Urbanization resource demand prediction management system based on big data analysis

Abstract

The application is suitable for the technical field of demand prediction, and particularly relates to a management system for urbanization resource demand prediction based on big data analysis, which comprises a collection device, a node sorting device, a demand writing device and a difference updating device; the collection device is used for collecting urbanization resource data of a city, cutting the data into a plurality of indexes, creating a branch node corresponding to each city, mounting a leaf node corresponding to each index in the branch node, collecting real-time data of each index and uploading the real-time data into the leaf node, integrating the branch node and the leaf node and generating a binary tree; and the node sorting device is used for sorting the binary tree. According to the urbanization process of a target city, the demand prediction tree can be used to dynamically adjust a leading city, so that the accuracy of resource demand prediction is greatly improved. In addition, by replacing difference items, the demand prediction tree can be corrected, so that the accuracy of resource demand prediction is further improved.

Description

Technical Field

[0001] This invention relates to the field of demand forecasting technology, and in particular to an urbanization resource demand forecasting and management system based on big data analysis. Background Technology

[0002] Urbanization resource demand forecasting refers to the process of quantitatively or qualitatively predicting and assessing the various resources needed by a city in the future, based on factors such as population growth, industrial development, land use changes, and urban expansion, during the urbanization process.

[0003] Current urbanization resource demand forecasting technologies typically rely on analyzing historical data trends. Such static data lacks dynamic adaptability and struggles to cope with sudden events (such as pandemics), policy adjustments, or industrial relocations, making it impossible to dynamically adjust forecasts based on these events. Identifying cities with higher urbanization levels provides templates for demand forecasting in cities with lower urbanization, enabling dynamic adjustments to forecasts and reducing trial-and-error costs. However, this also requires considering the characteristics of different cities. Significant differences exist in the dominant industrial structures of different cities. For example, some cities are tourism-driven with a high proportion of service industries, while others are manufacturing-centric. These two types of cities may exhibit significant differences in land use changes, population growth, and infrastructure evolution during the urbanization process.

[0004] Therefore, "how to use pioneering cities with similar attributes to provide guidance for predicting the urbanization resource demand of target cities" is the technical problem that this invention needs to solve. Summary of the Invention

[0005] The purpose of this invention is to provide an urbanization resource demand forecasting and management system based on big data analysis, in order to solve the problem raised in the background art of "how to use pioneering cities with similar attributes to provide guidance for forecasting the urbanization resource demand of target cities".

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A big data analytics-based urbanization resource demand forecasting and management system, the system comprising:

[0008] The system includes: a data acquisition device, a node sorting device, a demand writing device, and a difference update device;

[0009] The data acquisition device is used to collect urbanization resource data of the city, divide it into several indicators, create branch nodes corresponding to each city, attach leaf nodes corresponding to the indicators to the branch nodes, collect real-time data of each indicator, upload the real-time data to the leaf nodes, integrate the branch nodes and leaf nodes, and generate a binary tree.

[0010] The node sorting device is used to determine the target city for resource demand prediction, cluster the branch nodes into target nodes and other nodes, input the real-time data into a pre-built data comparison model, calculate the similarity between the target node and other nodes in turn, and sort the other nodes in order of the similarity from high to low to obtain a queue.

[0011] The demand writing device is used to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of preceding nodes are selected from the front of the queue to create a demand prediction tree. The target node and its corresponding leaf node are written to the left side of the demand prediction tree, and the preceding nodes and their corresponding leaf nodes are written to the right side of the demand prediction tree.

[0012] The difference update device is used to obtain popular topics in the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, define the difference items, find the cities with the same attribute tags, replace the difference items, align the left and right sides, generate a prediction report, and send the prediction report and the demand prediction tree to the preset terminal.

[0013] Furthermore, the data acquisition device includes:

[0014] Create a module to collect urbanization resource data of cities, divide it into several indicators, create branch nodes corresponding to each city, and attach leaf nodes corresponding to the indicators to the branch nodes.

[0015] The generation module is used to collect real-time data for each indicator, upload the real-time data to the leaf nodes, integrate the branch nodes and leaf nodes, and generate a binary tree.

[0016] Furthermore, the node sorting device includes:

[0017] The input module is used to determine the target city for resource demand forecasting, cluster the branch nodes into target nodes and other nodes, and input the real-time data into a pre-built data comparison model.

[0018] The module is used to calculate the similarity between the target node and other nodes in turn, and sort the other nodes in descending order of the similarity to obtain a queue.

[0019] Furthermore, the demand writing device includes:

[0020] A selection module is used to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of leading nodes are selected from the front of the queue to create a demand prediction tree.

[0021] The writing module is used to write the target node and its corresponding leaf node to the left side of the demand prediction tree, and to write the preceding node and its corresponding leaf node to the right side of the demand prediction tree.

[0022] Furthermore, the difference update device includes:

[0023] The access module is used to obtain popular topics from the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, and define the differences.

[0024] The sending module is used to find cities with the same attribute tags, replace the differences, align the left and right sides, generate a prediction report, and send the prediction report and demand prediction tree to a preset terminal.

[0025] Furthermore, the creation module includes:

[0026] A configuration unit is used to configure the weight value of each indicator and divide the real-time data into several levels, wherein each level corresponds to a base score;

[0027] A unit is established to define the product of the weight value and the base score as the comprehensive score, and to establish the correspondence between the comprehensive score and the city.

[0028] Furthermore, the generation module includes:

[0029] The setting unit is used to set the time window corresponding to the real-time data and insert the labels generated by the time window into the binary tree;

[0030] The construction unit is used to grant data access permissions to the binary tree and to build a permission management mechanism.

[0031] Furthermore, the obtaining module includes:

[0032] The calculation unit is used to calculate the difference value between the target node and the leaf nodes corresponding to other nodes using a preset difference formula;

[0033] The difference formula is:

[0034]

[0035] Where E is the difference value, a i For the real-time data of the i-th node in the target node, bi This refers to the real-time data of the i-th node among the other nodes;

[0036] A conversion unit is used to convert the difference value into a similarity value using a similarity formula;

[0037] The similarity formula is:

[0038]

[0039] Where S represents similarity and E represents difference.

[0040] Furthermore, the selection module includes:

[0041] A recording unit is used to record versions of the demand prediction tree and establish a mapping between version records and time windows;

[0042] An embedding unit is used to embed a replacement mechanism into the demand prediction tree.

[0043] Furthermore, the access module includes:

[0044] The search unit is used to construct a set of phrases consisting of several keywords, traverse preset platforms, find platform hotspots containing the keywords, and define them as popular topics;

[0045] The replacement unit is used to obtain several reference cities among cities with the same attribute label, and select at least one comparison indicator from each reference city to replace the difference item.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] By defining the creation module, resource demand forecasting can be refined and the analysis results can be specified, reducing analysis errors and facilitating dynamic adjustments to the analysis results. By defining the generation module, real-time data for each indicator can be displayed intuitively, greatly improving resource scheduling and risk warning capabilities during the urbanization process. By defining the selection module, the leading nodes of the target city in the urbanization process can be identified, providing the target city with reusable development paths and strategy templates, while significantly improving the accuracy of resource demand forecasting for the target city. By constructing a demand forecasting tree, leading cities can be dynamically adjusted according to the urbanization process of the target city, greatly improving the accuracy of resource demand forecasting. In addition, by replacing discrepancies, the demand forecasting tree can be corrected, further improving forecasting efficiency. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of a binary tree structure provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the demand prediction tree structure provided in an embodiment of the present invention;

[0050] Figure 3 A block diagram illustrating the composition of the urbanization resource demand forecasting and management system based on big data analysis provided in this embodiment of the invention;

[0051] Figure 4 This is a block diagram of the data acquisition equipment in the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention.

[0052] Figure 5 A block diagram of the node sorting device in the urbanization resource demand prediction and management system based on big data analysis provided in an embodiment of the present invention;

[0053] Figure 6 A block diagram of the demand writing device in the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention;

[0054] Figure 7 A block diagram showing the composition of the differential update device in the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention;

[0055] Figure 8 A block diagram illustrating the composition of the creation module in the urbanization resource demand forecasting and management system based on big data analysis provided in this embodiment of the invention;

[0056] Figure 9 A block diagram showing the composition of the generation module in the urbanization resource demand forecasting and management system based on big data analysis provided in this embodiment of the invention;

[0057] Figure 10 The diagram shows the composition of the modules in the urbanization resource demand forecasting and management system based on big data analysis provided in this embodiment of the invention.

[0058] Figure 11 A block diagram showing the composition of selected modules in the urbanization resource demand forecasting and management system based on big data analysis provided in this embodiment of the invention;

[0059] Figure 12 This is a block diagram of the access module in the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0061] Figure 1 , Figure 2 and Figure 3 The diagram shows the structural composition of an urbanization resource demand forecasting and management system 1 based on big data analysis provided in an embodiment of the present invention. The system includes: a data acquisition device 11, a node sorting device 12, a demand writing device 13, and a difference update device 14.

[0062] The acquisition device 11 is used to collect urbanization resource data of the city, divide it into several indicators, create branch nodes corresponding to each city, attach leaf nodes corresponding to each indicator to the branch nodes, collect real-time data of each indicator, upload the real-time data to the leaf nodes, integrate the branch nodes and leaf nodes, and generate a binary tree.

[0063] The process involves collecting urban resource data, including but not limited to population density, infrastructure data (such as roads, water and electricity load, and drainage), public service coverage (such as education and healthcare), industrial structure, land use rate, and housing conditions. This data is then categorized into several indicators, such as urbanization rate, population density, water and electricity load, and traffic flow. Branch nodes (parent nodes) are created for each city, and leaf nodes (child nodes) are created for each indicator, which are then attached to their respective parent nodes. Real-time data for each indicator is collected from publicly available data or relevant departments and written into the leaf nodes. A binary tree is constructed, providing a visual representation of the city's urban resource data.

[0064] The node sorting device 12 is used to determine the target city for resource demand prediction, cluster the branch nodes into target nodes and other nodes, input the real-time data into a pre-built data comparison model, calculate the similarity between the target node and other nodes in turn, and sort the other nodes in order of the similarity from high to low to obtain a queue.

[0065] The process involves identifying the target cities as the objects for resource demand forecasting; defining the branch nodes corresponding to the target cities as target nodes; and defining the other branch nodes as other nodes. Real-time data is input into a data comparison model, which calculates the similarity between each target node and each other node. This model integrates difference and similarity formulas, enabling high-concurrency, multi-dimensional comparative analysis and processing of large-scale indicator data. After similarity calculation, all other nodes are sorted in descending order of similarity, creating a queue that visually reflects the degree of similarity between each other node. In other words, the queue is a sequential set of cities that are relatively similar to the target city; similarity refers to similarities beyond urbanization resources, such as economic development levels and regional policies.

[0066] The demand writing device 13 is used to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of preceding nodes are selected from the front of the queue to create a demand prediction tree. The target node and its corresponding leaf node are written to the left side of the demand prediction tree, and the preceding nodes and their corresponding leaf nodes are written to the right side of the demand prediction tree.

[0067] Determine the urbanization development process of each city, which should be formulated by professionals or directly represented by the urbanization rate. From the top of the queue, select other nodes whose development process is higher than the target city and define them as leading nodes. Furthermore, the number of leading nodes should be pre-determined by professionals. If the number of leading nodes is too large, the similarity between leading nodes and target nodes will be low, affecting the reference validity of the indicator data in the leading nodes. If the number of leading nodes is too small, it may lead to large deviations in the indicators, also affecting the accuracy of the guidance. Create a demand forecasting tree, which is a tree-like data structure composed of left and right sides. The demand forecasting tree stores the corresponding indicators in the target node and leading nodes in relatively mirrored positions; for example, as shown in the appendix to the instruction manual. Figure 2 As shown, indicators A1 and B1 are arranged in a mirror image, and the data in indicators A1 and B1 are the real-time data corresponding to the same indicator; the advantage of doing this is that it can quickly find the differences between the target node and the preceding node.

[0068] The difference update device 14 is used to obtain popular topics in the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, define the difference items, find the cities with the same attribute tags, replace the difference items, align the left and right sides, generate a prediction report, and send the prediction report and the demand prediction tree to the preset terminal.

[0069] Popular topics are obtained from preset platforms, including social media platforms, news platforms, and policy announcement platforms. Popular topics are extracted from the interactive sections of these platforms through topic popularity analysis. These popular topics are then used to determine the attribute tags of the target city, including tags such as suitability for tourism, high compliance with waste sorting, housing shortages, traffic congestion, and abundant educational resources. The same positions on both sides of the demand prediction tree are compared to identify indicators with significant differences, i.e., discrepancies. Cities with the same attribute tags as the target city are then identified, and these cities are used to correct the discrepancies. Specifically, the correction process involves using indicators related to the attribute tags from the identified cities as control indicators to replace the discrepancies.

[0070] Define the left side of the demand forecast tree as real-time items and the right side as target items, write them into a preset template, and generate a forecast report. The preset template is created by professionals. Send the forecast report and the demand forecast tree to a preset terminal, which is a professional's terminal.

[0071] For example, as per the instruction manual Figure 2 As shown, the target city currently has an urbanization rate of 48%, and indicator A1, the urban population density, is 140 people / square kilometer. The pilot node has an urbanization rate of 55%, and indicator B1, the urban population density, is 152 people / square kilometer. The predicted result is that when the target city's urbanization rate is around 55%, the urban population density is approximately 152 people / square kilometer. However, this prediction is based on the assumption that the target city and the pilot node have roughly the same level of urban development. If, through analysis of trending topics on social media and news platforms, it is learned that a large-scale complex is about to be built in the pilot node, this could lead to a significant increase in regional electricity consumption (indicator A2). In this case, the electricity consumption indicator of the pilot node (indicator B2) is no longer sufficient for reference. A new city with a large-scale complex opening should be identified among those with roughly similar urban development, and its corresponding electricity consumption indicator should be used as a reference indicator. Indicator B2 is the difference item; the target city's indicator is stored on the left side of the demand forecast tree, while the pilot city's and the difference item are stored on the right side.

[0072] Figure 4 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The data acquisition device 11 includes:

[0073] Create module 111 to collect urbanization resource data of cities, divide it into several indicators, create branch nodes corresponding to each city, and attach leaf nodes corresponding to the indicators to the branch nodes.

[0074] Urbanization resource data is collected from various cities, including aspects such as infrastructure construction, public service coverage, housing supply, green space ratio, traffic flow, and urban expansion speed. The data in each aspect is structured to obtain several quantifiable and comparable indicators. A branch node is created for each city, and multiple leaf nodes are attached to each branch node, with each leaf node corresponding to an indicator.

[0075] The generation module 112 is used to collect real-time data for each indicator, upload the real-time data to the leaf node, integrate the branch nodes and leaf nodes, and generate a binary tree.

[0076] Upload the real-time data of each indicator to the corresponding leaf node, and create a binary tree using branch nodes and leaf nodes.

[0077] Figure 5 This diagram illustrates the structural composition of an urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The node sorting device 12 includes:

[0078] The input module 121 is used to determine the target city for resource demand prediction, cluster the branch nodes into target nodes and other nodes, and input the real-time data into a pre-built data comparison model.

[0079] The city that needs to be forecasted for resource demand is defined as the target city, and the branch node corresponding to the target city is defined as the target node; further, the branch nodes other than the target node are the other nodes.

[0080] Module 122 is used to calculate the similarity between the target node and other nodes sequentially, and sort the other nodes in descending order of similarity to obtain a queue.

[0081] Using a data comparison model, the similarity between the target node and each other node is calculated, and the nodes are sorted in descending order of similarity. The set of other nodes after sorting is defined as a queue.

[0082] Figure 6 This diagram illustrates the structural composition of an urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The demand writing device 13 includes:

[0083] Module 131 is selected to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of leading nodes are selected from the front of the queue to create a demand prediction tree.

[0084] The urbanization process of each city is determined, and based on this process, a predetermined number of pioneering nodes are selected from the front of the queue. The predetermined number is determined by professionals.

[0085] The writing module 132 is used to write the target node and its corresponding leaf node to the left side of the demand prediction tree, and to write the preceding node and its corresponding leaf node to the right side of the demand prediction tree.

[0086] Figure 7 This diagram illustrates the structural composition of an urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The differential update device 14 includes:

[0087] Access module 141 is used to obtain popular topics in the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, and define the differences.

[0088] By comparing the left and right sides of the demand forecast tree, the metrics corresponding to the attribute labels are defined as differences.

[0089] The sending module 142 is used to find cities with the same attribute labels, replace the differences, align the left and right sides, generate a prediction report, and send the prediction report and the demand prediction tree to a preset terminal.

[0090] Find cities with the same attribute tags as the target city, and replace the differences with the indicators corresponding to the attribute tags of the found cities; write the indicators in the replaced demand forecast tree into a preset template, generate a forecast report, and send it to a preset terminal, which can be a management terminal.

[0091] Figure 8 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The creation module 111 includes:

[0092] Configuration unit 1111 is used to configure the weight value of each indicator and divide the real-time data into several levels, wherein each level corresponds to a basic score.

[0093] Professionals assign a weight value to each indicator and divide the real-time data of each indicator into several levels, where each level is the fluctuation range and each level corresponds to a base score.

[0094] Establishment unit 1112 is used to define the product of the weight value and the basic score as the comprehensive score, and to establish the correspondence between the comprehensive score and the city.

[0095] The weighted value is multiplied by the base score to obtain the comprehensive score, with each city corresponding to a comprehensive score.

[0096] Figure 9 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The generation module 112 includes:

[0097] Setting unit 1121 is used to set the time window corresponding to the real-time data and insert the label generated by the time window into the binary tree.

[0098] Since urbanization resource data does not change significantly in a short period of time, it can be updated at a fixed frequency by setting time windows. By inserting labels generated by the time windows into the binary tree, the generation time of each urbanization resource data can be displayed intuitively.

[0099] The construction unit 1122 is used to grant data access permissions to the binary tree and to construct a permission management mechanism.

[0100] Since the binary tree stores urbanization resource data, some of which may involve sensitive information, an access control mechanism is embedded into the binary tree. This access control mechanism is a specific access control method, such as allowing city managers to access the full data, researchers to access anonymized data within the urbanization resource data, and enterprise users to access publicly available data within the urbanization resource data.

[0101] Figure 10 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The obtaining module 122 includes:

[0102] The calculation unit 1221 is used to calculate the difference value between the target node and the leaf nodes corresponding to other nodes using a preset difference formula.

[0103] The difference formula is:

[0104]

[0105] Where E is the difference value, a i For the i-th real-time data in the target node, b i This is the i-th real-time data among other nodes;

[0106] As mentioned above, suppose a i For real-time data of indicator A1, then b i In other words, the difference between indicator A1 and indicator B1 can be calculated using the difference formula based on the real-time data of indicator B1.

[0107] The conversion unit 1222 is used to convert the difference value into a similarity value using a similarity formula;

[0108] The similarity formula is:

[0109]

[0110] Where S represents similarity and E represents difference.

[0111] Continue using the difference values ​​to calculate the similarity between indicator A1 and indicator B1; it should be noted that the similarity of the target node is the average of the similarities of all indicators.

[0112] Figure 11 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The selection module 131 includes:

[0113] Recording unit 1311 is used to record versions of the demand prediction tree and establish a mapping between version records and time windows.

[0114] The demand forecasting tree is recorded using a versioning approach; that is, each time the demand forecasting tree is changed (such as node adjustment, data update or structure optimization), a corresponding version number is generated and the complete structure of that version and the parameters of the relevant branch nodes and leaf nodes are saved.

[0115] Embedding unit 1312 is used to embed a replacement mechanism into the demand prediction tree.

[0116] The replacement mechanism is as follows: the indicators related to the attribute labels in the found cities are identified as control indicators, and the differences are replaced by these control indicators.

[0117] Figure 12 This diagram illustrates the structural composition of the urbanization resource demand forecasting and management system based on big data analysis provided in an embodiment of the present invention. The access module 141 includes:

[0118] The search unit 1411 is used to construct a set of phrases consisting of several keywords, traverse preset platforms, find platform hotspots containing the keywords, and define them as popular topics.

[0119] Construct a set of phrases consisting of several keywords. The keywords should be determined by professionals. Traverse social media platforms, news platforms, and policy announcement platforms, and search for information such as text content, user comments, titles, and tags on each platform to see if any of the keywords in the phrase set are contained. If multiple pieces of content on a certain platform frequently contain these keywords, and the discussion and interaction volume reach a set threshold, then define this phenomenon as a platform hotspot. Define the topics corresponding to the platform hotspots as popular topics.

[0120] Replacement unit 1412 is used to obtain several reference cities among cities with the same attribute label, and select at least one comparison indicator from each reference city to replace the difference item.

[0121] Data from the reference cities that share the same attribute labels as the target city are identified as control indicators, and these control indicators are used to replace the differences.

[0122] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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.

[0123] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0124] 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 within the protection scope of the present invention.

Claims

1. A big data analytics-based urbanization resource demand forecasting and management system, characterized in that, The system includes: a data acquisition device, a node sorting device, a demand writing device, and a difference update device; The data acquisition device is used to collect urbanization resource data of the city, divide it into several indicators, create branch nodes corresponding to each city, attach leaf nodes corresponding to the indicators to the branch nodes, collect real-time data of each indicator, upload the real-time data to the leaf nodes, integrate the branch nodes and leaf nodes, and generate a binary tree. The node sorting device is used to determine the target city for resource demand prediction, cluster the branch nodes into target nodes and other nodes, input the real-time data into a pre-built data comparison model, calculate the similarity between the target node and other nodes in turn, and sort the other nodes in order of the similarity from high to low to obtain a queue. The demand writing device is used to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of preceding nodes are selected from the front of the queue to create a demand prediction tree. The target node and its corresponding leaf node are written to the left side of the demand prediction tree, and the preceding nodes and their corresponding leaf nodes are written to the right side of the demand prediction tree. The difference update device is used to obtain popular topics in the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, define the difference items, find the cities with the same attribute tags, replace the difference items, align the left and right sides, generate a prediction report, and send the prediction report and the demand prediction tree to the preset terminal. The acquisition device consists of a creation module and a generation module; The creation module includes: A configuration unit is used to configure the weight value of each indicator and divide the real-time data into several levels, wherein each level corresponds to a base score; A unit is established to define the product of the weight value and the base score as the comprehensive score, and to establish the correspondence between the comprehensive score and the city. The generation module includes: The setting unit is used to set the time window corresponding to the real-time data and insert the labels generated by the time window into the binary tree; A construction unit is used to grant data access permissions to the binary tree and to build a permission management mechanism; The node sorting device consists of an input module and an output module; The obtained module includes: The calculation unit is used to calculate the difference value between the target node and the leaf nodes corresponding to other nodes using a preset difference formula; The difference formula is: Where E is the difference value, a i For the real-time data of the i-th node in the target node, b i This refers to the real-time data of the i-th node among the other nodes; A conversion unit is used to convert the difference value into a similarity value using a similarity formula; The similarity formula is: Where S is the similarity and E is the difference value; The demand writing device consists of a selection module and a writing module; The selection module includes: A recording unit is used to record versions of the demand prediction tree and establish a mapping between version records and time windows; An embedding unit is used to embed a replacement mechanism into the demand prediction tree; The difference update device consists of an access module and a sending module; The access module includes: The search unit is used to construct a set of phrases consisting of several keywords, traverse preset platforms, find platform hotspots containing the keywords, and define them as popular topics; The replacement unit is used to obtain several reference cities among cities with the same attribute label, and select at least one comparison indicator from each reference city to replace the difference item.

2. The urbanization resource demand forecasting and management system based on big data analysis according to claim 1, characterized in that, The data acquisition device includes: Create a module to collect urbanization resource data of cities, divide it into several indicators, create branch nodes corresponding to each city, and attach leaf nodes corresponding to the indicators to the branch nodes. The generation module is used to collect real-time data for each indicator, upload the real-time data to the leaf nodes, integrate the branch nodes and leaf nodes, and generate a binary tree.

3. The urbanization resource demand forecasting and management system based on big data analysis according to claim 1, characterized in that, The node sorting device includes: The input module is used to determine the target city for resource demand forecasting, cluster the branch nodes into target nodes and other nodes, and input the real-time data into a pre-built data comparison model. The module is used to calculate the similarity between the target node and other nodes in turn, and sort the other nodes in descending order of the similarity to obtain a queue.

4. The urbanization resource demand forecasting and management system based on big data analysis according to claim 2, characterized in that, The demand writing device includes: A selection module is used to configure the development process of urban urbanization, wherein each branch node corresponds to a development process. Through the development process, a preset number of leading nodes are selected from the front of the queue to create a demand prediction tree. The writing module is used to write the target node and its corresponding leaf node to the left side of the demand prediction tree, and to write the preceding node and its corresponding leaf node to the right side of the demand prediction tree.

5. The urbanization resource demand forecasting and management system based on big data analysis according to claim 1, characterized in that, The difference update device includes: The access module is used to obtain popular topics from the preset platform and access them into the demand prediction tree, extract the attribute tags of the target city, compare the left and right sides of the demand prediction tree, and define the differences. The sending module is used to find cities with the same attribute tags, replace the differences, align the left and right sides, generate a prediction report, and send the prediction report and demand prediction tree to a preset terminal.

Images