Electronic device and control method therefor

Abstract

Disclosed are an electronic device and a control method therefor. In particular, the electronic device comprises: a memory including at least one storage medium and storing instructions; and at least one processor communicatively connected to the memory. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to: identify to-be-analyzed data corresponding to a request and an algorithm used for data analysis when the request for the data analysis is received; identify a schema corresponding to the to-be-analyzed data among a plurality of schemas related to the structure of a pre-constructed database; acquire, by using the identified algorithm, an analysis result related to the to-be-analyzed data and corresponding to the schema identified from the database; and provide the analysis result.

Description

Electronic device and control method thereof

[0001] The present disclosure relates to an electronic device and a method for controlling an electronic device. More specifically, it relates to an electronic device capable of performing data analysis and providing an analysis result, and a method for controlling the same.

[0002] Recently, with the miniaturization and high integration of electronic devices and the development of artificial intelligence-related technologies, various types of services are being provided to users. For example, users can receive information about their exercise records and various analysis results related to their workout history through applications on smartphones, smartwatches, etc.

[0003] Providing various types of services to users requires a process of collecting and analyzing the data to be used for those services. However, there may be differences in the types of services, as well as differences in the data schemas and data collection methods required to provide each service.

[0004] According to conventional technology, when a service provided to a user changes, or when an algorithm applied to data analysis or a model implementing that algorithm (e.g., a neural network model) changes, the problem is currently solved by developers manually modifying the content and schema of service data for service provision, updating the application provided to the user to reflect the changes, and updating data or programs on the server to implement the service.

[0005] The above information is presented merely as background information to aid in understanding the present disclosure, and no judgment or claim is made regarding which of the above contents is applicable as prior art relating to the present disclosure.

[0006] Various aspects of the present disclosure are intended to resolve at least the aforementioned problems and / or disadvantages and to provide at least some of the advantages described below. Accordingly, one aspect of the present disclosure provides an electronic device and a method for controlling the same that can automatically reflect changes in a database in service data for service provision and provide data analysis results suitable for the provided service.

[0007] Additional aspects may be described in part of the following description, become obvious from the description, or be understood by the implementation of the presented embodiments. According to one aspect of the present disclosure, an electronic device comprises one or more storage media, a memory for storing instructions, and at least one processor connected to the memory in a communicable manner. When the instructions are executed individually or collectively by the at least one processor, the electronic device, upon receiving a request for data analysis, identifies data to be analyzed corresponding to the request and an algorithm used for the data analysis, identifies a schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a pre-established database, and, using the identified algorithm, obtains an analysis result from the database that corresponds to the identified schema and is related to the data to be analyzed, and provides the analysis result.

[0008] Meanwhile, the above request includes text information entered by a user, and when the instructions are executed individually or collectively by the at least one processor, the electronic device may identify the data to be analyzed and the algorithm used for the data analysis based on the text information.

[0009] Meanwhile, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may identify the one algorithm as the algorithm used for data analysis if the text information contains information about one of a plurality of algorithms predefined, and if the text information does not contain information about one of the plurality of algorithms, input the text information into a learned language model to obtain information about the user's intention included in the text information, and identify the algorithm used for data analysis based on the information about the user's intention.

[0010] Meanwhile, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may identify data corresponding to the request based on information regarding the user's intention.

[0011] Meanwhile, each of the above-mentioned plurality of algorithms is performed by a plurality of analysis models including a neural network, and when the above instructions are executed individually or collectively by the at least one processor, the electronic device may input information regarding the data to be analyzed and the identified schema into the analysis model corresponding to the identified algorithm among the plurality of analysis models to obtain the analysis result.

[0012] Meanwhile, the electronic device may further include a communication interface, and when the instructions are executed individually or collectively by the at least one processor, the electronic device may receive the request from a user terminal through the communication interface, and when the analysis result is obtained, provide the analysis result by controlling the communication interface to transmit the analysis result to the user terminal.

[0013] Meanwhile, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may acquire resource information related to the configuration of a user interface for displaying the analysis result on the user terminal and control the communication interface to transmit the resource information to the user terminal.

[0014] Meanwhile, the plurality of schemas correspond to at least one of the plurality of services provided through the user terminal, and when the instructions are executed individually or collectively by the at least one processor, the electronic device can update service data for the plurality of services by generating data corresponding to each of the plurality of schemas based on the changed database when a change to the database is detected.

[0015] According to one aspect of the present disclosure, a method for controlling an electronic device comprises: when a request for data analysis is received, identifying data to be analyzed corresponding to the request and an algorithm used for the data analysis; identifying a schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a previously established database; obtaining an analysis result from the database corresponding to the identified schema and related to the data to be analyzed using the identified algorithm; and providing the analysis result.

[0016] Meanwhile, the above request includes text information entered by a user, and the step of identifying the data to be analyzed and the algorithm may include the step of identifying the data to be analyzed and the algorithm used for data analysis based on the text information.

[0017] Meanwhile, the step of identifying the data to be analyzed and the algorithm may include: a step of identifying one algorithm as the algorithm used for data analysis if the text information contains information about one of a plurality of algorithms already defined; a step of inputting the text information into a learned language model to obtain information about the user's intention included in the text information if the text information does not contain information about one of the plurality of algorithms; and a step of identifying the algorithm used for data analysis based on the information about the user's intention.

[0018] Meanwhile, the step of identifying the data to be analyzed and the algorithm may include the step of identifying data corresponding to the request based on information regarding the user's intention.

[0019] Meanwhile, the plurality of algorithms are performed by a plurality of analysis models including a neural network, and the step of obtaining the analysis result may include the step of obtaining the analysis result by inputting information regarding the data to be analyzed and the identified schema into an analysis model corresponding to the identified algorithm among the plurality of analysis models.

[0020] Meanwhile, the control method of the electronic device further includes the step of receiving the request from a user terminal, and the step of providing the analysis result may include the step of transmitting the analysis result to the user terminal when the analysis result is obtained.

[0021] Meanwhile, the control method of the electronic device may further include the step of acquiring resource information related to the configuration of a user interface for displaying the analysis result on the user terminal and the step of transmitting the resource information to the user terminal.

[0022] Meanwhile, the plurality of schemas correspond to at least one of the plurality of services provided through the user terminal, and the control method of the electronic device may further include the step of updating service data for the plurality of services by generating data corresponding to each of the plurality of schemas based on the changed database when a change to the database is detected.

[0023] According to one aspect of the present disclosure, one or more non-transient computer-readable storage media are provided, comprising one or more computer execution instructions that cause an electronic device to perform a series of operations when executed individually or collectively by one or more processors. The operations include the steps of, when a request for data analysis is received, identifying data to be analyzed corresponding to the request and an algorithm used for the data analysis, identifying a schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a previously established database, obtaining an analysis result from the database related to the data to be analyzed and corresponding to the identified schema using the identified algorithm, and providing the analysis result.

[0024] Other aspects, advantages, and key features of the present disclosure will become apparent to those skilled in the art from the following detailed description, taken in conjunction with the accompanying drawings.

[0025] Other aspects, features, and advantages of one or more embodiments according to the present disclosure will become more apparent from the following detailed description, together with the accompanying drawings.

[0026] FIG. 1 is a block diagram briefly illustrating the configuration of an electronic device according to one or more embodiments of the present disclosure,

[0027] FIG. 2 is a block diagram showing the configuration of an electronic device according to one or more embodiments of the present disclosure,

[0028] FIG. 3 is a drawing for illustrating a method of providing analysis results according to one or more embodiments of the present disclosure,

[0029] FIG. 4 is a diagram illustrating a method for providing analysis results using a language model and an analysis model according to one or more embodiments of the present disclosure,

[0030] FIGS. 5 and 6 are drawings illustrating a user interface according to one or more embodiments of the present disclosure, and,

[0031] FIG. 7 is a drawing illustrating a method for controlling an electronic device according to one or more embodiments of the present disclosure.

[0032] Throughout the drawings, the same reference numeral is understood to refer to the same part, component, and structure.

[0033] The following description is provided to aid in a comprehensive understanding of the various embodiments of the present disclosure as defined by the claims and their equivalents, with reference to the attached drawings. The following description includes various specific details to aid in such understanding, but these are merely illustrative. Accordingly, those skilled in the art will recognize that various changes and modifications to the various embodiments described herein may be made without departing from the scope and spirit of the present disclosure. Furthermore, for the sake of clarity and brevity, descriptions of known functions and structures may be omitted.

[0034] The terms and words used in the following description and claims are not limited to their dictionary meanings and are used to enable the inventor to understand the present disclosure clearly and consistently. Accordingly, those skilled in the art will clearly understand that the description of various embodiments of the present disclosure below is for illustrative purposes only and is not intended to limit the present disclosure as defined by the appended claims and their equivalents.

[0035] The singular forms of "a," "an," and "the" should be understood to include the plural unless the context clearly indicates otherwise. For example, the expression "a component surface" is interpreted to include one or more such surfaces.

[0036] In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, actions, or components such as parts) and do not exclude the presence of additional features.

[0037] In the present disclosure, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0038] Expressions such as "first," "second," "first," or "second" used in this disclosure may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0039] Where it is stated that a certain component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the said certain component may be directly connected to the said other component or connected through another component (e.g., a third component).

[0040] On the other hand, when it is stated that a certain component (e.g., a first component) is "directly connected" or "directly coupled" to another component (e.g., a second component), it may be understood that no other component (e.g., a third component) exists between said certain component and said other component.

[0041] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware.

[0042] Instead, in some situations, the expression “device configured to do something” may mean that the device is “capable of doing something” together with other devices or components. For example, the phrase “processor configured (or set) to perform A, B, and C” may mean a dedicated processor for performing those operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or application processor) capable of performing those operations by executing one or more software programs stored in a memory device.

[0043] In the embodiments, a 'module' or 'part' performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module and implemented by at least one processor, except for the 'module' or 'part' that needs to be implemented in specific hardware.

[0044] Meanwhile, the various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0045] Hereinafter, embodiments according to the present disclosure are described with reference to the attached drawings so that those skilled in the art can easily implement them.

[0046] It should be understood that the blocks of each flowchart and combinations of flowcharts may be performed by one or more computer programs containing computer execution instructions. The entirety of the one or more computer programs may be stored in a single memory device, or the one or more computer programs may be divided and stored in parts in multiple different memory devices.

[0047] Any function or operation described in this specification may be processed by a single processor or a combination of multiple processors. The single processor or the combination of multiple processors is a circuit that performs processing and includes an application processor (AP, e.g., a central processing unit (CPU)), a communication processor (CP, e.g., a modem), a graphics processing unit (GPU), a neural network processing unit (NPU) (e.g., an artificial intelligence (AI) chip), a wireless LAN (Wi-Fi) chip, a Bluetooth™ chip, a Global Positioning System (GPS) chip, a Near Field Communication (NFC) chip, a connectivity chip, a sensor controller, a touch controller, a fingerprint sensor controller, a display driver integrated circuit (IC), an audio codec (CODEC) chip, a Universal Serial Bus (USB) controller, a camera controller, an image processing IC, a microprocessor unit (MPU), a system-on-chip (SoC), an integrated circuit (IC), or a similar circuit.

[0048] FIG. 1 is a block diagram briefly illustrating the configuration of an electronic device according to one or more embodiments of the present disclosure, and FIG. 2 is a block diagram illustrating the configuration of an electronic device according to one or more embodiments of the present disclosure.

[0049] Referring to FIG. 1, the electronic device (100) may include a memory (110) and a processor (120). Also, referring to FIG. 2, the electronic device (100) may further include a communication interface (130), an input interface (140), and an output interface (150). However, in carrying out the present disclosure, new configurations may be added or some configurations may be omitted in addition to the configurations shown in FIG. 1 and FIG. 2.

[0050] The ‘electronic device (100)’ according to the present disclosure refers to a device capable of performing data analysis and providing analysis results. Additionally, the electronic device (100) may provide various types of services to a user. In the present disclosure, the term ‘service’ collectively refers to functions that provide information about a user or provide various analysis results along with information about a user.

[0051] For example, the electronic device (100) may be a server for managing a database and providing analysis results and services. However, there are no special limitations on the type of electronic device (100) according to the present disclosure.

[0052] At least one instruction regarding an electronic device (100) may be stored in the memory (110). Additionally, an operating system (O / S) for operating the electronic device (100) may be stored in the memory (110). Furthermore, various software programs or applications for operating the electronic device (100) may be stored in the memory (110) according to various embodiments of the present disclosure. Additionally, the memory (110) may include semiconductor memory such as flash memory or magnetic storage media such as a hard disk.

[0053] Specifically, various software modules for operating an electronic device (100) according to various embodiments of the present disclosure may be stored in the memory (110), and the processor (120) may control the operation of the electronic device (100) by executing the various software modules stored in the memory (110). For example, the memory (110) is accessed by the processor (120), and reading, writing, modifying, deleting, updating, etc. of data by the processor (120) may be performed.

[0054] Meanwhile, in the present disclosure, the term memory (110) may be used to include memory (110), ROM, RAM, or a memory card (e.g., micro SD card, memory stick) mounted in the processor (120).

[0055] In one embodiment of the present disclosure, various types of data, such as databases, data to be analyzed, and service data, may be stored in the memory (110). Additionally, various information, such as information about algorithms, information about neural network models, information about a plurality of schemas, and resource information, may be stored in the memory (110). The definitions and types of each data / information will be described later.

[0056] In addition, various information necessary within the scope of achieving the purpose of the present disclosure may be stored in the memory (110), and the information stored in the memory (110) may be updated as it is received from an external device or input by a user.

[0057] The processor (120) controls the overall operation of the electronic device (100). Specifically, the processor (120) is connected to the configuration of the electronic device (100) including a memory (110), and can control the overall operation of the electronic device (100) by executing at least one instruction stored in the memory (110) as described above.

[0058] The processor (120) can be implemented in various ways. For example, the processor (120) can be implemented as at least one of an Application Specific Integrated Circuit (ASIC), an embedded processor, a microprocessor, hardware control logic, a hardware Finite State Machine (FSM), or a Digital Signal Processor (DSP). Meanwhile, in this disclosure, the term processor (120) may be used to include a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), and a MPU (Micro Processor Unit), etc.

[0059] In one embodiment of the present disclosure, the processor (120) can perform data analysis and provide an analysis result.

[0060] The processor (120) may receive a request for data analysis. The "request for data analysis" is a general term for a request for the analysis of data to be provided to a user, and specifically may include a request for the analysis of data contained in a database and a request for the provision of analysis results. Additionally, the request for data analysis may be a request for a change in data to be provided to a user due to a change in the application or a change in the service.

[0061] Here, 'database' refers collectively to various types of data that can be provided to users and signifies a collection of all data that can be used for data analysis. For example, a database may include data collected by multiple users using user terminals, data entered by users or developers, and statistical data regarding multiple users; it may also include data processed in various ways from the data described above.

[0062] Specifically, the processor (120) may receive a request for data analysis based on a pre-configured event generated by the electronic device (100), or may receive a request for data analysis from a user terminal. The request for data analysis received from the user terminal may be a request based on user input, or a request based on a pre-defined API (application programming interface).

[0063] Additionally, the processor (120) may receive a voice signal corresponding to a user's utterance or text information entered by the user, and identify a request for data analysis by analyzing the voice signal or text information. For example, when a voice signal corresponding to a user's utterance is received, the processor (120) may input the received voice signal into a learned voice recognition model to obtain text information corresponding to the voice signal. Then, the processor (120) may input the text information into a learned natural language understanding model to obtain a request for data analysis.

[0064] When a request for data analysis is received, the processor (120) can identify the data to be analyzed corresponding to the request for data analysis and the algorithm used for data analysis. Here, 'data to be analyzed' refers to data that is the subject of analysis, and specifically, may include data necessary for data analysis according to the request.

[0065] Specifically, the processor (120) can identify what the data to be analyzed is based on a request for data analysis, and can also identify an algorithm suitable for performing data analysis according to the request among a plurality of predefined algorithms. For example, the processor (120) can identify that the data to be analyzed is "statistics of the same age group for pedometers" and that for data analysis, Algorithm A is suitable among predefined algorithms A, B, and C.

[0066] In one embodiment of the present disclosure, when a request for data analysis includes text information entered by a user, the processor (120) can identify data to be analyzed and an algorithm used for data analysis based on the text information.

[0067] If the text information contains information about one of the multiple algorithms already defined, the processor (120) can identify that one algorithm as an algorithm used for data analysis.

[0068] On the other hand, if the text information does not include information about one of the multiple algorithms, the processor (120) can input the text information into a learned language model to obtain information about the user's intent included in the text information. Then, the processor (120) can identify the algorithm used for data analysis based on the information about the user's intent.

[0069] Meanwhile, the processor (120) inputs text information into a learned language model to obtain information about the user's intention included in the text information, and can identify data corresponding to a request for data analysis, i.e., data to be analyzed, based on information about the user's intention.

[0070] The process of identifying an algorithm used for data analysis based on text information or information about the user's intent, and the process of identifying data to be analyzed based on information about the user's intent, will be explained in more detail with reference to Fig. 4.

[0071] The processor (120) can identify a schema corresponding to the identified data among a plurality of schemas related to the structure of the database already established.

[0072] A 'schema' refers to a framework that defines the structure of data in a database and can include information regarding the logical organization and relationships of objects within the database. For example, a schema may include tables that store data in the form of rows and columns, attributes for each row and column, indexes for data retrieval, and constraints to maintain data integrity. The term 'schema' can be replaced with terms such as 'data structure' or 'data model'.

[0073] Multiple schemas may be predefined to correspond to at least one of multiple services provided through a user terminal. For example, among the multiple schemas, a first schema may correspond to a service called 'provision of user's health score,' and among the multiple schemas, a second schema may correspond to two services called 'analysis of user's sleep records' and 'provision of wake-up alarm.'

[0074] Specifically, the processor (120) can identify a schema among a plurality of schemas that includes attributes related to the data to be analyzed. For example, if the data corresponding to the request for data analysis is "user's running distance," the processor (120) can identify a schema among a plurality of schemas that corresponds to a table containing attributes related to the user's running distance.

[0075] The processor (120) can use an identified algorithm to obtain an analysis result related to the identified data corresponding to the identified schema from the database, and can provide the analysis result. Here, 'analysis result' refers to the result of an analysis performed in response to a request for data analysis, and can be obtained not only to be related to the data corresponding to the request for data analysis, but also to be related to the identified schema. For example, the analysis result may include information related to a user (user information), analysis information about other users (statistical information), information about the comparison result between the information related to the user and the analysis information about other users, etc.

[0076] Specifically, the processor (120) can identify data having an identified schema in a pre-established database and obtain an analysis result by utilizing the relationship between the data having the identified schema and the data to be analyzed. As in the example described above, if the data corresponding to the request for data analysis is "user's running distance" and the corresponding schema includes "a table containing attributes related to running distance," the processor (120) can obtain "an analysis result indicating the relationship between the user's running distance and weight loss" from the database.

[0077] In the present disclosure, the analysis results obtained using a specific analysis method may vary depending on the algorithm used for data analysis, and in cases where the algorithm is implemented using a neural network model, they may vary depending on the neural network model. Hereinafter, the neural network model implementing the identified algorithm is referred to as the "analysis model."

[0078] In one embodiment of the present disclosure, each of the plurality of algorithms may be performed by a plurality of analysis models. In this case, the processor (120) may obtain an analysis result by inputting information regarding the data to be analyzed and the identified schema into the analysis model corresponding to the algorithm identified among the plurality of analysis models. The 'analysis model' may be trained to obtain an analysis result by referring to a database when information regarding the data to be analyzed and the identified schema is input. There are no particular limitations on the types of analysis models according to the present disclosure.

[0079] Meanwhile, when a request for data analysis is received from a user terminal, the processor (120) can provide the analysis results by controlling the communication interface (130) to transmit the acquired analysis results to the user terminal.

[0080] In this case, the processor (120) can obtain resource information related to the configuration of a user interface for displaying the analysis results on a user terminal, and can control a communication interface to transmit the resource information to the user terminal.

[0081] Specifically, the processor (120) can identify whether a change to the user interface (UI) is required when displaying the analysis results on a user terminal. If it is identified that a change to the user interface is required, the processor (120) can obtain resource information related to the configuration of the user interface and control the communication interface (130) to transmit the resource information to the user terminal. However, the processor (120) may control the communication interface (130) to transmit previously stored resource information to the user terminal without performing the process of identifying whether a change to the user interface is required when displaying the analysis results on a user terminal.

[0082] Here, 'resource information' refers to information related to the configuration of the user interface, and specifically, it may indicate what information is displayed at which location within the user interface to provide each service. For example, resource information may include information regarding text resources, image resources, audio resources, video resources, the layout of the user interface, the style of the user interface, etc., that can be provided through the user interface. The term 'resource information' may be replaced with terms such as 'resource file'.

[0083] For example, when a request for data analysis is received while a first user interface is displayed on a user terminal, the processor (120) can identify whether a change to the user interface is required when displaying the analysis result on the user terminal by comparing first resource information corresponding to the first user interface and second resource information corresponding to the second user interface for providing the analysis result. If there is a difference between the first resource information and the second resource information, the processor (120) can provide the second resource information along with the analysis result.

[0084] The communication interface (130) includes a circuit and can perform communication with an external device. Specifically, the processor (120) can receive various data or information from an external device connected through the communication interface (130) and can also transmit various data or information to the external device.

[0085] The communication interface (130) may include at least one of a WiFi module, a Bluetooth module, a wireless communication module, an NFC module, and an Ultra-Wide Band (UWB) module. Specifically, the WiFi module and the Bluetooth module can each perform communication using the WiFi method and the Bluetooth method. When using the WiFi module or the Bluetooth module, various connection information such as SSID is first transmitted and received, and then various information can be transmitted and received after establishing a communication connection using this information.

[0086] In addition, the wireless communication module can perform communication according to various communication standards such as IEEE, Zigbee, 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), and 5G (5th Generation). Furthermore, the NFC module can perform communication using the NFC (Near Field Communication) method, which utilizes the 13.56 MHz band among various RF-ID frequency bands such as 135 kHz, 13.56 MHz, 433 MHz, 860~960 MHz, and 2.45 GHz. Additionally, the UWB module can accurately measure the Time of Arrival (ToA), which is the time it takes for a pulse to reach a target, and the Angle of Arrival (AoA), which is the angle of arrival of the pulse at the transmitting device, through communication between UWB antennas. Accordingly, precise distance and location recognition within an error range of tens of centimeters indoors is possible.

[0087] In one embodiment of the present disclosure, the processor (120) may receive a request from a user terminal through a communication interface (130). When an analysis result is obtained, the processor (120) may control the communication interface (130) to transmit the analysis result to the user terminal.

[0088] In one embodiment of the present disclosure, when the processor (120) identifies that a change to the user interface is required when displaying the analysis results on the user terminal, it can control the communication interface (130) to transmit resource information related to the configuration of the user interface to the user terminal.

[0089] The processor (120) can control the communication interface (130) to transmit user information or data analysis requests to an external device that stores a database, and can receive user information or data analysis results from the external device through the communication interface (130).

[0090] The processor (120) can control the communication interface (130) to transmit text information to an external device that stores a language model, and can receive information about the user's intention corresponding to the text information from the external device through the communication interface (130).

[0091] The processor (120) can control the communication interface (130) to send a request for an analysis result to an external device that stores an analysis model, and can receive the analysis result from the external device through the communication interface (130).

[0092] Various embodiments implemented by the processor (120) transmitting and receiving various requests, responses, information, etc. to and from a user terminal and an external device using a communication interface (130) will be described in detail with reference to FIGS. 3 and 4.

[0093] The input interface (140) includes a circuit, and the processor (120) can receive user commands to control the operation of the electronic device (100) through the input interface (140). Specifically, the input interface (140) may be composed of components such as a microphone, a camera, and a remote control signal receiver. Additionally, the input interface (140) may be implemented in a form included in a display as a touch screen. In particular, the microphone can receive a voice signal and convert the received voice signal into an electrical signal.

[0094] In one embodiment of the present disclosure, the processor (120) may receive user input corresponding to a request for data analysis through an input interface (140). Additionally, the processor (120) may receive user input requesting the initiation of an operation of various embodiments according to the present disclosure through the input interface (140).

[0095] The output interface (150) includes a circuit, and the processor (120) can output various functions that the electronic device (100) can perform through the output interface (150). Also, the output interface (150) may include at least one of a display, a speaker, and an indicator.

[0096] The display can output image data under the control of the processor (120). Specifically, the display can output an image stored in the memory (110) under the control of the processor (120). In particular, the display according to one or more embodiments of the present disclosure may display a user interface stored in the memory (110). The display may be implemented as an LCD (Liquid Crystal Display Panel), OLED (Organic Light Emitting Diodes), etc., and the display may also be implemented as a flexible display, a transparent display, etc. depending on the case. However, the display according to the present disclosure is not limited to a specific type.

[0097] The speaker can output audio data under the control of the processor (120). The indicator can be lit under the control of the processor (120). Specifically, the indicator can be lit in various colors under the control of the processor (120). For example, the indicator can be implemented using LEDs (Light Emitting Diodes), LCDs (Liquid Crystal Display Panels), VFDs (Vacuum Fluorescent Displays), etc., but is not limited thereto.

[0098] In one embodiment of the present disclosure, the processor (120) can output the data to be analyzed, the identification result of the algorithm and schema, and the analysis result related to the data to be analyzed through the output interface (150).

[0099] According to the embodiments of the present disclosure described above with reference to FIGS. 1 and FIGS. 2, the electronic device (100) dynamically identifies data to be analyzed and an algorithm to be used for data analysis in response to a request for data analysis, and automatically reflects the analysis results obtained based on the identified data to be analyzed and the algorithm to be provided to the user.

[0100] In particular, even if the service to be provided to the user is changed, the data analysis algorithm or model is changed, the database is changed, or the data analysis result is changed, the electronic device (100) can automatically identify the analysis target data, algorithm, and schema corresponding to the changed service, and obtain the analysis result accordingly to provide the service.

[0101] Additionally, the electronic device (100) can perform data analysis and provide analysis results while minimizing changes to the application provided to the user and changes to the program for providing services, depending on the difference in the format and collection method of data between services.

[0102] FIG. 3 is a drawing for explaining a method of providing analysis results according to one or more embodiments of the present disclosure.

[0103] In FIG. 3, a health app (app, application) for a user is executed by a user terminal (200), and an analysis result based on data analysis is provided through the health app. A method for providing an analysis result according to the present disclosure is described.

[0104] In FIG. 3, 'health app data' collectively refers to data for running a health app on a user terminal (200), and 'service data' collectively refers to data stored in an electronic device (100) as data in a format defined to provide a plurality of services related to analysis results to the user.

[0105] In the present disclosure, 'external device' refers to a device that stores and manages a database. Service data and the database may be stored and managed by an electronic device (100) which is a single device, but in FIG. 3 and the description of FIG. 3, an embodiment is described in which service data is stored and managed by the electronic device (100) and the database is stored and managed by an external device (300).

[0106] An electronic device (100) may receive a request for data analysis, and such request may be received sequentially according to a plurality of APIs as illustrated in FIG. 3. For example, in FIG. 3, a plurality of APIs (application programming interfaces), referred to as the first API to the fourth API, refer to APIs that are pre-configured to correspond to a request for data analysis. In FIG. 3, the response may include an analysis result and information for displaying the analysis result on an app screen, as a response to the API. The first to fourth responses in FIG. 3 each refer to a response corresponding to the first API to the second API.

[0107] Referring to FIG. 3, the electronic device (100) can receive a first API from a user terminal (200) (S310). For example, the first API may include a request for information to be displayed on the app (application) screen of the user terminal (200).

[0108] When the first API is received, the electronic device (100) can transmit a first response to the user terminal (200) (S315). For example, if the first API is an API requesting information to be displayed at the top of the app screen of the user terminal (200), the first response may indicate that the information to be displayed at the top of the app screen of the user terminal (200) is information about a "bicycle".

[0109] After transmitting the first response, the electronic device (100) may receive a second API from the user terminal (200) (S320). For example, the second API may include a request for resource information regarding a bicycle. As described above, 'resource information' refers to information related to the configuration of the user interface, and specifically, may indicate what information is displayed at a specific location in the user interface for providing information about the bicycle.

[0110] When the second API is received, the electronic device (100) can transmit a second response to the user terminal (200) (S325). For example, the second response may include information indicating that the type of the user interface is 'bicycle', information indicating that the display range of the information is 'last week', and resource information for providing information about the bicycle.

[0111] After transmitting the second response, the electronic device (100) may receive a third API from the user terminal (200) (S330). For example, the third API may include a request for user information regarding a bicycle. Specifically, the third API may include a request for information regarding the history of the user of the user terminal (200) using the bicycle.

[0112] When the third API is received, the electronic device (100) can transmit the fourth API to the external device (300) (S335). For example, the fourth API may include user identification information (e.g., user ID) and period information (e.g., the second week of September) of the user terminal (200).

[0113] After transmitting the fourth API, the electronic device (100) may receive a fourth response from an external device (300) (S340). Then, when the fourth response is received, the electronic device (100) may transmit the fourth response to a user terminal (200) (S345). For example, the fourth response may include information that the driving distance of the user of the user terminal (200) in the second week of September is 5 km and information that the driving time is 60 minutes. If resource information is not transmitted to the user terminal (200) according to the second API and the second response, the fifth response may include resource information related to providing the information included in the fourth response.

[0114] After transmitting the fourth response, the electronic device (100) may receive a fifth API from the user terminal (200) (S350). For example, the fifth API may include a request for data analysis regarding a bicycle. Specifically, the fifth API may include a request for data analysis regarding statistical information, such as bicycle riding records of other users having the same age group and gender as the user.

[0115] Although not illustrated in FIG. 3, as described with reference to FIG. 1, when a data analysis request is received as the fifth API is received, the electronic device (100) can identify the data to be analyzed corresponding to the data analysis request and the algorithm used for data analysis, and can identify the schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of the database already established.

[0116] When the data, algorithm, and schema to be analyzed are identified, the electronic device (100) can transmit the 6th API to an external device (300) (S355). Specifically, the 6th API may include a request for data analysis regarding a bicycle, and may include a request for data analysis regarding statistical information, such as bicycle riding records of other users having the same age group and gender as the user. Additionally, the 6th API may include information regarding at least one of the identified data to be analyzed, the identified algorithm, and the identified schema.

[0117] In addition, the 6th API may include metadata for referencing a database. Here, 'metadata' may include information on which data included in the database will be referenced to obtain an analysis result. For example, the 6th API may include identification information of the user of the user terminal (200) (e.g., user ID), period information (e.g., second week of September), information on bicycle riding records of other users who have the same age group and gender as the user, information on the comparison results of riding records between the user and other users, etc.

[0118] After transmitting the 6th API, the electronic device (100) may receive a 5th response from an external device (300) (S360). When the 5th response is received, the electronic device (100) may transmit the 5th response to a user terminal (200) (S365). For example, the 5th response may include analysis results regarding a bicycle. Specifically, the 5th response may include information that the average driving distance of other users having the same age group and gender as the user is 5.6 km, information that the average driving time of other users is 63 minutes, information that the average heart rate of other users during driving is 150, and information regarding the comparison results of driving records between the user of the user terminal (200) and other users.

[0119] Meanwhile, the database may be continuously updated, and accordingly, analysis results related to the same target data may also change. Furthermore, if the analysis results change, the service data used to provide those results may also change.

[0120] Changes in analysis results and service data resulting from database updates may be performed manually by a data scientist or system administrator, but may also be performed automatically by an electronic device (100) and / or an external device (300) according to the present disclosure. Embodiments performed by the electronic device (100) will be described below.

[0121] In one embodiment of the present disclosure, an electronic device (100) can detect a change to a database (S3010). Specifically, the electronic device (100) can detect a change to a database by monitoring the database at preset intervals or by transmitting a request for monitoring to an external device (300). Here, the change to the database may include the addition, deletion, and exchange of data.

[0122] When a change to the database is detected, the electronic device (100) can update service data for multiple services (S3020). Specifically, the electronic device (100) can obtain an analysis result having a schema corresponding to multiple services based on the changed database. Then, the electronic device (100) can update service data based on the analysis result.

[0123] For example, the database may be managed in a schema-less structure that does not use a fixed schema when storing data, and the electronic device (100) may generate service data corresponding to each of a plurality of schemas by referring to a table defining the schema even when the database is changed, and may store the generated service data.

[0124] And, when one of the services is changed, the electronic device (100) can dynamically identify the schema corresponding to the changed service among the schemas and provide a service related to the analysis result using service data generated to correspond to the identified schema.

[0125] According to the embodiment of the present disclosure described above, resource information, which is information related to the configuration of a user interface, is not stored in the user terminal (200), and the electronic device (100) can transmit resource information, which is information related to the configuration of a user interface, to the user terminal (200) along with analysis results for the changed service even if the service to be provided to the user is changed.

[0126] In addition, the electronic device (100) can dynamically detect changes in the database even when the database is changed, and can automatically and effectively reflect the changes in the database in the service data.

[0127] Accordingly, the electronic device (100) can automatically reflect changes in the database in the service data for service provision without the need for a developer to manually change the content and schema of the service data for service provision, update the application provided to the user to reflect the changes, or update the data or program for implementing the service on the server, even if the database is changed, thereby enabling the provision of data analysis results suitable for the provided service.

[0128] For example, if information about a "pedometer" is provided at the top of the screen of a health app, and the information to be provided at the top of the screen of the health app is changed to information about a "bicycle" by a user or service provider, the electronic device (100) can provide an analysis result related to the data to be analyzed by linking the analysis result having a schema for providing information about a bicycle to an API.

[0129] FIG. 4 is a diagram illustrating a method of providing analysis results using a language model (1000) and an analysis model (2000) according to one or more embodiments of the present disclosure.

[0130] As illustrated in FIG. 4, the electronic device (100) may receive a request for data analysis, and the request for data analysis may include text information (S410). Here, the text information may be text information entered by a user, or text information obtained based on the user's voice.

[0131] For example, if text information is obtained based on a user's voice, the electronic device (100) may obtain the user's voice and input the user's voice into a voice recognition model to obtain text information corresponding to the user's voice. Additionally, the voice recognition process may be performed by a user terminal (200), and the electronic device (100) may receive text information corresponding to the user's voice from the user terminal (200).

[0132] If the text information includes information about the algorithm (S420-Y), the electronic device (100) can identify the data to be analyzed and the algorithm used for data analysis based on the text information (S450, S460).

[0133] Specifically, if the text information includes information about one of a plurality of algorithms that are already defined, the electronic device (100) can identify that one algorithm as an algorithm used for data analysis. For example, if the text information is "Calculate my health score using algorithm A," the electronic device (100) can identify algorithm A as an algorithm used for data analysis.

[0134] If the text information does not contain information about the algorithm (S420-N), the electronic device (100) inputs the text information into the language model (1000) (S430) to obtain information about the user's intention (S440).

[0135] The 'language model (1000)' performs natural language processing on input text information to understand the context and structure of the input text information and to obtain information about the user's intent corresponding to the text information. Specifically, the language model (1000) can obtain information about the user's intent by dividing the text information input by the user into multiple words or tokens, which are units smaller than words, converting each token into an embedding vector, and classifying the embedding vector into multiple predefined intent categories.

[0136] For example, the language model (1000) may be a large language model (LLM) that learns a vast amount of text data to perform natural language understanding and generation, or it may be a neural network model trained to identify algorithms and / or data to be analyzed corresponding to input text information. There are no particular limitations on the type of language model (1000) according to the present disclosure.

[0137] Specifically, if the text information does not include information about one of the multiple algorithms, the electronic device (100) can input the text information into a learned language model (1000) to obtain information about the user's intention included in the text information.

[0138] When information about the user's intention is obtained, the data to be analyzed and the algorithm used for data analysis can be identified based on the information about the user's intention (S450, S460).

[0139] In one embodiment of the present disclosure, the electronic device (100) can identify data to be analyzed based on information regarding the user's intention (S450). For example, if the text information is "Calculate my health score using algorithm A," the electronic device (100) can identify at least some of the data regarding the user's step count, exercise records, sleep time, food consumed, weight, body composition, heart rate, etc. as data to be analyzed. Here, the user's step count, exercise records, sleep time, food consumed, weight, body composition, heart rate, etc. may be data set to be related to the health score or set to be related to a health-related application.

[0140] In another example, if the text information is "calculate my health score without considering the 5 days of sleep records," the electronic device (100) inputs the text information into a learned language model (1000) and can identify at least some of the remaining data, excluding the data on sleep time over the past 5 days, among the data related to the health score of the example described above as data to be analyzed.

[0141] In one embodiment of the present disclosure, the electronic device (100) can identify an algorithm used for data analysis based on information regarding the user's intention (S460). For example, if the text information is "Calculate my health score in the modern way," the electronic device (100) inputs the text information into a learned language model (1000) and can identify Algorithm C, which is the most recent algorithm among a plurality of algorithms available to the electronic device (100), as the algorithm used for data analysis.

[0142] Meanwhile, the electronic device (100) can obtain an analysis result by inputting a request for an analysis result to the analysis model (2000) (S470) (S480). Then, when the analysis result is obtained, the electronic device (100) can provide the analysis result to the user terminal (200) (S490).

[0143] Specifically, the electronic device (100) can identify an analysis model (2000) corresponding to an identified algorithm among a plurality of analysis models (2000), and can input a request for an analysis result to the identified analysis model (2000). For example, the request for an analysis result may include information about a request for data analysis, identified data to be analyzed, and identified algorithm. Although not shown in FIG. 4, the request for an analysis result may also include information about an identified schema.

[0144] Meanwhile, the language model (1000) and the analysis model (2000) of FIG. 4 may be models stored in the electronic device (100) or models stored in at least one external device. For example, the language model (1000) may be stored in a first external device and the analysis model (2000) may be stored in a second external device. In this case, the electronic device (100) may transmit text information to the first external device and receive information regarding the user's intention from the first external device. Additionally, the electronic device (100) may transmit a request for an analysis result to the second external device and receive an analysis result from the second external device.

[0145] Meanwhile, FIG. 4 illustrates an exemplary case where the language model (1000) and the analysis model (2000) are implemented as separate neural network models, but the present disclosure is not limited thereto. In particular, when the language model (1000) is a large-scale language model (LLM), the language model (1000) and the analysis model (2000) may be implemented as a single integrated neural network model to perform both the operation of obtaining information about the user's intention corresponding to text information and the operation of obtaining an analysis result based on information about the data and schema to be analyzed.

[0146] According to the embodiments described above with reference to FIG. 4, the electronic device (100) can dynamically identify data and algorithms to be analyzed using a language model (1000), and can obtain analysis results using an analysis model (2000) corresponding to the identified algorithm.

[0147] In particular, in the past, when a database was changed, the process of reflecting it in the service data was performed manually by a developer or manager, which had the limitation of being difficult to link with a neural network model. However, the electronic device (100) according to the present disclosure automatically detects changes in the database and reflects them in the service data, so that a neural network model that matches the method desired by the user can be pluggably utilized to provide analysis results.

[0148] FIGS. 5 and FIGS. 6 are drawings illustrating a user interface according to one or more embodiments of the present disclosure.

[0149] FIG. 5 shows a user interface that displays information about a "pedometer" at the top of an app screen called "ABC Health". As illustrated in FIG. 5, the information displayed on the app screen may include information about the user. As illustrated in area (510) of FIG. 5, the information about the pedometer may include information that the user's step count today is 732, information that the user's target step count is 6,000, and information that the goal achievement rate is 12%.

[0150] FIG. 6 shows a user interface that displays information about "running" at the top of an app screen called "ABC Health". As illustrated in FIG. 6, the information displayed on the app screen may include analysis results along with information about the user.

[0151] As shown in the area (610) of FIG. 6, information about running may include information that the user's running distance today is 4.08 km, information that the running time is 23 minutes, information that the pace in km is 5 minutes 38 seconds, and information that the calories burned is 222 kcal.

[0152] Additionally, as illustrated in the area (620) of FIG. 6, information about running may include statistical information about the running records of other users who have the same gender (female) and age group (30s) as the user. For example, information about running may include information that the average pace of other users is 8 minutes and 20 seconds, information that the heart rate of other users is 92 bpm, and information that the total calories burned by other users is 682 kcal.

[0153] Furthermore, although not illustrated in FIG. 6, information regarding running may include various types of analysis results, such as the results of comparing the running records of the user with those of other users, and information on the readjustment of goals based on the comparison results.

[0154] In one embodiment of the present disclosure, the electronic device (100) can identify whether a change to the user interface (UI) is required when displaying the analysis results on a user terminal. And, if it is identified that a change to the user interface is required, the electronic device (100) can obtain resource information related to the configuration of the user interface and transmit the resource information to the user terminal.

[0155] For example, when a request for data analysis is received while a first user interface (e.g., the user interface of FIG. 5) is displayed on a user terminal, the electronic device (100) can identify whether a change to the user interface is required when displaying the analysis results on the user terminal by comparing first resource information corresponding to the first user interface with second resource information corresponding to a second user interface (e.g., the user interface of FIG. 6) for providing analysis results. If there is a difference between the first resource information and the second resource information, the electronic device (100) can transmit the second resource information to the user terminal.

[0156] According to the embodiments described above with reference to FIG. 5, even if the service to be provided to the user changes, such as when providing information about a "pedometer" as in FIG. 5 and then providing information about "running" as in FIG. 5, the electronic device (100) can transmit resource information, which is information related to the configuration of the user interface, along with the analysis result for the changed service, to the user terminal.

[0157] Accordingly, the electronic device (100) updates the application provided to the user despite changes in the service, and is able to provide a suitable service to the user without the need to update data or programs for implementing the service on the server.

[0158] FIG. 7 is a drawing showing a method for controlling an electronic device (100) according to one or more embodiments of the present disclosure.

[0159] The electronic device (100) may receive a request for data analysis (S710). Specifically, the electronic device (100) may receive a request for data analysis based on a pre-configured event that occurred in the electronic device (100), or it may receive a request for data analysis from a user terminal. A request for data analysis received from a user terminal may be a request based on user input, or it may be a request based on a pre-defined API (application programming interface).

[0160] The electronic device (100) can identify the data to be analyzed corresponding to the request for data analysis and the algorithm used for data analysis (S720).

[0161] Specifically, the electronic device (100) can identify what the data to be analyzed is based on a request for data analysis, and can also identify an algorithm suitable for performing data analysis according to the request among a plurality of predefined algorithms.

[0162] In one embodiment of the present disclosure, when a request for data analysis includes text information entered by a user, the electronic device (100) can identify data to be analyzed and an algorithm used for data analysis based on the text information.

[0163] Meanwhile, the electronic device (100) inputs text information into a learned language model to obtain information about the user's intention included in the text information, and can identify data corresponding to a request for data analysis, i.e., data to be analyzed, based on the information about the user's intention.

[0164] The electronic device (100) can identify a schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a pre-established database (S730). Specifically, the electronic device (100) can identify a schema containing attributes related to the data to be analyzed among a plurality of schemas.

[0165] The electronic device (100) can obtain an analysis result related to the data to be analyzed that corresponds to the schema identified from the database using an identified algorithm (S740). And, the electronic device (100) can provide the analysis result (S750).

[0166] Specifically, the electronic device (100) can identify data having a schema identified in a database and obtain an analysis result by using the relationship between the data having the identified schema and the data to be analyzed.

[0167] In the present disclosure, the type of analysis result obtained using a specific analysis method may vary depending on the algorithm used for data analysis, and in cases where the algorithm is implemented using a neural network model, it may vary depending on the neural network model, i.e., the analysis model.

[0168] Specifically, the electronic device (100) can obtain an analysis result by inputting information regarding the data to be analyzed and the identified schema into an analysis model corresponding to an algorithm identified among a plurality of analysis models. When information regarding the data to be analyzed and the identified schema is input, the 'analysis model' can be trained to obtain an analysis result by referring to a database. There are no particular limitations on the types of analysis models according to the present disclosure.

[0169] Meanwhile, the control method of the electronic device (100) according to the above-described embodiment may be implemented as a program and provided to the electronic device (100). In particular, the program including the control method of the electronic device (100) may be stored and provided on a non-transitory computer-readable medium.

[0170] Specifically, in a non-transient computer-readable recording medium comprising a program for executing a control method of an electronic device (100), the control method of the electronic device (100) may include the steps of: when a request for data analysis is received, identifying data to be analyzed corresponding to the request and an algorithm used for data analysis; identifying a schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a database that has been established; obtaining an analysis result related to the data to be analyzed corresponding to the identified schema from the database using the identified algorithm; and providing the analysis result.

[0171] Although a method for controlling an electronic device (100) and a computer-readable recording medium including a program for executing the method for controlling the electronic device (100) have been briefly described above, this is merely to avoid redundant descriptions, and it is obvious that various embodiments of the electronic device (100) can also be applied to a method for controlling the electronic device (100) and a computer-readable recording medium including a program for executing the method for controlling the electronic device (100).

[0172] The artificial intelligence-related function according to the present disclosure is operated through the processor (120) and memory (110) of the electronic device (100).

[0173] The processor (120) may be composed of one or more processors (120). In this case, the one or more processors (120) may include at least one of a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), and an NPU (Neural Processing Unit), but are not limited to the examples of the processor (120) described above.

[0174] The CPU is a general-purpose processor (120) capable of performing not only general operations but also artificial intelligence operations, and can efficiently execute complex programs through a multi-layer cache structure. The CPU is advantageous for a serial processing method that enables organic linkage between previous and next calculation results through sequential calculations. The general-purpose processor (120) is not limited to the examples described above, except for cases where it is specified as the CPU described above.

[0175] A GPU is a processor (120) for large-scale computations, such as floating-point operations used in graphics processing, and can perform large-scale computations in parallel by integrating a large number of cores. In particular, a GPU may be advantageous for parallel processing methods such as convolution operations compared to a CPU. Additionally, a GPU can be used as a co-processor (120) to complement the functions of a CPU. The processor (120) for large-scale computation is not limited to the examples described above, except for cases where it is specified as the aforementioned GPU.

[0176] The NPU is a processor (120) specialized for artificial intelligence computation using an artificial neural network, and each layer constituting the artificial neural network can be implemented in hardware (e.g., silicon). At this time, since the NPU is designed to be specialized according to the specifications required by the company, it has a lower degree of freedom compared to a CPU or GPU, but it can efficiently process the artificial intelligence computation required by the company. Meanwhile, as a processor (120) specialized for artificial intelligence computation, the NPU can be implemented in various forms such as a TPU (Tensor Processing Unit), an IPU (Intelligence Processing Unit), a VPU (Vision Processing Unit), etc. The artificial intelligence processor (120) is not limited to the examples described above, except for cases specified as the aforementioned NPU.

[0177] Additionally, one or more processors (120) may be implemented as a System on Chip (SoC). In this case, the SoC may further include, in addition to one or more processors (120), a memory (110) and a network interface such as a bus for data communication between the processor (120) and the memory (110).

[0178] When a plurality of processors (120) are included in a System on Chip (SoC) included in an electronic device (100), the electronic device (100) can perform operations related to artificial intelligence (e.g., operations related to learning or inference of an artificial intelligence model) by using some of the processors (120) among the plurality of processors (120). For example, the electronic device (100) can perform operations related to artificial intelligence by using at least one of a GPU, NPU, VPU, TPU, or hardware accelerator specialized for artificial intelligence operations such as convolution operations or matrix multiplication operations among the plurality of processors (120). However, this is merely one embodiment, and it is obvious that operations related to artificial intelligence can be processed using a CPU or a general-purpose processor (120).

[0179] Additionally, the electronic device (100) can perform operations related to artificial intelligence functions using multi-cores (e.g., dual cores, quad cores, etc.) included in a single processor (120). In particular, the electronic device (100) can perform artificial intelligence operations such as convolution operations and matrix multiplication operations in parallel using multi-cores included in the processor (120).

[0180] One or more processors (120) control input data to be processed according to predefined operation rules or artificial intelligence models stored in memory (110). The predefined operation rules or artificial intelligence models are characterized by being created through learning.

[0181] Here, being created through learning means that a predefined rule of operation or an artificial intelligence model of desired characteristics is created by applying a learning algorithm to a number of learning data. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server / system.

[0182] An artificial intelligence model may be composed of multiple neural network layers. At least one layer has at least one weight value and performs the layer's operation through the result of the operation of the previous layer and at least one defined operation. Examples of neural networks include CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), Deep Q-Networks, and Transformers; however, the neural networks in this disclosure are not limited to the aforementioned examples except where specified.

[0183] A learning algorithm is a method of training a specific target device (e.g., a robot) using a number of learning data to enable the target device to make decisions or predictions on its own. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithms in this disclosure are not limited to the aforementioned examples except where specified.

[0184] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory storage medium' simply means that it is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily. For example, a 'non-transitory storage medium' may include a buffer in which data is stored temporarily.

[0185] According to one or more embodiments, the method according to the various embodiments disclosed herein may be provided by being included 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 device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or an application store (e.g., Play Store). TM It can be distributed online (e.g., downloaded or uploaded) through ) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., downloadable app) may be temporarily stored or temporarily created in a device-readable storage medium such as the memory (110) of the manufacturer's server, the application store's server, or the relay server.

[0186] Each component (e.g., module or program) according to the various embodiments of the present disclosure as described above may be composed of a single or multiple entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be further included in the various embodiments. Generally or additionally, some components (e.g., module or program) may be integrated into a single entity to perform the same or similar functions as those performed by each of the respective components prior to integration.

[0187] Operations performed by a module, program, or other component according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

[0188] Meanwhile, the terms “part” or “module” as used in this disclosure include a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A “part” or “module” may be a component formed integrally, or a minimum unit or part thereof that performs one or more functions. For example, a module may be composed of an application-specific integrated circuit (ASIC).

[0189] Various embodiments of the present disclosure may be implemented as software comprising instructions stored on a machine-readable storage medium (e.g., a computer). The machine may include an electronic device (e.g., an electronic device (100)) according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage medium and operating according to the called instructions.

[0190] When the above instruction is executed by a processor, the processor may perform the function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or an interpreter.

[0191] It will be understood that various embodiments of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software, in accordance with the claims and the specification.

[0192] Such software may be stored on a non-transient computer-readable storage medium. The non-transient computer-readable storage medium stores one or more computer programs (software modules), and the one or more computer programs include computer execution instructions that enable the method of the present disclosure to be performed when executed by a processor of one or more electronic devices.

[0193] Such software may be stored in the form of a storage device, for example, read-only memory (ROM), regardless of whether it is erasable or rewritable; in the form of memory, for example, random access memory (RAM), memory chips, devices, or integrated circuits (IC); or in the form of an optically or magnetically readable medium, for example, a compact disc (CD), a digital video disc (DVD), a magnetic disc, a magnetic tape, etc. It will be understood that the storage device and storage medium are various embodiments of a non-transient machine-readable storage device suitable for storing one or more computer programs containing instructions that implement the various embodiments of the present disclosure at execution. Accordingly, the various embodiments of the present disclosure provide a program containing code for implementing an apparatus or method according to any one of the claims of this specification, and a non-transient machine-readable storage medium storing such a program.

[0194] Although the present disclosure has been described and illustrated with reference to various embodiments, those skilled in the art will understand that various changes in form or detail are possible without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents.

Claims

1. In an electronic device, Memory comprising one or more storage media and storing instructions; and At least one processor connected to communicate with the memory; comprising, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, upon receiving a request for data analysis, identifies the data to be analyzed corresponding to the request and the algorithm used for the data analysis. Identify the schema corresponding to the data to be analyzed among multiple schemas related to the structure of the established database, and Using the above-mentioned identified algorithm, an analysis result is obtained from the above-mentioned database that corresponds to the above-mentioned identified schema and relates to the data to be analyzed, and An electronic device that provides the above analysis results.

2. In Paragraph 1, The above request includes text information entered by the user, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that identifies the data to be analyzed and the algorithm used for the analysis of the data based on the text information above.

3. In Paragraph 2, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, If the text information above includes information about one of a plurality of algorithms previously defined, the one algorithm is identified as the algorithm used for the data analysis, and If the text information above does not include information about one of the plurality of algorithms, the text information is input into a learned language model to obtain information about the user's intention included in the text information, and An electronic device that identifies the algorithm used for data analysis based on information regarding the user's intention.

4. In Paragraph 3, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that identifies data corresponding to the request based on information regarding the user's intention.

5. In Paragraph 1, Each of the above plurality of algorithms is performed by a plurality of analysis models including a neural network, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that inputs information regarding the data to be analyzed and the identified schema into an analysis model corresponding to the identified algorithm among the plurality of analysis models to obtain the analysis result.

6. In Paragraph 1, In addition to a communication interface; and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Receiving the request from a user terminal through the communication interface above, and An electronic device that provides the analysis result by controlling the communication interface to transmit the analysis result to the user terminal when the analysis result is obtained.

7. In Paragraph 6, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Resource information related to the configuration of a user interface for displaying the above analysis results on the user terminal is obtained, An electronic device that controls the communication interface to transmit the above resource information to the user terminal.

8. In Paragraph 7, The above plurality of schemas correspond to at least one of the plurality of services provided through the user terminal, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that updates service data for the plurality of services by generating data corresponding to each of the plurality of schemas based on the changed database when a change to the database is detected.

9. In a method for controlling an electronic device, When a request for data analysis is received, a step of identifying the data to be analyzed corresponding to the request and the algorithm used for the data analysis; A step of identifying the schema corresponding to the data to be analyzed among a plurality of schemas related to the structure of a previously established database; A step of obtaining an analysis result from the database corresponding to the identified schema and related to the data to be analyzed, using the identified algorithm; and A method comprising the step of providing the above analysis results.

10. In Paragraph 9, The above request includes text information entered by the user, and The step of identifying the data to be analyzed and the algorithm is, A method comprising the step of identifying the data to be analyzed and the algorithm used for the analysis of the data based on the text information above.

11. In Paragraph 10, The step of identifying the data to be analyzed and the algorithm is, If the text information above includes information about one of a plurality of algorithms previously defined, a step of identifying said one algorithm as an algorithm used for said data analysis; If the text information does not include information about one of the plurality of algorithms, input the text information into a learned language model to obtain information about the user's intention included in the text information; and A method comprising the step of identifying the algorithm used for data analysis based on information regarding the user's intention.

12. In Paragraph 11, The step of identifying the data to be analyzed and the algorithm is, A method comprising the step of identifying data corresponding to the request based on information regarding the user's intention.

13. In Paragraph 9, The above plurality of algorithms are performed by a plurality of analysis models including neural networks, and The step of obtaining the above analysis results is, A method comprising the step of obtaining the analysis result by inputting information regarding the data to be analyzed and the identified schema into an analysis model corresponding to the identified algorithm among the plurality of analysis models.

14. In Paragraph 9, The step of receiving the above request from a user terminal; further comprising The step of providing the above analysis results is, A method comprising the step of transmitting the analysis result to the user terminal when the analysis result is obtained.

15. In Paragraph 14, A step of obtaining resource information related to the configuration of a user interface for displaying the above analysis results on the user terminal; and A method further comprising the step of transmitting the above resource information to the user terminal.

Images