Server and operating method thereof

Abstract

According to one embodiment disclosed herein, a server may be provided that includes a communication circuit, a memory, and a processor operatively connected to the communication circuit and the memory, where the processor may be configured to acquire historical data of a user related to battery charging and information about current driving of a target user, the method comprises the steps of extracting features, related to charging factors, of a user from historical data, setting a standard for determining habitual inertia related to the factors based on the features, and determining the habitual inertia of a target user based on the features of the target user and the standard, and providing guidance information on the habitual inertia of the target user based on at least one of the habitual and historical data of the target user and information on the current driving of the target user.

Description

Technical Field

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to Korean patent applications No. 10-2023-0129123 and No. 10-2023-0151951, filed with the Korean Intellectual Property Office on September 26, 2023 and November 6, 2023, respectively, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The embodiments disclosed herein relate to a server and its operating method. Background Technology

[0004] Recently, research and development of rechargeable batteries have been actively underway. Here, rechargeable batteries are batteries capable of being charged and discharged, and include traditional Ni / Cd and Ni / MH batteries, as well as the more recent lithium-ion batteries. Among rechargeable batteries, lithium-ion batteries have the advantage of a much higher energy density than traditional Ni / Cd and Ni / MH batteries. Furthermore, because lithium-ion batteries can be manufactured in small and lightweight forms, they are used as power sources for mobile devices, and recently, their application has expanded to powering electric vehicles, making them a promising next-generation energy storage medium.

[0005] These batteries are repeatedly charged and discharged, and when installed in a vehicle, the charging pattern can vary depending on the driver's preferences. Generally, many users prefer a regular charging habit to avoid running out of battery power. Summary of the Invention

[0006] Technical issues

[0007] The embodiments disclosed herein aim to provide a server and its operating method that can enhance user habits by determining user habits and providing guidance information related to those habits.

[0008] The embodiments disclosed herein are not limited to the objectives described above, and those skilled in the art will clearly understand from the following description other objectives not described.

[0009] Technical solution

[0010] According to one embodiment disclosed herein, a server may be provided, comprising: a communication circuit, a memory, and a processor operatively connected to the communication circuit and the memory, wherein the processor may be configured to acquire historical data of a user related to battery charging and information about the current driving of a target user, extract features of the user related to charging factors from the historical data, set criteria for determining habitual behavior related to factors based on the features, determine the habitual behavior of the target user based on the features and criteria, and provide guidance information about the habitual behavior of the target user based on at least one of the target user's habitual behavior and historical data and information about the current driving of the target user.

[0011] According to one implementation, the processor can extract the probability density function (PDF) for a factor, calculated by applying kernel density estimation (KDE) techniques to historical data, as a feature.

[0012] According to one implementation, the processor can set criteria based on the results of clustering features.

[0013] According to one implementation, the processor can set criteria based on the maximum probability density value of the features included in each group as a result of clustering.

[0014] According to one implementation, the processor can apply kernel density estimation by assigning higher weights to data acquired at time points closer to the current time in each historical data set.

[0015] According to one implementation, the processor can determine the habituality of a target user based on the result of comparing the maximum probability density derived from the characteristics of the target user with a standard.

[0016] According to one implementation, the processor can update the characteristics and habits of the target user by reflecting historical data acquired during each charging of the target user.

[0017] According to one implementation, the processor can calculate the remaining depth of discharge based on a habitually acquired state of charge (SOC) and information about the current driving, and provide guidance information including the remaining depth of discharge.

[0018] According to one embodiment disclosed herein, a method for operating a server may be provided, the method comprising the following steps: acquiring historical data of a user related to battery charging and information about the current driving of a target user; extracting features of the user related to charging factors from the historical data; setting criteria for determining habitual behavior related to factors based on the features; determining the habitual behavior of the target user based on the features and criteria; and providing guidance information about the habitual behavior of the target user based on at least one of the target user's habitual behavior and historical data and information about the current driving of the target user.

[0019] According to one implementation, the feature extraction step may include extracting the probability density function (PDF) for a factor, calculated by applying kernel density estimation (KDE) techniques to historical data, as a feature.

[0020] According to one implementation, the step of setting criteria may include setting criteria based on the results of clustering features.

[0021] According to one implementation, the step of setting criteria may include setting criteria based on the maximum probability density value of the features included in each group as a result of clustering.

[0022] According to one implementation, the feature extraction step may include applying kernel density estimation by assigning higher weights to data acquired at time points closer to the current time in each historical data set.

[0023] According to one implementation, the step of determining the habits of a target user may include determining the habits of the target user based on the result of comparing the maximum probability density derived from the characteristics of the target user with a standard.

[0024] According to one implementation, the step of providing guidance information may include calculating the remaining depth of discharge based on a habitually acquired state of charge (SOC) and information about the target user's current driving, and providing guidance information including the remaining depth of discharge.

[0025] Beneficial effects

[0026] According to the server and its operation method disclosed herein, user habits can be enhanced by determining user habits and providing guidance information related to those habits.

[0027] In addition, it can provide various effects that can be directly or indirectly identified through this document. Attached Figure Description

[0028] Figure 1 This is a block diagram illustrating the configuration of an information providing system according to one embodiment disclosed herein.

[0029] Figure 2 This is a view illustrating an example of extracting user characteristics according to one embodiment disclosed herein.

[0030] Figure 3 This is a view illustrating an example of extracting features by applying weights according to one embodiment disclosed herein.

[0031] Figure 4 This is a view showing an example of the result of clustering features according to one embodiment disclosed herein.

[0032] Figure 5 This is a view illustrating an example of a setting for determining a customary standard according to one embodiment disclosed herein.

[0033] Figure 6 This is a flowchart describing a method for operating a server according to one embodiment disclosed herein.

[0034] Figure 7 This is a block diagram illustrating the configuration of a server according to one embodiment disclosed herein. Detailed Implementation

[0035] In the following description, various embodiments of the present disclosure will be illustrated with reference to the accompanying drawings. However, it should be understood that this is not intended to limit the present disclosure to a particular embodiment, but rather to include various variations, equivalents, and / or alternatives to the embodiments of the present disclosure.

[0036] Unless the relevant context explicitly specifies otherwise, the singular form of the noun corresponding to an item in this document may include one or more items. In this document, each of the 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 include any one of the items listed together in the corresponding phrases of these phrases, or all possible combinations thereof. Terms such as “first,” “second,” “first,” or “second” may be used only to distinguish a corresponding component from another component, and not to limit the corresponding component in another aspect (e.g., in terms of importance or order). When a particular (e.g., first) component is described as “connected,” “linked,” or “combined” to another (e.g., second) component, whether or not the terms “functionally” or “communically” are used, this indicates that the particular component can be connected to the other component directly (e.g., wired), wirelessly, or via a third component.

[0037] Each of the components (e.g., modules or programs) described herein may include a single object or multiple objects. According to various implementations, one or more of the corresponding components or operations described above 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 in the same or similar manner as the corresponding components of the multiple components performed functions prior to integration. According to various implementations, operations performed by modules, programs, or other components may be performed sequentially, in parallel, repeatedly, or heuristically, or one or more operations may be performed in a different order or omitted, or one or more other operations may be added.

[0038] When used herein, the terms "module" or "component" can include units implemented as hardware, software, or firmware, and are used interchangeably with terms such as logic, logic block, component, or circuit. A module can be the smallest unit or part of an integrated component or a component that performs one or more functions. For example, according to one implementation, a module can be implemented as an application-specific integrated circuit (ASIC).

[0039] Various embodiments of this document can be implemented as software (e.g., a program or application) comprising one or more commands stored in a machine-readable storage medium (e.g., a memory). For example, a device's processor can retrieve at least one command from one or more commands stored in the storage medium and execute that command. This allows the device to be operated to perform at least one function according to at least one retrieved command. The one or more commands may include code generated by a compiler or code executable by an interpreter. Device-readable storage media may be provided in the form of non-transitory storage media. Here, "non-transitory storage media" refers to a tangible device and only means that it does not include signals (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and temporarily in the storage medium.

[0040] Figure 1 This is a block diagram illustrating the configuration of an information providing system according to one embodiment disclosed herein.

[0041] Reference Figure 1 The information providing system 1 may include a server 10, a battery 20, and an electronic device 30.

[0042] Information providing system 1 can acquire and analyze users' historical data related to battery charging and set criteria for determining users' habits. Furthermore, information providing system 1 can acquire historical charging-related data of target users and information about their current driving habits, determine the target users' habits, and provide guidance information on these habits. Therefore, information providing system 1 can induce reinforcement of the target users' habits.

[0043] Server 10 can acquire various historical data of the user and information about the target user's current driving. Server 10 can analyze the acquired data and information to determine the target user's habits and provide guidance information.

[0044] The battery can be a battery installed in the vehicle, and can be a battery pack or a battery module. For example, vehicle 20 can be equipped with an on-board diagnostic (OBD) device for acquiring data, and server 10 can receive charging history data and / or driving-related information from the OBD device.

[0045] Electronic device 30 may be a user terminal carried by a user. Electronic device 30 may include various types of devices capable of performing data communication. For example, 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., and is not limited to the above-mentioned devices. For example, electronic device 30 may include a server or gateway that can transmit data packets through applications.

[0046] For example, a user can be someone registered in information provision system 1. As an example, a user can be someone who has already subscribed to an application provided by the operator of information provision system 1. A user can use electronic device 30 to access services provided by server 10. For example, this service may include providing information services. For this purpose, an application for using information services can be installed on electronic device 30.

[0047] A user can run an application on electronic device 30 to subscribe to information services and confirm his or her type and guidance information. The application installed on electronic device 30 may be an application provided by the operating entity of information providing system 1 (e.g., a battery manufacturer).

[0048] The operation of server 10 will be described in detail below.

[0049] Server 10 can acquire historical data related to a user's battery charging and information about the target user's current driving. For example, server 10 can receive historical data and driving-related information from components such as the battery management system (BMS), vehicle BMS, OBD, and charger installed in the battery pack via communication circuits.

[0050] Server 10 can acquire and store historical data related to battery charging from users. This historical data may include various pieces of information such as the state of charge (SOC) at the start of charging, the SOC at the end of charging, and the charging time.

[0051] The target users can be those who provide guidance information. More specifically, the target users can be those who have already subscribed to the information service. Information about the current driving situation can include various items such as the start state of charge (SOC), current remaining SOC, driving time, and remaining mileage.

[0052] Server 10 can extract user features related to charging factors from various historical data of the user. Charging factors can be factors used to define charging-related habits. Server 10 can analyze the data and analyze habits related to charging factors. Charging factors may include, for example, charging start SOC, charging end SOC, charging time, charging day, etc. In the following text, for ease of description, charging factors will be described as charging start SOC.

[0053] According to one implementation, server 10 can extract the probability density function (PDF) for a factor, calculated by applying kernel density estimation (KDE) to historical data, as a feature. Kernel density estimation is a technique used when calculating data distribution, and the distribution of the data to be analyzed can be calculated using a kernel represented as a probability density.

[0054] Server 10 can use kernel density estimation to calculate the distribution of historical data as a probability density function. Even when the values ​​of historical data are discontinuous, server 10 can calculate a continuous probability density function.

[0055] According to one implementation, server 10 can apply kernel density estimation by assigning higher weights to data acquired at points closer to the current time in each historical data set. Therefore, server 10 can reduce reliance on recent data. That is, since a user's recent data further reflects their habits at the current time, server 10 can more accurately determine a user's current habits by assigning higher weights to data acquired at more recent times.

[0056] Server 10 can use extracted features to set customary criteria related to factors.

[0057] According to one implementation, server 10 can set criteria for determining habits based on the results of clustering features extracted from users. Server 10 can obtain the user's probability density function and perform clustering based on its shape, maximum probability density, etc. Server 10 can classify user features into multiple groups through clustering, and each group can represent different user habits related to charging factors.

[0058] For example, when the charging factor is the charging start SOC, multiple groups classified as a result of clustering by server 10 may exhibit different habits regarding the charging start SOC. As an example, multiple groups can be classified into groups with a habit of charging start SOC, groups without a habit of charging start SOC, and groups with a vague habit of charging start SOC.

[0059] According to one implementation, server 10 can set criteria based on the maximum probability density value of features included in each group classified as a result of clustering features. Server 10 can analyze the maximum probability density value of features included in each group classified as a result of clustering. Server 10 can analyze the maximum probability density value and set criteria for determining (classification) habits.

[0060] For example, server 10 can set the maximum value of the maximum probability density among the features included in groups that do not have the habit of starting charging at SOC as a first standard value, and set the minimum value of the maximum probability density among the features included in groups that have the habit of starting charging at SOC as a second standard value.

[0061] Server 10 can determine the habits of target users based on their characteristics and set criteria.

[0062] According to one implementation, server 10 can determine the habituality of a target user based on a comparison of the maximum probability density derived from the target user's characteristics with a standard. The target user's habituality may include, for example, information such as the presence or absence of a habit of starting charging at SOC and the habitual SOC at charging start.

[0063] As an example, when the maximum probability density of the target user is at or below the first reference value, server 10 can determine that the target user does not have a habit of starting charging at SOC. In another example, when the maximum probability density of the target user is at or above the second reference value, server 10 can determine that the target user has a habit of starting charging at SOC, and determine that the SOC with the maximum probability density is the target user's habitual SOC for starting charging.

[0064] According to one implementation, server 10 can update the characteristics and habits of the target user by reflecting historical data acquired each time the target user charges. Server 10 can update the characteristics and habits of the target user each time additional historical data of the target user is acquired, and provide more accurate habitual and guidance information to the target user. In one implementation, server 10 can assign a higher weight to newly acquired historical data than to previously acquired historical data.

[0065] Server 10 can provide guidance information about the target user's habits based on at least one of the target user's habits and historical data, and information about the target user's current driving. Server 10 can compare and analyze the charging-related habits included in the target user's habits with the charging-related data included in historical data and / or driving-related information, and provide guidance information.

[0066] According to one implementation, server 10 can calculate the remaining depth of discharge based on the charging start state of charge (SOC) obtained based on the target user's habits and information about the target user's current driving.

[0067] As an example, server 10 can calculate the remaining depth of discharge (DOD) based on the user's habitual charging start SOC and driving start SOC, and provide the user with the remaining DOD from the driving start time to the charging time according to the target user's habits.

[0068] As another example, server 10 can calculate the remaining DOD based on the user's habitual charging start SOC and current SOC, and provide the user with the remaining DOD from the current time point to the habitual charging time point.

[0069] As another example, server 10 can calculate the remaining DOD based on the user's habitual charging start SOC and driving end SOC, and provide the user with the remaining DOD up to the habitual charging time point during subsequent driving.

[0070] As described above, server 10 can provide guidance information including the remaining DOD, thereby encouraging users to improve their charging-related habits.

[0071] Figure 2 This is a view illustrating an example of extracting user characteristics according to one embodiment disclosed herein.

[0072] Reference Figure 2 Server 10 can extract user features related to charging factors from each of the user's historical data.

[0073] Server 10 can extract data about charging factors from each user's historical data. Figure 2 Example 210 shows user data on the charging factor when the charging factor is the state of charge at the start of charging, where the x-axis represents the state of charge at the start of charging and the y-axis represents the number of samples.

[0074] Server 10 can extract user features from charging factor data. In one implementation, server 10 can calculate a probability density function by applying kernel density estimation (KDE) to the charging factor data and extract the calculated probability density function as the user's features. For example, server 10 can represent each user's features as a probability density function for charging factors, such as... Figure 2 As shown in 220.

[0075] Figure 3 This is a view illustrating an example of extracting features by applying weights according to one embodiment disclosed herein.

[0076] Reference Figure 3 Server 10 can apply kernel density estimation by assigning higher weights to data acquired at time points closer to the current time point in each historical data set.

[0077] Server 10 can apply weighting function 320 to data 310 about charging factors. Weighting function 320 can be set to have a higher value as it gets closer to the current time point, and for example, server 10 can represent data about charging factors as a histogram 330 by multiplying the data 310 about charging factors by weighting function 320.

[0078] Server 10 can compute probability density function 340 by applying kernel density estimation techniques to histogram 330 about charging factors.

[0079] Figure 4 This is a view showing an example of the result of clustering features according to one embodiment disclosed herein.

[0080] Reference Figure 4 Server 10 can cluster features. Figure 4 410 shows the features extracted from each of the user's historical data, and 420 shows an example of the results of clustering the features.

[0081] According to one implementation, server 10 can perform clustering based on the maximum probability density value included in the user's features. For example, as Figure 4As shown in 420, server 10 can classify users into groups with weak charging habits, groups with strong charging habits, and groups with ambiguous habits based on the results of clustering user characteristics. For example, the group with strong charging habits can be classified as including users with large maximum probability density values.

[0082] Figure 5 This is a view illustrating an example of setting up a standard for determining custom according to one embodiment disclosed herein.

[0083] Reference Figure 5 Server 10 can set criteria for determining habituation based on the maximum probability density value of each group as a result of clustering.

[0084] Figure 5 Figure 510 is a graph showing the maximum probability density value for each user, where the x-axis represents the maximum probability density and the y-axis represents the number of samples. Server 10 can set criteria for determining habituation based on the clustering results and the maximum probability density value.

[0085] Server 10 can represent the maximum probability density of each user as follows: Figure 5 The diagram shown in Figure 520. For example, server 10 can cluster user features and separately represent the maximum probability density of features included in each group. For example, in Figure 5 In 520, the data marked C1 may be data of users included in a group that does not have the habit of starting to charge, and the data marked C3 may be data of users included in a group that has the habit of starting to charge.

[0086] In one implementation, server 10 may set the maximum value among the maximum probability densities of users included in group C1 who do not have a charging start habit as a first reference value for determining the habit. Furthermore, server 10 may set the minimum value among the maximum probability densities of users included in group C3 who do not have a charging start habit as a second reference value for determining the habit. For example, in Figure 5 In 520, the first reference value can be set to 0.020, and the second reference value can be set to 0.028.

[0087] Server 10 can determine the habituality of a target user based on a comparison of the maximum probability density derived from the target user's characteristics with a standard. For example, in Figure 5 In the process, when the maximum probability density value of the target user is less than 0.020, the server 10 can determine that the target user has a weak charging habit, while when the maximum probability density value is greater than 0.028, it can determine that the charging habit is strong.

[0088] Figure 6 This is a flowchart describing a method for operating a server according to one embodiment disclosed herein.

[0089] Reference Figure 6 The method of operating the server may include: acquiring historical data related to battery charging of the user and information about the current driving of the target user (S100), extracting features of the user related to charging factors from the historical data (S200), setting criteria for determining habitual behavior related to factors based on the features (S300), determining the habitual behavior of the target user based on the features and criteria (S400), and providing guidance information about the habitual behavior of the target user based on the habitual behavior and historical data of the target user and information about the current driving of the target user (S500).

[0090] In operation S100, server 10 can obtain various charging history data of the user and information about the target user's current driving. For example, server 10 can obtain information from the battery's BMS, charging equipment, and discharging equipment.

[0091] In operation S200, server 10 can extract user features related to charging factors from each historical data record. According to one implementation, server 10 can extract the probability density function (PDF) calculated by applying kernel density estimation (KDE) technology to each user's historical data record as the feature of each user.

[0092] In operation S300, server 10 can set criteria for determining habitual patterns associated with factors based on features. According to one implementation, server 10 can set the criteria based on the results of clustering the features.

[0093] In operation S400, server 10 can determine the habits of the target user based on the target user's characteristics and criteria. According to one implementation, server 10 can determine the user's habits based on the result of comparing the maximum probability density included in the target user's characteristics with the criteria.

[0094] In operation S500, server 10 can provide guidance information about the target user's habits based on at least one of the target user's habits and historical data, and information about the target user's current driving. According to one embodiment, server 10 can calculate the remaining depth of discharge based on the target user's habitual state of charge (SOC) and information about the target user's current driving, and provide guidance information including the remaining depth of discharge.

[0095] Figure 7 This is a block diagram illustrating a server configuration according to one embodiment disclosed herein.

[0096] Reference Figure 7 According to one embodiment, server 10 may include communication circuitry 11, processor 12, and memory 13.

[0097] The communication circuit 11 can support the establishment of wired or wireless communication connections between the server 10 and external electronic devices (e.g., vehicles or electronic devices) and the execution of communication through the established connections. According to one embodiment, the communication circuit 11 may include a wireless communication circuit (e.g., a cellular communication circuit, a short-range wireless communication circuit, or a Global Navigation Satellite System (GNSS) communication circuit) or a wired communication circuit (e.g., a local area network (LAN) communication circuit or a power line communication circuit), and communicate with external electronic devices via short-range communication networks (e.g., Bluetooth, WiFi Direct, or Infrared Data Association (IrDA)) or long-range communication networks (e.g., cellular networks, the Internet, computer networks) using the corresponding communication circuits described above. Various types of communication circuits 11 can be implemented as a single chip, or they can each be implemented as separate chips. According to one embodiment, the communication circuit 11 of the server 10 can be integrated with… Figure 1 The vehicle 20 and electronic devices 30 communicate.

[0098] Processor 12 can control the overall operation of server 10. In various embodiments, processor 12 may include one processor core (single core) or multiple processor cores. For example, processor 12 may include multi-core processors such as dual-core, quad-core, or hexa-core processors. According to embodiments, processor 12 may also include internal or external cache memory. According to embodiments, processor 12 may be configured as one or more processors. For example, processor 12 may include at least one of an application processor, a communication processor, or a graphics processing unit (GPU).

[0099] All or some of the processors 12 may be electrically connected or operatively coupled or linked to other components in server 10 (e.g., communication circuitry 11 or memory 13). Processor 12 may receive commands from other components, interpret the received commands, and perform calculations or process data according to the interpreted commands. Processor 12 may interpret messages, data, commands, or signals received from communication circuitry 11 and memory 13. Processor 12 may generate new messages, data, commands, or signals based on the received messages, data, commands, or signals. Processor 12 may provide the processed or generated messages, data, commands, or signals to communication circuitry 11 or memory 13.

[0100] Processor 12 can process data or signals generated or produced by a program. For example, processor 12 can request commands, data, or signals from memory 13 to execute or control a program. Processor 12 can record (or store) or update commands, data, or signals in memory 13 to execute or control a program. According to one embodiment, processor 12 can analyze various historical data of the user stored in memory 13 and set criteria for determining habits.

[0101] Memory 13 may store commands, control command codes, control data, or user data used to control server 10. For example, memory 13 may include at least one of an application program, operating system (OS), middleware, or device driver. Memory 13 may include one or more of volatile and non-volatile memory. 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. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc. Memory 13 may also include non-volatile media such as hard disk drive (HDD), solid-state drive (SSD), embedded multimedia card (eMMC), or universal flash storage (UFS). According to one embodiment, memory 13 may store historical data related to user charging.

[0102] As described above, although all components constituting the embodiments disclosed herein are described as being coupled or operating by being coupled, the embodiments disclosed herein are not necessarily limited to these embodiments. In other words, one or more of all components may operate by being selectively coupled without departing from the purpose and scope of the embodiments disclosed herein.

[0103] Furthermore, unless otherwise stated, terms such as “comprising,” “constituting,” or “having” above indicate that the corresponding component may be included, and therefore should be interpreted as further including another component, rather than excluding another component. Unless otherwise defined, all terms (including technical or scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments disclosed herein pertain. Commonly used terms (e.g., terms defined in dictionaries) should be interpreted as consistent with the meaning in the context of the relevant field and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined herein.

[0104] The above description is merely an exemplary description of the technical spirit disclosed herein, and those skilled in the art to which the embodiments disclosed herein pertain will be able to make various modifications and alterations to this document without departing from the essential characteristics of the embodiments disclosed herein. Therefore, the embodiments disclosed herein are not intended to limit the technical spirit disclosed herein, but are for illustrative purposes, and the scope of the technical spirit disclosed herein is not limited by these embodiments. The scope of the technical spirit disclosed herein should be interpreted by the appended claims, and all technical spirit within the equivalent scope should be interpreted as included within the scope of this document.

Claims

1. A server, the server comprising: Communication circuits; Memory; as well as A processor, operatively connected to the communication circuitry and the memory, The processor is configured as follows: Obtain historical data related to battery charging and information about the target user's current driving; Extract the user's charging-related features from the historical data; Based on the aforementioned features, standards are set to determine habitual criteria associated with the aforementioned factors; The habits of the target user are determined based on the characteristics of the target user and the criteria; and Based on at least one of the target user's habits and historical data and the information about the target user's current driving, provide guidance information about the target user's habits.

2. The server according to claim 1, wherein, The processor extracts the probability density function PDF for the factor, calculated by applying kernel density estimation (KDE) to the historical data, as the feature.

3. The server according to claim 2, wherein, The processor sets the criteria based on the results of clustering the features.

4. The server according to claim 3, wherein, The processor sets the criteria based on the maximum probability density value of the features included in each group as a result of clustering.

5. The server according to claim 2, wherein, The processor applies the kernel density estimation by assigning higher weights to data acquired at time points closer to the current time in each historical data set.

6. The server according to claim 1, wherein, The processor determines the habituality of the target user based on a comparison of the maximum probability density derived from the characteristics of the target user with the standard.

7. The server according to claim 1, wherein, The processor updates the target user's characteristics and habits by reflecting historical data acquired during each charging session.

8. The server according to claim 1, wherein, The processor calculates the remaining depth of discharge based on the habitually obtained state of charge (SOC) and information about the current driving, and provides the guidance information including the remaining depth of discharge.

9. A method for operating a server, the method comprising the following steps: Obtain historical data related to battery charging and information about the target user's current driving; Extract the user's charging-related features from the historical data; Based on the aforementioned features, a standard for determining habitual behavior related to the aforementioned factors is set. The habits of the target user are determined based on the characteristics of the target user and the criteria. as well as Based on at least one of the target user's habits and historical data and the information about the target user's current driving, provide guidance information about the target user's habits.

10. The method according to claim 9, wherein, The step of extracting the features includes the following steps: extracting the probability density function PDF for the factor, which is calculated by applying kernel density estimation (KDE) to the historical data, as the feature.

11. The method according to claim 10, wherein, The steps for setting the standard include the following: setting the standard based on the results of clustering the features.

12. The method according to claim 11, wherein, The steps for setting the criteria include the following: setting the criteria based on the maximum probability density value of the features included in each group as a result of clustering.

13. The method according to claim 10, wherein, The steps for extracting the features include the following: applying the kernel density estimation by assigning higher weights to data acquired at time points closer to the current time in each historical data set.

14. The method according to claim 9, wherein, The step of determining the habit of the target user includes the following steps: determining the habit of the target user based on the result of comparing the maximum probability density derived from the characteristics of the target user with the standard.

15. The method according to claim 9, wherein, The step of providing the guidance information includes the following steps: calculating the remaining depth of discharge based on the habitually acquired state of charge (SOC) at the start of charging and information about the current driving, and providing the guidance information including the remaining depth of discharge.

Images