Architectural design auxiliary system and method based on artificial intelligence

Abstract

The invention is suitable for the technical field of building design artificial intelligence application, and provides a building design auxiliary system and method based on artificial intelligence, and the method comprises the steps: obtaining an initial storage space distribution scheme of a target office space, and determining a corresponding designated work purpose and a target functional department, and obtaining video data of the reference office area used by the target functional department when the target functional department completes the specified work purpose. The storage efficiency and convenience of the office space can be remarkably improved by accurately optimizing the storage resource allocation and layout design of the target office space. By acquiring the video data in the reference office area, extracting the effective fragment of the interaction behavior between the staff and the storage area, and combining the data analysis in the two aspects of frequency and time, the distribution proportion and layout of the storage space are scientifically adjusted, so that the design better meets the actual demand.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence application in architectural design, and in particular relates to an artificial intelligence-based architectural design auxiliary system and method. Background Art

[0002] In the field of architectural design, traditional office space design usually relies on the designer's experience and general industry specifications for planning, especially in the allocation and layout of storage space. These methods are usually based on hypothetical usage scenarios or fixed resource allocation ratios, and it is difficult to fully consider the needs and behavioral characteristics of actual users. On this basis, designers may refer to the empirical data of similar projects, but they cannot dynamically adapt to the changes in storage resource requirements and the specific characteristics of personnel flow in different scenarios, resulting in low space utilization efficiency, uneven resource allocation or unreasonable layout.

[0003] Existing technologies mainly rely on static data or general specifications when trying to optimize space design, such as setting storage areas through area allocation formulas or fixed ratios. However, this approach shows obvious limitations when faced with complex and changing office scenarios. For high-frequency use areas, efficiency may decrease due to insufficient storage resources, while low-frequency use areas may cause waste due to excess resources. In addition, existing design methods lack in-depth consideration of ease of use, such as whether the relative position of the storage area and the work area is reasonable, and whether the time spent on movement of staff in daily operations is optimized. These factors make it difficult to derive accurate design solutions through traditional experience and specifications. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based architectural design assistance system and method, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: an artificial intelligence-based architectural design assistance method, the method comprising:

[0006] Obtain the initial storage space allocation plan for the target office space, determine the corresponding designated work purposes and target functional departments, and obtain video data of the reference office area used by the target functional departments when completing the designated work purposes;

[0007] Screen the video data and extract valid video clips containing the interaction between the staff and the storage area in the reference office area;

[0008] Based on the effective video clips, the storage area interaction frequency of the staff in the reference office area is calculated, and the storage area interaction frequency is compared with the preset reference frequency to obtain the frequency deviation degree value;

[0009] The effective video clips are further screened according to the contact duration, and the key interaction video clips are extracted. The key interaction video clips are analyzed, and the average time taken by the staff to move from the work area to the storage area is calculated. The average time taken is compared with the preset benchmark time to obtain the time deviation degree value;

[0010] The initial storage space allocation plan is optimized and adjusted in turn through the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation plan.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of calculating the storage area interaction frequency of the staff in the reference office area based on the effective video clips, comparing the storage area interaction frequency with the preset reference frequency, and obtaining the frequency deviation degree value include:

[0012] Extract all behavioral data of staff interacting with the storage area in the reference office area from valid video clips, ensure that the data covers core information such as timestamps and number of interactions, and exclude invalid or abnormal data;

[0013] Based on all the extracted behavioral data, calculate the staff's interaction frequency with the storage area within a specified time period;

[0014] The calculated storage area interaction frequency is compared with the preset reference frequency, the deviation between the two is analyzed, and the frequency deviation degree value is output in numerical form.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the steps of further screening the effective video clips according to the contact duration, extracting the key interaction video clips, analyzing the key interaction video clips, calculating the average time taken by the staff to move from the work area to the storage area, and comparing the average time taken with the preset reference time to obtain the time deviation degree value include:

[0017] The parts of the valid video clips involving the contact between the staff and the storage area are sorted by contact duration, and the key interaction video clips with a duration greater than the preset duration are screened out;

[0018] Analyze the selected key interactive video clips, track the path of the staff from the work area to the storage area, calculate the time consumed for each movement, and finally calculate the average time consumed as a quantitative indicator;

[0019] The calculated average time is compared with the preset benchmark time, the deviation between the two is analyzed, and the time deviation degree value is output in numerical form.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, the preset duration refers to the minimum effective time threshold required for the staff to perform actual interactive behavior in the storage area, which is used to eliminate short-term or accidental contact;

[0021] The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the steps of optimizing and adjusting the initial storage space allocation scheme in sequence by using the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation scheme include:

[0023] Extract the specific storage space allocation ratio from the initial storage space allocation plan, adjust the storage space allocation ratio using the frequency deviation value, optimize the allocation weight of the storage space of the target office space, and give priority to increasing the storage resource allocation ratio of high-frequency interaction areas;

[0024] Extract the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjust the distance from the storage area to the work area in combination with the time deviation degree value;

[0025] The optimization results of both frequency and time dimensions are integrated, and the adjusted storage resource allocation ratio and spatial layout are combined into the final storage space allocation plan.

[0026] An artificial intelligence-based architectural design assistance system, the system comprising: a data acquisition module, a video data screening module, a frequency dimension analysis module, a time dimension analysis module and a final solution generation module, wherein:

[0027] A data acquisition module is used to obtain an initial storage space allocation plan for a target office space, determine its corresponding designated work purpose and target functional department, and obtain video data of a reference office area used by the target functional department when completing the designated work purpose;

[0028] A video data screening module, used to screen the video data and extract valid video clips containing the interaction between the staff and the storage area in the reference office area;

[0029] A frequency dimension analysis module is used to calculate the storage area interaction frequency of the staff in the reference office area based on the effective video clips, compare the storage area interaction frequency with the preset reference frequency, and obtain the frequency deviation degree value;

[0030] The time dimension analysis module is used to further filter the effective video clips according to the contact duration, extract the key interaction video clips, analyze the key interaction video clips, calculate the average time taken by the staff to move from the work area to the storage area, and compare the average time taken with the preset benchmark time to obtain the time deviation degree value;

[0031] The final solution generation module is used to optimize and adjust the initial storage space allocation solution in turn through the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation solution.

[0032] As a further limitation of the technical solution of the embodiment of the present invention, the frequency dimension analysis module specifically includes:

[0033] A video data extraction unit is used to extract all behavioral data of the staff interacting with the storage area in the reference office area from valid video clips, ensuring that the data covers the core information of timestamps and interaction times, and excluding invalid or abnormal data;

[0034] An interaction frequency calculation unit, used to calculate the interaction frequency of the staff in the storage area within a specified time period based on all extracted behavior data;

[0035] A frequency deviation degree value output unit is used to compare the calculated storage area interaction frequency with a preset reference frequency, analyze the deviation between the two, and output the frequency deviation degree value in numerical form;

[0036] The preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

[0037] As a further limitation of the technical solution of the embodiment of the present invention, the time dimension analysis module specifically includes:

[0038] A video data extraction unit, used to sort the parts of the valid video clips involving the contact between the staff and the storage area according to the contact duration, and screen out key interaction video clips whose duration is greater than a preset duration;

[0039] The average time calculation unit is used to analyze the selected key interaction video clips, track the path of the staff from the work area to the storage area, calculate the time consumed for each movement, and finally calculate the average time consumed as a quantitative indicator;

[0040] A time deviation degree value output unit is used to compare the calculated average time consumption with the preset reference time, analyze the deviation between the two, and output the time deviation degree value in numerical form;

[0041] The preset duration refers to the minimum effective time threshold required for staff to conduct actual interactive behaviors in the storage area, which is used to eliminate short-term or accidental contacts;

[0042] The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

[0043] As a further limitation of the technical solution of the embodiment of the present invention, the final solution generation module specifically includes:

[0044] A ratio optimization unit is used to extract a specific storage space allocation ratio from the initial storage space allocation plan, adjust the storage space allocation ratio using the frequency deviation value, optimize the allocation weight of the storage space of the target office space, and give priority to increasing the storage resource allocation ratio of the high-frequency interaction area;

[0045] A layout optimization unit is used to extract the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjust the distance from the storage area to the work area in combination with the time deviation degree value;

[0046] The final plan generation unit is used to integrate the optimization results of the two dimensions of frequency and time, and integrate the adjusted storage resource allocation ratio and space layout into the final storage space allocation plan.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] By accurately optimizing the storage resource allocation and layout design of the target office space, the efficiency and convenience of office space storage have been significantly improved. By obtaining video data in the reference office area, extracting effective clips of the interaction between the staff and the storage area, and combining frequency and time data analysis, the allocation ratio and layout of the storage space are scientifically adjusted to make the design more in line with actual needs.

[0049] In terms of storage resource allocation, the present invention can dynamically adjust the resource allocation weights of high-frequency interaction areas through frequency analysis, effectively avoiding the problems of resource redundancy and insufficient allocation. At the same time, by screening key interaction behaviors and analyzing path time consumption, the present invention further optimizes the relative position of the storage area and the work area, reduces the movement time of staff in daily operations, and improves the overall space utilization efficiency.

[0050] The present invention combines data analysis technology with space design concepts, provides quantitative basis and scientific decision-making support for office space, and breaks the limitations of traditional empirical design. At the same time, it has a wide range of applications, not only serving office spaces, but also being extended to medical, industrial, commercial and other fields, providing reference value for optimizing storage needs of various types of spaces. Through this systematic optimization method, the design of storage space is more reasonable and efficient, and it helps to promote the development of the field of architectural design towards intelligence and dataization, which has important technical significance and practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0052] Figure 2 A flow chart of obtaining a frequency deviation degree value in a method provided in an embodiment of the present invention;

[0053] Figure 3 A flow chart of obtaining a time deviation degree value in a method provided in an embodiment of the present invention;

[0054] Figure 4 A flowchart of obtaining a final storage space allocation solution in the method provided in an embodiment of the present invention;

[0055] Figure 5 An application architecture diagram of a system provided by an embodiment of the present invention;

[0056] Figure 6 A structural block diagram of a frequency dimension analysis module in a system provided by an embodiment of the present invention;

[0057] Figure 7 A structural block diagram of a time dimension analysis module in a system provided by an embodiment of the present invention;

[0058] Figure 8 This is a structural block diagram of a final solution generation module in a system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0061] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0062] Specifically, an artificial intelligence-based architectural design assistance method comprises the following steps:

[0063] Step S100, obtaining an initial storage space allocation plan for a target office space, determining its corresponding designated work purpose and target functional department, and obtaining video data of a reference office area used by the target functional department when completing the designated work purpose.

[0064] In the embodiment of the present invention, the target office space is an office space that is being planned or to be built, and its main functions and uses have been preliminarily determined, such as for meetings, collaborative work, or independent task processing. This space serves a specific functional department and supports clear work scenarios and needs. The design needs to be planned in combination with the actual use and space characteristics.

[0065] The initial storage space allocation plan is usually derived from architectural design planning, industry standards and reference case analysis, and may also refer to the results of user demand research. This plan includes the overall allocation ratio of storage space, the allocation of different functional areas (such as file storage, equipment storage or personal item storage area, etc.), and the preliminary storage area layout.

[0066] The designated work purpose and target functional department can be determined by analyzing the functional positioning of the target office space. For example, the type of work tasks that the space needs to support can be determined based on the planned use purpose, and the functional department responsible for the task, such as the R&D team, sales team, or administrative support department, can be confirmed through communication with the project leader.

[0067] To obtain video data of reference office areas, it is necessary to match office spaces with similar functions and uses as the target space in historical data. These reference areas are usually areas that have been used by the target functional department before and can reflect similar work scenes and storage needs. By coordinating with the facility management or technical support department to obtain relevant video data and ensure privacy protection, the monitoring data of the appropriate time period and area can be screened to provide materials for subsequent analysis.

[0068] Furthermore, the artificial intelligence-based architectural design assistance method further includes the following steps:

[0069] Step S200 , screening the video data to extract valid video clips containing the interaction between the staff and the storage area in the reference office area.

[0070] In an embodiment of the present invention, the collected video data of the reference office area is uploaded to a video processing platform to ensure data format compatibility, and the data is preliminarily cleaned to remove irrelevant time periods or images that do not meet the requirements, such as idle time periods or images with no human activities.

[0071] Using video analysis technology, a pre-trained behavior detection model is used to identify behaviors involving people interacting with storage areas in the video. These behaviors usually include people approaching storage areas, opening or closing storage devices, and storing and retrieving items.

[0072] Set filtering conditions for behavior recognition, such as contact distance, dwell time, interaction action type, etc., to further filter out irrelevant images and ensure that the extracted clips only include actual interaction activities.

[0073] Conduct a secondary review of the selected interaction fragments to ensure that these fragments cover different time periods and usage scenarios to avoid affecting the analysis results due to uneven data samples.

[0074] The final screened valid interaction fragments are saved to the specified storage path to provide a data basis for subsequent frequency calculation and behavior analysis.

[0075] Furthermore, the artificial intelligence-based architectural design assistance method further includes the following steps:

[0076] Step S300, based on the effective video clips, calculate the storage area interaction frequency of the staff in the reference office area, compare the storage area interaction frequency with the preset reference frequency, and obtain a frequency deviation degree value.

[0077] Specifically, Figure 2 A flow chart for obtaining a frequency deviation degree value is shown.

[0078] The method of calculating the storage area interaction frequency of the staff in the reference office area based on the effective video clips and comparing the storage area interaction frequency with the preset reference frequency to obtain the frequency deviation degree value specifically includes the following steps:

[0079] Step S301, extracting all behavioral data of the staff interacting with the storage area in the reference office area from the valid video clips, ensuring that the data covers the core information of timestamp and number of interactions, and excluding invalid or abnormal data;

[0080] Step S302, based on all extracted behavior data, calculating the staff's storage area interaction frequency within a specified time period;

[0081] Step S303, comparing the calculated storage area interaction frequency with a preset reference frequency, analyzing the deviation between the two, and outputting a frequency deviation degree value in numerical form.

[0082] The preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

[0083] In the embodiment of the present invention, computer vision technology and behavior recognition algorithms are used to process valid video clips and automatically detect the interactive behaviors of staff members in the storage area. The types of behaviors detected include approaching the storage area, opening the cabinet door, storing and retrieving items, etc., to ensure that each interactive behavior is accurately marked. The core information of the interactive behavior is extracted, including the timestamp (the specific time when the interaction occurred), the location of the storage area, and the number of interactions, which is used to quantify the behavioral data.

[0084] Screen the extracted behavioral data to exclude invalid or abnormal data. For example, filter out misidentified actions (such as non-interactive behaviors marked as interactive), or remove redundant records (such as the same interaction is marked multiple times). Ensure that the remaining data can truly reflect the actual interaction between the staff and the storage area.

[0085] The filtered behavior data is classified and summarized according to the specified time period (such as daily, weekly or custom time period) to calculate the interaction frequency of the storage area. The frequency calculation formula is: the number of interactions divided by the total duration in the time period. For example, if there are 30 interactions in a day, the interaction frequency is 30 / 1 day, that is, 30 times per day.

[0086] The calculated storage area interaction frequency is compared with the preset reference frequency to calculate the frequency deviation value. The deviation value can be expressed as a percentage, and the calculation formula is: deviation percentage = ((actual frequency - reference frequency) / reference frequency) × 100%. For example, the reference frequency is 20 times / day, the actual frequency is 30 times / day, and the deviation is ((30-20) / 20) × 100% = 50%. This result shows that the actual usage frequency is 50% higher than expected.

[0087] The benefit of this approach is that it can accurately quantify the usage requirements of storage areas in a data-driven way, avoiding the design errors based on traditional experience or assumptions. Through the analysis of frequency deviation, it can be found whether the allocation of storage space is insufficient or redundant, providing a scientific basis for optimizing the design.

[0088] As for the development prospects of existing technologies, this method combines behavior detection with architectural design, promoting the intelligent development of space planning. It can help designers better understand user behavior, provide personalized and dynamically optimized design solutions, and provide a data foundation for future intelligent buildings and human-computer interaction design.

[0089] Furthermore, the artificial intelligence-based architectural design assistance method further includes the following steps:

[0090] Step S400, further filter the valid video clips according to the contact duration, extract the key interaction video clips, analyze the key interaction video clips, calculate the average time it takes for the staff to move from the work area to the storage area, and compare the average time with the preset benchmark time to obtain the time deviation degree value.

[0091] Specifically, Figure 3 A flow chart for obtaining a time deviation degree value is shown.

[0092] The effective video clips are further screened according to the contact duration, and the key interaction video clips are extracted. The key interaction video clips are analyzed, and the average time taken by the staff to move from the work area to the storage area is calculated. The average time taken is compared with the preset benchmark time, and the time deviation degree value is obtained. Specifically, the following steps are included:

[0093] Step S401, sorting the parts of the valid video clips involving the contact between the staff and the storage area according to the contact duration, and screening out key interaction video clips whose duration is greater than a preset duration;

[0094] Step S402, analyzing the selected key interaction video clips, tracking the path of the staff moving from the work area to the storage area, and calculating the time consumed for each movement, and finally calculating the average time consumed as a quantitative indicator;

[0095] Step S403, comparing the calculated average time consumption with the preset reference time, analyzing the deviation between the two, and outputting the time deviation degree value in numerical form.

[0096] The preset duration refers to the minimum effective time threshold required for staff to conduct actual interactive behaviors in the storage area, which is used to eliminate short-term or accidental contacts;

[0097] The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

[0098] In the embodiment of the present invention, the effective video clips are processed, and the interaction between the staff and the storage area is detected using computer vision technology, and the duration of each contact is recorded. The video clips are sorted by time according to the contact duration, and a preset duration is set as a screening threshold, such as 2 seconds. Clips with a duration greater than the preset duration are screened out. These key interaction clips can truly reflect the effective use of the storage area by the staff.

[0099] Perform path tracking analysis on the selected key interaction segments, and use the positioning algorithm to extract the trajectory data of the staff moving from the work area to the storage area. Combine the trajectory and timestamp to calculate the time consumed for each movement. For example, it takes 8 seconds, 6 seconds, and 7 seconds for a staff member to move from the desk to the storage area, and record these times as basic data.

[0100] All movement times are counted and the average is calculated as an important quantitative indicator reflecting the convenience of the current layout. For example, the time consumption data for multiple interactions are 8 seconds, 6 seconds, and 7 seconds respectively, and the average time consumption is calculated to be 7 seconds. This average time consumption is compared with the preset benchmark time (for example, 5 seconds) to obtain the time deviation degree value. The time deviation degree value can be expressed as a percentage, for example, ((7-5) / 5)×100%=40%, indicating that the movement time consumption is 40% higher than expected, reflecting that the storage area may be located in an unreasonable manner or there are problems with the path design.

[0101] Through the above analysis, we can accurately identify the problem points in the space design, such as whether the storage area distribution needs to be adjusted or whether the path needs to be optimized. This method helps to optimize the space layout in a data-driven way and eliminate the design errors caused by subjective judgment.

[0102] The advantage of this setting is that it can eliminate accidental or invalid behavior data, ensure the accuracy of the analysis, and reflect the advantages and disadvantages of storage space design through quantitative results, providing a scientific basis for space optimization. This method has wide applicability and can be applied not only to the optimization of office space, but also to the medical, industrial and commercial fields. For example, in a hospital, the movement lines of medical staff can be analyzed to optimize the drug storage area, or the layout of the parts storage area can be optimized in a factory. In the future, this space optimization technology based on behavioral data will become an important tool for intelligent building and dynamic space design, promoting the development of design from experience-driven to data-driven.

[0103] Furthermore, the artificial intelligence-based architectural design assistance method further includes the following steps:

[0104] Step S500, optimizing and adjusting the initial storage space allocation plan in sequence through the frequency deviation degree value and the time deviation degree value to obtain a final storage space allocation plan.

[0105] Specifically, Figure 4 A flow chart for obtaining the final storage space allocation plan is shown.

[0106] Among them, the initial storage space allocation plan is optimized and adjusted in turn through the frequency deviation degree value and the time deviation degree value, and the final storage space allocation plan specifically includes the following steps:

[0107] Step S501, extracting a specific storage space allocation ratio from the initial storage space allocation plan, adjusting the storage space allocation ratio using the frequency deviation value, optimizing the allocation weight of the storage space of the target office space, and giving priority to increasing the storage resource allocation ratio of the high-frequency interaction area;

[0108] Step S502, extracting the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjusting the distance from the storage area to the work area in combination with the time deviation degree value;

[0109] Step S503, combining the optimization results of the two dimensions of frequency and time, and integrating the adjusted storage resource allocation ratio and space layout into a final storage space allocation plan.

[0110] In an embodiment of the present invention, the specific allocation ratio of the storage space is extracted from the initial storage space allocation plan to clarify the resource allocation of each functional area. For example, the file storage area accounts for 30%, the equipment storage area accounts for 50%, and the personal item storage area accounts for 20%. The allocation ratio is optimized using the frequency deviation degree value, and the storage resource ratio of the high-frequency interaction area is increased first. If the frequency deviation degree value is 50%, it means that the actual usage frequency of the equipment storage area is 50% higher than the design requirement. The adjusted ratio increases the equipment storage area to 75%, while reducing the ratio of the file storage area and the personal item storage area to 15% and 10%. This optimization can ensure that high-frequency use areas receive more adequate resource allocation and reduce resource waste in low-frequency use areas.

[0111] Extract the spatial layout information of the target office space storage area from the initial storage space allocation plan to determine the relative distance between the storage area and the work area. For example, storage area A is 15 meters away from the work area, and storage area B is 20 meters away from the work area. Combined with the time deviation degree value, make adjustments to optimize the location of the storage area. If the time deviation degree value is 40%, it means that the staff spends 40% more time than expected during the movement process. By shortening the distance between storage area A and the work area to 10 meters and adjusting the location of storage area B to be away from the core work area, the movement time of the high-frequency storage area can be reduced, while optimizing the space utilization of the low-frequency storage area, achieving the effect of rationalizing the overall movement line.

[0112] In one example, the initial resource ratio of the equipment storage area was 50%, and the frequency deviation value was 50%, which was adjusted to 75% through optimization. The ratios of the file storage area and the personal item storage area were reduced to 15% and 10%, respectively. The initial distance of storage area A was 15 meters, and the average moving time was 7 seconds, while the preset benchmark time was 5 seconds. By adjusting the distance of storage area A to 10 meters, the moving time dropped to 5 seconds, close to the benchmark value, optimizing the convenience of the space while freeing up more resources and locations to serve high-frequency use areas.

[0113] The combination of the two adjustments makes the allocation ratio and spatial layout of storage space more in line with actual usage needs, which not only improves the resource supply in high-frequency use areas, but also reduces resource waste in low-frequency use areas. The optimized design not only meets storage needs, but also improves efficiency and convenience, and ultimately achieves reasonable allocation and efficient use of space, providing data-driven scientific support for the overall architectural design, reflecting a significant improvement in humanity and practicality.

[0114] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0115] Among them, in another preferred embodiment provided by the present invention, an artificial intelligence-based architectural design assistance system includes:

[0116] The data acquisition module 100 is used to obtain an initial storage space allocation plan for a target office space, determine its corresponding designated work purpose and target functional department, and obtain video data of a reference office area used by the target functional department when completing the designated work purpose.

[0117] In the embodiment of the present invention, the target office space is an office space that is being planned or to be built, and its main functions and uses have been preliminarily determined, such as for meetings, collaborative work, or independent task processing. This space serves a specific functional department and supports clear work scenarios and needs. The design needs to be planned in combination with the actual use and space characteristics.

[0118] The initial storage space allocation plan is usually derived from architectural design planning, industry standards and reference case analysis, and may also refer to the results of user demand research. This plan includes the overall allocation ratio of storage space, the allocation of different functional areas (such as file storage, equipment storage or personal item storage area, etc.), and the preliminary storage area layout.

[0119] The designated work purpose and target functional department can be determined by analyzing the functional positioning of the target office space. For example, the type of work tasks that the space needs to support can be determined based on the planned use purpose, and the functional department responsible for the task, such as the R&D team, sales team, or administrative support department, can be confirmed through communication with the project leader.

[0120] To obtain video data of reference office areas, it is necessary to match office spaces with similar functions and uses as the target space in historical data. These reference areas are usually areas that have been used by the target functional department before and can reflect similar work scenes and storage needs. By coordinating with the facility management or technical support department to obtain relevant video data and ensure privacy protection, the monitoring data of the appropriate time period and area can be screened to provide materials for subsequent analysis.

[0121] Furthermore, the artificial intelligence-based architectural design assistance system also includes:

[0122] The video data screening module 200 is used to screen the video data and extract valid video clips containing the interaction between the staff and the storage area in the reference office area.

[0123] In an embodiment of the present invention, the collected video data of the reference office area is uploaded to a video processing platform to ensure data format compatibility, and the data is preliminarily cleaned to remove irrelevant time periods or images that do not meet the requirements, such as idle time periods or images with no human activities.

[0124] Using video analysis technology, a pre-trained behavior detection model is used to identify behaviors involving people interacting with storage areas in the video. These behaviors usually include people approaching storage areas, opening or closing storage devices, and storing and retrieving items.

[0125] Set filtering conditions for behavior recognition, such as contact distance, dwell time, interaction action type, etc., to further filter out irrelevant images and ensure that the extracted clips only include actual interaction activities.

[0126] Conduct a secondary review of the selected interaction fragments to ensure that these fragments cover different time periods and usage scenarios to avoid affecting the analysis results due to uneven data samples.

[0127] The final screened valid interaction fragments are saved to the specified storage path to provide a data basis for subsequent frequency calculation and behavior analysis.

[0128] Furthermore, the artificial intelligence-based architectural design assistance system also includes:

[0129] The frequency dimension analysis module 300 is used to calculate the storage area interaction frequency of the staff in the reference office area based on the effective video clips, compare the storage area interaction frequency with the preset reference frequency, and obtain the frequency deviation degree value.

[0130] Specifically, Figure 6 It shows a structural block diagram of the frequency dimension analysis module 300 in the system provided by an embodiment of the present invention.

[0131] Among them, in the preferred implementation manner provided by the present invention, the frequency dimension analysis module 300 specifically includes:

[0132] The video data extraction unit 301 is used to extract all behavioral data of the staff interacting with the storage area in the reference office area from the valid video clips, ensure that the data covers the core information of timestamp and number of interactions, and exclude invalid or abnormal data;

[0133] An interaction frequency calculation unit 302, for calculating the storage area interaction frequency of the staff within a specified time period based on all extracted behavior data;

[0134] The frequency deviation degree value output unit 303 is used to compare the calculated storage area interaction frequency with the preset reference frequency, analyze the deviation between the two, and output the frequency deviation degree value in numerical form;

[0135] The preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

[0136] In the embodiment of the present invention, computer vision technology and behavior recognition algorithms are used to process valid video clips and automatically detect the interactive behaviors of staff members in the storage area. The types of behaviors detected include approaching the storage area, opening the cabinet door, storing and retrieving items, etc., to ensure that each interactive behavior is accurately marked. The core information of the interactive behavior is extracted, including the timestamp (the specific time when the interaction occurred), the location of the storage area, and the number of interactions, which is used to quantify the behavioral data.

[0137] Screen the extracted behavioral data to exclude invalid or abnormal data. For example, filter out misidentified actions (such as non-interactive behaviors marked as interactive), or remove redundant records (such as the same interaction is marked multiple times). Ensure that the remaining data can truly reflect the actual interaction between the staff and the storage area.

[0138] The filtered behavior data is classified and summarized according to the specified time period (such as daily, weekly or custom time period) to calculate the interaction frequency of the storage area. The frequency calculation formula is: the number of interactions divided by the total duration in the time period. For example, if there are 30 interactions in a day, the interaction frequency is 30 / 1 day, that is, 30 times per day.

[0139] The calculated storage area interaction frequency is compared with the preset reference frequency to calculate the frequency deviation value. The deviation value can be expressed as a percentage, and the calculation formula is: deviation percentage = ((actual frequency - reference frequency) / reference frequency) × 100%. For example, the reference frequency is 20 times / day, the actual frequency is 30 times / day, and the deviation is ((30-20) / 20) × 100% = 50%. This result shows that the actual usage frequency is 50% higher than expected.

[0140] The benefit of this approach is that it can accurately quantify the usage requirements of storage areas in a data-driven way, avoiding the design errors based on traditional experience or assumptions. Through the analysis of frequency deviation, it can be found whether the allocation of storage space is insufficient or redundant, providing a scientific basis for optimizing the design.

[0141] As for the development prospects of existing technologies, this method combines behavior detection with architectural design, promoting the intelligent development of space planning. It can help designers better understand user behavior, provide personalized and dynamically optimized design solutions, and provide a data foundation for future intelligent buildings and human-computer interaction design.

[0142] Furthermore, the artificial intelligence-based architectural design assistance system also includes:

[0143] The time dimension analysis module 400 is used to further filter the effective video segments according to the contact duration, extract the key interaction video segments, analyze the key interaction video segments, calculate the average time it takes for the staff to move from the work area to the storage area, and compare the average time with the preset benchmark time to obtain the time deviation degree value.

[0144] Specifically, Figure 7 It shows a structural block diagram of the time dimension analysis module 400 in the system provided by an embodiment of the present invention.

[0145] In a preferred embodiment of the present invention, the time dimension analysis module 400 specifically includes:

[0146] The video data extraction unit 401 is used to sort the parts of the valid video clips involving the contact between the staff and the storage area according to the contact duration, and filter out the key interaction video clips whose duration is greater than a preset duration;

[0147] The average time consumption calculation unit 402 is used to analyze the selected key interaction video clips, track the path of the staff moving from the work area to the storage area, calculate the time consumed for each movement, and finally calculate the average time consumption as a quantitative indicator;

[0148] The time deviation degree value output unit 403 is used to compare the calculated average time consumption with the preset reference time, analyze the deviation between the two, and output the time deviation degree value in numerical form;

[0149] The preset duration refers to the minimum effective time threshold required for staff to conduct actual interactive behaviors in the storage area, which is used to eliminate short-term or accidental contacts;

[0150] The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

[0151] In the embodiment of the present invention, the effective video clips are processed, and the interaction between the staff and the storage area is detected using computer vision technology, and the duration of each contact is recorded. The video clips are sorted by time according to the contact duration, and a preset duration is set as a screening threshold, such as 2 seconds. Clips with a duration greater than the preset duration are screened out. These key interaction clips can truly reflect the effective use of the storage area by the staff.

[0152] Perform path tracking analysis on the selected key interaction segments, and use the positioning algorithm to extract the trajectory data of the staff moving from the work area to the storage area. Combine the trajectory and timestamp to calculate the time consumed for each movement. For example, it takes 8 seconds, 6 seconds, and 7 seconds for a staff member to move from the desk to the storage area, and record these times as basic data.

[0153] All movement times are counted and the average is calculated as an important quantitative indicator reflecting the convenience of the current layout. For example, the time consumption data for multiple interactions are 8 seconds, 6 seconds, and 7 seconds respectively, and the average time consumption is calculated to be 7 seconds. This average time consumption is compared with the preset benchmark time (for example, 5 seconds) to obtain the time deviation degree value. The time deviation degree value can be expressed as a percentage, for example, ((7-5) / 5)×100%=40%, indicating that the movement time consumption is 40% higher than expected, reflecting that the storage area may be located in an unreasonable manner or there are problems with the path design.

[0154] Through the above analysis, we can accurately identify the problem points in the space design, such as whether the storage area distribution needs to be adjusted or whether the path needs to be optimized. This method helps to optimize the space layout in a data-driven way and eliminate the design errors caused by subjective judgment.

[0155] The advantage of this setting is that it can eliminate accidental or invalid behavior data, ensure the accuracy of the analysis, and reflect the advantages and disadvantages of storage space design through quantitative results, providing a scientific basis for space optimization. This method has wide applicability and can be applied not only to the optimization of office space, but also to the medical, industrial and commercial fields. For example, in a hospital, the movement lines of medical staff can be analyzed to optimize the drug storage area, or the layout of the parts storage area can be optimized in a factory. In the future, this space optimization technology based on behavioral data will become an important tool for intelligent building and dynamic space design, promoting the development of design from experience-driven to data-driven.

[0156] Furthermore, the artificial intelligence-based architectural design assistance system also includes:

[0157] The final solution generation module 500 is used to optimize and adjust the initial storage space allocation solution in sequence through the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation solution.

[0158] Specifically, Figure 8 It shows a structural block diagram of the final solution generating module 500 in the system provided by the embodiment of the present invention.

[0159] In the preferred embodiment of the present invention, the final solution generation module 500 specifically includes:

[0160] The ratio optimization unit 501 is used to extract a specific storage space allocation ratio from the initial storage space allocation plan, adjust the storage space allocation ratio using the frequency deviation degree value, optimize the allocation weight of the storage space of the target office space, and give priority to increasing the storage resource allocation ratio of the high-frequency interaction area;

[0161] The layout optimization unit 502 is used to extract the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjust the distance from the storage area to the work area in combination with the time deviation degree value;

[0162] The final solution generation unit 503 is used to integrate the optimization results of the two dimensions of frequency and time, and integrate the adjusted storage resource allocation ratio and space layout into a final storage space allocation solution.

[0163] In an embodiment of the present invention, the specific allocation ratio of the storage space is extracted from the initial storage space allocation plan to clarify the resource allocation of each functional area. For example, the file storage area accounts for 30%, the equipment storage area accounts for 50%, and the personal item storage area accounts for 20%. The allocation ratio is optimized using the frequency deviation degree value, and the storage resource ratio of the high-frequency interaction area is increased first. If the frequency deviation degree value is 50%, it means that the actual usage frequency of the equipment storage area is 50% higher than the design requirement. The adjusted ratio increases the equipment storage area to 75%, while reducing the ratio of the file storage area and the personal item storage area to 15% and 10%. This optimization can ensure that high-frequency use areas receive more adequate resource allocation and reduce resource waste in low-frequency use areas.

[0164] Extract the spatial layout information of the target office space storage area from the initial storage space allocation plan to determine the relative distance between the storage area and the work area. For example, storage area A is 15 meters away from the work area, and storage area B is 20 meters away from the work area. Combined with the time deviation degree value, make adjustments to optimize the location of the storage area. If the time deviation degree value is 40%, it means that the staff spends 40% more time than expected during the movement process. By shortening the distance between storage area A and the work area to 10 meters and adjusting the location of storage area B to be away from the core work area, the movement time of the high-frequency storage area can be reduced, while optimizing the space utilization of the low-frequency storage area, achieving the effect of rationalizing the overall movement line.

[0165] In one example, the initial resource ratio of the equipment storage area was 50%, and the frequency deviation value was 50%, which was adjusted to 75% through optimization. The ratios of the file storage area and the personal item storage area were reduced to 15% and 10%, respectively. The initial distance of storage area A was 15 meters, and the average moving time was 7 seconds, while the preset benchmark time was 5 seconds. By adjusting the distance of storage area A to 10 meters, the moving time dropped to 5 seconds, close to the benchmark value, optimizing the convenience of the space while freeing up more resources and locations to serve high-frequency use areas.

[0166] The combination of the two adjustments makes the allocation ratio and spatial layout of storage space more in line with actual usage needs, which not only improves the resource supply in high-frequency use areas, but also reduces resource waste in low-frequency use areas. The optimized design not only meets storage needs, but also improves efficiency and convenience, and ultimately achieves reasonable allocation and efficient use of space, providing data-driven scientific support for the overall architectural design, reflecting a significant improvement in humanity and practicality.

[0167] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0169] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0171] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An artificial intelligence-based architectural design assistance method, characterized in that: The method comprises: Obtain the initial storage space allocation plan for the target office space, determine the corresponding designated work purposes and target functional departments, and obtain video data of the reference office area used by the target functional departments when completing the designated work purposes; Screen the video data and extract valid video clips containing the interaction between the staff and the storage area in the reference office area; Based on the effective video clips, the storage area interaction frequency of the staff in the reference office area is calculated, and the storage area interaction frequency is compared with the preset reference frequency to obtain the frequency deviation degree value; The effective video clips are further screened according to the contact duration, and the key interaction video clips are extracted. The key interaction video clips are analyzed, and the average time taken by the staff to move from the work area to the storage area is calculated. The average time taken is compared with the preset benchmark time to obtain the time deviation degree value; The initial storage space allocation plan is optimized and adjusted in turn through the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation plan.

2. The artificial intelligence-based architectural design assistance method according to claim 1, characterized in that: The steps of calculating the storage area interaction frequency of the staff in the reference office area based on the valid video clips, comparing the storage area interaction frequency with the preset reference frequency, and obtaining the frequency deviation degree value include: Extract all behavioral data of staff interacting with the storage area in the reference office area from valid video clips, ensure that the data covers core information such as timestamps and number of interactions, and exclude invalid or abnormal data; Based on all the extracted behavioral data, calculate the staff's interaction frequency with the storage area within a specified time period; The calculated storage area interaction frequency is compared with the preset reference frequency, the deviation between the two is analyzed, and the frequency deviation degree value is output in numerical form.

3. The artificial intelligence-based architectural design assistance method according to claim 1, characterized in that: The preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

4. The artificial intelligence-based architectural design assistance method according to claim 1, characterized in that: The effective video clips are further screened according to the contact duration, key interaction video clips are extracted, the key interaction video clips are analyzed, the average time taken by the staff to move from the work area to the storage area is calculated, and the average time taken is compared with the preset benchmark time. The steps of obtaining the time deviation degree value include: The parts of the valid video clips involving the contact between the staff and the storage area are sorted by contact duration, and the key interaction video clips with a duration greater than the preset duration are screened out; Analyze the selected key interactive video clips, track the path of the staff from the work area to the storage area, calculate the time consumed for each movement, and finally calculate the average time consumed as a quantitative indicator; The calculated average time is compared with the preset benchmark time, the deviation between the two is analyzed, and the time deviation degree value is output in numerical form.

5. The artificial intelligence-based architectural design assistance method according to claim 4 is characterized in that: The preset duration refers to the minimum effective time threshold required for staff to conduct actual interactive behaviors in the storage area, which is used to eliminate short-term or accidental contacts; The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

6. The artificial intelligence-based architectural design assistance method according to claim 1, characterized in that: The steps of optimizing and adjusting the initial storage space allocation plan in sequence by using the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation plan include: Extract the specific storage space allocation ratio from the initial storage space allocation plan, adjust the storage space allocation ratio using the frequency deviation value, optimize the allocation weight of the storage space of the target office space, and give priority to increasing the storage resource allocation ratio of high-frequency interaction areas; Extract the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjust the distance from the storage area to the work area in combination with the time deviation degree value; The optimization results of both frequency and time dimensions are integrated, and the adjusted storage resource allocation ratio and spatial layout are combined into the final storage space allocation plan.

7. An artificial intelligence-based architectural design assistance system, characterized in that: The system includes: a data acquisition module, a video data screening module, a frequency dimension analysis module, a time dimension analysis module and a final solution generation module, wherein: A data acquisition module is used to obtain an initial storage space allocation plan for a target office space, determine its corresponding designated work purpose and target functional department, and obtain video data of a reference office area used by the target functional department when completing the designated work purpose; A video data screening module, used to screen the video data and extract valid video clips containing the interaction between the staff and the storage area in the reference office area; A frequency dimension analysis module is used to calculate the storage area interaction frequency of the staff in the reference office area based on the effective video clips, compare the storage area interaction frequency with the preset reference frequency, and obtain the frequency deviation degree value; The time dimension analysis module is used to further filter the effective video clips according to the contact duration, extract the key interaction video clips, analyze the key interaction video clips, calculate the average time taken by the staff to move from the work area to the storage area, and compare the average time taken with the preset benchmark time to obtain the time deviation degree value; The final solution generation module is used to optimize and adjust the initial storage space allocation solution in turn through the frequency deviation degree value and the time deviation degree value to obtain the final storage space allocation solution.

8. The artificial intelligence-based architectural design assistance system according to claim 7, characterized in that: The frequency dimension analysis module specifically includes: A video data extraction unit is used to extract all behavioral data of the staff interacting with the storage area in the reference office area from valid video clips, ensuring that the data covers the core information of timestamps and interaction times, and excludes invalid or abnormal data; An interaction frequency calculation unit, used to calculate the interaction frequency of the staff in the storage area within a specified time period based on all extracted behavior data; A frequency deviation degree value output unit is used to compare the calculated storage area interaction frequency with a preset reference frequency, analyze the deviation between the two, and output the frequency deviation degree value in numerical form; The preset benchmark frequency refers to the average interaction frequency of the storage area of ​​the reference office area under the same type of work purpose. The preset benchmark frequency can be obtained through historical data statistics or set according to space design requirements and standard behavior patterns.

9. The artificial intelligence-based architectural design assistance system according to claim 8, characterized in that: The time dimension analysis module specifically includes: A video data extraction unit, used to sort the parts of the valid video clips involving the contact between the staff and the storage area according to the contact duration, and screen out key interaction video clips whose duration is greater than a preset duration; The average time calculation unit is used to analyze the selected key interaction video clips, track the path of the staff from the work area to the storage area, calculate the time consumed for each movement, and finally calculate the average time consumed as a quantitative indicator; A time deviation degree value output unit is used to compare the calculated average time consumption with the preset reference time, analyze the deviation between the two, and output the time deviation degree value in numerical form; The preset duration refers to the minimum effective time threshold required for staff to conduct actual interactive behaviors in the storage area, which is used to eliminate short-term or accidental contacts; The preset reference time refers to the expected average moving time from the work area to the storage area, which is set based on reference office areas or industry design standards. The preset reference time can be obtained through historical data statistics, design specification requirements or user behavior analysis.

10. The artificial intelligence-based architectural design assistance system according to claim 9, characterized in that: The final solution generation module specifically includes: A ratio optimization unit is used to extract a specific storage space allocation ratio from the initial storage space allocation plan, adjust the storage space allocation ratio using the frequency deviation value, optimize the allocation weight of the storage space of the target office space, and give priority to increasing the storage resource allocation ratio of the high-frequency interaction area; A layout optimization unit is used to extract the spatial layout of the storage area of ​​the target office space from the initial storage space allocation plan, and adjust the distance from the storage area to the work area in combination with the time deviation degree value; The final plan generation unit is used to integrate the optimization results of the two dimensions of frequency and time, and integrate the adjusted storage resource allocation ratio and space layout into the final storage space allocation plan.

Images