Drawing method, computer equipment and medium based on AI model

Abstract

This application provides a drawing method, computer device, and medium based on an AI model. The AI ​​model-based drawing method includes: acquiring initial data of the interior design to be drawn; acquiring the current user's historical learning information, historical exam information, and historical work browsing information; predicting prompts needed by the current user based on the historical learning information, historical exam information, and historical work browsing information, obtaining multiple candidate prompts; outputting multiple candidate prompts for the current user to select multiple target prompts from among them; and inputting the multiple target prompts and the initial interior design data into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model. This application can improve the drawing efficiency of AI models.

Description

Technical Field

[0001] This application relates to the field of AI model drawing technology, specifically to a drawing method, computer device, and medium based on an AI model. Background Art

[0002] In industries such as architectural design, AI (Artificial Intelligence) models can be provided for drawing related to interior design. For example, AI models can be used to render the decoration effect of a bare building or to render interior design line drawings to obtain interior design renderings.

[0003] When using AI models to draw interior design-related content, users usually need to manually input prompts to get the desired effect. For example, a user can input the prompt "creamy style" to get the AI ​​model to draw an interior design rendering with a creamy style.

[0004] However, this method of manually inputting prompts is very inconvenient, and the prompts require users to think repeatedly, summarize and refine them, which greatly reduces the drawing efficiency of AI models. Summary of the Invention

[0005] The embodiments of this application provide a drawing method, computer device, and medium based on an AI model, which aim to improve the drawing efficiency of the AI ​​model.

[0006] In a first aspect, embodiments of this application provide a drawing method based on an AI model, the drawing method based on an AI model comprising:

[0007] Obtain the initial data for the interior design to be drawn;

[0008] Retrieve the current user's historical learning information, historical exam information, and historical works browsing information;

[0009] Based on the historical learning information, the historical exam information, and the historical works browsing information, the prompt words needed by the current user are predicted, resulting in multiple candidate prompt words;

[0010] Output multiple candidate suggestion words so that the current user can select multiple target suggestion words from the multiple candidate suggestion words;

[0011] The target prompts and the initial interior design data are input into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0012] In some embodiments, the output of a plurality of candidate suggestion words includes:

[0013] Obtain the user demand level for each of the candidate suggestion words;

[0014] Based on the user demand level, the multiple candidate prompt words are sorted from largest to smallest to obtain the first order;

[0015] According to the first order, output multiple candidate prompt words.

[0016] In some embodiments, the historical learning information includes a first knowledge point learned by the current user during a historical period; and / or

[0017] The historical exam information includes the second knowledge point in the current user's exam during the historical period, and the third knowledge point in the second knowledge point in which the current user answered incorrectly; and / or

[0018] The historical works browsing information includes multiple preset prompts associated with the preset interior design works browsed by the current user during the historical period;

[0019] The user demand for the candidate suggestion words can be determined through the following steps:

[0020] Determine the number of times the candidate prompt words appear in multiple first knowledge points, multiple second knowledge points, multiple second knowledge points, and multiple preset prompt words;

[0021] The user demand for the candidate suggestion words is obtained by weighted summation of the occurrence counts.

[0022] In some embodiments, the weights for weighted summation of the occurrence counts are determined in the following manner:

[0023] Determine the first historical moment of the most recently learned first knowledge point in the historical learning information;

[0024] Determine the second historical moment of the second knowledge point in the most recent exam from the historical exam information;

[0025] Determine the third historical moment of the most recent incorrect answer to the third knowledge point in the historical examination information;

[0026] Determine the fourth historical moment of the preset interior design work that was most recently viewed in the historical works browsing information;

[0027] Based on the chronological order of the first historical moment, the second historical moment, the third historical moment, and the fourth historical moment, different weights are assigned to the occurrence frequency of the candidate prompt words in multiple first knowledge points, multiple second knowledge points, multiple second knowledge points, and multiple preset prompt words.

[0028] In some embodiments, the prediction of prompt words needed by the current user based on the historical learning information, the historical exam information, and the historical works browsing information yields a plurality of candidate prompt words, including:

[0029] Identify the first keyword among multiple first knowledge points, the second keyword among multiple second knowledge points, and the third keyword among multiple third knowledge points;

[0030] The first keyword, the second keyword, the third keyword, and a set of multiple preset prompt words are used as the prompt word set;

[0031] Based on the user demand for each prompt word in the prompt word set, a plurality of candidate prompt words are determined in the prompt word set.

[0032] In some embodiments, determining a plurality of candidate prompt words based on the user demand for each prompt word in the prompt word set includes:

[0033] Based on the user demand for the prompt words in the prompt word set, all prompt words in the prompt word set are sorted from largest to smallest to obtain a second order;

[0034] In the second order, a preset number of prompt words are determined to be ranked first, and these are used as multiple candidate prompt words.

[0035] In some embodiments, the plurality of candidate prompt words further includes a plurality of fourth prompt words, and after obtaining the initial data of the interior design to be drawn, the method further includes:

[0036] Identify multiple interior design elements in the initial interior design data;

[0037] Among multiple preset interior design works, a target interior design work that has at least one interior design element from the initial interior design data is identified.

[0038] Multiple preset prompt words associated with the target interior design work are used as multiple fourth prompt words.

[0039] In some embodiments, determining multiple interior design elements in the initial interior design data includes:

[0040] Obtain the target neural network model for identifying interior design elements;

[0041] The initial interior design data is input into the target neural network model to receive multiple interior design elements from the initial interior design data output by the target neural network model.

[0042] Secondly, embodiments of this application provide a drawing device based on an AI model, the drawing device based on the AI ​​model comprising:

[0043] The first acquisition module is used to acquire the initial data of the interior design to be drawn;

[0044] The second acquisition module is used to acquire the current user's historical learning information, historical exam information, and historical works browsing information;

[0045] The prediction module is used to predict the prompt words needed by the current user based on the historical learning information, the historical exam information, and the historical works browsing information, and obtain multiple candidate prompt words;

[0046] The selection module is used to output multiple candidate prompt words, so that the current user can select multiple target prompt words from the multiple candidate prompt words;

[0047] The drawing module is used to input multiple target prompts and the initial data of the interior design into a preset AI drawing model, so as to receive the interior design renderings output by the AI ​​drawing model.

[0048] Thirdly, embodiments of this application provide a computer device including a processor and a memory, wherein the memory stores a computer program configured to be executed by the processor to implement the AI ​​model-based drawing method as described in any of the preceding claims.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program configured to be executed by a processor to implement the AI ​​model-based drawing method as described in any of the preceding claims.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program or instructions, which are executed by a processor to implement the AI ​​model-based drawing method as described in any of the preceding claims.

[0051] The beneficial effects of the embodiments of this application are as follows:

[0052] In the embodiments of this application, multiple target prompt words are predicted by historical learning information, historical exam information, and historical work browsing information. Then, based on the initial data of the interior design to be drawn and the multiple target prompt words, they are input into the preset AI drawing model to obtain the corresponding interior design rendering. Users do not need to manually input prompt words; users can complete the drawing of the AI ​​model simply by selecting prompt words, thereby improving the drawing efficiency of the AI ​​model. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic flowchart of an embodiment of the AI ​​model-based drawing method provided in this application;

[0055] Figure 2 This is a schematic flowchart of another embodiment of the AI ​​model-based drawing method provided in this application;

[0056] Figure 3 This is a schematic flowchart of another embodiment of the AI ​​model-based drawing method provided in this application;

[0057] Figure 4 This is a schematic flowchart of another embodiment of the AI ​​model-based drawing method provided in this application;

[0058] Figure 5 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0059] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, in the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features.

[0061] Firstly, embodiments of this application provide a drawing method based on an AI model. Specifically, refer to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of an AI model-based drawing method. Figure 1 In this context, the AI ​​model-based drawing method may include:

[0062] 101. Obtain the initial data for the interior design to be drawn.

[0063] In the embodiments of this application, the initial data of the interior design to be drawn refers to the original data of the interior design that needs to be drawn to obtain the interior design rendering, such as the decoration design drawings of the bare shell, the interior design line drawings, etc.

[0064] 102. Obtain the current user's historical learning information, historical exam information, and historical works browsing information.

[0065] In the embodiments of this application, the current user refers to the user currently logged into a platform that provides AI model drawing functionality. This platform interfaces with platforms for learning, practicing, and assessing content such as interior design, as well as platforms that provide interior design work browsing functionality, to obtain the current user's historical learning and exam information from the platforms for learning, practicing, and assessing content such as interior design. The current user's historical work browsing information can be obtained from the platforms that provide interior design work browsing functionality. The platforms that provide interior design work browsing functionality can have multiple preset interior design works available for users to study and appreciate.

[0066] In the embodiments of this application, the current user's historical learning information refers to the current user's historical learning records on topics such as interior design. The current user's historical examination information refers to the current user's historical examination records on topics such as interior design. The current user's historical work browsing information refers to the current user's browsing records of preset interior design works.

[0067] 103. Based on historical learning information, historical exam information, and historical works browsing information, predict the prompt words needed by the current user and obtain multiple candidate prompt words.

[0068] In the embodiments of this application, historical learning information, historical exam information, and historical work browsing information represent the current user's historical needs for content such as interior design. Therefore, based on historical learning information, historical exam information, and historical work browsing information, the prompt words needed by the current user can be predicted, making the prediction of the prompt words needed by the current user more accurate.

[0069] It is understandable that users may have doubts or misunderstandings during the process of learning history, taking history exams, and browsing historical works. Therefore, they may need to further understand and consolidate the relevant content. Thus, predicting the prompts needed by the user based on historical learning information, historical exam information, and historical work browsing information can match the predicted multiple candidate prompts with the user's needs.

[0070] 104. Output multiple candidate prompts so that the current user can select multiple target prompts from among the multiple candidate prompts.

[0071] In the embodiments of this application, multiple candidate prompt words can be output to the current user's terminal, so that the current user can select multiple target prompt words from the multiple candidate prompt words. In this way, the current user does not need to manually input prompt words, nor does he / she need to repeatedly think, summarize and refine to obtain prompt words. By selecting from multiple candidate prompt words, multiple target prompt words can be determined.

[0072] 105. Input multiple target prompts and initial interior design data into the preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0073] In the embodiments of this application, the preset AI (Artificial Intelligence) drawing model provides AI drawing functionality, which can be used to draw according to multiple input target prompts and initial interior design data to obtain corresponding interior design renderings. The AI ​​drawing functionality of the AI ​​drawing model can be obtained through prior model training, and is not limited here.

[0074] As can be seen, in the above embodiments of this application, multiple target prompt words are predicted by historical learning information, historical exam information and historical work browsing information. Then, based on the initial data of the interior design to be drawn and the multiple target prompt words, they are input into the preset AI drawing model to obtain the corresponding interior design rendering. Users do not need to manually input prompt words. Users can complete the drawing of the AI ​​model simply by selecting prompt words, thereby improving the drawing efficiency of the AI ​​model.

[0075] In some embodiments of this application, such as Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, multiple candidate prompt words are output, which may include:

[0076] 201. Obtain the user demand for each candidate suggestion word.

[0077] In the embodiments of this application, each candidate suggestion word has a corresponding user demand score. The user demand score represents the degree of matching between the candidate suggestion word and user needs.

[0078] In some embodiments of this application, the calculation method for user demand is described. Specifically, historical learning information may include a first knowledge point learned by the current user in a historical period; and / or, historical exam information may include a second knowledge point in the current user's exam in a historical period, and a third knowledge point in which the current user answered incorrectly; and / or historical work browsing information may include multiple preset prompts associated with preset interior design works browsed by the current user in a historical period, wherein the multiple preset prompts associated with preset interior design works may be pre-marked based on actual conditions. It is understood that the first knowledge point, second knowledge point, and third knowledge point can all be knowledge points in interior design content, such as wall stone dry-hanging construction technology, wall wood veneer construction technology, door and window decoration engineering construction, etc.

[0079] Accordingly, the user demand for the candidate prompt words can be determined through the following steps: determining the number of times the candidate prompt words appear in multiple first knowledge points, multiple second knowledge points, multiple second knowledge points, and multiple preset prompt words; and weighting and summing the number of appearances to obtain the user demand for the candidate prompt words, making the determined user demand more accurate.

[0080] In some embodiments of this application, the weights for weighted summation of occurrence counts can be determined as follows: determining the first historical moment of the most recently learned first knowledge point in historical learning information; determining the second historical moment of the most recently taken second knowledge point in historical exam information; determining the third historical moment of the most recently answered incorrectly third knowledge point in historical exam information; determining the fourth historical moment of the most recently viewed preset interior design work in historical work browsing information; and assigning different weights to the occurrence counts of the selected prompt words in multiple first knowledge points, multiple second knowledge points, multiple second knowledge points, and multiple preset prompt words based on the chronological order of the first, second, third, and fourth historical moments.

[0081] Since each first knowledge point in the historical learning information corresponds to a corresponding user learning time, the user learning time closest to the current time can be determined among multiple user learning times and used as the first historical time of the most recent first knowledge point in the historical learning information.

[0082] Since each second knowledge point in the historical exam information corresponds to a user's exam time, the user's exam time closest to the current time can be determined from among the user's exam times of multiple second knowledge points, and used as the second historical time of the most recent exam for the second knowledge point in the historical exam information.

[0083] Since each third knowledge point in the historical exam information corresponds to a user's exam time, the user's exam time closest to the current time can be determined from among the user's exam times for multiple third knowledge points, and this time can be used as the third historical time of the third knowledge point for which the answer was most recently wrong in the historical exam information.

[0084] Since each preset interior design work in the historical works browsing information can correspond to a corresponding user browsing time, the user browsing time closest to the current time can be determined among multiple user browsing times and used as the fourth historical moment of the preset interior design work that was most recently viewed in the historical works browsing information.

[0085] In the chronological order of the first, second, third, and fourth historical moments, the closer the historical moment is to the current time, the greater the weight of the occurrence frequency of the candidate suggestion word among multiple corresponding keywords. Taking the first, second, third, and fourth historical moments as an example, the weight of the occurrence frequency of the candidate suggestion word among multiple first keywords, the weight of the occurrence frequency of the candidate suggestion word among multiple second keywords, the weight of the occurrence frequency of the candidate suggestion word among multiple third keywords, and the weight of the occurrence frequency of the candidate suggestion word among multiple preset suggestions decreases in that order. In this way, a more accurate user demand can be obtained by weighted summation.

[0086] 202. Sort the multiple candidate prompts from highest to lowest according to user demand to obtain the first order.

[0087] 203. Output multiple candidate prompts in the first order.

[0088] In the embodiments of this application, multiple candidate prompt words are output in a first order. For example, a prompt word sequence formed by multiple candidate prompt words can be displayed, and the multiple candidate prompt words in the prompt word sequence are ordered in the first order. In this way, the user can first see the candidate prompt words with greater user demand, thereby selecting the desired target prompt word more quickly.

[0089] In some embodiments of this application, such as Figure 3 As shown, in Figures 1 to 2 Based on any of the embodiments shown, and according to historical learning information, historical exam information, and historical work browsing information, the prompt words needed by the current user are predicted, resulting in multiple candidate prompt words, which may include:

[0090] 301. Identify the first keyword among multiple first knowledge points, the second keyword among multiple second knowledge points, and the third keyword among multiple third knowledge points.

[0091] In the embodiments of this application, the first knowledge point, the second knowledge point, and the third knowledge point all include corresponding keywords. Keywords may include, for example, at least one of interior design style and interior design element. Interior design style may include, for example, modern style, cream style, Nordic style, natural wood style, etc. Interior design elements may include, for example, ceilings, doors and windows, tables and chairs, wall decorations, floor decorations, and the area range of the interior design, etc.

[0092] The interior design area range can be a preset area range encompassing the floor area of ​​the interior space. Alternatively, it can be a preset area range encompassing the area to be designed (including at least one of the floor area, wall area, and ceiling area).

[0093] 302. The set of the first keyword, the second keyword, the third keyword, and multiple preset prompt words is used as the prompt word set.

[0094] In the embodiments of this application, since the first keyword, the second keyword, the third keyword, and multiple preset prompt words may all be prompt words needed by the user, the set of the first keyword, the second keyword, the third keyword, and multiple preset prompt words can be used as the prompt word set.

[0095] 303. Based on the user demand for each prompt word in the prompt word set, determine multiple candidate prompt words in the prompt word set.

[0096] In the embodiments of this application, for each prompt word in the prompt word set, a corresponding user demand level can be determined, and then based on the user demand level, multiple candidate prompt words can be determined in the prompt word set. For example, prompt words in the prompt word set whose user demand level is greater than a preset demand level threshold can all be used as candidate prompt words, thereby making the candidate prompt words more in line with user needs.

[0097] In some embodiments of this application, determining multiple candidate prompt words based on the user demand for each prompt word in the prompt word set may include: sorting all prompt words in the prompt word set from largest to smallest according to the user demand for each prompt word in the prompt word set to obtain a second order; in the second order, determining a preset number of prompt words that rank highly and serving as multiple candidate prompt words, thereby avoiding an excessive number of candidate prompt words that would cause users to spend too much time searching for the prompt words they need, and improving the overall accuracy of the recommended candidate prompt words.

[0098] In some embodiments of this application, the user demand level of each prompt word in the prompt word set can be determined in the following way: for each prompt word in the prompt word set, determine the number of times the prompt word appears in multiple first keywords, multiple second keywords, multiple third keywords, and multiple preset prompt words; based on the number of occurrences, determine the user demand level of that prompt word in the prompt word set. It can be seen that, based on the number of occurrences, a user demand level that better matches user needs can be determined.

[0099] In some embodiments of this application, determining the user demand level of a prompt word in the prompt word set based on its frequency of occurrence may include: for the prompt word in the prompt word set, performing a weighted summation of the frequency of occurrence of the prompt word in multiple first keywords, multiple second keywords, multiple third keywords, and multiple preset prompt words to obtain a comprehensive frequency of occurrence; and determining the user demand level of the prompt word in the prompt word set based on the comprehensive frequency of occurrence, for example, the comprehensive frequency of occurrence can be directly used as the user demand level of the prompt word. It can be seen that by using weighted summation, a more accurate user demand level can be obtained, thereby making the determined candidate prompt words more in line with user needs.

[0100] The weighting of the frequency of the prompt word in multiple primary keywords, multiple secondary keywords, multiple tertiary keywords, and multiple preset prompt words can be set based on the chronological order of the first, second, third, and fourth historical moments. Taking the chronological order as first, second, third, and fourth historical moments as an example, the weighting of the frequency of the prompt word in multiple primary keywords, the weighting of the frequency of the prompt word in multiple secondary keywords, the weighting of the frequency of the prompt word in multiple tertiary keywords, and the weighting of the frequency of the prompt word in multiple preset prompt words decreases sequentially.

[0101] In some embodiments of this application, such as Figure 4 As shown, in Figures 1 to 3 Based on any of the embodiments shown, the plurality of candidate prompt words further includes a plurality of fourth prompt words. After obtaining the initial data of the interior design to be drawn, it may also include:

[0102] 401. Identify multiple interior design elements in the initial interior design data.

[0103] In embodiments of this application, multiple interior design elements in the initial interior design data may include, for example, ceilings, doors and windows, tables and chairs, wall decorations, floor decorations, and the range of interior design area.

[0104] The range of interior architectural design area can be a preset area range encompassing the interior floor area. Alternatively, the architectural design area can be a preset area range encompassing the area to be designed (including at least one of the floor area, wall area, and ceiling area), thus ensuring a better match between the determined target interior design and the initial interior design data.

[0105] In some embodiments of this application, interior design elements in initial interior design data can be identified using a neural network model. Specifically, determining multiple interior design elements in initial interior design data may include: obtaining a target neural network model for identifying interior design elements; inputting the initial interior design data into the target neural network model to receive the multiple interior design elements in the initial interior design data output by the target neural network model. The target neural network model for identifying interior design elements can be obtained through a corresponding model training dataset and model training, and is not limited thereto.

[0106] 402. Among multiple preset interior design works, identify the target interior design work that has at least one interior design element from the initial interior design data.

[0107] In the embodiments of this application, multiple preset interior design works can be obtained from a platform that provides an interior design work browsing function. Each preset interior design work is pre-marked with its own interior design elements. Therefore, by comparing the interior design elements, at least one target interior design work that has at least one interior design element in the initial interior design data can be determined from among the multiple preset interior design works.

[0108] 403. Use multiple preset prompts associated with the target interior design work as multiple fourth prompts.

[0109] In the embodiments of this application, since each preset interior design work is also pre-labeled with multiple preset prompts, after determining the target interior design work, the multiple preset prompts associated with the target interior design work can be directly used as multiple fourth prompts, and as at least a portion of multiple candidate prompts. This provides users with a richer selection of candidate prompts that better meet their needs, avoiding the need for users to manually input prompts and thus improving the drawing efficiency of the AI ​​model.

[0110] Secondly, based on the AI ​​model-based drawing method of the above embodiments, embodiments of this application provide an AI model-based drawing apparatus, which is used to execute the steps of any embodiment of the AI ​​model-based drawing method described above. Specifically, the AI ​​model-based drawing apparatus may include:

[0111] The first acquisition module is used to acquire the initial data of the interior design to be drawn;

[0112] The second acquisition module is used to acquire the current user's historical learning information, historical exam information, and historical works browsing information;

[0113] The prediction module is used to predict the prompt words needed by the current user based on historical learning information, historical exam information, and historical works browsing information, and obtain multiple candidate prompt words;

[0114] The selection module outputs multiple candidate suggestions, allowing the current user to choose multiple target suggestions from among them.

[0115] The drawing module is used to input multiple target prompts and initial interior design data into a preset AI drawing model, and to receive the interior design renderings output by the AI ​​drawing model.

[0116] Thirdly, embodiments of this application provide a computer device that integrates any of the AI ​​model-based drawing apparatuses provided in the embodiments of this application. The computer device includes a processor and a memory, the memory storing a computer program configured to be executed by the processor to implement the AI ​​model-based drawing method as described in any of the above embodiments, for example:

[0117] The system acquires initial data for the interior design to be drawn; it acquires the current user's historical learning information, historical exam information, and historical work browsing information; based on the historical learning information, historical exam information, and historical work browsing information, it predicts the prompts needed by the current user and obtains multiple candidate prompts; it outputs multiple candidate prompts for the current user to select multiple target prompts from among them; and it inputs the multiple target prompts and the initial data for the interior design into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0118] Fourthly, embodiments of this application provide a computer device that integrates any of the AI ​​model-based drawing devices provided in embodiments of this application. For example... Figure 5 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0119] The computer device may include components such as a processor 501 with one or more processing cores, a storage unit 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will understand that... Figure 5The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0120] The processor 501 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 502, and by calling data stored in the storage unit 502, thereby providing overall monitoring of the computer device. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 501.

[0121] Storage unit 502 can be used to store software programs and modules. Processor 501 executes various functional applications and data processing by running the software programs and modules stored in storage unit 502. Storage unit 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 502 may also include a memory controller to provide processor 501 with access to storage unit 502.

[0122] The computer equipment also includes a power supply 503 that supplies power to the various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0123] The computer device may also include an input unit 504, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0124] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 501 in the computer device loads the executable files corresponding to the processes of one or more application programs into the storage unit 502 according to the following instructions, and the processor 501 runs the application programs stored in the storage unit 502 to realize various functions, such as:

[0125] The system acquires initial data for the interior design to be drawn; it acquires the current user's historical learning information, historical exam information, and historical work browsing information; based on the historical learning information, historical exam information, and historical work browsing information, it predicts the prompts needed by the current user and obtains multiple candidate prompts; it outputs multiple candidate prompts for the current user to select multiple target prompts from among them; and it inputs the multiple target prompts and the initial data for the interior design into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0126] Fifthly, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. The computer-readable storage medium stores a computer program configured to be executed by a processor to implement the AI ​​model-based drawing method as described in any of the preceding claims, for example:

[0127] The system acquires initial data for the interior design to be drawn; it acquires the current user's historical learning information, historical exam information, and historical work browsing information; based on the historical learning information, historical exam information, and historical work browsing information, it predicts the prompts needed by the current user and obtains multiple candidate prompts; it outputs multiple candidate prompts for the current user to select multiple target prompts from among them; and it inputs the multiple target prompts and the initial data for the interior design into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0128] Sixthly, embodiments of this application provide a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform an AI model-based drawing method as described in any of the preceding claims, for example:

[0129] The system acquires initial data for the interior design to be drawn; it acquires the current user's historical learning information, historical exam information, and historical work browsing information; based on the historical learning information, historical exam information, and historical work browsing information, it predicts the prompts needed by the current user and obtains multiple candidate prompts; it outputs multiple candidate prompts for the current user to select multiple target prompts from among them; and it inputs the multiple target prompts and the initial data for the interior design into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model.

[0130] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A drawing method based on an AI model, characterized in that, The AI ​​model-based drawing method includes: Obtain the initial data for the interior design to be drawn; the initial data for the interior design includes the decoration design drawings of the bare structure and the interior design line drawings; The system retrieves the current user's historical learning information, historical exam information, and historical work browsing information. The historical learning information includes the first knowledge point learned by the current user during a historical period. The historical exam information includes the second knowledge point in the exam taken by the current user during a historical period, and the third knowledge point in which the current user answered incorrectly. The historical work browsing information includes multiple preset prompts associated with preset interior design works browsed by the current user during a historical period. Based on the historical learning information, the historical exam information, and the historical works browsing information, the prompt words needed by the current user are predicted, resulting in multiple candidate prompt words; Output multiple candidate suggestion words so that the current user can select multiple target suggestion words from the multiple candidate suggestion words; Input multiple target prompts and the initial interior design data into a preset AI drawing model to receive the interior design renderings output by the AI ​​drawing model; The method involves predicting the prompt words needed by the current user based on the historical learning information, the historical exam information, and the historical works browsing information, resulting in multiple candidate prompt words, including: Identify the first keyword among multiple first knowledge points, the second keyword among multiple second knowledge points, and the third keyword among multiple third knowledge points; The first keyword, the second keyword, the third keyword, and a set of multiple preset prompt words are used as the prompt word set; Based on the user demand for each prompt word in the prompt word set, a plurality of candidate prompt words are determined in the prompt word set.

2. The drawing method based on an AI model as described in claim 1, characterized in that, The output of multiple candidate prompt words includes: Obtain the user demand level for each of the candidate suggestion words; Based on the user demand level, the multiple candidate prompt words are sorted from largest to smallest to obtain the first order; According to the first order, output multiple candidate prompt words.

3. The drawing method based on an AI model as described in claim 2, characterized in that, The user demand for the candidate suggestion words is determined through the following steps: Determine the number of times the candidate prompt words appear in multiple first knowledge points, multiple second knowledge points, multiple third knowledge points, and multiple preset prompt words; The user demand for the candidate suggestion words is obtained by weighted summation of the occurrence counts.

4. The drawing method based on an AI model as described in claim 3, characterized in that, The weights for the weighted summation of the occurrence counts are determined in the following way: Determine the first historical moment of the most recently learned first knowledge point in the historical learning information; Determine the second historical moment of the second knowledge point in the most recent exam from the historical exam information; Determine the third historical moment of the most recent incorrect answer to the third knowledge point in the historical examination information; Determine the fourth historical moment of the preset interior design work that was most recently viewed in the historical works browsing information; Based on the chronological order of the first historical moment, the second historical moment, the third historical moment, and the fourth historical moment, different weights are assigned to the occurrence frequency of the candidate prompt words in multiple first knowledge points, multiple second knowledge points, multiple second knowledge points, and multiple preset prompt words.

5. The drawing method based on an AI model as described in claim 4, characterized in that, Based on the user demand level of each prompt word in the prompt word set, a plurality of candidate prompt words are determined in the prompt word set, including: Based on the user demand for the prompt words in the prompt word set, all prompt words in the prompt word set are sorted from largest to smallest to obtain a second order; In the second order, a preset number of prompt words are determined to be ranked first, and these are used as multiple candidate prompt words.

6. The drawing method based on an AI model as described in claim 1, characterized in that, The multiple candidate prompt words also include multiple fourth prompt words. After obtaining the initial data of the interior design to be drawn, the process further includes: Identify multiple interior design elements in the initial interior design data; Among multiple preset interior design works, a target interior design work that has at least one interior design element from the initial interior design data is identified. Multiple preset prompt words associated with the target interior design work are used as multiple fourth prompt words.

7. The drawing method based on an AI model as described in claim 6, characterized in that, Identify multiple interior design elements in the initial interior design data, including: Obtain the target neural network model for identifying interior design elements; The initial interior design data is input into the target neural network model to receive multiple interior design elements from the initial interior design data output by the target neural network model.

8. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program configured to be executed by the processor to implement the AI ​​model-based drawing method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program configured to be executed by a processor to implement the AI ​​model-based drawing method according to any one of claims 1 to 7.

Images