A GIS-based intelligent prediction and management method and system for urban resources

Abstract

The present invention discloses a GIS-based intelligent prediction management method and system for urban resources, which relates to the field of computer technology, including: collecting resource scenario data, formatting data standards, generating at least one resource data set, and forming a GIS resource map; marking resource data sub-tables in the GIS resource map according to resource occupation conditions; training and generating a resource allocation model according to a resource request test set; forming a sample resource demand prediction test set, and training and generating a request prediction model according to the sample resource demand prediction test set; collecting resource requests, generating a request solution according to the resource allocation model, and predicting subsequent requests according to the request prediction model. By setting a resource allocation training module, a resource prediction training module, and a resource allocation module, the request demand is decomposed into basic units, and preparations are made in advance in the system, so that when subsequent requests are made, they can be solved in time.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a GIS-based urban resource intelligent prediction management method and system. Background Art

[0002] In recent years, driven by the technological waves such as 5G and new infrastructure, the use of the advantages and characteristics of the new generation of the Internet of Things, with the goal of building a real-life three-dimensional China, has created a "city brain" that has become a new hot spot in the cutting-edge technology field of urban construction and the development of various sectors and industries. The purpose of building a smart city management system is to achieve data interconnection and resource sharing, analyze the city's full-time and space data, effectively allocate public resources to support the environment, continuously improve social governance, and promote sustainable urban development.

[0003] The existing smart urban management dispatch system lacks a unified processing architecture and process, and the demand decomposition and prediction of resource allocation are insufficient, resulting in insufficient matching of the system's solutions to resource needs. At the same time, there is insufficient preparation for subsequent needs for resource allocation, which prolongs the time it takes to resolve needs. Summary of the invention

[0004] In order to solve the above technical problems, a GIS-based urban resource intelligent prediction and management method and system are provided. This technical solution solves the problem that the existing smart urban management dispatching system proposed in the above background technology lacks a unified processing architecture and process, and the demand decomposition and prediction of resource allocation are insufficient, resulting in insufficient matching of the system's solutions to resource needs. At the same time, there is insufficient preparation for subsequent needs for resource demand allocation, which leads to prolonged demand resolution time.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A GIS-based intelligent prediction and management method for urban resources, comprising:

[0007] Collect resource scenario data, format the data according to the data standard, generate at least one resource data set, set at least one resource data sub-table under the resource data set, generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map;

[0008] Generate map areas on the GIS resource map and correspond the map areas to resource data sets one by one;

[0009] According to the resource occupancy, resource data is divided into tables and occupancy is marked in the GIS resource map;

[0010] If the resource data sub-table is marked as occupied, the resource data sub-table cannot be called;

[0011] If the resource data sub-table is not marked as occupied, the resource data sub-table can be called;

[0012] Obtain at least one sample resource request to form a resource request test set, and train and generate a resource allocation model according to the resource request test set;

[0013] Obtain at least one sample resource request and a subsequent sample resource request, match the sample resource request with the subsequent sample resource request one by one to form a sample resource demand prediction test set, and train and generate a request prediction model based on the sample resource demand prediction test set;

[0014] Collect resource requests, generate request solutions based on the resource allocation model, predict subsequent requests based on the request prediction model, book resources in advance, mark the resource occupancy of the booked resources, and set waiting time for the marked resources;

[0015] If the reserved resource is not called within the waiting time, the resource reservation status is canceled and the resource occupation mark is removed;

[0016] If the reserved resources are called during the waiting time, the resource reservation status will be continued and the resource occupancy mark will be continued.

[0017] Preferably, the data standard formatting process comprises the following steps:

[0018] Aggregate resource scenario data, and divide the resource scenario data into at least one basic resource unit, where the basic resource unit only contains a single resource attribute;

[0019] Mark resource attributes for basic resource units, and make a one-to-one correspondence between basic resource units and resource attribute marks;

[0020] The basic resource units with the same resource attributes are aggregated and arranged to form a resource data table;

[0021] Assign resource attributes to the resource data sub-list, wherein the resource attributes are resource attributes of basic resource units in the resource data sub-list;

[0022] Basic resource units with similar resource attributes are aggregated to form a resource data set.

[0023] Preferably, the forming of the GIS resource map comprises the following steps;

[0024] Establishing a GIS layer, establishing a coordinate system on the GIS layer, and dividing the GIS layer to form at least one map area;

[0025] Match map areas to resource data sets one by one;

[0026] Take the coordinates of the whole points in each map area as grid points, and assign the coordinates of each grid point to the resource data table in the resource data set corresponding to the map area;

[0027] The resource data is divided into tables and marked according to the coordinates to the corresponding grid points in the map area.

[0028] Preferably, the step of marking the occupancy of the resource data sub-tables comprises the following steps:

[0029] Resource requests trigger the resource allocation model and generate request solutions;

[0030] According to the requested solution, resources are deployed, GIS resource maps are called, and corresponding resource data sub-tables are retrieved according to the path map area to the grid points within the map area;

[0031] The allocated resource data sub-table is marked as occupied.

[0032] Preferably, the training and generating of the resource allocation model according to the resource request test set includes the following steps:

[0033] Decompose the resource requests in the resource request test set to obtain a resource request basic unit, which only contains a single resource attribute;

[0034] Big data collects events that occur in the basic unit of resource request. For each resource attribute, the number of events that occur with the resource attribute is counted separately, and the conditional probability of each resource attribute is calculated using the conditional probability formula;

[0035] The resource request basic unit is assigned the resource attribute with the highest conditional probability;

[0036] The resource request basic unit is associated with the resource data sub-table with the same resource attribute, and the path of the resource data sub-table in the GIS resource map is recorded as the calling path;

[0037] The conditional probability formula is as follows:

[0038]

[0039] Among them, P is the conditional probability of each resource attribute, A is the number of events in which the resource attribute occurs, and B is the number of events in which the resource request basic unit occurs.

[0040] Preferably, the training to generate a request prediction model comprises the following steps:

[0041] Obtain a sample resource demand prediction test set, decompose the sample resource request into basic requests, decompose the sample resource subsequent request into basic subsequent requests, then each sample resource request corresponds to a basic request combination set, and each sample resource subsequent request corresponds to a basic subsequent request combination set;

[0042] According to the correspondence between the sample resource request and the sample resource subsequent request, the basic request combination set is matched with the basic subsequent request combination set;

[0043] For any basic request, find two basic request combinations whose intersection element is exactly the basic request;

[0044] Calling two basic subsequent request combination sets corresponding to the two basic request combination sets, making an intersection of the two basic subsequent request combination sets, and then the basic subsequent request in the intersection is the subsequent request corresponding to the basic request;

[0045] The basic request is associated with its corresponding basic subsequent request to obtain a request prediction model.

[0046] Preferably, generating a request solution according to the resource allocation model comprises the following steps:

[0047] When obtaining an actual resource request, decomposing the resource request into at least one resource request basic unit;

[0048] According to the resource attribute of the resource request basic unit, a resource data sub-table with the same resource attribute is called;

[0049] When calling the resource data sub-table, use the calling path of the resource data sub-table to call the corresponding resource data sub-table in the GIS resource map;

[0050] Summarize all resource data calls into separate tables to get the requested solution.

[0051] Preferably, predicting subsequent requests according to the request prediction model comprises the following steps:

[0052] For any resource request, decompose the resource request into at least one basic request;

[0053] For each basic request, calling a basic subsequent request associated with the basic request in the request prediction model;

[0054] All basic subsequent requests corresponding to the basic request are combined and summarized as the predicted subsequent request.

[0055] A GIS-based intelligent prediction and management system for urban resources, used to implement the above-mentioned GIS-based intelligent prediction and management method for urban resources, comprising:

[0056] A standardization processing module, the standardization processing module is used to process the data standard format, generate at least one resource data set, and set at least one resource data sub-table under the resource data set;

[0057] A marking module, which is used to mark the resource data sub-tables on the map according to the coordinates to form a GIS resource map. The marking module is also used to mark the resource data sub-tables in the GIS resource map according to the resource occupancy situation;

[0058] A map generation module, wherein the map generation module is used to generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map;

[0059] A resource allocation training module, wherein the resource allocation training module is used to generate a resource allocation model according to a resource request test set training;

[0060] A resource prediction training module, wherein the resource prediction training module is used to train and generate a request prediction model based on a sample resource demand prediction test set;

[0061] The resource allocation module is used to generate a request solution according to the request prediction model and the resource allocation model, and to predict subsequent requests according to the request prediction model and make resource reservations in advance.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] By setting up a resource allocation training module, a resource prediction training module and a resource allocation module, the request demand is decomposed into basic units, and a resource allocation model and a request prediction model are formed according to the basic unit training. When there is actual resource demand, the corresponding solution can be formed according to the basic elements that constitute the actual resource demand, and a prediction plan can be generated according to its basic elements, so as to prepare in the system in advance. When the request is made later, it can be resolved in time, reducing waiting time and improving resolution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic diagram of the process of the intelligent prediction and management method of urban resources based on GIS of the present invention;

[0065] Figure 2 It is a schematic diagram of the data standard formatting process of the present invention;

[0066] Figure 3 A schematic diagram of the process of forming a GIS resource map of the present invention;

[0067] Figure 4A schematic diagram of a process of generating a resource allocation model according to resource request test set training in the present invention;

[0068] Figure 5 A schematic diagram of the training generation request prediction model process of the present invention;

[0069] Figure 6 A schematic diagram of a process of generating a request solution according to a resource allocation model of the present invention;

[0070] Figure 7 This is a schematic diagram of the process of predicting subsequent requests based on a request prediction model of the present invention. DETAILED DESCRIPTION

[0071] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0072] Reference Figure 1-7 As shown, a GIS-based intelligent prediction and management method for urban resources includes:

[0073] Collect resource scenario data, format the data according to the data standard, generate at least one resource data set, set at least one resource data sub-table under the resource data set, generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map;

[0074] Generate map areas on the GIS resource map and correspond the map areas to resource data sets one by one;

[0075] According to the resource occupancy, resource data is divided into tables and occupancy is marked in the GIS resource map;

[0076] If the resource data sub-table is marked as occupied, the resource data sub-table cannot be called;

[0077] If the resource data sub-table is not marked as occupied, the resource data sub-table can be called;

[0078] Obtain at least one sample resource request to form a resource request test set, and train and generate a resource allocation model according to the resource request test set;

[0079] Obtain at least one sample resource request and a subsequent sample resource request, match the sample resource request with the subsequent sample resource request one by one to form a sample resource demand prediction test set, and train and generate a request prediction model based on the sample resource demand prediction test set;

[0080] Collect resource requests, generate request solutions based on the resource allocation model, predict subsequent requests based on the request prediction model, book resources in advance, mark the resource occupancy of the booked resources, and set waiting time for the marked resources;

[0081] If the reserved resource is not called within the waiting time, the resource reservation status is canceled and the resource occupation mark is removed;

[0082] If the reserved resources are called during the waiting time, the resource reservation status will be continued and the resource occupancy mark will be continued.

[0083] The data standard formatting process includes the following steps:

[0084] Aggregate resource scenario data, and divide the resource scenario data into at least one basic resource unit, where the basic resource unit only contains a single resource attribute;

[0085] Mark resource attributes for basic resource units, and make a one-to-one correspondence between basic resource units and resource attribute marks;

[0086] The basic resource units with the same resource attributes are aggregated and arranged to form a resource data table;

[0087] Assign resource attributes to the resource data sub-list, wherein the resource attributes are resource attributes of basic resource units in the resource data sub-list;

[0088] Aggregate basic resource units of the same resource attributes to form a resource data set;

[0089] Data standard formatting processing divides the resources used for resource demand processing into multiple basic units, so that when they are called, they can be called together in the form of a combination of basic units, so that they can form as many combinations as possible in limited basic units to meet as many processing requirements as possible, and at the same time, they can also meet resource requirements more accurately.

[0090] Forming a GIS resource map includes the following steps:

[0091] Establishing a GIS layer, establishing a coordinate system on the GIS layer, and dividing the GIS layer to form at least one map area;

[0092] Match map areas to resource data sets one by one;

[0093] Take the coordinates of the whole points in each map area as grid points, and assign the coordinates of each grid point to the resource data table in the resource data set corresponding to the map area;

[0094] The resource data is divided into tables and marked according to coordinates to the corresponding grid points in the map area;

[0095] GIS resource maps store resource data in tables according to the categories of resource data sets on the map. When calling, they can be quickly called according to the classification, saving calling time.

[0096] Marking the occupancy of resource data sub-tables includes the following steps:

[0097] Resource requests trigger the resource allocation model and generate request solutions;

[0098] According to the requested solution, resources are deployed, GIS resource maps are called, and corresponding resource data sub-tables are retrieved according to the path map area to the grid points within the map area;

[0099] The allocated resource data sub-table is marked as occupied.

[0100] The following steps are involved in training and generating a resource allocation model based on the resource request test set:

[0101] Decompose the resource requests in the resource request test set to obtain a resource request basic unit, which only contains a single resource attribute;

[0102] Big data collects events that occur in the basic unit of resource request. For each resource attribute, the number of events that occur with the resource attribute is counted separately, and the conditional probability of each resource attribute is calculated using the conditional probability formula;

[0103] The resource request basic unit is assigned the resource attribute with the highest conditional probability;

[0104] The resource attribute with the largest conditional probability must be the resource attribute with the strongest correlation with the resource request basic unit, and therefore, it must be regarded as the resource attribute of the resource request basic unit;

[0105] The resource request basic unit is associated with the resource data sub-table with the same resource attribute, and the path of the resource data sub-table in the GIS resource map is recorded as the calling path;

[0106] When calling the resource data sub-table, the calling path can be used to quickly find the corresponding resource data sub-table and resolve the basic unit of resource request;

[0107] The conditional probability formula is as follows:

[0108]

[0109] Among them, P is the conditional probability of each resource attribute, A is the number of events in which the resource attribute occurs, and B is the number of events in which the resource request basic unit occurs.

[0110] Training the request prediction model includes the following steps:

[0111] Obtain a sample resource demand prediction test set, decompose the sample resource request into basic requests, decompose the sample resource subsequent request into basic subsequent requests, then each sample resource request corresponds to a basic request combination set, and each sample resource subsequent request corresponds to a basic subsequent request combination set;

[0112] According to the correspondence between the sample resource request and the sample resource subsequent request, the basic request combination set is matched with the basic subsequent request combination set;

[0113] However, the correspondence between at least one basic request in the basic request combination set and at least one basic subsequent request in the basic subsequent request combination set is unclear, that is, which basic subsequent request in the basic subsequent request combination set each basic request corresponds to;

[0114] Therefore, for any basic request, find the combined set of two basic requests whose intersection element is exactly the basic request;

[0115] Calling two basic subsequent request combination sets corresponding to the two basic request combination sets, making an intersection of the two basic subsequent request combination sets, and then the basic subsequent request in the intersection is the subsequent request corresponding to the basic request;

[0116] The reason is that both basic request combination sets include the basic request, therefore, the two basic subsequent request combination sets corresponding to the two basic request combination sets must include the basic subsequent request corresponding to the basic request, but since the intersection of the two basic request combination sets happens to be the basic request, therefore, the intersection of the two basic subsequent request combination sets corresponding to the two basic request combination sets must be the basic subsequent request corresponding to the basic request;

[0117] The basic request and the corresponding basic subsequent request are associated to obtain a request prediction model, that is, when at least one basic request after decomposition is obtained, the corresponding basic subsequent request can be obtained as a prediction according to the request prediction model.

[0118] Based on the resource provisioning model, generating a request solution consists of the following steps:

[0119] When obtaining an actual resource request, decomposing the resource request into at least one resource request basic unit;

[0120] According to the resource attribute of the resource request basic unit, a resource data sub-table with the same resource attribute is called;

[0121] When calling the resource data sub-table, use the calling path of the resource data sub-table to call the corresponding resource data sub-table in the GIS resource map;

[0122] Summarize all resource data calls into separate tables to get the requested solution.

[0123] According to the request prediction model, predicting subsequent requests includes the following steps:

[0124] For any resource request, decompose the resource request into at least one basic request;

[0125] For each basic request, calling a basic subsequent request associated with the basic request in the request prediction model;

[0126] All basic subsequent requests corresponding to the basic request are combined and summarized as predicted subsequent requests;

[0127] The purpose of predicting subsequent requests is to prepare the data that needs to be allocated in advance and to reserve resources in advance to avoid allocation when subsequent requests appear. This will not only take more time, but also cause the allocated resources to be occupied, resulting in waiting, which prolongs the time to resolve the needs.

[0128] A GIS-based intelligent prediction and management system for urban resources, used to implement the above-mentioned GIS-based intelligent prediction and management method for urban resources, comprising:

[0129] A standardization processing module, the standardization processing module is used to process the data standard format, generate at least one resource data set, and set at least one resource data sub-table under the resource data set;

[0130] A marking module, which is used to mark the resource data sub-tables on the map according to the coordinates to form a GIS resource map. The marking module is also used to mark the resource data sub-tables in the GIS resource map according to the resource occupancy situation;

[0131] A map generation module, wherein the map generation module is used to generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map;

[0132] A resource allocation training module, wherein the resource allocation training module is used to generate a resource allocation model according to a resource request test set training;

[0133] A resource prediction training module, wherein the resource prediction training module is used to train and generate a request prediction model based on a sample resource demand prediction test set;

[0134] The resource allocation module is used to generate a request solution according to the request prediction model and the resource allocation model, and to predict subsequent requests according to the request prediction model and make resource reservations in advance.

[0135] The working process of the above GIS-based urban resource intelligent prediction and management system is as follows:

[0136] Step 1: The standardization processing module is used to format the data standard, generate at least one resource data set, and set at least one resource data sub-table under the resource data set, generate coordinates for the resource data sub-table, the marking module marks the resource data sub-table on the map according to the coordinates, and the map generation module forms a GIS resource map;

[0137] Step 2: obtaining at least one sample resource request to form a resource request test set, and the resource allocation training module generates a resource allocation model according to the resource request test set training;

[0138] Step 3: obtaining at least one sample resource request and a subsequent sample resource request, matching the sample resource request with the subsequent sample resource request one by one to form a sample resource demand prediction test set, and the resource prediction training module trains and generates a request prediction model based on the sample resource demand prediction test set;

[0139] Step 4: The resource allocation module collects resource requests, generates request solutions based on the resource allocation model, predicts subsequent requests based on the request prediction model, makes resource reservations in advance, marks resource occupancy for the reserved resources, and sets waiting time for the marked resources;

[0140] Step 5: During the operation of the resource allocation module, the labeling module labels the resource data in the GIS resource map according to the resource occupancy situation.

[0141] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned GIS-based intelligent prediction and management method for urban resources is executed.

[0142] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0143] To sum up, the advantages of the present invention are: by setting up a resource allocation training module, a resource prediction training module and a resource allocation module, the request demand is decomposed into basic units, and a resource allocation model and a request prediction model are formed according to the basic unit training. When there is actual resource demand, the corresponding solution can be formed according to the basic elements that constitute the actual resource demand, and a prediction plan can be generated according to its basic elements, so as to prepare in the system in advance, and when the request is made subsequently, it can be solved in time, reducing waiting time and improving solution efficiency.

[0144] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A GIS-based intelligent prediction and management method for urban resources, characterized in that: include: Collect resource scenario data, format the data according to the data standard, generate at least one resource data set, set at least one resource data sub-table under the resource data set, generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map; Generate map areas on the GIS resource map and correspond the map areas to resource data sets one by one; According to the resource occupancy, resource data is divided into tables and occupancy is marked in the GIS resource map; If the resource data sub-table is marked as occupied, the resource data sub-table cannot be called; If the resource data sub-table is not marked as occupied, the resource data sub-table can be called; Obtain at least one sample resource request to form a resource request test set, and train and generate a resource allocation model according to the resource request test set; Obtain at least one sample resource request and a subsequent sample resource request, match the sample resource request with the subsequent sample resource request one by one to form a sample resource demand prediction test set, and train and generate a request prediction model based on the sample resource demand prediction test set; Collect resource requests, generate request solutions based on the resource allocation model, predict subsequent requests based on the request prediction model, book resources in advance, mark the resource occupancy of the booked resources, and set waiting time for the marked resources; If the reserved resource is not called within the waiting time, the resource reservation status is canceled and the resource occupation mark is removed; If the reserved resource is called during the waiting time, the resource reservation status will be continued and the resource occupancy mark will be continued; The training generation request prediction model comprises the following steps: Obtain a sample resource demand prediction test set, decompose the sample resource request into basic requests, decompose the sample resource subsequent request into basic subsequent requests, then each sample resource request corresponds to a basic request combination set, and each sample resource subsequent request corresponds to a basic subsequent request combination set; According to the correspondence between the sample resource request and the sample resource subsequent request, the basic request combination set is matched with the basic subsequent request combination set; For any basic request, find two basic request combinations whose intersection element is exactly the basic request; Calling two basic subsequent request combination sets corresponding to the two basic request combination sets, and making an intersection of the two basic subsequent request combination sets, where the basic subsequent request in the intersection is the subsequent request corresponding to the basic request; Associating the basic request with the corresponding basic subsequent request to obtain a request prediction model, that is, when at least one basic request after decomposition is obtained, the corresponding basic subsequent request can be obtained as a prediction according to the request prediction model; The method of generating a resource allocation model based on the resource request test set training comprises the following steps: Decompose the resource requests in the resource request test set to obtain a resource request basic unit, which only contains a single resource attribute; The resource request basic unit is associated with the resource data sub-table with the same resource attribute, and the path of the resource data sub-table in the GIS resource map is recorded as the calling path.

2. The GIS-based intelligent prediction and management method for urban resources according to claim 1 is characterized in that: The data standard formatting process comprises the following steps: Aggregate resource scenario data, and divide the resource scenario data into at least one basic resource unit, where the basic resource unit only contains a single resource attribute; Mark resource attributes for basic resource units, and make a one-to-one correspondence between basic resource units and resource attribute marks; The basic resource units with the same resource attributes are aggregated and arranged to form a resource data table; Resource attributes are allocated to the resource data sub-list, where the resource attributes are resource attributes of basic resource units in the resource data sub-list.

3. The GIS-based urban resource intelligent prediction and management method according to claim 2 is characterized in that: The formation of the GIS resource map comprises the following steps; Establishing a GIS layer, establishing a coordinate system on the GIS layer, and dividing the GIS layer to form at least one map area; Match map areas to resource data sets one by one; Take the coordinates of the whole points in each map area as grid points, and assign the coordinates of each grid point to the resource data table in the resource data set corresponding to the map area; The resource data is divided into tables and marked according to the coordinates to the corresponding grid points in the map area.

4. The GIS-based urban resource intelligent prediction and management method according to claim 3 is characterized in that: The occupancy marking of the resource data sub-table comprises the following steps: Resource requests trigger the resource allocation model and generate request solutions; According to the requested solution, resources are allocated, GIS resource maps are called, and corresponding resource data sub-tables are retrieved; The allocated resource data sub-table is marked as occupied.

5. The GIS-based intelligent prediction and management method for urban resources according to claim 4 is characterized in that: Generating a request solution according to the resource allocation model includes the following steps: When obtaining an actual resource request, decomposing the resource request into at least one resource request basic unit; According to the resource attribute of the resource request basic unit, a resource data sub-table with the same resource attribute is called; When calling the resource data sub-table, use the calling path of the resource data sub-table to call the corresponding resource data sub-table in the GIS resource map; Summarize all resource data calls into separate tables to get the requested solution.

6. The GIS-based intelligent prediction and management method for urban resources according to claim 5 is characterized in that: Predicting subsequent requests according to the request prediction model includes the following steps: For any resource request, decompose the resource request into at least one basic request; For each basic request, calling a basic subsequent request associated with the basic request in the request prediction model; All basic subsequent requests corresponding to the basic request are combined and summarized as the predicted subsequent request.

7. A GIS-based intelligent prediction and management system for urban resources, used to implement the GIS-based intelligent prediction and management method for urban resources as claimed in any one of claims 1 to 6, characterized in that: include: A standardization processing module, the standardization processing module is used to process the data standard format, generate at least one resource data set, and set at least one resource data sub-table under the resource data set; A marking module, which is used to mark the resource data sub-tables on the map according to the coordinates to form a GIS resource map. The marking module is also used to mark the resource data sub-tables in the GIS resource map according to the resource occupancy situation; A map generation module, wherein the map generation module is used to generate coordinates for the resource data sub-table, mark the resource data sub-table on the map according to the coordinates, and form a GIS resource map; A resource allocation training module, wherein the resource allocation training module is used to generate a resource allocation model according to a resource request test set training; A resource prediction training module, wherein the resource prediction training module is used to train and generate a request prediction model based on a sample resource demand prediction test set; The resource allocation module is used to generate a request solution according to the request prediction model and the resource allocation model, and to predict subsequent requests according to the request prediction model and make resource reservations in advance.

Images