiple battery-related factors for each user; A step of generating feature data indicating the relationship between at least two factors expected to be correlated among the plurality of factors based on each time series data; and A method of operating a server, comprising a step of classifying the above-mentioned feature data into multiple clusters and defining multiple patterns based on the characteristics of each cluster.

12. In paragraph 11, The step of generating the above feature data is: A step of calculating a joint probability mass function (Joint PMF) for at least two factors from the time series data; A step of applying a kernel function (KDE) to the above joint probability mass function to produce a joint probability density function (Joint PDF) of at least two factors; and A method of operating a server, comprising the step of generating the feature data representing the joint probability density of at least two factors.

13. In paragraph 11, The step of defining the above multiple patterns is: A step of classifying the feature data into the plurality of clusters based on the relationship of the at least two factors derived from the feature data and the distribution of each of the at least two factors; A step of generating representative feature data by fusing feature data included in each cluster for each of the above clusters; and A method of operating a server, comprising a step of defining the plurality of patterns based on the relationship of the at least two factors derived from the representative feature data and the distribution of each of the at least two factors.

14. In paragraph 11, A method of operating a server, further comprising the step of determining a plurality of types for classifying users based on the plurality of patterns defined above.

Images