KR-20260062557-A - Artificial intelligence-based drawing recommendation device and its control method

Abstract

The output unit outputs screen information including at least one of a search term input area, a recommended drawing output area, and a mode selection button; the input unit receives a search term related to drawing recommendations from a user on the search term input area; a plurality of pre-stored training data related to architectural drawings; and a control unit that converts the input search term into an image embedding vector and a text embedding vector, respectively. In particular, the control unit calculates the matching probability of the plurality of image embedding vectors and the text embedding vectors, and controls the operation of the output unit so that at least one recommended drawing is included in the recommended drawing output area based on the calculated probability.

Inventors

• 오세욱

Assignees

• 오세욱

Dates

Publication Date

20260507

Application Date

20241029

Claims (5)

1. An output unit that outputs screen information including at least one of a search term input area, a recommended drawing output area, and a mode selection button; An input unit that receives search terms related to drawing recommendations from a user on the above-mentioned search term input area; and It includes a control unit that performs contrastive learning using image information and text information included in a plurality of pre-stored training data related to architectural drawings, converts the image information into an image embedding vector based on the learning result, and converts the input search term into a text embedding vector. The above control unit is, Calculate the matching probability of a plurality of the above image embedding vectors and the above text embedding vectors, and A drawing recommendation device characterized by controlling the operation of the output unit so that at least one recommended drawing is included in the recommended drawing output area based on a calculated probability.
2. In paragraph 1, The above training data is, A drawing recommendation device characterized by including image information extracted from a previously created architectural drawing and at least one parameter composed of text.
3. In paragraph 2, The above control unit is, A drawing recommendation device characterized by extracting image information and at least one parameter by performing a preprocessing process using information related to the above-mentioned architectural drawing.
4. In paragraph 3, The above plurality of parameters are, A drawing recommendation device characterized by including descriptive text information corresponding to a plurality of components included in the above architectural drawing.
5. In paragraph 3, The above plurality of parameters are, A drawing recommendation device characterized by including at least one of a work sequence corresponding to the above-mentioned architectural drawing, an immediate work drawing, and an immediate work drawing.

Description

Artificial intelligence-based drawing recommendation device and its control method The present invention relates to a device for recommending a drawing library using an artificial neural network and a method for controlling the same. As the architectural design progresses, the designer creates detailed drawings to materialize the design. Generally, rather than creating detailed drawings from scratch, the designer searches for reference drawings within existing completed project files and adapts the retrieved drawings to create the detailed drawings. Considering the number of drawings constituting a project and the complexity of the project file tree, the repetitive search for appropriate reference drawings whenever a designer creates a detail drawing consumes a significant amount of time and labor costs. Therefore, to overcome the aforementioned drawbacks of manual search methods that rely on the designer's memory, there is a need for a drawing recommendation system utilizing artificial intelligence. Figure 1 illustrates the components of a drawing recommendation device (100) according to the present invention. FIGS. 2 and FIGS. 3 show the output screen of a drawing recommendation device (100) operating in a first operating mode. FIG. 4 shows the output screen of a drawing recommendation device (100) operating in a second operating mode. FIG. 5 is a conceptual diagram showing an artificial intelligence model (500) used by a drawing recommendation device (100). FIG. 6 is an example of an architectural drawing that an artificial intelligence model (500) uses for learning. Hereinafter, embodiments of the present invention are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments disclosed below. Furthermore, in order to clearly disclose the present invention in the drawings, parts unrelated to the present invention have been omitted, and identical or similar reference numerals in the drawings indicate identical or similar components. The purpose and effects of the present invention may be naturally understood or become clearer from the following description, and the purpose and effects of the present invention are not limited to the description below alone. The objectives, features, and advantages of the present invention will become clearer through the following detailed description. Furthermore, in describing the present invention, if it is determined that a detailed description of known technology related to the present invention may unnecessarily obscure the essence of the invention, such detailed description will be omitted. Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. Referring to FIG. 1, a block diagram showing the components of a drawing recommendation device (100) according to the present invention is shown. As shown in FIG. 1, the drawing recommendation device (100) may include at least one of an input unit (110), an output unit (120), a control unit (130), a communication unit (140), and a memory (150). The input unit (110) may include a camera or video input unit for inputting a video signal, a microphone or audio input unit for inputting an audio signal, and a user input unit for receiving information from a user (e.g., a touch key, a mechanical key, etc.). Specifically, the input unit (110) is for receiving information from a user, and when information is input through the input unit (110), the control unit (130) can control the operation of the drawing recommendation device (100) to correspond to the input information. Such an input unit (110) may include mechanical input means and touch input means. As an example, the touch input means may consist of a virtual key, soft key, or visual key displayed on a touchscreen through software processing, or a touch key placed on a part other than the touchscreen. Meanwhile, the virtual key or visual key may have various forms and may be displayed on the touchscreen, for example, as a graphic, text, icon, video, or a combination thereof. In one embodiment, the input unit (110) can receive a search term related to drawing recommendations from the user. In another embodiment, the input unit (110) may receive user input related to the operation mode of the drawing recommendation device (100). For example, the input unit (110) may receive user input related to either a first operation mode for determining recommended drawings from a drawing library stored in memory (150) or a second operation mode for generating recommended drawings using a generative artificial intelligence model. In another embodiment, the input unit (110) may receive user input for selecting any one of at least one recommended drawing output. In another embodiment, the input unit (110) may receive user input related