Charging time prediction apparatus and method of operating same

Abstract

A charging time prediction device, according to one embodiment disclosed in this document, includes a communication circuit and a processor, the processor may be configured to: receive, from an external electronic device through the communication circuit, first battery information including a current value, a temperature value, a state of charge (SoC), and a state of health (SoH) of a battery included in the external electronic device during a specified period of time; receiving, through the communication circuit, information about a driving speed of the external electronic device and / or information about whether the external electronic device and the external charger are connected to each other during the specified time period; extracting a charging interval in the specified time period based on the first battery information, the information about the driving speed, and / or the information about the connection state during the specified time period; and generating a charging time prediction model by using the current value, the temperature value, the SoC, and the SoH at a first point in time of the charging section, and the SoC at a second point in time of the charging section.

Description

Technical Field

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of Korean Patent Application No. 10-2022-0103001 filed in the Korean Intellectual Property Office on August 17, 2022, the entire contents of which are hereby incorporated herein by reference.

[0004] Embodiments disclosed herein relate to a charging time prediction device and an operating method thereof. Background Art

[0005] Recently, the research and development of secondary batteries have been actively carried out. Here, the secondary battery as a rechargeable / dischargeable battery may include all conventional nickel (Ni) / cadmium (Cd) batteries, Ni / metal hydride (MH) batteries, etc., and the recent lithium-ion batteries. Among the secondary batteries, lithium-ion batteries have a much higher energy density than conventional Ni / Cd batteries, Ni / MH batteries, etc. In addition, lithium-ion batteries can be made small and light, so lithium-ion batteries have been used as power sources for mobile devices, and recently their scope of use has been expanded to power sources for electric vehicles, attracting attention as the next generation of energy storage media.

[0006] The required charging time is used by the user to determine whether to continue charging the battery to the target state of charge (SoC), so it is important to accurately provide the required charging time to the user.

[0007] Conventionally, in order to predict the required charging time, a method of calculating the required charging time matching the current temperature of the battery and the SoC based on a preset table has been used. Summary of the invention

[0008] Technical issues

[0009] However, the conventional charging time prediction scheme has a limitation in that an error occurs between the calculated required charging time and the actual required charging time due to limited data capacity of a preset table and failure to consider a degradation rate of a battery.

[0010] Embodiments disclosed herein are intended to provide a charging time prediction device and an operating method thereof that can predict a required charging time while minimizing an error from an actual required charging time.

[0011] Technical problems of the embodiments disclosed herein are not limited to the above-mentioned technical problems, and other unmentioned technical problems will be clearly understood by those of ordinary skill in the art from the following description.

[0012] Technical Solution

[0013] A charging time prediction device according to an embodiment disclosed herein includes a communication circuit and a processor, wherein the processor is configured to receive first battery information including a current value, a temperature value, a state of charge (SoC), and a state of health (SoH) of a battery included in the external electronic device during a specified time period from an external electronic device through the communication circuit, receive information about a driving speed of the external electronic device within the specified time period and / or information about whether the external electronic device is connected to an external charger through the communication circuit, extract a charging period from the specified time period based on the first battery information within the specified time period, the information about the driving speed, and / or the information about the connection, and generate a charging time prediction model by using the current value, the temperature value, the SoC, and the SoH at a first time point in the charging period and the SoC at a second time point in the charging period.

[0014] According to the embodiments disclosed herein, the processor may also be configured to receive second battery information including a current value, a temperature value, a SoC, and a SoH of the battery at a specified time point from an external electronic device through a communication circuit, and predict the required charging time from the SoC at the specified time point to the target SoC based on a charging time prediction model.

[0015] According to an embodiment disclosed herein, the first battery information may include model information of the battery, and the processor may be further configured to generate a charging time prediction model corresponding to the model information.

[0016] According to an embodiment disclosed herein, the processor may be further configured to extract at least a portion of a first period in which a current value of the battery is greater than or equal to a specified current value from the specified time period as a charging period.

[0017] According to an embodiment disclosed herein, the processor may be further configured to extract at least a portion of a second period in which a driving speed of the external electronic device is a designated speed and the external electronic device is connected to an external charger from the first period as a charging period.

[0018] According to an embodiment disclosed herein, the processor may be further configured to extract at least a portion of the third period as the charging period by excluding the data disconnection period, the period in which the charging time is less than a specified time, and the period in which the charging amount is less than a specified charging amount from the second period.

[0019] According to an embodiment disclosed herein, the processor may be further configured to extract a period as a charging period by excluding a period in which a current variation value of the battery is greater than or equal to a specified variation value from the third period.

[0020] According to the embodiments disclosed herein, the processor may be further configured to send the required charging time to an external electronic device through a communication circuit to provide the user with the predicted required charging time.

[0021] A charging time prediction method according to an embodiment disclosed herein includes the following steps: obtaining first battery information including a current value, a temperature value, a state of charge (SoC), and a state of health (SoH) of a battery included in an external electronic device within a specified time period, obtaining information about a driving speed of the external electronic device and / or information about whether the external electronic device is connected to an external charger, extracting a charging period from the specified time period based on the first battery information within the specified time period, the information about the driving speed, and / or the information about the connection, and generating a charging time prediction model by using the current value, the temperature value, the SoC, and the SoH at a first time point in the charging period and the SoC at a second time point in the charging period.

[0022] According to an embodiment disclosed herein, the first battery information may include model information of the battery, and the step of generating a charging time prediction model may include the following steps: generating a charging time prediction model corresponding to the model information.

[0023] According to an embodiment disclosed herein, the step of extracting the charging period may include the step of extracting at least a portion of a first period in which a current value of the battery is greater than or equal to a specified current value from a specified time period as the charging period.

[0024] According to an embodiment, the step of extracting the charging period may include extracting at least a portion of a second period in which a driving speed of the external electronic device is a designated speed and the external electronic device is connected to the external charger from the first period as the charging period.

[0025] According to an embodiment disclosed herein, the step of extracting the charging period may include the step of extracting at least a portion of the third period as the charging period by excluding a data disconnection period, a period in which the charging time is less than a specified time, and a period in which the charged amount is less than a specified charged amount from the second period.

[0026] According to an embodiment disclosed herein, the step of extracting the charging period may include the step of extracting a period as the charging period by excluding a period in which a current variation value of the battery is greater than or equal to a specified variation value from the third period.

[0027] Technical Effects

[0028] According to the embodiments disclosed herein, the required charging time may be predicted based on a charging time prediction model generated and / or trained using battery information including current value, temperature value, SoC and SoH of the battery, thereby improving the accuracy of predicting the required charging time.

[0029] According to the embodiments disclosed herein, by extracting information about the charging period from battery information, the prediction accuracy of the required charging time of the charging time prediction model can be further enhanced.

[0030] According to the embodiments disclosed herein, the predicted required charging time may be provided to the user, thereby improving the convenience of the user.

[0031] Furthermore, various effects directly or indirectly recognized from the present disclosure can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a block diagram illustrating a charging time prediction apparatus according to an embodiment.

[0033] Figure 2 is an operation flow chart of a charging time prediction device according to an embodiment.

[0034] Figure 3 is an operation flow chart of a charging time prediction device according to an embodiment.

[0035] Figure 4 is an operation flow chart of a charging time prediction device according to an embodiment.

[0036] Figure 5 is a view showing an interface provided to a user by a charging time prediction apparatus according to an embodiment. DETAILED DESCRIPTION

[0037] Hereinafter, various embodiments of the present disclosure will be disclosed with reference to the accompanying drawings. However, the present description is not intended to limit the present disclosure to a specific embodiment, and it should be understood to include various modifications, equivalents and / or substitutes according to the embodiments of the present disclosure.

[0038] It should be understood that the various embodiments of this document and the terms used therein are not intended to limit the technical features set forth herein to specific embodiments, and include various changes, equivalents, or alternatives to the corresponding embodiments. With respect to the description of the drawings, similar reference numerals may be used to refer to similar or related elements. It should be understood that the singular form of a noun corresponding to an item may include one or more things, unless the relevant context clearly indicates otherwise.

[0039] When used herein, each of such phrases 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 item or all possible combinations of the items listed together in the corresponding phrase in the phrase. Such terms as “1st,” “2nd,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used to simply distinguish a corresponding component from another component and do not limit the components in other aspects (e.g., importance or order) unless otherwise mentioned.

[0040] Herein, it should be understood that when an element (e.g., a first element) is referred to as being "connected," "coupled," or "linked" to another element (e.g., a second element) with or without the term "operably" or "communicatively," or "coupled" or "connected" to another element (e.g., the second element), this means that the element may be connected to the other element directly (e.g., wired), wirelessly, or via a third element.

[0041] According to an embodiment of the present disclosure, the method according to various embodiments of the present disclosure disclosed herein may be included and provided in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or distributed online through an application store or directly between two user devices (e.g., downloaded or uploaded). If distributed online, at least a portion of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium such as a memory of a manufacturer server, a server of an application store, or a relay server.

[0042] According to various embodiments, each component (e.g., module or program) in the above-mentioned components may include a single entity or multiple entities, and some of the multiple entities may be arranged separately in different components. According to various embodiments, one or more of the above-mentioned components may be omitted, or one or more other components may be added. Alternatively or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, according to various embodiments, the integrated component may still perform one or more functions of each component in the multiple components in the same or similar manner as the manner in which the corresponding components in the multiple components perform functions before integration. According to various embodiments, the operations performed by a module, program or another component may be performed sequentially, in parallel, repeatedly or heuristically, or one or more of the operations may be performed or omitted in different orders, or one or more other operations may be added.

[0043] Figure 1 is a block diagram illustrating a charging time prediction apparatus according to an embodiment.

[0044] Reference Figure 1 , the charging time prediction device 110 may include a communication circuit 111, a memory 113 and / or a processor 115. According to some embodiments, in the charging time prediction device 110, the Figure 1 At least one of the components of the present invention may be included, or one or more other components may be added. In some implementations, some of these components may be implemented as a single integrated circuit.

[0045] The communication circuit 111 may wirelessly or wiredly transmit and receive data to and from the first external electronic device 120 and / or the second external electronic device 130. Herein, the first external electronic device 120 may be an electric vehicle using electric energy, and the second external electronic device 130 may be a portable electronic device such as a smartphone or a tablet personal computer (PC).

[0046] According to an embodiment, the communication circuit 111 may receive information about a battery included in the first external electronic device 120 from the first external electronic device 120. Herein, the information about the battery may include model information, a current value, a temperature value, a SoC, and / or a SoH of the battery included in the first external electronic device 120. The communication circuit 111 may receive a target SoC set based on a user input from the first external electronic device 120 or the second external electronic device 130. According to an embodiment, the communication circuit 111 may transmit the information received from the first external electronic device 120 and / or the second external electronic device 130 to the processor 115.

[0047] According to an embodiment, the communication circuit 111 may transmit the command data received from the processor 115 to the first external electronic device 120 and / or the second external electronic device 130. For example, the command data may include information about the required charging time predicted by the processor 115. The command data may include an instruction for causing the first external electronic device 120 and / or the second external electronic device 130 to output a specified alarm through a user interface (e.g., a display, a speaker).

[0048] The memory 113 may be a volatile memory or a nonvolatile memory. For the memory 113 as a volatile memory, a random access memory (RAM), a dynamic RAM (DRAM), a static RAM (SRAM), etc. may be used. For the memory 113 as a nonvolatile memory, a read-only memory (ROM), a programmable ROM (PROM), an electrically variable ROM (EAROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a flash memory, etc. may be used. The examples listed above of the memory 113 are only examples and are not limited thereto.

[0049] The memory 113 may store various data used by at least one component of the charging time prediction device 110 (e.g., the communication circuit 111 and / or the processor 115). For example, the memory 113 may store a charging time prediction model generated by the processor 115. The memory 113 may classify and store the charging time prediction model generated by the processor 115 according to the battery model information included in the external electronic device (e.g., the first external electronic device 120). For example, the battery model information may include model information of the first external electronic device 120 in which the battery is arranged, original equipment manufacturing (OEM) information of the battery (e.g., manufacturer information of the battery), and / or manufacturing year information of the battery.

[0050] The processor 115 may execute software to control at least one other component connected to the processor 115, and may process or calculate various data. According to an embodiment, the processor 115 may control at least one other component connected to the processor 115 to perform the overall operation of the charging time prediction device 110. The processor 115 may include at least one of processing devices such as an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a microcontroller, or a microprocessor.

[0051] According to an embodiment, the processor 115 may generate and / or train a charging time prediction model.

[0052] According to an embodiment, the processor 115 may generate a charging time prediction model by using battery information received from the first external electronic device 120 through the communication circuit 111. The processor 115 may generate a charging time prediction model by using battery information received from the first external electronic device 120 and train the generated charging time prediction model.

[0053] According to an embodiment, the processor 115 may generate a charging time prediction model corresponding to the model information of the battery included in the acquired battery information. For example, the model information of the battery may include model information of the first external electronic device 120 in which the battery is arranged, OEM information of the battery (e.g., manufacturer information of the battery), and / or manufacturing year information of the battery. According to an embodiment, the processor 115 may train the generated charging time prediction model by using battery information including the same model information.

[0054] According to an embodiment, the processor 115 may acquire first battery information from the first external electronic device 120 through the communication circuit 111. For example, the first battery information may include a current value, a temperature value, SoC, and SoH of a battery included in the first external electronic device 120. According to an embodiment, the first battery information may be acquired in real time or periodically.

[0055] According to an embodiment, the processor 115 may receive information about the driving speed of the first external electronic device 120 and / or information about whether the first external electronic device 120 is connected to an external charger from the first external electronic device 120 through the communication circuit 111. According to an embodiment, the information about the driving speed and / or the information about the connection may be acquired in real time or periodically.

[0056] According to an embodiment, the processor 115 may analyze data within a specified time period. According to an embodiment, the processor 115 may extract the charging period by analyzing data within a specified time period (e.g., first battery information measured within a specified time period, information about driving speed, and / or information about connection). Hereinafter, a method for extracting a charging period from a specified time period will be described. In an embodiment, the specified time period may be a time window (e.g., one week, one day, one hour, three hours) in which the processor 115 analyzes battery information.

[0057] According to an embodiment, the processor 115 may extract a charging period based on first battery information within a specified period, information about a driving speed of the first external electronic device 120 , and / or information about whether the first external electronic device 120 is connected to an external charger.

[0058] According to an embodiment, the processor 115 may extract a charging period based on the current value of the battery included in the first battery information. According to an embodiment, the processor 115 may extract a charging period based on a period in which the current value of the battery is greater than or equal to a specified current value based on the first battery information. According to an embodiment, the processor 115 may extract at least a portion of a period in which the current value of the battery is greater than or equal to a specified current value as a charging period based on the first battery information. In this article, the specified current value may be 0A. When the current value of the battery exceeds 0A, this may indicate that the battery is charged, and when the current value of the battery is less than 0A, this may indicate that the battery is discharged.

[0059] According to an embodiment, the processor 115 may extract a charging period based on information about the driving speed of the first external electronic device 120 and information about whether the first external electronic device 120 is connected to an external charger. According to an embodiment, the processor 115 may extract a charging period based on a period in which the driving speed of the first external electronic device 120 is a specified speed and the first external electronic device 120 is connected to an external charger. According to an embodiment, the processor 115 may extract at least a portion of a period in which the driving speed of the first external electronic device 120 is a specified speed and the first external electronic device 120 is connected to an external charger as a charging period. Herein, the specified speed may be 0 km / hr.

[0060] According to an embodiment, the processor 115 may extract the charging period by excluding a data disconnection period, a period in which the charging time is less than a specified time, and a period in which the charged amount is less than a specified charged amount from the specified time period based on the first battery information.

[0061] According to an embodiment, the processor 115 can extract the charging period by excluding the period in which the battery current change value is greater than or equal to the specified change value. When the battery current change value is greater than or equal to the specified change value during battery charging, this may indicate that noise occurs in the measured current.

[0062] According to an embodiment, the processor 115 may extract a first period in which the current value of the battery is greater than or equal to the specified current value from the specified time period. The processor 115 may extract a second period in which the driving speed of the external electronic device is the specified speed and the external electronic device is connected to the external charger from the first period. The processor 115 may extract a third period by excluding a data disconnection period, a period in which the charging time is less than the specified time, and a period in which the charging amount is less than the specified charging amount from the second period.

[0063] According to an embodiment, the second period may include a data disconnection period. For example, the third period included in the second period and the fourth period included in the fourth period may include a data disconnection period. When the remaining period excluding the data disconnection period from the fourth period is a period less than a specified time, the processor 115 may extract the third period excluding the fourth period as a charging period. In this article, the data disconnection period may refer to a period in which no data is acquired from the first external electronic device 120 for a specific time or more.

[0064] According to an embodiment, the processor 115 can extract the charging period by excluding the period in which the charge amount of the battery is less than the specified charge amount based on the SoC change amount. For example, when the SoC change amount of the third period included in the second period and the fourth period in the fourth period is less than the specified change amount, the processor 115 can extract the third period as the charging period by excluding the fourth period.

[0065] According to an embodiment, the processor 115 may extract the charging period by excluding a period in which a current variation value of the battery is greater than or equal to a designated variation value from the third period.

[0066] According to an embodiment, the processor 115 may generate and / or train a charging time prediction model by using the current value, temperature value, SoC, and SoH of the battery during the extracted charging period. Hereinafter, a method of generating and / or training a charging time prediction model performed by the processor 115 will be described. In an embodiment, the charging time prediction model may be a machine learning model for obtaining a required charging time as output data by using the current value, temperature value, SoC, SoH, and target SoC of the battery at the charging start time as input data.

[0067] According to an embodiment, the processor 115 may identify a current value, a temperature value, a SoC, and a SoH of the battery within a charging period extracted from a specified period. According to an embodiment, the processor 115 may identify a current value, a temperature value, a SoC, and a SoH of the battery at each of at least two time points of the charging period.

[0068] According to an embodiment, the processor 115 may train a charging time prediction model based on the current value, temperature value, SoC and SoH at a first time point and the SoC at a second time point. For example, the processor 115 may train a charging time prediction model by using the current value, temperature value, SoC and SoH at a first time point and the SoC at a second time point as input data of the charging time prediction model.

[0069] In an embodiment, the processor 115 may adjust the parameters (or weight values) of the hidden layer of the charging time prediction model based on the output data of the charging time prediction model based on the current value, temperature value, SoC and SoH at the first time point and the SoC at the second time point, and the difference between the first time point and the second time point. In an embodiment, the processor 115 may adjust the parameters (or weight values) of the hidden layer of the charging time prediction model so that the error between the output data of the charging time prediction model and the difference is a value within a specified error.

[0070] According to an embodiment, the processor 115 may repeatedly train the charging time prediction model by using the data of the charging period. According to an embodiment, the processor 115 may repeatedly train the charging time prediction model by using the current value, temperature value, SoC and / or SoC at each time point. For example, the charging time prediction model may be trained using the data at the first time point and the second time point of the charging period, and the charging time prediction model may be trained using the data at the third time point and the fourth time point of the charging period.

[0071] According to an embodiment, the processor 115 may terminate the training of the charging time prediction model based on the output data of the charging time prediction model. According to an embodiment, the processor 115 may terminate the training of the charging time prediction model when the error between the output data of the charging time prediction model and the difference between at least two time points of the charging period is within a specified error.

[0072] According to an embodiment, the processor 115 may generate and / or train a charging time prediction model using a machine learning model (eg, a gradient boosting machine (GBM) or a distributed random forest (DRF)).

[0073] Hereinafter, a method for predicting the required charging time based on the trained charging time prediction model, which is performed by the processor 115 , will be described.

[0074] According to an embodiment, the processor 115 may predict the required charging time based on the generated and / or trained charging time prediction model.

[0075] According to an embodiment, the processor 115 may acquire second battery information from the first external electronic device 120 through the communication circuit 111. For example, the second battery information may include current value, temperature value, SoC, and SoH of a battery included in the first external electronic device 120 at a specified time point.

[0076] According to an embodiment, the processor 115 may predict the required charging time from the SoC included in the second battery information to the target SoC based on the charging time prediction model. In this article, the target SoC may refer to one of the SOCs between the SoC of the battery at a specified time point included in the second battery information and the SoC when the battery is fully charged. According to an embodiment, the processor 115 may obtain the target SoC set based on the user input from the first external electronic device 120 or the second external electronic device 130. In this case, the processor 115 may output an interface (e.g., Figure 5 The first screen 510 of the embodiment of the present invention is used to obtain a user input for selecting a target SoC.

[0077] According to an embodiment, the processor 115 may provide the user with the predicted required charging time. According to an embodiment, the processor 115 may send command data to the first external electronic device 120 and / or the second external electronic device 130 through the communication circuit 111. For example, the command data may include information about the predicted required charging time. The command data may include information for causing the first external electronic device 120 and / or the second external electronic device 130 to output a specified alarm (e.g., Figure 5 The second screen 520) instructions.

[0078] Figure 2 is an operation flow chart of a charging time prediction device according to an embodiment. Figure 1 Components to describe Figure 2 .

[0079] exist Figure 2 The embodiments shown in the drawings may be examples, and the order of operations according to various embodiments of the present disclosure may be different from that in the drawings. Figure 2 The order shown in the Figure 2 For some operations shown in the drawings, the order of operations may be changed, or the operations may be combined.

[0080] According to an embodiment, operations 205 to 215 may be understood to be executed by the processor 115 of the charging time prediction device 110 .

[0081] Reference Figure 2 , in operation 205 , the charging time prediction device 110 may generate and / or train a charging time prediction model.

[0082] According to an embodiment, the charging time prediction apparatus 110 may generate a charging time prediction model by using battery information acquired from the first external electronic device 120. The charging time prediction apparatus 110 may generate a charging time prediction model by using battery information acquired from the first external electronic device 120 and train the generated charging time prediction model.

[0083] According to an embodiment, the charging time prediction device 110 may generate a charging time prediction model corresponding to the model information of the battery included in the acquired battery information. For example, the model information of the battery may include model information of the first external electronic device 120 in which the battery is arranged, OEM information of the battery (e.g., manufacturer information of the battery), and / or manufacturing year information of the battery. According to an embodiment, the charging time prediction device 110 may train the generated charging time prediction model by using battery information including the same model information.

[0084] Reference will be made to the following description Figure 3 and Figure 4 The operations of generating and / or training a charging time prediction model performed by the charging time prediction device 110 will be described in detail.

[0085] In operation 210 , the charging time prediction apparatus 110 may predict a required charging time based on the charging time prediction model generated and / or trained in operation 205 .

[0086] According to an embodiment, the charging time prediction apparatus 110 may acquire second battery information from the first external electronic device 120. For example, the second battery information may include a current value, a temperature value, SoC, and SoH of a battery included in the first external electronic device 120 at a specified time point.

[0087] According to an embodiment, the charging time prediction device 110 may predict the required charging time from the SoC included in the second battery information to the target SoC based on the charging time prediction model. Herein, the target SoC may refer to one of the SOCs between the SoC of the battery at a specified time point included in the second battery information and the SoC when the battery is fully charged. According to an embodiment, the charging time prediction device 110 may obtain the target SoC set based on user input from the first external electronic device 120 or the second external electronic device 130. In this case, the charging time prediction device 110 may output an interface (e.g., Figure 5 The first screen 510 of the embodiment of the present invention is used to obtain a user input for selecting a target SoC.

[0088] In operation 215, the charging time prediction device 110 may provide the user with the required charging time predicted in operation 210. According to an embodiment, the charging time prediction device 110 may send command data to the first external electronic device 120 and / or the second external electronic device 130. For example, the command data may include information about the required charging time predicted in operation 210. The command data may include a command for causing the first external electronic device 120 and / or the second external electronic device 130 to output a specified alarm (e.g., Figure 5 The second screen 520) instructions.

[0089] Figure 3 is an operation flow chart of a charging time prediction device according to an embodiment. Figure 1 Components to describe Figure 3 .

[0090] exist Figure 3 The embodiments shown in the drawings may be examples, and the order of operations according to various embodiments of the present disclosure may be different from that in the drawings. Figure 3 The order shown in the Figure 3 For some operations shown in the drawings, the order of operations may be changed, or the operations may be combined.

[0091] According to an embodiment, operations 305 to 315 may be understood to be executed by the processor 115 of the charging time prediction device 110 .

[0092] Reference Figure 3 In operation 305, the charging time prediction apparatus 110 may acquire first battery information from the first external electronic device 120. For example, the first battery information may include a current value, a temperature value, a SoC, and a SoH of a battery included in the first external electronic device 120. According to an embodiment, the first battery information may be acquired in real time or periodically.

[0093] According to an embodiment, the charging time prediction device 110 may analyze data within a specified time period. According to an embodiment, the charging time prediction device 110 may extract the charging time period by analyzing data within a specified time period (e.g., first battery information measured within a specified time period, information about driving speed, and / or information about connection). Hereinafter, a method of extracting a charging time period from a specified time period performed by the charging time prediction device 110 will be described. In an embodiment, the specified time period may be a time window (e.g., one week, one day, one hour, three hours) in which the charging time prediction device 110 analyzes battery information.

[0094] In operation 310, the charging time prediction device 110 may extract a charging period from a specified time period. According to an embodiment, the charging time prediction device 110 may obtain information about a driving speed of the first external electronic device 120 and / or information about whether the first external electronic device 120 is connected to an external charger from the first external electronic device 120. According to an embodiment, the information about the driving speed and / or the information about the connection may be obtained in real time or periodically. According to an embodiment, the charging time prediction device 110 may extract a charging period based on the first battery information within a specified time period, the information about the driving speed of the first external electronic device 120, and / or the information about whether the first external electronic device 120 is connected to an external charger.

[0095] According to an embodiment, the charging time prediction device 110 may extract the charging period based on the current value of the battery included in the first battery information. According to an embodiment, the charging time prediction device 110 may extract the charging period based on the period in which the current value of the battery is greater than or equal to a specified current value based on the first battery information.

[0096] According to an embodiment, the charging time prediction apparatus 110 may extract the charging period based on information about the driving speed of the first external electronic device 120 and information about whether the first external electronic device 120 is connected to an external charger. According to an embodiment, the charging time prediction apparatus 110 may extract the charging period based on a period in which the driving speed of the first external electronic device 120 is a specified speed and the first external electronic device 120 is connected to an external charger.

[0097] According to an embodiment, the charging time prediction device 110 may extract the charging time period by excluding a data disconnection period, a period in which the charging time is less than a specified time, and a period in which the charged amount is less than a specified charged amount from the specified time period based on the first battery information.

[0098] According to an embodiment, the charging time prediction device 110 can extract the charging period by excluding the period in which the current change value of the battery is greater than or equal to the specified change value. When the current change value of the battery is greater than or equal to the specified change value during battery charging, this may indicate that noise occurs in the measured current.

[0099] Reference will be made to the following description Figure 4 The operation of extracting the charging time period performed by the charging time prediction device 110 will be described in detail.

[0100] In operation 315, the charging time prediction device 110 may generate and / or train a charging time prediction model by using the current value, temperature value, SoC, and SoH of the battery within the charging period extracted in operation 310. In an embodiment, the charging time prediction model may be a machine learning model for obtaining a required charging time as output data by using the current value, temperature value, SoC, SoH, and target SoC of the battery at the charging start time as input data.

[0101] According to an embodiment, the charging time prediction device 110 may identify a current value, a temperature value, a SoC, and a SoH of a battery within a charging period extracted from a specified time period. According to an embodiment, the charging time prediction device 110 may identify a current value, a temperature value, a SoC, and a SoH of a battery at each of at least two time points of the charging period.

[0102] According to an embodiment, the charging time prediction device 110 may train a charging time prediction model based on the current value, temperature value, SoC and SoH at a first time point and the SoC at a second time point. For example, the charging time prediction device 110 may train a charging time prediction model by using the current value, temperature value, SoC and SoH at a first time point and the SoC at a second time point as input data of the charging time prediction model.

[0103] In an embodiment, the charging time prediction device 110 may adjust the parameters (or weight values) of the hidden layer of the charging time prediction model based on the output data of the charging time prediction model based on the current value, temperature value, SoC and SoH at the first time point and the SoC at the second time point, and the difference between the first time point and the second time point. In an embodiment, the charging time prediction device 110 may adjust the parameters (or weight values) of the hidden layer of the charging time prediction model so that the error between the output data of the charging time prediction model and the difference is a value within a specified error.

[0104] According to an embodiment, the charging time prediction device 110 may repeatedly train the charging time prediction model by using the data of the charging period. According to an embodiment, the charging time prediction device 110 may repeatedly train the charging time prediction model by using the current value, temperature value, SoC and / or SoC at each time point. For example, the charging time prediction model may be trained using the data at the first time point and the second time point of the charging period, and the charging time prediction model may be trained using the data at the third time point and the fourth time point of the charging period.

[0105] According to an embodiment, the charging time prediction device 110 may terminate the training of the charging time prediction model based on the output data of the charging time prediction model. According to an embodiment, the charging time prediction device 110 may terminate the training of the charging time prediction model when the error between the output data of the charging time prediction model and the difference between at least two time points of the charging period is within a specified error.

[0106] According to an embodiment, the charging time prediction device 110 may generate and / or train a charging time prediction model by using a machine learning model (eg, GBM or DRF).

[0107] Figure 4 is an operation flow chart of a charging time prediction device according to an embodiment. Figure 1 Components to describe Figure 4 . Figure 4 It can be understood as implementation Figure 3 FIG. 3 is a diagram of operation 310 .

[0108] exist Figure 4 The embodiments shown in the drawings may be examples, and the order of operations according to various embodiments of the present disclosure may be different from that in the drawings. Figure 4 The order shown in the Figure 4 For some operations shown in the drawings, the order of operations may be changed, or the operations may be combined.

[0109] According to an embodiment, operations 405 to 415 may be understood to be executed by the processor 115 of the charging time prediction device 110 .

[0110] Reference Figure 4 In operation 405, the charging time prediction device 110 may extract a first period in which the current value of the battery is greater than or equal to the specified current value from the specified time period. Herein, the specified current value may be 0 A. When the current value of the battery exceeds 0 A, this may indicate that the battery is charged, and when the current value of the battery is less than 0 A, this may indicate that the battery is discharged.

[0111] In operation 410, the charging time prediction apparatus 110 may extract a second period in which the driving speed of the external electronic device is a designated speed and the external electronic device is connected to the external charger from the first period extracted in operation 405. Herein, the designated speed may be 0 km / hr.

[0112] In operation 415 , the charging time prediction apparatus 110 may extract a third period by excluding a data disconnection period, a period in which a charging time is less than a designated time, and a period in which a charged amount is less than a designated charged amount from the second period extracted in operation 410 .

[0113] According to an embodiment, the second period extracted in operation 410 may include a data disconnection period. For example, a third period included in the second period and a fourth period included in the fourth period may include a data disconnection period. When the remaining period excluding the data disconnection period from the fourth period is a period less than a specified time, the charging time prediction device 110 may extract the third period excluding the fourth period as the charging period. In this article, the data disconnection period may refer to a period in which data is not acquired from the first external electronic device 120 for a specific time or more.

[0114] According to an embodiment, the charging time prediction device 110 can extract the charging period by excluding the period in which the charge amount of the battery is less than the specified charge amount based on the SoC change amount. For example, when the SoC change amount of the third period included in the second period and the fourth period in the fourth period is less than the specified change amount, the charging time prediction device 110 can extract the third period excluding the fourth period as the charging period.

[0115] According to an embodiment, in operation 420, the charging time prediction apparatus 110 may extract a charging period by excluding a period in which a current change value of the battery is greater than or equal to a specified change value from the third period extracted in operation 415. When a current change value of the battery is greater than or equal to a specified change value during battery charging, this may indicate that noise occurs in the measured current.

[0116] Figure 5 FIG. 1 is a diagram showing an interface provided to a user by a charging time prediction device according to an embodiment. Figure 1 Components to describe Figure 5 .

[0117] The charging time prediction device 110 may display the charging time prediction result through the display of the first external electronic device 120 and / or the display of the second external electronic device 130. Figure 5 The first picture 510 and / or the second picture 520.

[0118] According to an embodiment, the charging time prediction device 110 may output a first screen 510 through a display of the first external electronic device 120 or a display of the second external electronic device 130 to obtain a user input for selecting a target SoC. The first screen 510 may include an interface for guiding a user to select whether to receive a target SoC and / or a required charging time notification through a touch input. The charging time prediction device 110 may determine whether to send a target SoC and / or a required charging time notification based on a user input input through a display displaying the first screen 510.

[0119] According to an embodiment, the charging time prediction apparatus 110 may output a second screen 520 to provide the user with the predicted required charging time through a display of the first external electronic device 120 or a display of the second external electronic device 130. According to an embodiment, when the user selects to receive a required charging time notification by displaying the first screen 510, the charging time prediction apparatus 110 may output the second screen 520 at the time when battery charging of the first external electronic device 120 starts. The second screen 520 may include information on whether battery charging of the first external electronic device 120 starts, a target SoC, and a predicted required charging time.

[0120] Unless otherwise specified, the terms such as "including", "consisting of" or "having" described above may indicate that the corresponding components may be inherent, and therefore should be interpreted as also including other components without excluding other components. Unless otherwise defined, all terms including technical or scientific terms have the same meanings as those generally understood by ordinary technicians in the field to which the embodiments disclosed herein belong. Commonly used terms similar to terms defined in dictionaries should be interpreted as having the same meanings as the contextual meanings of the relevant technology, and should not be interpreted as having ideal or overly formal meanings unless they are clearly defined in this document.

Claims

1. A charging time prediction device, the charging time prediction device comprising: Communication circuits; as well as processor, The processor is configured to: receiving first battery information from an external electronic device through the communication circuit, the first battery information including a current value, a temperature value, a state of charge (SoC), and a state of health (SoH) of a battery included in the external electronic device during a specified time period; receiving, through the communication circuit, information about a driving speed of the external electronic device within the specified time period and / or information about whether the external electronic device is connected to an external charger; extracting a charging period from the designated time period based on the first battery information, the information about the driving speed, and / or the information about the connection within the designated time period; and A charging time prediction model is generated by using the current value, the temperature value, the SoC, and the SoH at a first time point of the charging period and the SoC at a second time point of the charging period.

2. The charging time prediction device according to claim 1, wherein: The processor is also configured to generate the charging time prediction model based on a machine learning model.

3. The charging time prediction device according to claim 1, wherein: The processor is further configured to: receiving second battery information from the external electronic device through the communication circuit, wherein the second battery information includes a current value, a temperature value, a SoC, and a SoH of the battery at a specified time point; as well as A required charging time from the SoC at the designated time point to a target SoC is predicted based on the charging time prediction model.

4. The charging time prediction device according to claim 1, wherein: The first battery information includes model information of the battery, and The processor is further configured to generate the charging time prediction model corresponding to the model information.

5. The charging time prediction device according to claim 1, wherein: The processor is further configured to extract at least a portion of a first period in which a current value of the battery is greater than or equal to a specified current value from the specified time period as the charging period.

6. The charging time prediction device according to claim 5, wherein: The processor is further configured to extract, from the first period, at least a portion of a second period in which a driving speed of the external electronic device is a designated speed and the external electronic device is connected to the external charger as the charging period.

7. The charging time prediction device according to claim 6, wherein: The processor is further configured to extract at least a portion of a third period as the charging period by excluding a data disconnection period, a period in which a charging time is less than a designated time, and a period in which a charged amount is less than a designated charged amount from the second period.

8. The charging time prediction device according to claim 7, wherein: The processor is further configured to extract a period as the charging period by excluding a period in which a current change value of the battery is greater than or equal to a specified change value from the third period.

9. The charging time prediction device according to claim 1, wherein: The processor is further configured to transmit the required charging time to the external electronic device through the communication circuit to provide the predicted required charging time to a user.

10. A charging time prediction method, the charging time prediction method comprising the following steps: Acquire first battery information, wherein the first battery information includes a current value, a temperature value, a state of charge (SoC), and a state of health (SoH) of a battery included in the external electronic device within a specified time period; acquiring information about a driving speed of the external electronic device and / or information about whether the external electronic device is connected to an external charger; extracting a charging period from the designated time period based on the first battery information, the information about the driving speed, and / or the information about the connection within the designated time period; as well as A charging time prediction model is generated by using the current value, the temperature value, the SoC, and the SoH at a first time point of the charging period and the SoC at a second time point of the charging period.

11. The charging time prediction method according to claim 10, wherein: The first battery information includes model information of the battery, and The step of generating the charging time prediction model includes the following steps: generating the charging time prediction model corresponding to the model information.

12. The charging time prediction method according to claim 10, wherein: The step of extracting the charging period includes the step of extracting at least a portion of a first period in which the current value of the battery is greater than or equal to a specified current value from the specified time period as the charging period.

13. The charging time prediction method according to claim 12, wherein: The step of extracting the charging period includes extracting, from the first period, at least a portion of a second period in which a driving speed of the external electronic device is a designated speed and the external electronic device is connected to the external charger as the charging period.

14. The charging time prediction method according to claim 13, wherein: The step of extracting the charging period includes the step of extracting at least a part of a third period as the charging period by excluding a data disconnection period, a period in which a charging time is less than a designated time, and a period in which a charged amount is less than a designated charged amount from the second period.

15. The charging time prediction method according to claim 14, wherein: The step of extracting the charging period includes the step of extracting a period as the charging period by excluding a period in which a current change value of the battery is greater than or equal to a specified change value from the third period.

Images