Big data-based investment attraction analysis method and system

Abstract

The invention is suitable for the technical field of investment attraction analysis, and particularly relates to a big data-based investment attraction analysis method and system, and the method comprises the steps: S100: obtaining a storefront distribution diagram of a region, marking the positions of a region entrance and exit and shops, creating a plurality of blocks corresponding to the shops in a one-to-one manner, and according to the distances from the shops to the region entrance and exit, carrying out the one-to-one correspondence with the shops, carrying out the one-to-one correspondence with the shops; sequencing the plurality of blocks, integrating the sequenced plurality of blocks to generate a plurality of block columns, one of which corresponds to one area of the area; s200, acquiring video monitoring data in the area, counting the number of people entering each shop, segmenting the number of people into a plurality of segments, and configuring a color matching corresponding to each segment; according to the method, the area can be finely analyzed by generating the plurality of columns, the business layout can be more accurately optimized, more accurate investment attraction requirements can be formulated by utilizing the number of customers in the competitive area and the excellent area by generating the analysis report, and meanwhile, the investment attraction analysis process is also greatly simplified.

Description

Technical Field

[0001] The present invention relates to the technical field of investment promotion analysis, and in particular to an investment promotion analysis method and system based on big data. Background Art

[0002] Regional investment analysis is generally conducted through multiple steps including market research, competitor analysis, consumer behavior research, and financial evaluation. First, market research is conducted to understand local market demand, consumer preferences, and consumption trends. Then, the company determines its own investment positioning by analyzing competitors’ brand portfolios, pricing strategies, and market shares. Consumer behavior data is then used to analyze potential customers’ shopping habits and needs in order to optimize the regional business layout.

[0003] However, since it is impossible to quickly determine the business distribution and number of customers in each area, the above process requires a large number of market visits, and then professionals determine the investment direction based on their work experience. There are many subjective factors and a lack of unified standards. Therefore, "how to combine competitive areas and excellent areas to provide data support for investment analysis" is the technical problem that the present invention needs to solve. Summary of the invention

[0004] The purpose of the present invention is to provide an investment promotion analysis method and system based on big data to solve the problem of "how to combine competitive areas and excellent areas to provide data support for investment promotion analysis" raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A big data-based investment promotion analysis method, the method comprising:

[0007] S100: Obtain a store distribution map of a region, divide it into several areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to one area;

[0008] S200: Obtain video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color scheme corresponding to each segment, classify the blocks into the segments, and render and change the color of the blocks using the color scheme corresponding to the segments;

[0009] S300: reading out the attributes of each block, wherein the attributes include at least: clothing, beauty and catering, and inserting a label consisting of the attributes into the block;

[0010] S400: Integrate several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, construct an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

[0011] Furthermore, the S100 includes:

[0012] In the store distribution map, find the import and export, where the number of the import and export is greater than or equal to 1;

[0013] The distance from the store to the nearest entrance and exit is calculated, and the blocks are sorted according to the distance.

[0014] Furthermore, the S100 further includes:

[0015] A corresponding relationship between the slice area and the number of blocks is configured, and blank blocks are inserted into the number of blocks;

[0016] The video surveillance data is used to count the number of visits to the blank block, and the prediction result of the blank block is determined based on the number of visits and the labels in the column.

[0017] Further, the S200 includes:

[0018] Using a preset video image processing technology, extracting portrait features from the video surveillance data, and adding identifiers to the portrait features;

[0019] Based on the identification, the access duration of each portrait feature is calculated, a residence time set is generated, and the residence time set is embedded into a number block.

[0020] Further, the S300 includes:

[0021] Establishing a mapping of stores, dwell time sets and attributes, and using the mapping to modify the analysis report;

[0022] The stores are divided according to the residence time set to determine the popularity of the stores.

[0023] Further, the S400 includes:

[0024] Linking multi-dimensional data to the analysis report, wherein the multi-dimensional data includes at least: sales data and environmental data;

[0025] Dynamically monitor the missing items and excellent items, determine the change process, and synchronize the change process into the analysis report.

[0026] Furthermore, the method further comprises:

[0027] Deploy interactive feedback points in the area, and push selection windows to the interactive feedback points;

[0028] Receive the selection results uploaded by the user, extract the feedback items, and integrate the feedback items into the analysis report.

[0029] Furthermore, the system comprises:

[0030] A generation module is used to obtain a store distribution map of a region, divide it into several areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to a region;

[0031] The color changing module is used to obtain the video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color matching corresponding to each segment, classify the blocks into the segments, and use the color matching corresponding to the segments to render and change the color of the blocks;

[0032] An insertion module is used to read out the attributes of each block, wherein the attributes include at least: clothing, beauty and catering, and insert a label consisting of the attributes into the block;

[0033] The sending module is used to integrate the several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, build an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

[0034] Furthermore, the generation module includes:

[0035] A search unit, configured to search for the import and export in the store distribution map, wherein the number of the import and export is greater than or equal to 1;

[0036] A sorting unit, used to calculate the distance from the store to the nearest entrance and exit, and sort the blocks according to the distance;

[0037] A configuration unit, configured to configure a correspondence between the slice area and the number of blocks, and insert blank blocks into the number of blocks;

[0038] The prediction unit is used to use the video monitoring data to count the number of visits to the blank block, and determine the prediction result of the blank block based on the number of visits and the labels in the block column.

[0039] Furthermore, the color changing module includes:

[0040] An adding unit, configured to extract the portrait features in the video surveillance data by using a preset video image processing technology, and to add an identifier to the portrait features;

[0041] The embedding unit is used to calculate the access time of each portrait feature according to the identifier, generate a residence time set, and embed the residence time set into a number block.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By obtaining the store distribution map, the commercial distribution in the area can be determined to provide data support for investment analysis. By counting the number of people entering the store, the customer flow trend of each store can be determined, which is convenient for quantifying the investment analysis. By determining the color scheme, the number of people in each store can be intuitively displayed to optimize the allocation of investment resources, while greatly improving the convenience of data analysis and business strategy improvement. By generating several columns, the region can be analyzed in detail and the business layout can be optimized more accurately. By generating analysis reports, the number of customers in competitive areas and excellent areas can be used to formulate more accurate investment needs, which can also greatly simplify the investment analysis process. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of a big data-based investment promotion analysis method provided by an embodiment of the present invention;

[0045] Figure 2 A first sub-process flowchart of the big data-based investment promotion analysis method provided by an embodiment of the present invention;

[0046] Figure 3 A second sub-process flowchart of the big data-based investment promotion analysis method provided by an embodiment of the present invention;

[0047] Figure 4 A third sub-process flowchart of the big data-based investment promotion analysis method provided in an embodiment of the present invention;

[0048] Figure 5 A fourth sub-process flowchart of the big data-based investment promotion analysis method provided in an embodiment of the present invention;

[0049] Figure 6A block diagram of the composition of the big data-based investment promotion analysis system provided by an embodiment of the present invention;

[0050] Figure 7 A block diagram of the composition of a generation module in a big data-based investment promotion analysis system provided by an embodiment of the present invention;

[0051] Figure 8 A block diagram of the composition of the color changing module in the big data-based investment promotion analysis system provided by an embodiment of the present invention;

[0052] Fig. 9 A block diagram of the composition of the insertion module in the big data-based investment promotion analysis system provided by an embodiment of the present invention;

[0053] Fig.10 A block diagram of the composition of the sending module in the big data-based investment promotion analysis system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] In Example 1, Figure 1 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown and described in detail below:

[0056] S100: Obtain a store distribution map of the area, divide it into several areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to an area.

[0057] Get the store distribution map of the area, divide the entire area into multiple areas based on geographical features, road networks or administrative divisions, and ensure that each area has a reasonable size; mark the locations of the regional entrances and exits on the store distribution map, and mark the location of each shop, create a block for each shop, calculate the distance from each block to the regional entrance and exit, and sort the blocks according to this distance; if there are multiple regional entrances and exits, calculate the distance from each block to the nearest regional entrance and exit.

[0058] Integrate the sorted blocks to generate block columns, and create a block column for each area in the region, where the blocks are mainly used to store the attributes of the stores and represent the locations of the stores, and the block columns are mainly used to quantify the location of each store.

[0059] S200: Obtain video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color scheme corresponding to each segment, classify the blocks into the segments, and use the color scheme corresponding to the segments to render and change the color of the blocks.

[0060] The video surveillance data of each store in the area is collected, and the number of people entering the store is counted using visual technology and image recognition algorithms. The data is divided into multiple segments, each of which corresponds to a different color scheme. In other words, the corresponding blocks are rendered and colored according to the number of people in the store.

[0061] S300: Read out the attributes of each block, wherein the attributes include at least clothing, beauty and catering, and insert a tag consisting of the attributes into the block.

[0062] The attributes of each block are read out, where the attributes are the store formats corresponding to the block, and labels consisting of the attributes are inserted into the blocks. The advantage of this is that the format distribution of the area can be displayed more intuitively, so as to find format gaps.

[0063] S400: Integrate several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, construct an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

[0064] Integrate the columns corresponding to each area in the region to obtain a column group; determine the competitive area and the excellent area from the region, where the competitive area can be the area within a preset distance, and the excellent area can be the area with a larger passenger flow within a larger distance; input the column group corresponding to the competitive area and the excellent area into the analysis model to determine the excellent items and missing items; the excellent items are the blocks corresponding to the stores with the largest number of people, and the missing items are the blocks corresponding to the business formats lacking in the area; fill the missing items and excellent items into the analysis template to obtain an analysis report.

[0065] In this embodiment, it is first necessary to find out the competition area, determine the column group corresponding to the competition area, find out the store with the largest number of people in each column in the column group, and determine these stores as excellent items.

[0066] In Example 2, Figure 2 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown, and S100 is described in detail below, as follows:

[0067] S101: Find the import and export in the store distribution map, where the number of the import and export is greater than or equal to 1.

[0068] In the store distribution map, find the import and export, where the number of import and export may be 1 or more.

[0069] S102: Calculate the distance from the store to the nearest entrance and exit, and sort the blocks according to the distance.

[0070] If the number of regional entrances and exits is 1, the blocks are sorted directly according to the distance from the store to the regional entrances and exits. If there are multiple regional entrances and exits, find the nearest regional entrance and exit to each block, calculate the distance between the nearest regional entrance and exit and the block, and then sort the blocks according to this distance; if the distances from the blocks to the regional entrances and exits are the same, they are tied in the sorting.

[0071] In Example 3, Figure 2 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown, and S100 is further described in detail below, as follows:

[0072] S103: configuring the correspondence between the area and the number of blocks, and inserting blank blocks into the number of blocks.

[0073] Create a number of columns for each area and determine the positions of the blank blocks in the columns, where the blank blocks correspond to the stores in the area that have not yet been recruited.

[0074] S104: Count the number of visits to the blank block using the video surveillance data, and determine the prediction result of the blank block based on the number of visits and the labels in the column.

[0075] Obtain video surveillance data near the store corresponding to the blank block and count the number of visits, where the number of visits is the number of people passing through the store corresponding to the blank block; determine the investment expectations for the blank block based on the number of visits to the blank block and the lack of business formats in the area. The investment expectations include not only business format expectations, but also rent and scale, etc.

[0076] In Example 4, Figure 3 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown, and S200 is described in detail below, as follows:

[0077] S201: extracting portrait features from the video surveillance data using a preset video image processing technology, and adding identifiers to the portrait features.

[0078] Using video image processing technology, multi-dimensional portrait features including face, body shape and clothing are extracted from video surveillance data, and one portrait feature is selected as an identifier.

[0079] S202: Based on the identifier, calculate the access time of each portrait feature, generate a residence time set, and embed the residence time set into a number block.

[0080] The visit duration of the portrait features is calculated and a residence time set is generated, where each store generates a residence time set.

[0081] For example, by using video image processing technology, the portrait features of customer A entering a store are extracted from the video surveillance data, and A's backpack is selected as an identifier from the portrait features. By monitoring the movement of the identifier in the video surveillance data, the time when A enters and exits the store is determined, and the visit duration of A is calculated. In this way, the visit duration of all users entering the store is counted and integrated to obtain a residence time set.

[0082] In Example 5, Figure 4 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown, and S300 is described in detail below, as follows:

[0083] S301: Establish a mapping of stores, residence time sets and attributes, and use the mapping to modify the analysis report.

[0084] Establish a mapping between stores, residence time sets and attributes; for example, by querying a specific store, you can quickly find its corresponding residence time set and attributes; the advantage of doing this is that you can quickly call up data related to the store.

[0085] S302: Divide the stores according to the residence time set to determine the popularity of the stores.

[0086] The popularity of each store is determined based on the store's residence time set. If the sum of the residence time set is larger, the store is more popular.

[0087] In Example 6, Figure 5 The implementation process of the investment promotion analysis method based on big data provided by an embodiment of the present invention is shown, and S400 is described in detail below, as follows:

[0088] S401: Linking multi-dimensional data to the analysis report, wherein the multi-dimensional data at least includes: sales data and environmental data.

[0089] Link multi-dimensional data to the analysis report. In addition to customer flow, investment analysis should also consider store sales data and store reputation.

[0090] S402: Dynamically monitor the missing items and excellent items, determine the change process, and synchronize the change process into the analysis report.

[0091] According to the changes in stores in the area, the missing items and excellent items are dynamically adjusted, and the change process is recorded; by recording the change process, the changes in user consumption trends can be predicted, thereby providing decision support for investment analysis.

[0092] In Example 7, different from Example 1, in this embodiment of the present invention, the method further includes:

[0093] Deploy interactive feedback points in the area, and push selection windows to the interactive feedback points;

[0094] Receive the selection results uploaded by the user, extract the feedback items, and integrate the feedback items into the analysis report.

[0095] Interactive feedback points are deployed in the area, where the interactive feedback points can be the service desk of the area or a preset electronic device. The main function of the interactive feedback points is to receive service requirements uploaded by users; users generate feedback items by clicking on the form in the selection window; the feedback items are the business formats or specific brands that users hope to introduce.

[0096] Figure 6 The structure block diagram of the investment promotion analysis system based on big data provided by an embodiment of the present invention is shown. The investment promotion analysis system based on big data 1 includes:

[0097] The generating module 11 is used to obtain a store distribution map of a region, divide it into a plurality of areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to a region;

[0098] The color changing module 12 is used to obtain the video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color matching corresponding to each segment, classify the blocks into the segments, and use the color matching corresponding to the segments to render and change the color of the blocks;

[0099] Insertion module 13, used to read out the attributes of each block, wherein the attributes include at least: clothing, beauty and catering, and insert a label consisting of the attributes into the block;

[0100] The sending module 14 is used to integrate the several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, build an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

[0101] Figure 7 The structure diagram of the investment promotion analysis system based on big data provided by an embodiment of the present invention is shown, and the generation module 11 includes:

[0102] A search unit 111 is used to search for the import and export in the store distribution map, wherein the number of the import and export is greater than or equal to 1;

[0103] A sorting unit 112, used to calculate the distance from the store to the nearest entrance and exit, and sort the blocks according to the distance;

[0104] A configuration unit 113, configured to configure a correspondence between the slice area and the number of blocks, and insert blank blocks into the number of blocks;

[0105] The prediction unit 114 is used to use the video surveillance data to count the number of visits to the blank block, and determine the prediction result of the blank block based on the number of visits and the labels in the block column.

[0106] Figure 8 The structure diagram of the investment promotion analysis system based on big data provided by an embodiment of the present invention is shown, and the color changing module 12 includes:

[0107] An adding unit 121 is used to extract the portrait features in the video surveillance data by using a preset video image processing technology, and add an identifier to the portrait features;

[0108] The embedding unit 122 is used to calculate the access time of each portrait feature according to the identifier, generate a residence time set, and embed the residence time set into a number block.

[0109] Fig. 9 The structure diagram of the investment promotion analysis system based on big data provided by an embodiment of the present invention is shown, and the insertion module 13 includes:

[0110] A correction unit 131 is used to establish a mapping of stores, residence time sets and attributes, and to correct the analysis report using the mapping;

[0111] The division unit 132 is used to divide the stores according to the residence time set to determine the popularity of the stores.

[0112] Fig.10 The structure block diagram of the investment promotion analysis system based on big data provided by an embodiment of the present invention is shown, and the sending module 14 includes:

[0113] A linking unit 141 is used to link multi-dimensional data to the analysis report, wherein the multi-dimensional data at least includes: sales data and environmental data;

[0114] The synchronization unit 142 is used to dynamically monitor the missing items and excellent items, determine the change process, and synchronize the change process into the analysis report.

[0115] The generating module 11 is mainly used to complete step S100, the color changing module 12 is mainly used to complete step S200, the inserting module 13 is mainly used to complete step S300, and the sending module 14 is mainly used to complete step S400;

[0116] The search unit 111 is mainly used to complete step S101, the sorting unit 112 is mainly used to complete step S102, the configuration unit 113 is mainly used to complete step S103, and the prediction unit 114 is mainly used to complete step S104;

[0117] The adding unit 121 is mainly used to complete step S201, and the embedding unit 122 is mainly used to complete step S202;

[0118] The correction unit 131 is mainly used to complete step S301, and the division unit 132 is mainly used to complete step S302;

[0119] The link unit 141 is mainly used to complete step S401, and the synchronization unit 142 is mainly used to complete step S402.

[0120] 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.

[0121] 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.

[0122] 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. A big data-based investment promotion analysis method, characterized in that: The method comprises: S100: Obtain a store distribution map of a region, divide it into several areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to one area; S200: Obtain video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color scheme corresponding to each segment, classify the blocks into the segments, and render and change the color of the blocks using the color scheme corresponding to the segments; S300: reading out the attributes of each block, wherein the attributes include at least: clothing, beauty and catering, and inserting a label consisting of the attributes into the block; S400: Integrate several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, construct an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

2. The big data-based investment promotion analysis method according to claim 1, characterized in that: The S100 includes: In the store distribution map, find the import and export, where the number of the import and export is greater than or equal to 1; The distance from the store to the nearest entrance and exit is calculated, and the blocks are sorted according to the distance.

3. The big data-based investment promotion analysis method according to claim 1, characterized in that: The S100 further includes: A corresponding relationship between the slice area and the number of blocks is configured, and blank blocks are inserted into the number of blocks; The video surveillance data is used to count the number of visits to the blank block, and the prediction result of the blank block is determined based on the number of visits and the labels in the column.

4. The big data-based investment promotion analysis method according to claim 1, characterized in that: The S200 includes: Using a preset video image processing technology, extracting portrait features from the video surveillance data, and adding identifiers to the portrait features; Based on the identification, the access duration of each portrait feature is calculated, a residence time set is generated, and the residence time set is embedded into a number block.

5. The big data-based investment promotion analysis method according to claim 4 is characterized in that: The S300 includes: Establishing a mapping of stores, dwell time sets and attributes, and using the mapping to modify the analysis report; The stores are divided according to the residence time set to determine the popularity of the stores.

6. The investment promotion analysis method based on big data according to claim 1 is characterized in that: The S400 includes: Linking multi-dimensional data to the analysis report, wherein the multi-dimensional data includes at least: sales data and environmental data; Dynamically monitor the missing items and excellent items, determine the change process, and synchronize the change process into the analysis report.

7. The big data-based investment promotion analysis method according to claim 1, characterized in that: The method further comprises: Deploy interactive feedback points in the area, and push selection windows to the interactive feedback points; Receive the selection results uploaded by the user, extract the feedback items, and integrate the feedback items into the analysis report.

8. A big data-based investment promotion analysis system, characterized in that: The system comprises: A generation module is used to obtain a store distribution map of a region, divide it into several areas, and mark the locations of the entrances and exits and stores in each area, create blocks corresponding to the stores one by one, sort the blocks according to the distance between the stores and the entrances and exits, integrate the sorted blocks, and generate block columns, wherein each block column corresponds to a region; The color changing module is used to obtain the video surveillance data in the area, count the number of people entering each area, divide the number of people into several segments, configure the color matching corresponding to each segment, classify the blocks into the segments, and use the color matching corresponding to the segments to render and change the color of the blocks; An insertion module is used to read out the attributes of each block, wherein the attributes include at least: clothing, beauty and catering, and insert a label consisting of the attributes into the block; The sending module is used to integrate the several columns corresponding to each area in the region to obtain a column group, split the region into a competitive region and an excellent region, build an analysis model of consumer demand, input the column group corresponding to the competitive region into the analysis model, output missing items, input the column group corresponding to the excellent region into the analysis model, output excellent items, integrate the missing items, excellent items and a preset analysis template to obtain an analysis report, and send the analysis report to a preset terminal.

9. The big data-based investment promotion analysis system according to claim 8, characterized in that: The generation module comprises: A search unit, configured to search for the import and export in the store distribution map, wherein the number of the import and export is greater than or equal to 1; A sorting unit, used to calculate the distance from the store to the nearest entrance and exit, and sort the blocks according to the distance; A configuration unit, configured to configure a correspondence between the slice area and the number of blocks, and insert blank blocks into the number of blocks; The prediction unit is used to use the video monitoring data to count the number of visits to the blank block, and determine the prediction result of the blank block based on the number of visits and the labels in the block column.

10. The big data-based investment promotion analysis system according to claim 8, characterized in that: The color changing module comprises: An adding unit, configured to extract the portrait features in the video surveillance data by using a preset video image processing technology, and to add an identifier to the portrait features; The embedding unit is used to calculate the access time of each portrait feature according to the identifier, generate a residence time set, and embed the residence time set into a number block.

Images