Electronic device for generating configuration and design information about system corresponding to technical idea and operating method thereof

Abstract

This electronic device for generating configuration and design information about a system corresponding to a technical idea comprises: a communication interface for performing a communication connection with an external apparatus or an external server; a memory for storing a first language model for outputting a vector value corresponding to text data when the text data corresponding to a user input is input; and a processor connected to the memory and generating the configuration and design information about the system corresponding to the technical idea on the basis of data corresponding to the user input by executing at least one instruction. The processor may: identify text data corresponding to user input data when the user input data is acquired; acquire first metadata on the basis of the vector value output by inputting the text data to the language model; transmit the first metadata to the external server via the communication interface so that the first metadata is input to a second language model stored in the external server; identify the system corresponding to the technical idea on the basis of second metadata corresponding to an output vector value of the second language model received from the external server; identify a technical configuration corresponding to the identified system and a connection relationship between respective technical configurations; and acquire configuration information about the system on the basis of the technical configuration and the connection relationship.

Description

Electronic device for generating configuration and design information of a system corresponding to a technical idea and a method of operation thereof

[0001] The present disclosure relates to an electronic device for generating configuration and design information of a system corresponding to a technical idea and a method of operating the same, and more specifically, to a device for providing a configuration diagram, circuit diagram, product information, and code information of a system corresponding to a technical idea and a method of operating the same.

[0002] An artificial intelligence system is a computer system that implements human-level intelligence, in which machines learn and make judgments on their own, and whose recognition rate improves with use.

[0003] Artificial intelligence technology consists of machine learning (deep learning) technology, which utilizes algorithms to self-classify and learn the characteristics of input data, and component technologies that mimic the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms.

[0004] The elemental technologies may include, for example, linguistic understanding technology that recognizes human language / characters, visual understanding technology that recognizes objects like human vision, reasoning / prediction technology that judges information to logically reason and predict, knowledge representation technology that processes human experience information into knowledge data, and motion control technology that controls autonomous driving of vehicles and the movement of robots.

[0005] Inference prediction is a technology that logically reasones and predicts by judging information, and includes knowledge / probability-based inference, optimization prediction, preference-based planning, and recommendation.

[0006] Knowledge representation is a technology that automates the processing of human experiential information into knowledge data, and includes knowledge construction (data generation / classification) and knowledge management (data utilization).

[0007] Even if ordinary people have technical ideas, they lack engineering knowledge and experience, making it difficult to design products, circuits, and code to actually implement those ideas, and thus creating barriers to technology commercialization.

[0008] Therefore, there is a need to explore methods that can automatically design actual products, circuits, and code corresponding to technical ideas, and obtain information regarding necessary parts, estimates, etc.

[0009] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned may be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims.

[0010] An electronic device for generating configuration and design information of a system corresponding to a technical idea according to the present embodiment comprises: a communication interface that performs a communication connection with an external device or an external server; a memory that stores a first language model that outputs a vector value corresponding to the text data when text data corresponding to a user input is input; and a processor connected to the memory and generating configuration and design information of a system corresponding to a technical idea based on data corresponding to the user input by executing at least one instruction. The processor can, when user input data is acquired, identify text data corresponding to the user input data, acquire first metadata based on a vector value output by inputting the text data into the first language model, transmit the first metadata to an external server through the communication interface so that it is input into a second language model stored on an external server, identify a system corresponding to the technical idea based on second metadata corresponding to the output vector value of the second language model received from the external server, identify a technical configuration corresponding to the identified system and a connection relationship between each technical configuration, and acquire configuration information of the system based on the technical configuration and the connection relationship.

[0011] The processor can identify a technology category corresponding to the identified system based on the second metadata, and identify a technology configuration corresponding to the identified technology category and the connection relationships between each technology configuration.

[0012] The processor can identify whether to supplement detailed technical information corresponding to a subcategory of the technical category based on third metadata corresponding to a vector value output by inputting the second metadata into the first language model, and if it is identified that supplementation is required, it can obtain additional information about the detailed technical information.

[0013] When detailed technical information corresponding to a subcategory of the identified technical category is identified, the processor can identify the technical configuration and the connection relationship between each technical configuration based on at least one of the identified detailed technical information.

[0014] The processor can acquire component information that matches the configuration diagram of the system and generate a circuit diagram corresponding to the system configuration diagram based on the acquired component information.

[0015] The above processor can generate estimation information of the system based on the configuration diagram of the system and the component information.

[0016] The above processor can generate code corresponding to the operation of the system based on the configuration diagram of the system and the circuit diagram.

[0017] A method of operation of an electronic device for generating configuration and design information of a system corresponding to a technical idea according to one embodiment of the present disclosure may include: an operation of identifying text data corresponding to the user input data when user input data is acquired; an operation of acquiring first metadata based on a vector value output by inputting the text data into the first language model; an operation of transmitting the first metadata to an external server through the communication interface so that it is input into a second language model stored on an external server; an operation of identifying a system corresponding to the technical idea based on second metadata corresponding to the output vector value of the second language model received from the external server; an operation of identifying a technical configuration corresponding to the identified system and a connection relationship between each technical configuration; and an operation of acquiring configuration information of the system based on the technical configuration and the connection relationship.

[0018] A non-transient computer-readable recording medium according to one embodiment of the present disclosure may store at least one instruction that is executed by a processor of an electronic device to perform a method of operation of the electronic device.

[0019] By using the aforementioned electronic device and its method of operation, anyone can easily implement technical ideas into actual products, circuits, and code.

[0020] By simplifying and streamlining the design of electronic devices, information regarding technology commercialization, necessary parts, estimates, etc., can be obtained.

[0021] Aspects, features, and advantages of specific embodiments of the present disclosure will become more apparent from the following description with reference to the accompanying drawings.

[0022] FIG. 1 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure.

[0023] FIG. 2 is a flowchart for explaining a method of operation of an electronic device according to one embodiment of the present disclosure.

[0024] FIG. 3 is a flowchart for explaining the operation of an electronic device for obtaining a system configuration diagram corresponding to a user idea according to one embodiment of the present disclosure.

[0025] FIG. 4 is a flowchart for explaining the operation of an electronic device that obtains information about a circuit diagram, code, and estimate corresponding to a system configuration diagram according to one embodiment of the present disclosure.

[0026] FIG. 5 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure.

[0027] The embodiments described herein are subject to various modifications and may have various forms; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure. In relation to the description of the drawings, similar reference numerals may be used for similar components.

[0028] In describing the present disclosure, if it is determined that a detailed description of related known functions or configurations could unnecessarily obscure the essence of the present disclosure, such detailed description is omitted.

[0029] Additionally, the following embodiments may be modified in various other forms, and the scope of the technical concept of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to fully convey the technical concept of the present disclosure to those skilled in the art.

[0030] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of the rights. Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Where it is stated that a component (e.g., Component 1) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., Component 2), it should be understood that the component may be directly connected to the other component or connected through the other component (e.g., Component 3).

[0035] 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 the certain component and the other component.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] Hereinafter, embodiments according to the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them.

[0041] The electronic device (100) may be an electronic device (100) capable of performing an operation to generate configuration and design information of a system corresponding to a technical idea.

[0042] The electronic device (100) may be a device that performs computational operations on data, information, and signals. For example, it may include at least one of a desktop PC, a smartphone, a tablet PC, a laptop PC, a netbook computer, a mobile device, and a wearable device, but is not limited thereto.

[0043] In addition, the electronic device (100) may be a server, for example, a computer that provides services to clients via a network. The server may be an FTP server, a web server, a database server, or a cloud server, and the server may be built with an operating system such as Linux.

[0044] A server may include multiple different functions and may not necessarily be a single device, and each function may be implemented by distributing it across multiple devices.

[0045] An electronic device (100) according to one embodiment of the present disclosure is not limited to the above-described device, and the electronic device (100) may be implemented as an electronic device (100) having two or more functions of the above-described devices.

[0046] FIG. 1 is a block diagram illustrating the configuration of an electronic device (100) according to one embodiment of the present disclosure.

[0047] Referring to FIG. 1, the electronic device (100) may include a communication interface (110), a memory (120), and a processor (130).

[0048] However, the configuration included in the electronic device (100) is not limited thereto and may be formed by omitting some configurations or adding other additional configurations. For example, the electronic device (100) may further include a user interface and a display.

[0049] The communication interface (110) may include a wireless communication interface, a wired communication interface, or an input interface. The wireless communication interface may communicate with various external devices using wireless communication technology or mobile communication technology. Such wireless communication technologies may include, for example, Bluetooth, Bluetooth Low Energy, CAN communication, Wi-Fi, Wi-Fi Direct, ultrawide band (UWB), Zigbee, infrared data association (IrDA), or near field communication (NFC), and mobile communication technologies may include 3GPP, Wi-Max, LTE (Long Term Evolution), 5G, etc.

[0050] A wireless communication interface can be implemented using an antenna, a communication chip, a substrate, etc., capable of transmitting electromagnetic waves to the outside or receiving electromagnetic waves transmitted from the outside.

[0051] A wired communication interface can communicate with various devices based on a wired communication network. Here, the wired communication network can be implemented using physical cables, such as, for example, pair cables, coaxial cables, fiber optic cables, or Ethernet cables.

[0052] Depending on the embodiment, either the wireless communication interface or the wired communication interface may be omitted. Accordingly, the electronic device (100) may include only a wireless communication interface or only a wired communication interface. In addition, the electronic device (100) may be equipped with an integrated communication interface (110) that supports both wireless connection via the wireless communication interface and wired connection via the wired communication interface.

[0053] The electronic device (100) is not limited to having one communication interface (110) that performs a communication connection in one manner, but may include a plurality of communication interfaces (110) that perform communication connections in multiple manners.

[0054] The processor (130) can transmit or receive various information by establishing a communication connection with an external server, external device, etc., through the communication interface (110).

[0055] For example, the processor (130) can receive information, data, text, images, etc. corresponding to the user's idea input from an external device, an external server, etc. through the communication interface (110).

[0056] The processor (130) can transmit system configuration information, system configuration diagrams, categories of devices constituting the system, circuit diagrams, component information, quotation information, code information, etc. corresponding to the user's idea to external devices, external servers, etc., through the communication interface (110).

[0057] Additionally, the processor (130) can transmit or receive output vector values ​​of the language model, metadata corresponding to the vector values, text data, etc. by performing a communication connection through a communication interface with an external server, etc.

[0058] In addition, the processor (130) can perform communication connections with external devices, external servers, etc., through the communication interface (110) to transmit or receive an artificial intelligence model, structural information, parameter information, function information, etc., for obtaining system configuration information, system configuration diagram, circuit diagram, component information, code information, etc., corresponding to the user's idea.

[0059] The memory (120) stores various programs or data temporarily or non-temporarily and transmits the stored information to the processor (130) upon the call of the processor (130). Additionally, the memory (120) can store various information required for the operation, processing, or control operation of the processor (130) in an electronic format.

[0060] The memory (120) may include, for example, at least one of a main memory and an auxiliary memory. The main memory may be implemented using a semiconductor storage medium such as ROM and / or RAM. The ROM may include, for example, a conventional ROM, EPROM, EEPROM and / or MASK-ROM. The RAM may include, for example, a DRAM and / or SRAM. The auxiliary memory may be implemented using at least one storage medium capable of storing data permanently or semi-permanently, such as a flash memory device, an SD (Secure Digital) card, a solid state drive (SSD), a hard disk drive (HDD), an optical recording medium such as a magnetic drum, a compact disc (CD), a DVD, or a laser disc, a magnetic tape, a magneto-optical disc and / or a floppy disk.

[0061] The memory (120) can store information about the user's technical idea. The memory (120) can store information about the configuration and category of the system corresponding to the user's technical idea. The memory (120) can store information about the configuration information of the system corresponding to the user's technical idea, the system configuration diagram, circuit diagram, code information, quotation information, component information, etc.

[0062] Additionally, the memory (120) can store vector values ​​output from the language model, data corresponding to the vector values, for example, metadata, text data, etc.

[0063] In addition, the memory (120) can store structural information, parameter information, and function information for the artificial intelligence model.

[0064] The processor (130) controls the overall operation of the electronic device (100). Specifically, the processor (130) is connected to the configuration of the electronic device (100) including the memory (120) as described above, and can control the overall operation of the electronic device (100) by executing at least one instruction stored in the memory (120) as described above. In particular, the processor (130) can be implemented as a single processor as well as as a plurality of processors.

[0065] The processor (130) may be implemented in various ways. For example, one or more processors (130) may include one or more of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), MIC (Many Integrated Core), DSP (Digital Signal Processor), NPU (Neural Processing Unit), hardware accelerator, or machine learning accelerator. One or more processors (130) may control one or any combination of other components of the electronic device (100) and may perform operations or data processing related to communication. One or more processors (130) may execute one or more programs or instructions stored in memory (120). For example, one or more processors (130) may perform a method according to one embodiment of the present disclosure by executing one or more instructions stored in memory (120).

[0066] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one processor (130) or by a plurality of processors (130). For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an artificial intelligence dedicated processor).

[0067] One or more processors (130) may be implemented as a single-core processor including one core, or as one or more multicore processors including multiple cores (e.g., homogeneous multicore or heterogeneous multicore). When one or more processors (130) are implemented as multicore processors, each of the multiple cores included in the multicore processor may include internal processor memory such as on-chip memory (120), and a common cache shared by the multiple cores may be included in the multicore processor (130). Additionally, each of the multiple cores (or some of the multiple cores) included in the multicore processor (130) may independently read and execute program instructions for implementing a method according to one embodiment of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one embodiment of the present disclosure.

[0068] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor, or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor, or the first operation and the second operation may be performed by a first core included in a multi-core processor and the third operation may be performed by a second core included in a multi-core processor.

[0069] In embodiments of the present disclosure, the processor (130) may mean a system-on-chip (SoC) in which one or more processors (130) and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, GPU, APU, MIC, DSP, NPU, hardware accelerator or machine learning accelerator, etc., but the embodiments of the present disclosure are not limited thereto.

[0070] The processor (130) is connected to the aforementioned user interface, communication interface (110), memory (120), and display and can perform an operation to obtain system information corresponding to the user's technical idea.

[0071] A more specific method by which the processor (130) operates and controls the electronic device (100) is explained together with FIGS. 2 to 4.

[0072] FIG. 2 is a flowchart for explaining a method of operation of an electronic device according to one embodiment of the present disclosure.

[0073] Referring to FIG. 2, the processor (130) can identify text data corresponding to the user input data when user input data is obtained (S110).

[0074] If the user input data is text data, the processor (130) can identify the text data, and if the user input data is voice data, it can identify the text data corresponding to the voice data using the voice recognition method described above.

[0075] Here, the text data corresponding to the user input data may include content regarding technical ideas.

[0076] Technical ideas may include, for example, information including the engineering design of electronic devices or the configuration of electronic devices, such as wireless speakers, wireless mice, remote-controlled lights, robotic vacuum cleaners, highway speed sensors, and search and rescue drones, but are not limited thereto.

[0077] The processor (130) can input text data into the first language model and obtain first metadata based on the output vector value (S120).

[0078] The processor (130) can identify the technical configuration of a system or electronic device corresponding to the user's technical idea based on natural language processing and tokenization operations for user input containing the technical idea.

[0079] Here, the first language model may be a type of language model that performs natural language processing and tokenization of text data (a preprocessing operation of breaking text data into small units called tokens).

[0080] Natural Language Processing (NLP) is a method that computer programs can use to interpret human language.

[0081] Natural language processing models can perform information retrieval operations to search for and identify target data contained in the data, information extraction operations to extract target data contained in the data, operations to classify sentences, documents, etc., operations to classify words, syntactic analysis, sentiment analysis, and operations to determine semantic roles, and are also used in speech recognition models to implement speech recognition and automatic dialogue systems.

[0082] A language model is a model trained to output the statistically most appropriate output value based on input values ​​(natural language, usually user sentences).

[0083] The first language model may be a simplified language model that is implemented with a simple structure and parameters compared to a general language model and performs natural language processing and tokenization operations with a relatively small processing load. Additionally, when information regarding machine code is input, the first language model can output a corresponding output vector value or text corresponding to the vector value.

[0084] Additionally, the first language model may include, but is not limited to, a verification and prediction model for the designability of system configuration information (or system configuration diagram; hereinafter, system configuration information or system configuration diagram may be used interchangeably), and a verification and prediction model for component matching. The designability of system configuration information or system configuration diagram, and the verification and prediction model for component matching may be separate models.

[0085] The processor (130) can input text data corresponding to user input into a first language model and obtain first metadata consisting of a vector value or text based on the output value.

[0086] The processor (130) can transmit the first metadata to an external server via a communication interface (110) so that it is input into a second language model stored on an external server (S130).

[0087] Here, the second language model stored on an external server may be a large language model, such as GPT, Phi, BERT, LaMDA, LLaMA, RoBERTa, etc., but is not limited thereto.

[0088] Based on large language models, Natural Language Processing (NLP), which recognizes and interprets input natural language, and Natural Language Generation (NLG), which generates, enhances, and reconstructs words and sentences, can be performed.

[0089] More specifically, large language models can be used for machine translation, text summarization, question-answering systems, dialogue systems, content generation, etc.

[0090] Large language models convert input text data into vector values ​​in a latent space through text embeddings, identify the context of words and phrases with similar meanings as well as other relationships between words, such as parts of speech, based on the vector values ​​in the latent space, and output results for natural language processing, natural language generation, etc., based on the relationships between these vector values.

[0091] An external server can input first metadata received from an electronic device into a large language model and obtain second metadata consisting of vector values ​​or text based on the output value, and can transmit the second metadata to the electronic device.

[0092] The processor (130) can identify a system corresponding to a technology idea based on the output vector value of a second language model received from an external server or second metadata corresponding to the text (S140).

[0093] The processor (130) can identify the technical configuration corresponding to the identified system and the connection relationships between each technical configuration (S150).

[0094] The processor (130) can identify a technology category corresponding to an identified system based on the second metadata. The processor (130) can identify a technology configuration corresponding to the identified technology category and a connection relationship between each technology configuration.

[0095] The technology category may be the type (or category) of product included in the technology idea, or the name of the product.

[0096] For example, the technology category may be a wireless speaker, the technology configuration may be a communication interface (110), a speaker, and a processor (130), and the connection relationship may refer to the electrical wired and wireless connection relationship of each configuration, such as the communication interface (110), the speaker, and the processor (130).

[0097] The processor (130) can identify whether to supplement detailed technical information corresponding to a subcategory of a technical category based on third metadata corresponding to a vector value output by inputting second metadata into a first language model.

[0098] Here, the first language model may be pre-learned based on essential components (or parts) for each pre-configured system or technology category of the system, or information regarding essential components (or parts) for each pre-configured system or technology category of the system may be pre-stored in memory.

[0099] When detailed technical information corresponding to a subcategory of an identified technical category is identified, the processor (130) can identify technical configurations and the relationships between each technical configuration based on at least one of the identified detailed technical information.

[0100] For example, if the category of the technology idea is wireless speaker, the subcategories could be battery-powered wireless speaker and wired wireless speaker.

[0101] In other words, a detailed classification corresponding to the technology category of a technology idea can be detailed technology information corresponding to a sub-category.

[0102] In addition, the sub-category may be the mode of operation of the technology configuration corresponding to the technology category (e.g., manual, automatic, wired, wireless, rechargeable, wired connection, etc.).

[0103] At this time, the processor (130) can identify that there are two or more subcategories corresponding to the technology category, and if the user input does not match the subcategory, it is necessary to supplement the detailed technology information corresponding to the subcategory.

[0104] In addition, the processor (130) can identify that there is no essential configuration in the identified system configuration information or system configuration diagram based on the third metadata corresponding to the output value of the second metadata input into the first language model, and identify that the detailed technical information needs to be supplemented.

[0105] If it is identified that supplementation is needed, the processor (130) can obtain additional information on the detailed technology and provide the obtained additional information to the user by outputting it through a display.

[0106] For example, if the technology category corresponding to the user input is identified as a wireless speaker, the processor (130) can obtain additional information regarding the detailed technology, such as whether it is wired or battery-rechargeable, and provide the obtained additional information to the user by outputting it through a display, thereby inducing additional input or selection by the user.

[0107] In addition, the processor (130) can provide guidance information to the user by outputting it through a display, requesting the user to input additional detailed technical information corresponding to a sub-category of the technical category.

[0108] The processor (130) can obtain recommendation information for additional information for each sub-category and output it to the user through a display.

[0109] At this time, the processor (130) can obtain and provide to the user detailed technical information corresponding to the sub-category, which is mapped to a higher rank as the actual sales volume of the corresponding part, product, etc. is higher and to a lower rank as the sales volume is lower.

[0110] The processor (130) can obtain configuration information of the system or generate a configuration diagram based on the technical configuration and connection relationship (S160). For example, the configuration information or configuration diagram of the system may be an image, drawing, picture, GUI including a speaker, battery, communication unit, control unit (processing unit), amplifier, etc., when the electronic device corresponding to the user's technical idea is a wireless speaker.

[0111] And, the processor (130) can acquire component information that matches the system configuration information or the system configuration diagram, and generate a circuit diagram corresponding to the system configuration information or the system configuration diagram based on the acquired component information.

[0112] The processor (130) can generate system estimation information based on system configuration information (or configuration diagram) and component information.

[0113] The processor (130) can generate code corresponding to the operation of the system based on the system configuration information (or configuration diagram) and circuit diagram.

[0114] The above-described embodiment can be implemented together with a prediction and verification model of a system configuration diagram, verification of the prediction model of the system configuration diagram based on component data, and a prediction operation, which is explained together with FIGS. 3 and 4.

[0115] FIG. 3 is a flowchart for explaining the operation of an electronic device (100) that obtains system configuration information or a configuration diagram corresponding to a user idea according to one embodiment of the present disclosure.

[0116] Referring to FIG. 3, the processor (130) can acquire data corresponding to user input (S210). User input may be voice data, text data, or image data.

[0117] However, not limited to this, the processor (130) may also receive data corresponding to user input from an external device through the communication interface (110).

[0118] When data corresponding to user input is obtained through the user interface, the processor (130) can identify the system corresponding to the user input.

[0119] Specifically, the processor (130) can input text corresponding to a technical idea corresponding to a user input containing a technical idea into a first language model to perform natural language processing and tokenization (S220).

[0120] The processor (130) can identify the technical configuration of the system, electronic device (100) corresponding to the user's technical idea based on natural language processing and tokenization operations for user input containing the technical idea.

[0121] And, the processor (130) can identify the technical configuration corresponding to the identified system and the connection relationships between each technical configuration.

[0122] The processor (130) can generate system configuration information or a configuration diagram based on the technical configuration and the connection relationships between each technical configuration.

[0123] More specifically, the processor (130) can identify the technology category of the system, the technology configuration, and the relationship between each technology configuration based on the first vector value (or first metadata) output by inputting text corresponding to user input into the first language model and the second vector value (or second metadata) output by inputting the first vector value (or second metadata) into the second language model.

[0124] At this time, as described above together with FIG. 2, the first language model may be stored in the memory (110) of the electronic device (100), and the second language model may be a large language model stored in an external server. In this case, the processor (130) inputs text corresponding to user input into the first language model and transmits the output vector value or first metadata corresponding to the text to the external server through the communication interface (110), and the external server may input the first metadata received from the electronic device (100) into the second language model to obtain the output vector value or second metadata corresponding to the text and transmit it to the electronic device (100).

[0125] The processor (130) can identify a technology category corresponding to the identified system, and identify a technology configuration corresponding to the identified technology category and a connection relationship between each technology configuration.

[0126] The technology category may be the type (or category) of product included in the technology idea, or the name of the product.

[0127] For example, the technology category may be a wireless speaker, the technology configuration may be a communication interface, a speaker, and a processor, and the connection relationship may refer to the electrical wired and wireless connection relationships of each configuration, such as the communication interface, speaker, and processor.

[0128] When detailed technical information corresponding to a subcategory of an identified technical category is identified, the processor (130) can identify technical configurations and the relationships between each technical configuration based on at least one of the identified detailed technical information.

[0129] For example, if the category of the technology idea is wireless speaker, the subcategories could be battery-powered wireless speaker and wired wireless speaker.

[0130] In other words, a detailed classification corresponding to the technology category of a technology idea can be detailed technology information corresponding to a sub-category.

[0131] In addition, the sub-category may be the mode of operation of the technology configuration corresponding to the technology category (e.g., manual, automatic, wired, wireless, rechargeable, wired connection, etc.).

[0132] The processor (130) can provide detailed technical information corresponding to at least one of the technical categories and sub-categories to the user by outputting it through a display.

[0133] In addition, the processor (130) can identify whether to supplement detailed technical information corresponding to a subcategory of a technical category based on the output third vector value (or third metadata) by inputting the second vector value into the first language model.

[0134] At this time, the processor (130) can identify that there are two or more subcategories corresponding to the technology category, and if the user input does not match the subcategory, it is necessary to supplement the detailed technology information corresponding to the subcategory.

[0135] If it is identified that supplementation is needed, the processor (130) can obtain additional information on the detailed technology and provide the obtained additional information to the user by outputting it through a display.

[0136] For example, if the technology category corresponding to the user input is identified as a wireless speaker, the processor (130) can obtain additional information regarding the detailed technology, such as whether it is wired or battery-rechargeable, and provide the obtained additional information to the user by outputting it through a display, thereby inducing additional input or selection by the user.

[0137] In addition, the processor (130) can provide guidance information to the user by outputting it through a display, requesting the user to input additional detailed technical information corresponding to a sub-category of the technical category.

[0138] The processor (130) can obtain recommendation information for additional information for each sub-category and output it to the user through a display.

[0139] At this time, the processor (130) can obtain and provide to the user detailed technical information corresponding to the sub-category, which is mapped to a higher rank as the actual sales volume of the corresponding part, product, etc. is higher and to a lower rank as the sales volume is lower.

[0140] The processor (130) can identify whether the actual design of the system's configuration diagram is feasible based on the output value by inputting information about the configuration information or configuration diagram obtained into the system configuration verification and prediction model (210). Here, the system configuration verification and prediction model (210) may be included in the first language model, but is not limited thereto.

[0141] The system configuration verification and prediction model (210) may include a technical database (200) or be connected to the technical database (200), and the processor (130) may obtain verification and prediction information regarding the design feasibility of the system configuration diagram based on the technical database (200).

[0142] If the design of the system configuration diagram is not possible (S230-N), the processor (130) can re-identify the technical configuration of the system and electronic device (100) corresponding to the user's technical idea based on natural language processing and tokenization operations for user input containing the technical idea.

[0143] If the design of the system configuration diagram is possible (S230-Y), the processor (130) can obtain the system configuration diagram and component information included in the configuration diagram (S240). The processor (130) can obtain component information for the system configuration diagram corresponding to the technical idea, such as the processor (130), circuit, inverter, converter, communication unit, speaker, amplifier, control unit, etc., that configures the system based on the system's power consumption and data throughput.

[0144] The processor (130) can identify whether the configuration diagram and component information of the acquired system are finalized. The processor (130) can input the configuration diagram and component information of the acquired system into a system configuration verification and prediction model (220) and identify whether the configuration diagram and component information of the acquired system are designable based on the output value. Here, the system configuration verification and prediction model (220) may be included in the first language model, but is not limited thereto.

[0145] The system configuration verification and prediction model (220) may include a technical database (200) or be connected to the technical database (200), and the processor (130) may obtain verification and prediction information regarding the design feasibility of the system configuration diagram and component configuration based on the technical database (200).

[0146] If the system configuration diagram and component information are not identified as designable and the acquired system configuration diagram and component information are not finally confirmed (S250-N), the processor (130) can acquire the system configuration diagram and component information again.

[0147] At this time, the processor (130) can re-acquire system configuration diagrams and component information that have a similarity to previously acquired system configuration diagrams and component information that is less than a preset value.

[0148] Therefore, it is possible to obtain configuration diagrams and component information different from the previously obtained system configuration diagrams and component information.

[0149] When the system configuration diagram and component information are identified as designable and the acquired system configuration diagram and component information are finally confirmed (S250-Y), the processor (130) can output the system configuration diagram through a display and provide it to the user (S260).

[0150] FIG. 4 is a flowchart for explaining the operation of an electronic device (100) that obtains information about a circuit diagram, code, and estimate corresponding to a system configuration diagram according to one embodiment of the present disclosure.

[0151] Referring to FIG. 4, the processor (130) can identify a system configuration diagram (S310). Here, the system configuration diagram may be one that has already been obtained by the method described above, or it may correspond to a new user input for the system configuration diagram.

[0152] The processor (130) can tokenize information included in the system configuration diagram (S320). The processor (130) can identify whether a part included in the system configuration diagram is matched based on the tokenized information. Whether a part is matched means whether there is an actual matching part, accessory, component, or product in the configuration included in the system configuration diagram.

[0153] Here, the processor (130) can input information about the system configuration diagram into a component data-based structure prediction model (310) connected to the component database (300) and identify whether the component included in the system configuration diagram matches the actual component based on the output value. However, the component data-based structure prediction model (310) may be included in the first language model, but is not limited thereto.

[0154] The processor (130) can receive component information included in the system configuration diagram by establishing a communication connection with an external server through the communication interface (110).

[0155] If actual parts cannot be matched to the system configuration diagram (S330-N), the processor (130) can re-identify the system configuration diagram.

[0156] Here, the system configuration diagram may be a second system configuration diagram in which the similarity to a previously identified system configuration diagram (first system configuration diagram) is less than a preset value.

[0157] And, the processor (130) can identify a group of candidates for a system configuration that can be actually designed based on actual part information received from an external server, the user's technical idea, and the technical category corresponding to the idea.

[0158] The processor (130) can identify a second system configuration diagram among the candidates that has a similarity to a previously acquired system configuration diagram that is less than a preset value.

[0159] And, the processor (130) can identify the frequency of re-identification of the second system configuration diagram relative to the number of times the first system configuration diagram is identified at each preset period.

[0160] If the re-identification frequency is greater than or equal to a preset value, the processor (130) identifies that there are two or more subcategories corresponding to a technology category and that even if a subcategory is not matched to the user input, there is no need to supplement detailed technology information corresponding to the subcategory, and can obtain a system configuration diagram based on component information corresponding to an existing technology category.

[0161] In other words, if the frequency of re-identifying the system configuration diagram increases because the actual parts do not match due to configuring parts based on detailed technical information corresponding to overly specific subcategories, the actual part matching rate can be increased by acquiring the system configuration diagram according to a technical category, which is a more comprehensive higher-level category than the subcategories.

[0162] In other words, a system configuration diagram that differs from the existing one is obtained to enable the acquisition of new component matching information.

[0163] If actual parts can be matched to the system configuration diagram (S330-Y), the processor (130) can obtain a parts list (or parts list, part list) (S340).

[0164] At this time, the processor (130) can obtain the estimate information and price information of the system configuration by summing the prices of the parts included in the parts list obtained based on the system configuration diagram, and can provide the obtained estimate information and price information to the user by outputting them through a display.

[0165] The processor (130) can generate a circuit diagram based on a system configuration diagram (a first system configuration diagram or a second system configuration diagram) and a parts list (S350).

[0166] When the circuit diagram is finally confirmed (S360-Y), the processor (130) can obtain information about the circuit diagram, estimate, and code corresponding to the system configuration diagram and parts list (S370).

[0167] The processor (130) can generate code corresponding to the operation of the system based on the generated circuit diagram.

[0168] Here, the estimate is information regarding the cost incurred when designing a circuit by configuring the system with actual matched components, and the code information may be algorithm or code information for operating the actual system or circuit.

[0169] The processor (130) can provide the generated circuit diagram, estimation information, and code information to the user by outputting them through a display.

[0170] The implementation method of the verification and prediction model (210, 220, 310) according to the above-described embodiment can be trained using conventional data learning models such as Fusat and OneShot, and the learning method can be diverse without being separately restricted to API integration or self-learning. In addition, the verification and prediction model (210, 220, 310) may be included in the first language model and stored in the memory of the electronic device, but may also be implemented as separate models.

[0171] The natural language processing unit checks the DB and algorithms through natural language tokenization to determine whether there is a lack of configuration, and each model (210, 220, 310) is a prediction model implemented to perform calculations on input data based on data learning such as FUSESAT and ONESAT by tokenizing the necessary data step by step from the big data owned by NuCode.

[0172] If configuration is possible, the system configuration diagram can be divided and sent so that the first language model can recognize it. The first language model can then determine the missing essential elements and send a command to re-question, or provide the user with a method to obtain the answer to the missing essential elements through research.

[0173] FIG. 5 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure.

[0174] Referring to FIG. 5, the electronic device may further include a user interface (140) and a display (150) in addition to the configuration described above.

[0175] The user interface (140) may include a button, a lever, a switch, a touch interface, etc., and the touch interface may be implemented in a way that receives input by the user's touch on a display (150) screen implemented together with a touch panel.

[0176] The processor (130) can receive user input through the user interface (140). The user input may correspond to text data containing content about the user's technical ideas.

[0177] However, not limited to this, if the user interface (140) is a microphone, the processor (130) can receive the user's voice input and convert the voice data corresponding to the received voice input into text data using a voice recognition function.

[0178] A microphone can refer to a module that acquires sound and converts it into an electrical signal, and it may be a condenser microphone, ribbon microphone, moving coil microphone, piezoelectric microphone, carbon microphone, or MEMS (Micro Electro Mechanical System) microphone. Additionally, it can be implemented in omnidirectional, bidirectional, unidirectional, subcardioid, supercardioid, or hypercardioid configurations.

[0179] The processor (130) can identify user voice commands based on acquired user voice information. Specifically, the processor (130) may include a Speech to Text (STT) module and can identify electrical signals corresponding to the user voice in the form of text through the STT module. The processor (130) can perform an operation corresponding to the identified user voice command. Here, when identifying user voice commands, the processor (130) can use a language model (LM) or an Automatic Sound Recognition (ASR) model to identify user voice commands contained in electrical signals corresponding to the user voice or text corresponding to electrical signals.

[0180] When user voice data is acquired, the user terminal inputs the user's voice data into a pre-trained speech recognition model to acquire text data corresponding to the voice data, and may transmit the acquired text data to a server.

[0181] Here, the speech recognition model may be an Automatic Sound Recognition (ASR) model.

[0182] A speech recognition model may include a preprocessing module that performs preprocessing operations on speech data, such as signal amplification and feature extraction.

[0183] A speech recognition model may include a pattern identification module that recognizes phonemes, syllables, and words, which are elements necessary to construct a sentence, based on features obtained through the preprocessing of speech signals to produce result values ​​from features.

[0184] The speech recognition model may include a post-processing module that performs a post-processing operation to obtain a sentence by reconstructing phonemes, syllables, and words for vector values ​​output from a language module or a speech recognition module.

[0185] The display (150) may include various types of display panels, such as an LCD (Liquid Crystal Display) panel, an OLED (Organic Light Emitting Diodes) panel, an AM-OLED (Active-Matrix Organic Light-Emitting Diode), an LcoS (Liquid Crystal on Silicon), a QLED (Quantum dot Light-Emitting Diode) and DLP (Digital Light Processing), a PDP (Plasma Display Panel) panel, an inorganic LED panel, and a Micro LED panel, but is not limited thereto. Meanwhile, the display (150) may form a touchscreen together with a touch panel and may be made of a flexible panel.

[0186] The display (150) can be implemented in a 2D shape such as a square or a rectangle, but is not limited thereto and can be implemented in various shapes such as a circle, a polygon, or a 3D shape.

[0187] The display (150) may be placed in one area of ​​the surface of the electronic device (100), but is not limited thereto, and may be implemented as a three-dimensional hologram projected in three-dimensional space or as a projection projected onto a two-dimensional plane.

[0188] The display (150) may be included as a component of the electronic device (100), but is not limited thereto, and a separately provided display (150) device may be connected wirelessly / wiredly to the electronic device (100) through a communication interface (110) or an input / output interface to output an image, video, or GUI according to a signal from the processor (130). In this case, the processor (130) may establish a wireless / wired connection with the display (150) device through the communication interface (110) or an input / output interface to transmit a signal for outputting an image, video, or GUI.

[0189] The processor (130) can provide the user with a system configuration diagram, circuit diagram, component information, code information, etc. corresponding to the user's technical idea by outputting them through the display (150).

[0190] The processor (130) can provide to the user a GUI, icon, indicator, image, or video corresponding to the system configuration diagram, circuit diagram, component information, code information, etc., by outputting it through the display (150).

[0191] According to one embodiment, 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 distributed online (e.g., download or upload) through an application store (e.g., Play Store™) 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 on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0192] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

Claims

1. An electronic device that generates configuration and design information of a system corresponding to a technical idea, A communication interface that establishes a communication connection with an external device or external server; A memory storing a first language model that outputs a vector value corresponding to the text data when text data corresponding to user input is input; and A processor connected to the memory and generating configuration and design information of a system corresponding to a technical idea based on data corresponding to user input by executing at least one instruction; The above processor is, When user input data is obtained, text data corresponding to the user input data is identified, and The above text data is input into the above first language model to obtain first metadata based on the output vector value, and The above first metadata is transmitted to an external server via the communication interface so that it is input into a second language model stored on an external server, and Identifying a system corresponding to the technical idea based on second metadata corresponding to the output vector value of the second language model received from the external server, and Identify the technical configurations corresponding to the above-identified systems and the connection relationships between each technical configuration, and An electronic device that obtains configuration information of the system based on the above technical configuration and the above connection relationship.

2. In Paragraph 1, The above processor is, Identifying a technology category corresponding to the identified system based on the second metadata above, and An electronic device that identifies a technology configuration corresponding to the above-identified technology category and the connection relationships between each technology configuration.

3. In Paragraph 2, The above processor is, Identify whether detailed technical information corresponding to a subcategory of the technical category is supplemented based on third metadata corresponding to a vector value output by inputting the second metadata into the first language model, and An electronic device that obtains additional information on the detailed technology when it is identified that the above supplementation is required.

4. In Paragraph 3, The above processor is, An electronic device that identifies the connection relationship between the technology configuration and each technology configuration based on at least one of the identified detailed technology information when detailed technology information corresponding to a subcategory of the identified technology category is identified.

5. In Paragraph 1, The above processor is, Obtain component information that matches the configuration diagram of the above system, and An electronic device that generates a circuit diagram corresponding to the system configuration diagram based on the above-mentioned acquired component information.

6. In Paragraph 5, The above processor is, An electronic device that generates estimation information of the system based on the configuration diagram of the system and the component information.

7. In Paragraph 5, The above processor is, An electronic device that generates code corresponding to the operation of the system based on the configuration diagram and circuit diagram of the system.

8. A method of operation of an electronic device that generates configuration and design information of a system corresponding to a technical idea, When user input data is obtained, an operation to identify text data corresponding to the user input data; The operation of inputting the above text data into the above first language model and obtaining the first metadata based on the output vector value; The operation of transmitting the above first metadata to an external server via the communication interface so that it is input into a second language model stored on an external server; An operation to identify a system corresponding to the technical idea based on second metadata corresponding to the output vector value of the second language model received from the external server; An operation to identify a technical configuration corresponding to the above-mentioned identified system and the connection relationships between each technical configuration; and A method of operating an electronic device comprising: an operation of obtaining configuration information of the system based on the above technical configuration and the above connection relationship.

9. A non-transient computer-readable recording medium storing at least one instruction that is executed by a processor of an electronic device to cause said electronic device to perform the method of operation of claim 8.

Images