Complex layout diagnosis method and system based on data fusion and medium
Through data fusion technology, combining video and space basic data, customer flow and sales data are analyzed, the problem of insufficient global perspective and manual experience in the optimization of the complex layout is solved, scientific optimization of merchant location and public area functions is achieved, and the overall customer flow is improved. and space utilization efficiency.
Patent Information
- Application Number
- CN202411107106.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-08
AI Technical Summary
The existing technology lacks a global perspective and relies on manual experience in the optimization of comprehensive layout, resulting in unreasonable merchant layout, unable to fully consider spatial factors and customer flow interaction, and lacks scientificity and objectivity.
A comprehensive layout diagnosis method based on data fusion is adopted to construct a three-dimensional model through video data acquisition and spatial basic data, and a correlation analysis is carried out in combination with customer flow and sales data to generate comprehensive analysis results to optimize merchant location and public area functions.
It realizes refined analysis and optimization of the layout of the complex, provides data-driven merchant site selection and public area function optimization suggestions, and improves overall passenger flow and space utilization efficiency.
Smart Images

Figure CN118917486A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of complex layout analysis, and in particular to a complex layout diagnosis method, system and medium based on data fusion. Background Art
[0002] Existing technologies all optimize store layout after opening and operation by monitoring the instantaneous customer flow or daily cumulative customer flow of each merchant in the complex and combining field surveys or manual experience. The following problems often occur: 1. Lack of global perspective: Relying solely on instantaneous passenger flow or daily cumulative passenger flow data often lacks a global perspective on the spatial layout of the entire complex. It is impossible to systematically understand the mutual influence and interaction between various areas, and the spatial correlation is insufficient. Failure to integrate spatial basic data means that spatial factors such as channel width, merchant visibility, and the impact of adjacent public facilities (such as elevators and toilets) cannot be fully considered, resulting in unreasonable merchant layout and missed opportunities to increase overall passenger flow; 2. Reliance on manual experience: Reliance on field surveys and manual experience may lead to subjectivity. The number of experienced experts is limited, and the labor cost is high, the efficiency is low, and the scientificity and objectivity of layout optimization are insufficient, making it difficult to achieve refined and data-driven optimization.
[0003] The Chinese patent with the announcement number CN108306962A discloses a commercial big data analysis system, through which users can conveniently view the analysis results of commercial passenger flow data indicators. However, the Chinese patent with the announcement number CN108306962A mainly only generally summarizes the classification and analysis process of data, and cannot specifically solve the above-mentioned technical problems. Summary of the invention
[0004] The present invention solves the problem that the existing complex layout optimization lacks a global perspective and relies on manual experience. A complex layout diagnosis method, system and medium based on data fusion are proposed, which fully considers the fusion of real-time passenger flow and spatial basic data, analyzes the correlation between passenger flow aggregation data and sales data, conducts comprehensive layout analysis and diagnosis of the complex, and provides data reference for merchant location selection and public area function optimization.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A complex layout diagnosis method based on data fusion includes the following steps: S1, collect and obtain video data of major locations in the complex, and fit several video images to generate passenger flow distribution data; S2, obtain the spatial site conditions based on the spatial basic data of the complex, and establish a three-dimensional spatial model in combination with the complex drawings; S3, aggregating passenger flow data by using passenger flow distribution data and spatial basic data to generate passenger flow aggregation data and passenger flow heat distribution map; S4, conducts correlation analysis on passenger flow aggregation data and sales data, and finally generates a comprehensive analysis result, and generates a space optimization plan based on the comprehensive analysis result.
[0006] In the present technical solution, firstly, the video data of the main locations of the complex are acquired according to the video acquisition device to ensure coverage without blind spots, and the video images are fitted to ensure the accuracy of the data; then, the scope of the basic spatial data of the complex is determined, and after acquiring the basic spatial data, a three-dimensional spatial model can be constructed to facilitate intuitive observation of the spatial data; then, the passenger flow distribution data and the spatial basic data are respectively subjected to real-time passenger flow aggregation, and processed to generate passenger flow aggregation data; finally, the passenger flow aggregation data and the sales data are correlated and analyzed, and finally a comprehensive analysis result is determined, and then the corresponding optimization plan is specified according to the comprehensive analysis result to provide suggestions on merchant location selection or optimization suggestions on public area functions, so as to ensure the realization of refined analysis and data-driven optimization of the layout of the complex.
[0007] The present invention is further configured as follows: The step S1 comprises: S11, placing video acquisition devices at key locations of the complex to cover the complex; S12, collecting video data of several different images and transmitting the video data to a central server for processing; S13, matching feature points in different video images to find the corresponding relationship of overlapping areas; S14, time synchronization is performed on video data of different video images to generate passenger flow distribution data.
[0008] In this technical solution, the video acquisition devices are first installed in the main positions of the complex to cover the entire area within the complex. After the installation is completed, the video data of different pictures are obtained through these video acquisition devices, and these video data are sent to the central server linked to the video acquisition devices; the feature points in the video data of different video pictures are matched in the central server to determine the correspondence between the overlapping areas; finally, the video data of different video pictures are synchronized in time to ensure the accuracy of the data.
[0009] The present invention is further configured as follows: The step S2 comprises: S21, determining the spatial area range of the complex, and obtaining spatial basic data within the spatial area range to obtain spatial on-site conditions; S22, establishing a spatial basic database according to the complex drawing data and spatial basic data; S23, build a three-dimensional model of the complex based on the spatial basic database and integrate the layout and height data of each floor of the complex.
[0010] In this technical solution, firstly, all the areas where the spatial basic data of the complex needs to be collected are identified, then the corresponding spatial basic data are collected or queried within the spatial area, and then the three-dimensional drawings of the complex are obtained, and the three-dimensional drawings and spatial basic data are stored in the spatial basic database, and preprocessed and classified; finally, a three-dimensional model of the complex is constructed based on the data in the spatial basic database.
[0011] The present invention is further configured as follows: The step S3 comprises: S31, pre-processing the passenger flow distribution data and formatting the spatial basic data; S32, aggregating the processed data to obtain the passenger flow in a certain area within the time period and generate passenger flow aggregation data; S33, integrates the passenger flow information of all areas and constructs a passenger flow heat distribution map.
[0012] In this technical solution, the real-time passenger flow distribution data is preprocessed and the spatial basic data is formatted to provide a basis for subsequent data aggregation. The indicator function is used for calculation and the passenger flow point data in the area is statistically obtained to obtain the passenger flow in the area and the time period. Finally, the corresponding passenger flow heat map is generated.
[0013] The present invention is further configured as follows: The step S4 comprises: S41, obtaining sales data of merchants in the complex, and aligning the time period of the sales data with the passenger flow aggregation data; S42, after normalizing the passenger flow aggregation data and sales data, the Pearson correlation coefficient is used to measure the linear relationship between the two; S43, forming a comprehensive analysis result based on the linear relationship and the existing space utilization efficiency analysis result, and generating a space optimization plan.
[0014] In this technical solution, after obtaining the passenger flow aggregation data, the complex layout is diagnosed, the sales data is obtained from the after-sales line, and the sales data is aligned with the passenger flow aggregation data to ensure the consistency and comparability of the data. The linear relationship between the passenger flow aggregation data and the sales data is then measured using the Pearson correlation coefficient. The density distribution and merchant revenue analysis has been completed, followed by space utilization efficiency and congested area analysis, and finally a comprehensive analysis result is formed, based on which space optimization and recommendations are made.
[0015] The passenger flow in a certain area during the time period is specifically expressed as: Among them, N j (t) is the passenger flow, I(P i (t)∈A j ) is the indicator function, P i (t) is the passenger flow point in time period t, A j It is the basic spatial data, representing a set of complex areas.
[0016] In this technical solution, the aggregation of passenger flow points within the region and time period is achieved by calculating the above-mentioned regional passenger flow.
[0017] The present invention is further configured as follows: The Pearson correlation coefficient is used to measure the linear relationship between the two, and the following formula is used specifically: in, and are the standardized data of passenger flow aggregation data and sales data, r j is the correlation coefficient, and the correlation between the passenger flow aggregation data and the sales data is determined according to the value range of the correlation coefficient.
[0018] In the present technical scheme, the value range of the correlation coefficient is between -1 and 1. If the correlation coefficient is greater than 0, the two are linearly positively correlated. If the correlation coefficient is less than 0, the two are linearly negatively correlated. If the correlation coefficient is equal to 0, there is no obvious linear relationship between the two.
[0019] The present invention is further configured as follows: The standardization process uses the following calculation formula: in, and are the mean and standard deviation of passenger flow aggregation data in area j, and are the mean and standard deviation of sales data in region j respectively.
[0020] In this technical solution, the passenger flow aggregation data and sales data are subjected to the same standardized processing to eliminate the impact of data magnitudes in different regions and time periods.
[0021] A complex layout diagnosis system based on data fusion, using the above-mentioned complex layout diagnosis method based on data fusion, comprises: Passenger flow data collection module collects video data from major locations in the complex and generates passenger flow distribution data; The spatial data acquisition module builds a three-dimensional spatial model based on the spatial basic data of the complex and combined with the complex drawings; Data fusion module aggregates passenger flow data by combining passenger flow distribution data and spatial basic data; The correlation analysis module performs correlation analysis on passenger flow aggregation data and sales data to generate comprehensive analysis results.
[0022] The diagnostic system in this technical solution mainly includes a passenger flow data acquisition module, a spatial data acquisition module, a data fusion module and a correlation analysis module, wherein the data fusion module is connected to the correlation analysis module, and the data fusion module is respectively connected to the passenger flow data acquisition module and the spatial data acquisition module. The above-mentioned passenger flow data acquisition module, spatial data acquisition module, data fusion module and correlation analysis module can perform comprehensive layout analysis and diagnosis on the complex.
[0023] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned complex layout diagnosis method based on data fusion are executed.
[0024] In the technical solution, the above-mentioned complex layout diagnosis method based on data fusion is executed by a computer program stored in a computer calibration storage medium.
[0025] The present invention can bring the following beneficial effects: 1. The present invention relates to a complex layout diagnosis method based on data fusion, which fully considers the fusion of real-time passenger flow and spatial basic data, analyzes the correlation between passenger flow aggregation data and sales data, conducts comprehensive layout analysis and diagnosis of the complex, and provides data reference for merchant location selection and public area function optimization; 2. The present invention relates to a complex layout diagnosis system based on data fusion, which can perform comprehensive layout analysis and diagnosis of the complex through the functions of passenger flow data acquisition module, spatial data acquisition module, data fusion module and correlation analysis module. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a flowchart of a complex layout diagnosis method based on data fusion in the present application.
[0027] Figure 2 It is a schematic diagram of a complex layout diagnosis system based on data fusion in the present application. DETAILED DESCRIPTION
[0028] In order to make the objectives, technical solutions 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 implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0029] Example 1 This embodiment proposes a complex layout diagnosis method based on data fusion, referring to Figure 1 , which includes the following steps.
[0030] Step S1, firstly collect the video data of each main location of the complex, and then fit multiple video images of the same time period to obtain passenger flow distribution data.
[0031] More specifically, step S1 mainly includes the following sub-steps.
[0032] Step S11, installing the video acquisition device. Specifically, the video acquisition device is installed at a main position of the complex to ensure that the video acquisition device can cover the entire complex.
[0033] Step S12, then start collecting and obtaining video data containing different pictures, and after the collection is completed, send the video data to the central server for processing.
[0034] Step S13, performing feature matching on feature points in different video images to find out the corresponding relationship of overlapping areas.
[0035] Step S14, time synchronization is performed on the video data of different video frames, and finally complete passenger flow distribution data is obtained.
[0036] In the above technical solution, the video acquisition devices are first installed at the main positions of the complex to cover the entire area within the complex. After the installation is completed, the video data of different pictures are obtained through these video acquisition devices, and these video data are sent to the central server linked to the video acquisition devices; the feature points in the video data of different video pictures are matched in the central server to determine the correspondence between the overlapping areas; finally, the video data of different video pictures are synchronized in time to ensure the accuracy of the data.
[0037] As for the video acquisition device, a camera is generally used. As for the selection of the camera, a camera with high resolution and a wide-angle lens is generally used to ensure that it can cover a larger area.
[0038] Corresponding requirements are also put forward for the installation height and angle of the video acquisition device. The installation height should ensure that a large area can be overlooked. The angle of the video acquisition device should be adjusted according to actual conditions to ensure the best field of view. The field of view direction can be flexibly adjusted according to changes in passenger flow in the complex to ensure comprehensive coverage of different video acquisition devices in the complex at different times.
[0039] Corresponding video acquisition devices are arranged at the main locations of the complex, including the main passages, entrances, store doors and public areas of the complex, to ensure that the complex can be covered without blind spots.
[0040] All video acquisition devices are connected to the central server. After acquiring the corresponding video data, they send the video data to the central server. By setting a fixed sending cycle, after an interval of one sending cycle, the video data of this sending cycle period is transmitted to the central server through the corresponding communication method.
[0041] In this embodiment, the interval of the sending cycle is set to once every 3 hours, that is, the complex running for 12 hours a day needs to send video data four times.
[0042] The communication method between the video acquisition device and the central server generally adopts wired transmission, but it is certainly not limited to wired transmission. The main thing is to achieve fast transmission of video data.
[0043] When necessary, the video data collected by the video acquisition device is encrypted, which will significantly increase the cost of diagnosis but can improve the security of the video data.
[0044] The purpose of matching feature points in different video images is to find overlapping areas in different video images and to establish corresponding relationships between overlapping areas in different video images.
[0045] Finally, the data of different video images need to be time synchronized to ensure the accuracy and reliability of the subsequent data fusion process.
[0046] Step S2, obtaining the spatial site conditions based on the spatial basic data of the complex, and then establishing a three-dimensional spatial model in combination with the complex drawings.
[0047] Step S2 mainly includes the following sub-steps.
[0048] Step S21, first determine the spatial area range of the complex, and obtain corresponding spatial basic data within the determined spatial area range to obtain the spatial site situation.
[0049] Step S22, a spatial basic database is constructed by jointly using the comprehensive drawing data obtained through query and the above-mentioned spatial basic data.
[0050] Step S23, establishing a three-dimensional model of the complex based on the above-mentioned spatial basic database, integrating the layout and height data of each floor of the complex.
[0051] In the above technical scheme, firstly, all the areas where the spatial basic data of the complex needs to be collected are identified, then the corresponding spatial basic data are collected or queried within the spatial area, and then the three-dimensional drawings of the complex are obtained, and the three-dimensional drawings and spatial basic data are stored in the spatial basic database, and preprocessed and classified; finally, a three-dimensional model of the complex is constructed based on the data in the spatial basic database.
[0052] The spatial area scope of the complex includes commercial areas, public areas, passages, entrances and exits, toilets, floors and roads. Of course, its scope can also be expanded according to the actual situation of the complex, and they are not listed here one by one.
[0053] For complex drawings, they can be three-dimensional drawings, and of course they can also be more popular CAD drawings.
[0054] The spatial basic database contains spatial dimension information of each spatial area, which can be flexibly retrieved according to actual needs.
[0055] The 3D model of the complex is based on GIS and BIM, that is, on Geographic Information System and Building Information Modeling.
[0056] Step S3, aggregating the passenger flow distribution data and the spatial basic data to generate passenger flow aggregation data and a passenger flow heat distribution map.
[0057] More specifically, step S3 includes the following sub-steps.
[0058] Step S31, pre-processing the passenger flow distribution data and formatting the spatial basic data.
[0059] Regarding the preprocessing of passenger flow distribution data, it mainly involves formatting the real-time passenger flow data.
[0060] More specifically, there is a real-time passenger flow data point set P i (t), Among them, P i (t) = (x i ,y i , t), which means that at time t, at position (x i ,y i ) passenger flow point.
[0061] Regarding the formatting of spatial basic data, the details are as follows: Represent the spatial basic data as a set of regions A j , each region is defined by its boundary coordinates.
[0062] Step S32, aggregating the processed data to obtain the passenger flow in a certain area within the time period.
[0063] As for step S32, it mainly includes aggregation of regional passenger flow and aggregation of passenger flow in time period.
[0064] The aggregation process of regional passenger flow includes: Calculate in each complex area A j The passenger flow point data N j , specifically expressed as: Among them, I(P i ∈A j ) is the indicator function, when P i In A j The value is 1 when it is inside, otherwise P i The value of is 0.
[0065] The aggregation process of passenger flow in a time period includes: Using t to represent the time period, the passenger flow can be aggregated by time period. The passenger flow in a certain area during the t period can be expressed as: In the above formula, N j (t) is the passenger flow, I(P i (t)∈A j ) is the indicator function, P i (t) is the passenger flow point in time period t, A j It is the basic spatial data, representing a set of complex areas.
[0066] In the above technical solution, the aggregation of passenger flow points within the region and time period is achieved by calculating the above regional passenger flow.
[0067] Step S33, integrating the passenger flow information of all areas and constructing a passenger flow heat distribution map.
[0068] Generate a passenger flow heat map using the kernel density estimation formula as follows: Among them, K is the kernel function, h is the bandwidth parameter, (x i ,y i ) are the coordinates of the passenger flow point.
[0069] In the above technical solution, the real-time passenger flow distribution data is preprocessed, and the spatial basic data is formatted to provide a basis for subsequent data aggregation. The indicator function is used for calculation and the passenger flow point data in the area is statistically obtained to obtain the passenger flow in the area and the time period. Finally, the corresponding passenger flow heat map is generated.
[0070] Finally, in step S4, correlation analysis is performed on the passenger flow aggregation data and the sales data, and a comprehensive analysis result is finally generated, and a space optimization plan is generated based on the comprehensive analysis result.
[0071] Step S4 mainly includes the following sub-steps.
[0072] Step S41, obtaining sales data about merchants in the complex, the sales data specifically including sales volume, average customer spending and number of transactions; then aligning the time periods of the sales data and customer flow aggregation data to ensure data consistency and comparability.
[0073] Then, step S42 is performed to standardize the passenger flow aggregate data and sales data in order to eliminate the influence of data magnitudes in different regions and time periods. Then, the Pearson correlation coefficient is used to measure the linear relationship between the passenger flow aggregate data and sales data.
[0074] More specifically, the standardization process uses the following calculation formula: in, and are the mean and standard deviation of passenger flow aggregation data in area j, and are the mean and standard deviation of sales data in region j respectively.
[0075] In the above technical solution, the passenger flow aggregation data and sales data are subjected to the same standardization processing to eliminate the impact of data magnitudes in different regions and time periods.
[0076] The process of using the Pearson correlation coefficient to measure the linear relationship between the two is as follows: Calculate the correlation coefficient: in, and are the standardized data of passenger flow aggregation data and sales data, r j is the correlation coefficient, and the correlation between the passenger flow aggregation data and the sales data is determined according to the value range of the correlation coefficient.
[0077] In the above technical solution, the correlation coefficient ranges between -1 and 1. If the correlation coefficient is greater than 0, the two are linearly positively correlated. If the correlation coefficient is less than 0, the two are linearly negatively correlated. If the correlation coefficient is equal to 0, there is no obvious linear relationship between the two.
[0078] Furthermore, after the above process is completed, in order to determine whether the above correlation is significant, the p-value of the correlation coefficient is calculated. The specific formula is: Where n is the number of samples. Then look up the t distribution table and determine the corresponding p-value; if the p-value is less than the significance level (usually set to 0.05), the correlation is significant.
[0079] Step S43, forming a comprehensive analysis result based on the linear relationship and the existing space utilization efficiency analysis result, and generating a space optimization plan.
[0080] Step S43 includes: evaluating the existing space utilization efficiency and finding possible space waste or congested areas.
[0081] Finally, a comprehensive analysis result is formed, and a corresponding space optimization plan can be generated to put forward space optimization suggestions, including merchant location selection suggestions, channel layout improvement suggestions, and public area function optimization suggestions.
[0082] In the above technical solution, after obtaining the passenger flow aggregation data, the complex layout is diagnosed, the sales data is obtained from the after-sales line, and the sales data is aligned with the passenger flow aggregation data to ensure the consistency and comparability of the data. The linear relationship between the passenger flow aggregation data and the sales data is then measured using the Pearson correlation coefficient. The density distribution and merchant revenue analysis are completed, followed by space utilization efficiency and congested area analysis, and finally a comprehensive analysis result is formed, based on which space optimization and recommendations are made.
[0083] In this embodiment, first, video data of the main locations of the complex are collected and acquired according to the video acquisition device to ensure coverage without blind spots, and these video images are fitted to ensure the accuracy of the data; then, the scope of the basic data of the complex space is determined, and after the basic spatial data is acquired, a three-dimensional spatial model can be constructed to facilitate intuitive observation of the spatial data; then, the passenger flow distribution data and the spatial basic data are respectively subjected to real-time passenger flow aggregation, and processed to generate passenger flow thermal data; finally, the passenger flow aggregation data and the sales data are correlated and analyzed, and finally a comprehensive analysis result is determined, and then the corresponding optimization plan is specified according to the comprehensive analysis result to provide merchant location site selection suggestions or public area function optimization suggestions, so as to ensure the realization of refined analysis and data-driven optimization of the complex layout.
[0084] Example 2 On the basis of a complex layout diagnosis method based on data fusion described in Example 1, this example further proposes a complex layout diagnosis system based on data fusion, which mainly includes a passenger flow data acquisition module, a spatial data acquisition module, a data fusion module and a correlation analysis module, wherein the passenger flow data acquisition module and the spatial data acquisition module are respectively connected to the data fusion module, and the data fusion module is connected to the correlation analysis module.
[0085] For the passenger flow data acquisition module, its main functions are: collecting and acquiring video data from major locations of the complex, and then generating passenger flow distribution data; the generated passenger flow distribution data provides a data source for subsequent data fusion; for more detailed functions performed by the passenger flow data acquisition module, please refer to the process of step S1 in Example 1.
[0086] The spatial data acquisition module mainly performs the following functions: constructing a three-dimensional spatial model based on the spatial basic data of the complex and combining the complex drawings; the constructed three-dimensional spatial model can easily extract the corresponding diagnostic information data. For more detailed functions performed by the spatial data acquisition module, please refer to the process of step S2 in Example 1.
[0087] For the data fusion module, its main functions are: aggregating passenger flow data by combining passenger flow distribution data and spatial basic data; finally, passenger flow aggregation data can be obtained; its functions also include data preprocessing, spatial data formatting, real-time passenger flow aggregation and passenger flow thermal generation; for more detailed functions performed by the data fusion module, please refer to the process of step S3 in Example 1.
[0088] For the correlation analysis module, correlation analysis is performed on the passenger flow aggregation data and the sales data to generate a comprehensive analysis result. For more detailed functions performed by the correlation analysis module, reference may be made to the process of step S4 in Example 1.
[0089] The diagnostic system in this technical solution mainly includes a passenger flow data acquisition module, a spatial data acquisition module, a data fusion module and a correlation analysis module, wherein the data fusion module is connected to the correlation analysis module, and the data fusion module is respectively connected to the passenger flow data acquisition module and the spatial data acquisition module. The above-mentioned passenger flow data acquisition module, spatial data acquisition module, data fusion module and correlation analysis module can perform comprehensive layout analysis and diagnosis on the complex.
[0090] The functions performed by the diagnostic system of this embodiment mainly include: first, acquiring video data of the main locations of the complex according to the video acquisition device to ensure coverage without blind spots, and fitting these video images to ensure the accuracy of the data; then determining the scope of the basic data of the complex space, and after acquiring the basic spatial data, being able to construct a three-dimensional spatial model to facilitate intuitive observation of the spatial data; then, performing real-time passenger flow aggregation on the passenger flow distribution data and the basic spatial data, respectively, and processing to generate passenger flow thermal data; finally, performing correlation analysis on the passenger flow aggregation data and the sales data, and finally determining that there are comprehensive analysis results, and then specifying corresponding optimization plans based on the comprehensive analysis results to provide merchant location site selection suggestions or public area function optimization suggestions, to ensure the realization of refined analysis and data-driven optimization of the layout of the complex.
[0091] Example 3 Based on Example 1 or Example 2, this embodiment further proposes a computer-readable storage medium, on which a corresponding computer program is stored. When the computer program is run by a processor, the steps of a complex layout diagnosis method based on data fusion as described above are executed.
[0092] In the above technical solution, the above-mentioned complex layout diagnosis method based on data fusion is executed by a computer program stored in a computer calibration storage medium.
[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention is described in detail with reference to the embodiments, it should be understood by those skilled in the art that any modification or equivalent replacement of the technical solutions of the present invention does not depart from the spirit and scope of the technical solutions of the present invention and should be included in the scope of the claims of the present invention.
Claims
1. A complex layout diagnosis method based on data fusion, It is characterized in that The following steps are involved: S1, collect and obtain video data of major locations in the complex, and fit several video images to generate passenger flow distribution data; S2, obtain the spatial site conditions based on the spatial basic data of the complex, and establish a three-dimensional spatial model in combination with the complex drawings; S3, aggregating passenger flow data by using passenger flow distribution data and spatial basic data to generate passenger flow aggregation data and passenger flow heat distribution map; S4, conducts correlation analysis on passenger flow aggregation data and sales data, and finally generates a comprehensive analysis result, and generates a space optimization plan based on the comprehensive analysis result.
2. A complex layout diagnosis method based on data fusion according to claim 1, It is characterized in that The step S1 comprises: S11, placing video acquisition devices at key locations of the complex to cover the complex; S12, collecting video data of several different images and transmitting the video data to a central server for processing; S13, matching feature points in different video images to find the corresponding relationship of overlapping areas; S14, time synchronization is performed on video data of different video images to generate passenger flow distribution data.
3. A complex layout diagnosis method based on data fusion according to claim 1, It is characterized in that The step S2 comprises: S21, determining the spatial area range of the complex, and obtaining spatial basic data within the spatial area range to obtain spatial on-site conditions; S22, establishing a spatial basic database according to the complex drawing data and spatial basic data; S23, build a three-dimensional model of the complex based on the spatial basic database and integrate the layout and height data of each floor of the complex.
4. A complex layout diagnosis method based on data fusion according to claim 1, 2 or 3, It is characterized in that The step S3 comprises: S31, pre-processing the passenger flow distribution data and formatting the spatial basic data; S32, aggregating the processed data to obtain the passenger flow in a certain area within the time period and generate passenger flow aggregation data; S33, integrates the passenger flow information of all areas and constructs a passenger flow heat distribution map.
5. A complex layout diagnosis method based on data fusion according to claim 1, 2 or 3, It is characterized in that The step S4 comprises: S41, obtaining sales data of merchants in the complex, and aligning the time period of the sales data with the passenger flow aggregation data; S42, after normalizing the passenger flow aggregation data and sales data, the Pearson correlation coefficient is used to measure the linear relationship between the two; S43, forming a comprehensive analysis result based on the linear relationship and the existing space utilization efficiency analysis result, and generating a space optimization plan.
6. A complex layout diagnosis method based on data fusion according to claim 4, It is characterized in that The passenger flow in a certain area during the time period is specifically expressed as: Among them, N j (t) is the passenger flow, I(P i (t)∈A j ) is the indicator function, P i (t) is the passenger flow point in time period t, A j It is the basic spatial data, representing a set of complex areas.
7. A complex layout diagnosis method based on data fusion according to claim 5, It is characterized in that The Pearson correlation coefficient is used to measure the linear relationship between the two, and the following formula is used specifically: in, and are the standardized data of passenger flow aggregation data and sales data, r j is the correlation coefficient, The correlation between the passenger flow aggregation data and the sales data is determined based on the value range of the correlation coefficient.
8. The complex layout diagnosis method based on data fusion according to claim 5, It is characterized in that The standardization process uses the following calculation formula: in, and are the mean and standard deviation of passenger flow aggregation data in area j, and are the mean and standard deviation of sales data in region j respectively.
9. A complex layout diagnosis system based on data fusion, using a complex layout diagnosis method based on data fusion as claimed in any one of claims 1 to 8, It is characterized in that include: Passenger flow data collection module collects video data from major locations in the complex and generates passenger flow distribution data; The spatial data acquisition module builds a three-dimensional spatial model based on the spatial basic data of the complex and combined with the complex drawings; Data fusion module aggregates passenger flow data by combining passenger flow distribution data and spatial basic data; The correlation analysis module performs correlation analysis on passenger flow aggregation data and sales data to generate comprehensive analysis results.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the complex layout diagnosis method based on data fusion as claimed in any one of claims 1 to 8 are executed.
