Block code service apparatus and method

Abstract

The present disclosure discloses a block code service apparatus. The block code service apparatus according to the present disclosure comprises: a command analysis unit that generates at least one embedding vector on the basis of a user command; a database management unit that manages a database of a plurality of block codes each configured in a block code format; a block selection unit that selects, from among the plurality of block codes, at least one block code corresponding to the at least one embedding vector; and a block connection unit that connects the selected block codes to generate an artificial intelligence model.

Description

Block code service device and method

[0001] The present disclosure relates to a block code service apparatus and method, and more specifically, to a block code service apparatus and method that selects block codes corresponding to user commands and connects the selected block codes to generate an artificial intelligence model.

[0002] In modern software development environments, there is a growing need for systems that automatically generate and recommend code based on user commands. In particular, block coding is gaining attention to help users with limited coding experience or non-experts easily implement software functions. Block coding allows users to intuitively organize code without complex syntax knowledge by visually arranging pre-defined code in a block format.

[0003] While block coding has lowered the difficulty of code development, the inconvenience of users having to manually select and arrange each block remains. Particularly in large-scale projects, the process of individually selecting and combining block codes is inefficient, and it can be difficult to find the optimal block code that meets specific requirements. Therefore, there is a need for technology that allows users to select the necessary block codes and connects them to enable the combination of selected blocks to be executable.

[0004] The present disclosure aims to provide an artificial intelligence model generated by selecting block codes corresponding to user commands and connecting the selected block codes.

[0005] The problems that this disclosure aims to solve are not limited to those described above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0006] A block code service device according to one embodiment of the present disclosure may include: a command analysis unit that generates at least one embedding vector based on a user command; a database management unit that manages a database of a plurality of block codes configured in a block code format; a block selection unit that selects at least one block code corresponding to at least one embedding vector among the plurality of block codes; and a block linking unit that generates an artificial intelligence model by linking the selected block codes.

[0007] In some embodiments, the block code service device may further include an error detection unit that detects errors in an artificial intelligence model and provides error information to a user terminal.

[0008] In some embodiments, the block code service device may further include an interface providing unit that provides an interface for receiving user commands.

[0009] In some embodiments, the database may include a block database containing a plurality of block codes and a vector database generated by embedding the plurality of block codes.

[0010] In some embodiments, each of the plurality of block codes may include at least one of the block's title, description, and tag.

[0011] A block code service method according to one embodiment of the present disclosure may include: generating at least one embedding vector based on a user command; generating a database of a plurality of block codes configured in a block code format; selecting at least one block code corresponding to at least one embedding vector among the plurality of block codes; and generating an artificial intelligence model by concatenating the selected block codes.

[0012] In some embodiments, the block code service method may further include the step of detecting an error in an artificial intelligence model; and the step of providing error information to a user terminal.

[0013] In some embodiments, the block code service method may further include the step of providing an interface for receiving user commands.

[0014] In some embodiments, the step of creating a database may include: creating a block database comprising a plurality of block codes; and creating a vector database by embedding the plurality of block codes.

[0015] In some embodiments, each of the plurality of block codes may include at least one of the block's title, description, and tag.

[0016] The block code service device and method according to the present disclosure can provide an artificial intelligence model generated by selecting block codes corresponding to user commands and connecting the selected block codes.

[0017] In addition, the block code service device and method according to the present disclosure can provide error information to a user terminal when there is an error in the generated artificial intelligence model.

[0018] The effects according to the present disclosure are not limited to those described above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0019] FIG. 1 is a drawing showing a block code service system according to one embodiment of the present disclosure.

[0020] FIG. 2 is a drawing showing a block code service device according to one embodiment of the present disclosure.

[0021] FIG. 3 is a diagram illustrating a block code service method according to one embodiment of the present disclosure.

[0022] FIG. 4 is a drawing showing a block database according to one embodiment of the present disclosure.

[0023] FIG. 5 is a drawing showing a vector database according to one embodiment of the present disclosure.

[0024] FIG. 6 is a diagram for selecting a block code corresponding to a user command according to one embodiment of the present disclosure.

[0025] FIG. 7 is a drawing showing an interface for receiving user commands according to one embodiment of the present disclosure.

[0026] FIG. 8 is a diagram showing an artificial intelligence model generated by connecting block codes according to one embodiment of the present disclosure.

[0027] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the contents described in the attached drawings. However, the present invention is not limited or restricted by exemplary embodiments. Unless otherwise defined, all terms used in this specification (including technical and scientific terms) shall be used in a meaning that is commonly understood by those skilled in the art to which this disclosure belongs, but this may vary depending on the intent of those skilled in the art, case law, the emergence of new technology, etc.

[0028] Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant explanatory sections. Accordingly, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the content throughout this disclosure.

[0029] Throughout this specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, the singular form used in this specification includes the plural form unless specifically stated otherwise. Additionally, the expression "at least one of a, b, and / or c" as used throughout this specification may encompass 'a alone', 'b alone', 'c alone', 'a and b', 'a and c', 'b and c', or 'a, b, and c all'.

[0030] Meanwhile, terms such as "first and / or second" used in this specification may be used to describe various components, but they are used solely for the purpose of distinguishing one component from another and are not intended to limit the scope to the components referred to by such terms. For example, without departing from the scope of the present invention, the first component may be named the second component, and the second component may also be named the first component.

[0031] Additionally, terms such as “…part,” “…module,” etc., as described in this specification refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software. Furthermore, embodiments of this disclosure may be represented in this specification by functional block configurations and various processing steps. These functional block codes may be implemented by various numbers of hardware and / or software configurations that execute specific functions. For example, embodiments of this disclosure may employ integrated circuit configurations such as memory, processing, logic, look-up tables, etc., which can execute various functions under the control of one or more microprocessors or other control devices.

[0032] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the embodiments, technical details that are well known in the art to which the present invention pertains and are not directly related to the present invention will be omitted. This is to ensure that the essence of the present invention is conveyed more clearly without obscuring it by omitting unnecessary explanations. For the same reason, some components in the accompanying drawings may be exaggerated, omitted, or schematically depicted. Furthermore, the size of each component does not entirely reflect its actual size. Throughout this specification, the same reference numerals may refer to the same or corresponding components.

[0033]

[0034] FIG. 1 is a drawing showing a block code service system according to one embodiment of the present disclosure.

[0035] Referring to FIG. 1, a block code service system (100) according to one embodiment of the present disclosure may include a block code service device (110), a user terminal (120), a database (130), and a network (140).

[0036] The block code service device (110) and the user terminal (120) can communicate with each other through a network (140). The block code service device (110) and the user terminal (120) can communicate with each other through various networks (140), such as a wired network or a wireless network such as Bluetooth, WiFi, LTE, etc.

[0037] The user terminal (120) can receive an artificial intelligence model composed of block codes from the block code service device (110) in response to a user command. The user terminal (120) may correspond to a computing terminal such as a computer, smartphone, or tablet operated by a user. Additionally, the user terminal (120) may correspond to a target customer terminal such as a company, developer, or marketer that requires a block code service.

[0038] The user terminal (120) can transmit user commands to the block code service device (110) via the network (140). For example, the user command may be a command requesting the creation of an artificial intelligence model required by the user, such as "create a model that can analyze CSV files."

[0039] A block code service device (110) can select block codes corresponding to user commands received from a user terminal (120) from a database (130), and can generate an artificial intelligence model by connecting the selected block codes so that a combination of the selected block codes can be executed. In the present disclosure, a service that provides an artificial intelligence model generated by selecting and connecting block codes corresponding to user commands to a user terminal (120) may be referred to as a block code service.

[0040] More specifically, the block code service device (110) can embedding a user command into a vector space as shown in FIG. 6 and then select a block code (S) that is closest to the embedded vector (C) at a distance (d). In the present disclosure, embedding may mean converting data composed of text into a vector form and placing it in a multidimensional space. Additionally, a vector space may mean a mathematical space in which vectors representing the characteristics of a block code, such as the title, description, and tags of the block code, are placed, as shown in FIG. 5 and FIG. 6.

[0041] For example, the block code closest to the vector in which the user command is embedded may be a block code that serves the role of loading a CSV file. Subsequently, the block code service device (110) may select additional necessary block codes based on the selected block code. For example, if a block code for loading a CSV file is selected, a block code for preprocessing data included in the CSV file and a block code for analyzing and visualizing data included in the CSV file may be additionally selected.

[0042] The block code service device (110) can connect the selected block codes by considering the role of each selected block code. For example, if data preprocessing is required before analyzing data in a CSV file, the block code service device (110) can generate an artificial intelligence model corresponding to a user command by connecting block codes in the order of loading the CSV file, block codes preprocessing the data included in the CSV file, and block codes analyzing and visualizing the data included in the CSV file. However, this is merely an example, and the block code service device (110) can generate an artificial intelligence model by selecting and connecting block codes in various ways to generate an artificial intelligence model corresponding to a user command.

[0043] In some embodiments, the block code service device (110) may be implemented as a cloud server and may provide block code services to a user terminal (120) through the cloud service.

[0044] The database (130) may include a block database (131) and a vector database (132).

[0045] The block database (131) can store data including information representing the characteristics of the blocks, such as titles, descriptions, and tags, in block codes retrieved via API. For example, the block database (131) can store data including titles, descriptions, and tags in block codes included in the Langchain library, which is a type of Python library.

[0046] The vector database (132) can store vectors that embed each of the block codes stored in the block database (131). For example, each of the block codes can be converted into a vector form according to a title, description, and tag and represented in a vector space, and the vector database (132) can store data representing each of the block codes in a vector space.

[0047] As described above, the block code service device (110) according to the present disclosure can provide an artificial intelligence model generated by selecting block codes corresponding to user commands and connecting the selected block codes to a user terminal (120).

[0048]

[0049] FIG. 2 is a drawing showing a block code service device according to one embodiment of the present disclosure.

[0050] FIG. 2 may be described with reference to FIG. 1. Referring to FIG. 2, a block code service device (210) according to one embodiment of the present disclosure may include a command analysis unit (211), a database management unit (212), a block selection unit (213), a block connection unit (214), and a control unit (215).

[0051] The command analysis unit (211) can receive user commands from the user terminal (120) and can generate an embedding vector by embedding the user commands into a vector space. In some embodiments, the block code service device (210) may further include an interface providing unit (not shown) that provides a user interface to the user terminal (120) for receiving user commands, as described below with reference to FIG. 7.

[0052] The database management unit (212) may be a configuration that manages the database (130), such as creating or deleting the database (130). For example, the database management unit (212) may load the Langchain library via API and store data including titles, descriptions, and tags in the block codes included in the Langchain library in the block database (131).

[0053] Additionally, the database management unit (212) may store vectors that embed each of the block codes stored in the block database (131) in the vector database (132). However, this is merely an example, and the database management unit (212) may store block codes in the block database (131) by loading various types of libraries. Additionally, the database management unit (212) may delete unnecessary block codes from the database (130).

[0054] The block selection unit (213) can select block codes corresponding to user commands from among the block codes stored in the block database (131). For example, the block selection unit (213) can select at least one block code corresponding to an embedding vector in which the command analysis unit (211) has embedded the user command. In some embodiments, the block selection unit (213) can select the block code that is closest in vector space to the embedding vector in which the user command has embedded. Subsequently, the block selection unit (213) can select additional necessary block codes based on the selected block code.

[0055] The block linking unit (214) can generate an artificial intelligence model by linking selected block codes so that a combination of block codes selected by the block selection unit (213) can be executed. For example, as described above with reference to FIG. 1, if data preprocessing is required before analyzing data in a CSV file, the block code service device (210) can generate an artificial intelligence model corresponding to a user command by linking in the order of a block code that loads a CSV file - a block code that preprocesses data included in the CSV file - a block code that analyzes and visualizes data included in the CSV file.

[0056] The control unit (215) can control the overall operation of the block code service device (210) and can manage the control flow or data flow between the command analysis unit (211), the database management unit (212), the block selection unit (213), and the block connection unit (214).

[0057] In some embodiments, the block code service device (210) may further include an error detection unit (not shown). The error detection unit (not shown) can detect errors in the artificial intelligence model generated by the block connection unit (214) and provide error information to the user terminal (120) so that the user can correct the errors in the artificial intelligence model.

[0058]

[0059] FIG. 3 is a diagram illustrating a block code service method according to one embodiment of the present disclosure.

[0060] Figure 3 can be explained with reference to the aforementioned Figures 1 and 2.

[0061] Referring to FIG. 3, a block code service method (S100) according to one embodiment of the present disclosure may include the steps of: generating at least one embedding vector based on a user command (S110); generating a database for a plurality of block codes configured in a block code format (S120); selecting at least one block code corresponding to at least one embedding vector among the plurality of block codes (S130); and generating an artificial intelligence model by concatenating the selected block codes (S140).

[0062] FIG. 3 illustrates steps S110 to S140 being performed sequentially, but is not limited thereto; some steps may be merged and performed simultaneously, some steps may be omitted, or new steps may be added.

[0063] In step S110, at least one embedding vector can be generated based on a user command. For example, a user command such as "Generate a model that can analyze CSV files" may be provided from the user terminal (120) described above with reference to FIG. 1, and an embedding vector can be generated by embedding the user command in a vector space. The embedding vector can subsequently serve as a criterion for selecting and connecting block code suitable for the user command.

[0064] In step S120, a database of multiple block codes configured in a block code format can be created.

[0065] In some embodiments, step S120 may further include the step of creating a block database containing a plurality of block codes and the step of creating a vector database by embedding the plurality of block codes.

[0066] In some embodiments, each of the plurality of block codes may include at least one of the block's title, description, and tag.

[0067] In step S130, at least one block code corresponding to at least one embedding vector among a plurality of block codes can be selected.

[0068] In some embodiments, the block code closest to the embedding vector generated in step S110 in the vector space may be selected. Subsequently, additional block codes required to enable the artificial intelligence model to execute may be further selected based on the selected block code.

[0069] In step S140, an artificial intelligence model can be created by connecting the selected block codes. For example, an artificial intelligence model can be created by connecting the selected block codes, taking into account the respective roles of the block codes selected in step S130. For example, an artificial intelligence model can be created by connecting the block codes in the order of loading a CSV file, preprocessing the data contained in the CSV file, and analyzing and visualizing the data contained in the CSV file.

[0070] In some embodiments, the block code service method (S100) may further include the step of detecting an error in an artificial intelligence model and the step of providing error information to a user terminal. The block code service method (S100) may provide the error information of the artificial intelligence model to a user terminal (120) so that the user can correct the error in the artificial intelligence model.

[0071] In some embodiments, the block code service method (S100) may further include the step of providing an interface for receiving user commands.

[0072]

[0073] FIG. 4 is a drawing showing a block database according to one embodiment of the present disclosure.

[0074] FIG. 4 can be described with reference to FIG. 1 to FIG. 3. Referring to FIG. 4, the block database (231) may include various block codes, and each block code may include information representing each block code, such as a title, description, and tag.

[0075] In FIG. 4, a block database (231) including six block codes (block codes A to F) is illustrated as an example, but this is merely an example, and the number of block codes included in the block database (231) and the information included in the block codes may be determined differently.

[0076] In some embodiments, the database management unit (212) can load the Langchain library through an API and store block codes included in the Langchain library in the block database (231) with titles, descriptions, and tags attached.

[0077]

[0078] FIG. 5 is a drawing showing a vector database according to one embodiment of the present disclosure.

[0079] FIG. 5 can be described with reference to FIG. 1 to FIG. 4. Referring to FIG. 5, block codes (B) embedded in a vector space may be arranged. For example, each of the embedded block codes (B) shown in FIG. 5 may represent the case where the block codes (block codes A to F) described with reference to FIG. 4 are embedded in a vector space. Additionally, each of the axes (X-axis, Y-axis, Z-axis) of the vector space shown in FIG. 5 may, for example, correspond to the title, description, tag, etc. of the block codes.

[0080]

[0081] FIG. 6 is a diagram for selecting a block code corresponding to a user command according to one embodiment of the present disclosure.

[0082] FIG. 6 can be described with reference to FIG. 1 through 5 described above. Referring to FIG. 6, the command analysis unit (211) can generate an embedding vector (C) by embedding a user command in a vector space. Subsequently, the block selection unit (213) can select a block code (S) that is closest in distance (d) to the embedding vector (C) in the vector space, for example. Additionally, the block selection unit (213) can select additional block codes (B) that are additionally required to enable an artificial intelligence model to execute based on the selected block code (S).

[0083]

[0084] FIG. 7 is a drawing showing an interface for receiving user commands according to one embodiment of the present disclosure.

[0085] FIG. 7 can be described with reference to FIG. 1 through 6 described above. Referring to FIG. 7, a block code service device (110) can provide an interface for receiving user commands to a user terminal (120) as shown in FIG. 7. The user can input commands required by the user into a command input window (CMD) of the user terminal (120), and the input user commands can be provided to the block code service device (110) through a network (140). The block code service device (110) can generate an artificial intelligence model corresponding to the user commands using a database (130) and provide it to the user terminal (120) through the network (140).

[0086]

[0087] FIG. 8 is a diagram showing an artificial intelligence model generated by connecting block codes according to one embodiment of the present disclosure.

[0088] FIG. 8 can be described with reference to FIG. 1 through 7 described above. Referring to FIG. 8, the artificial intelligence model (AM) may include a first block code (BL1), a second block code (BL2), a third block code (BL3), and a fourth block code (BL4). However, this is merely an example for convenience of explanation and the technical concept of the present disclosure is not limited thereto.

[0089] The first block code (BL1) may, for example, be the block code closest to the embedding vector generated by embedding user commands in a vector space.

[0090] For example, to execute the first block code (BL1), a chat model trained based on various training data to understand the user's question and provide a relevant answer, a memory that remembers previous conversation history or key information with the user to maintain the context of the conversation, and a prompt template that maintains the tone and style of the answer of the artificial intelligence model (AM) may be required.

[0091] A block code service device (110) can generate an artificial intelligence model (AM) by connecting each of a second block code (BL2) that performs a chat model function, a third block code (BL3) that performs a memory function, and a fourth block code (BL4) that performs a prompt template function to the first block code (BL1) to execute the first block code (BL1).

[0092]

[0093] Meanwhile, the embodiments disclosed in this specification may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium. A computer-readable recording medium may include all types of recording media that store instructions decipherable by a computer. Examples include ROM, RAM, magnetic tape, magnetic disk, flash memory, optical data storage devices, etc. A computer-readable recording medium may be distributed and executed by networked computer systems.

[0094] The above descriptions are specific embodiments for carrying out the present disclosure. The present disclosure will include not only the embodiments described above, but also embodiments that can be simply modified or easily modified. Furthermore, the present disclosure will include technologies that can be easily modified and implemented using the embodiments described above. Accordingly, the scope of the present disclosure should not be limited to the embodiments described above, but should be defined by the claims set forth below as well as equivalents to the claims of the present disclosure.

Claims

1. A command analysis unit that generates at least one embedding vector based on a user command; A database management unit that manages a database for multiple block codes configured in a block code format; A block selection unit for selecting at least one block code corresponding to at least one embedding vector among the plurality of block codes; and A block code service device including a block linker that generates an artificial intelligence model by linking selected block codes.

2. In Paragraph 1, A block code service device further comprising an error detection unit that detects errors in the above artificial intelligence model and provides error information to a user terminal.

3. In Paragraph 1, A block code service device further comprising an interface providing unit that provides an interface for receiving the above user command.

4. In Paragraph 1, The above database is a block code service device comprising a block database including the plurality of block codes and a vector database generated by embedding the plurality of block codes.

5. In Paragraph 1, A block code service device in which each of the above plurality of block codes includes at least one of a block title, description, and tag.

6. A step of generating at least one embedding vector based on a user command; A step of creating a database for multiple block codes configured in a block code format; A step of selecting at least one block code corresponding to at least one embedding vector among the plurality of block codes; and A block code service method comprising the step of generating an artificial intelligence model by connecting selected block codes.

7. In Paragraph 6, A step of detecting errors in the above artificial intelligence model; and A block code service method further comprising the step of providing error information to a user terminal.

8. In Paragraph 6, A block code service method further comprising the step of providing an interface for receiving the above user command.

9. In Paragraph 6, The step of creating the above database is, A step of creating a block database including the above plurality of block codes; and A block code service method comprising the step of generating a vector database by embedding the above plurality of block codes.

10. In Paragraph 6, A block code service method in which each of the above plurality of block codes includes at least one of a block title, description, and tag.

Images