Land division optimization method and system of network platform, terminal and storage medium

Abstract

The invention relates to a land division optimization method and system for a network platform, a terminal and a storage medium, and relates to the technical field of big data, and the method comprises the steps: carrying out the statistics of land information of a target block in response to the input operation of query information; according to the land information and the query information of the target block, extracting a division basis of the target block; performing feature extraction operation on the land information to obtain land features; according to the division basis, performing weighting operation on the land features to obtain input features; in response to the parameter input operation, obtaining model parameters of the division optimization model; calling a division optimization model, and optimizing the division range of the target block according to the input features to obtain a division optimization result of the target block; and performing visualization processing on the division optimization result to obtain a land division chart, and displaying the land division chart. The method and the device have the effects of improving the land division quality and providing convenient land division result query.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a land division optimization method, system, terminal and storage medium for a network platform. Background Art

[0002] With the increase of urban population and the continuous expansion of urban scale, more and more areas need to be controlled, and the contradiction between urban planning and urban development is becoming more and more obvious. This new urban development goal has undoubtedly brought new challenges to domestic urban planning and planning management. How to improve the quality of land division and the rationality of layout under the premise of the continuous expansion of urban planning areas and the increasing urban population has become an important issue facing urban development.

[0003] The relevant technology usually adopts a simulation algorithm, which first solves the quantitative structure of urban land use under different scenarios, and then uses the model to simulate land use transformation under the constraints of the quantitative structure, and finally obtains the optimal layout of land division under the corresponding scenario.

[0004] Regarding the above-mentioned related technologies, the inventors believe that the simulation algorithm cannot solve the problem of cross-level constraint transmission, that is, the related technologies lack information fusion at different levels, resulting in low quality of land division. Summary of the invention

[0005] In order to improve the quality of land division and provide convenient land division result query, the present application provides a land division optimization method, system, terminal and storage medium on a network platform.

[0006] In the first aspect, the present application provides a land division optimization method for a network platform, which adopts the following technical solution: A land division optimization method for a network platform, comprising: In response to the input operation of the query information, the land information of the target block is counted, wherein the land information includes land division rule restrictions, land division strategy and the location of the target block; Extracting the division basis of the target block according to the land information of the target block and the query information; Performing a feature extraction operation on the land information to obtain land features; According to the division basis, weighting operation is performed on the land characteristics to obtain input characteristics; In response to the parameter input operation, obtaining model parameters of the partition optimization model, and inputting the model parameters into the partition optimization model; Calling the partition optimization model, optimizing the partition range of the target block according to the input features, and obtaining a partition optimization result of the target block; The division optimization result is visualized to obtain a land division chart, and the land division chart is displayed.

[0007] By adopting the above technical solution, the division range of the target block is optimized according to the query information input by the relevant personnel, and the division optimization result of the target block is obtained. Not only can the land division be updated according to the specified requirements to improve the quality of the land division, but also convenient land division result query is provided to simplify the operation.

[0008] Optionally, an optimization step is performed, the optimization step comprising: calling the partition optimization model, optimizing the i-th partition range of the target block according to the land characteristics, and obtaining the i+1-th partition range of the target block, where i is a positive integer and the initial value of i is 1; Executing a comparison step, the comparison step comprising: comparing the difference between the i-th division range and the i+1-th division range to obtain a change in the i-th division range, and storing the change data corresponding to the i-th division range in a local memory; Executing a display step, the display step comprising: displaying the change of the i-th division range in an animation form; Update i to i+1, repeat the optimization step, the comparison step and the display step until the land division rule restrictions are met, and take the i+1th division range as the division optimization result.

[0009] By adopting the above technical solution, the division range of the target block can be continuously updated through the division optimization model, so that the quality of the division range is continuously improved. Moreover, the relevant personnel can intuitively observe the continuous optimization of the division range, so that the relevant personnel can intuitively understand the optimization direction and optimization range of land division.

[0010] Optionally, a spatial clustering operation is performed on the target block according to the land information to obtain a spatial pattern distribution of the target block, wherein the spatial pattern distribution represents the spatial distribution of land uses within the target block; Obtaining the development intensity of each location within the target block; Dividing the target block according to the development intensity to obtain the development intensity distribution of the target block; The division optimization result is updated with reference to the spatial pattern distribution and the development intensity distribution.

[0011] By adopting the above technical solution, the division optimization results are updated according to the spatial pattern distribution and the development intensity distribution, so that the division optimization results integrate multiple factors and improve the credibility of the division optimization results.

[0012] Optionally, obtaining building information in a sub-block of the target block, the building information including the number of buildings and building types; According to the building information, the current development direction of the sub-block is obtained; Extracting the target current development direction of the sub-block and the nearby current development directions of the nearby blocks of the sub-block, and obtaining the industrial development information of the sub-block; Calling a development prediction model to perform development prediction according to the industrial development information, the current development direction of the target and the current development direction of nearby areas, and obtaining the development potential of the sub-block; The location information and development potential of the sub-block are integrated to obtain the land information of the sub-block.

[0013] By adopting the above technical solution, the land information of the sub-block is obtained according to the location information and development potential of the sub-block, so that the land information can represent the main information of the target block, which is conducive to improving the accuracy of subsequent land division.

[0014] Optionally, a conditional function is set according to the global condition of the target block to obtain a global constraint; Obtaining a neighborhood constraint according to a relationship between the target block and blocks near the target block; According to the land information of the target block, natural factors, traffic factors and economic factors are classified and regressed to obtain local constraints; Integrating the global constraint, the neighborhood constraint and the local constraint to obtain a constraint factor; Obtaining a loss function based on land information of the target block; The partition optimization model is trained using the constraint factor and the loss function.

[0015] By adopting the above technical solution, the partition optimization model is trained using constraint factors and loss functions to ensure the quality of the partition optimization model. Moreover, the setting of constraint factors and loss functions can improve the generalization ability, stability and efficiency of the partition optimization model.

[0016] Optionally, in response to receiving an input operation of a residential situation of a resident in an edge area of ​​a sub-block in the target block, obtaining the residential situation of the resident, wherein the residential situation of the resident includes a residential location, a number of residents, and occupations of the residents; According to the residential conditions of the residents, statistics on the residents' travel conditions; Performing feature extraction operations on the residential conditions of the residents and the travel conditions of the residents to obtain residential characteristics of the residents in the marginal area; The partition optimization model is called to update the partition range of the sub-block according to the residential characteristics of the residents.

[0017] By adopting the above technical solution, the division range of the target block is updated according to the living conditions of residents in the marginal area, so that the division range is more in line with the interests of the residents and the rationality of the division optimization results is improved.

[0018] Optionally, collecting public facility information of the edge area, the public facility information including the location, type and quantity of the public facilities; Obtaining the flow tendency of residents in the marginal area according to the public facilities information; Weighting the resident mobility tendency according to the land information to obtain the resident mobility weight tendency; The division relationship between the edge area and the target block is updated according to the resident flow weight tendency.

[0019] By adopting the above technical solution, the division relationship between the marginal area and the target block is updated according to the weight tendency of residents' mobility, making the aforementioned division relationship more accurate and effectively meeting the needs of residents in the marginal area.

[0020] In the second aspect, the present application provides a land division optimization system on a network platform, which adopts the following technical solutions: A land division optimization system on a network platform, comprising: The acquisition module is used to obtain query information, land information, partition optimization model, spatial clustering operation, development intensity, building information, development prediction model, global conditions, loss function, and residents' living conditions; A memory, used to store a program of any of the above-mentioned methods for optimizing land division on a network platform; The program in the processor and the memory can be loaded and executed by the processor to implement any of the above-mentioned land division optimization methods for the network platform.

[0021] By adopting the above technical solution, the division range of the target block is optimized according to the query information input by the relevant personnel, and the division optimization result of the target block is obtained. Not only can the land division be updated according to the specified requirements to improve the quality of the land division, but also convenient land division result query is provided to simplify the operation.

[0022] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution: An intelligent terminal comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and execute any one of the above-mentioned methods.

[0023] In a fourth aspect, the present application provides a computer storage medium capable of storing corresponding programs, which is convenient for improving the quality of land division and providing convenient query of land division results, and adopts the following technical solutions: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the land division optimization method of any of the above-mentioned network platforms.

[0024] In summary, the present application includes at least one of the following beneficial technical effects: According to the query information input by relevant personnel, the division range of the target block is optimized to obtain the optimized division result of the target block. Not only can the land division be updated according to the specified requirements to improve the quality of land division, but also convenient land division result query is provided to simplify the operation; The division range of the target block can be continuously updated through the division optimization model, so that the quality of the division range is continuously improved. Moreover, it allows relevant personnel to intuitively observe the continuous optimization of the division range, so that relevant personnel can intuitively understand the optimization direction and optimization range of land division; The division optimization results are updated according to the spatial pattern distribution and development intensity distribution, so that the division optimization results integrate multiple factors and improve the credibility of the division optimization results. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of a land division optimization method of a network platform provided in an embodiment of the present application.

[0026] Figure 2 It is a flow chart of an operation method of a partitioning optimization model provided in an embodiment of the present application.

[0027] Figure 3 It is a flowchart of a method for updating partition optimization results provided in an embodiment of the present application.

[0028] Figure 4 It is a flow chart of a method for obtaining land information provided in an embodiment of the present application.

[0029] Figure 5 It is a flowchart of a training method for a partition optimization model provided in an embodiment of the present application.

[0030] Figure 6 It is a flow chart of a first method for optimizing the division of edge areas provided in an embodiment of the present application.

[0031] Figure 7 It is a flow chart of a second method for optimizing the division of edge areas provided in an embodiment of the present application.

[0032] Figure 8 It is a structural diagram of a land division optimization system of a network platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figures 1 to 8 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] The present application embodiment discloses a land division optimization method for a network platform. Figure 1 , the method comprising: Step 101: In response to an input operation of query information, statistics are collected on land information of a target block, where the land information includes land division rule restrictions, land division strategy, and the location of the target block.

[0035] The query information is used to uniquely identify the target block. Optionally, the query information includes at least one of the location information, area, name, and number of the target block. Exemplarily, the candidate blocks are displayed on a display screen. In response to a selection operation of the target block in the candidate blocks, the target block is obtained.

[0036] The land information can be input by the user or preset.

[0037] The land division rule restrictions refer to the laws, regulations, policies, technical specifications and model iteration strategies set in the process of land division. Exemplarily, the land division rules include at least one of land use, land area and shape, maximum number of people that the land can carry, and total number of people planned for the land.

[0038] The land division strategy refers to the standard or criterion for dividing land. Exemplarily, the land division strategy includes at least one of a natural development strategy, an ecological protection strategy, an economic development strategy, a resident service strategy, and an ecological protection and economic development coordination strategy.

[0039] In actual scenarios, there are usually multiple different sub-blocks within the target block. For example, sub-block A in the target block is commercial land, and sub-block B is agricultural land. Based on the land features of different sub-blocks collected by hand, the land features of the sub-blocks are integrated to obtain the land information of the target block.

[0040] Step 102: Extract the basis for dividing the target block based on the land information and query information of the target block.

[0041] The division basis refers to the criteria and restrictions for dividing the target block. Optionally, the division basis includes but is not limited to at least one of land division rules, land division strategies, the shape and location of the target block, the area of ​​the target block, and the maximum number of people that the target block can carry. For example, the division basis includes dividing the target block according to the economic development strategy and the shape of the target block.

[0042] In some embodiments, the division basis can be expressed in vector form. For example, the division basis is [3, 45, 6], where the first bit of the vector represents the land division strategy, the second bit represents the area of ​​the target block, and the third bit represents the land use. Then, "3" in the vector represents that the land division strategy adopts the economic development strategy, "45" represents that the area of ​​the target block is 450,000 square meters, and "6" represents that the target block is for agricultural planting.

[0043] Furthermore, when there are multiple different sub-blocks within the target block, the basis for dividing the sub-blocks is extracted according to the land information and query information of the sub-blocks, and the basis for dividing the sub-blocks is integrated to obtain the basis for dividing the target block.

[0044] Step 103: Perform feature extraction operation on the land information to obtain land features.

[0045] The feature extraction operation is used to extract features that reflect land information. Land features can reflect the content of land information.

[0046] Exemplarily, a feature extraction model is called to perform feature extraction operations on land information to obtain land features. The feature extraction model may be any one of a convolutional neural network, a deep learning model, and an encoder.

[0047] Step 104: According to the division basis, weighting operation is performed on the land features to obtain input features.

[0048] Furthermore, the basis for division includes a land division strategy. According to the land division strategy of the target block, a weight value corresponding to the land division strategy is determined from a preset mapping table. According to the aforementioned weight value, the land features are weighted to obtain input features. Since different land division strategies have different demands for land, the importance of different sub-features in the input features will also be different. For example, when adopting an economic development strategy, more emphasis will be placed on features such as industrial output value and benchmark land price in land features; and when adopting a resident service strategy, more emphasis will be placed on road accessibility, the number and types of public facilities in land features.

[0049] Furthermore, the land division strategy is related to the land use. For example, when the land use is commercial, the land division strategy is the corresponding economic development strategy.

[0050] In some other embodiments, in response to a weight value input operation, an input weight value is obtained, and a weighting operation is performed on the land features according to the input weight to obtain the input features.

[0051] Step 105: In response to the parameter input operation, the model parameters of the partition optimization model are obtained, and the model parameters are input into the partition optimization model.

[0052] In some other embodiments, if no parameter input operation is received, preset model parameters are used and input into the partition optimization model.

[0053] Step 106: calling the partition optimization model, optimizing the partition range of the target block according to the input features, and obtaining the partition optimization result of the target block.

[0054] Optionally, the partitioning optimization model is implemented using a model based on CA (Cellular Automat).

[0055] The division optimization result includes at least one of the boundaries, development potential, use, and area of ​​different blocks within the target block.

[0056] Step 107: Visualize the division optimization result to obtain a land division chart, and display the land division chart.

[0057] The land division chart is used to visually show the difference between before and after land optimization. The land division chart includes table form and statistical chart form.

[0058] In some embodiments, when there are multiple different sub-blocks within the target block, a map of the target block is displayed on a display screen, and each sub-block is displayed on the map. The sub-division optimization results corresponding to each sub-block are marked on the map. Specifically, the land use, development potential, etc. of the sub-block are marked on the sub-block.

[0059] In some embodiments, a land division chart is generated based on the land area in the land optimization result and the original land area of ​​the target block. Specifically, a line chart is generated with time as the horizontal axis and the land area as the vertical axis to intuitively show how the land area will change after the land division optimization.

[0060] In some embodiments, when there are multiple different sub-blocks within the target block, a land division chart is generated according to the change in the area ratio of the sub-blocks. Specifically, a fan chart is used to display the area ratio of different land uses. Specifically, a bar chart is used to display the change value of the area of ​​each type of land after the land division is optimized.

[0061] In an illustrative example, this embodiment can be applied to a land planning scenario. For example, for the development of commercial land in a target block, the user can use the economic development strategy to optimize each sub-block in the target block, thereby obtaining the optimized area and boundaries of different sub-blocks and showing the economic development potential of different sub-blocks. This helps relevant personnel to clearly understand which blocks should be developed and which blocks have high development potential.

[0062] By adopting the above technical solution, the division range of the target block is optimized according to the query information input by the relevant personnel, and the division optimization result of the target block is obtained. Not only can the land division be updated according to the specified requirements to improve the quality of the land division, but also convenient land division result query is provided to simplify the operation.

[0063] The present application embodiment discloses a method for operating a partition optimization model. Figure 2 , the method comprising: Step 201: Execute the optimization step, which includes: calling the partition optimization model, optimizing the i-th partition range of the target block according to the land characteristics, and obtaining the i+1-th partition range of the target block, where i is a positive integer and the initial value of i is 1.

[0064] In this embodiment, the partition optimization model will iterate and repeat the partition range of the target block continuously to ensure that a highly accurate partition optimization result can be obtained.

[0065] Step 202: Execute a comparison step, which includes: comparing the difference between the ith division range and the (i+1)th division range, obtaining the change of the ith division range, and storing the change data corresponding to the ith division range in the local memory.

[0066] The change data includes the area change and boundary line change between the ith division range and the i+1th division range.

[0067] Step 203: Execute a display step, the display step comprising: displaying the change of the i-th division range in an animation form.

[0068] Exemplarily, the i-th division range and the i+1-th division range are displayed on the map, and the i-th division range and the i+1-th division range are marked with different colors.

[0069] Exemplarily, with i as the horizontal axis and the area value corresponding to the i-th division range as the vertical axis, a line graph is generated to show the changes in the division range.

[0070] Step 204: update i to i+1, repeat the optimization step, comparison step and display step until the land division rule restrictions are met, and take the i+1th division range as the division optimization result.

[0071] The land division rule restriction includes a model iteration strategy. Optionally, the model iteration strategy includes ending when the update ratio of the target block reaches a threshold and ending when the number of iterations reaches an upper limit.

[0072] In some other embodiments, in response to receiving a continue iteration operation, i is updated to i + 1. For example, a continue iteration button is displayed on a display screen, and when the continue iteration button receives a trigger operation, i is updated to i + 1, thereby implementing the iteration operation.

[0073] By adopting the above technical solution, the division range of the target block can be continuously updated through the division optimization model, so that the quality of the division range is continuously improved. Moreover, the relevant personnel can intuitively observe the continuous optimization of the division range, so that the relevant personnel can intuitively understand the optimization direction and optimization range of land division.

[0074] In the following embodiments, after obtaining the partition optimization result, in order to improve the credibility and accuracy of the partition optimization result, it is also necessary to use other parameters as references to update the partition optimization result. Therefore, the embodiment of the present application discloses a method for updating the partition optimization result. Figure 3 , the method comprising: Step 301: Perform spatial clustering operation on the target block according to the land information to obtain the spatial pattern distribution of the target block. The spatial pattern distribution represents the spatial distribution of land use in the target block.

[0075] Exemplarily, the land use of each sub-block in the target block is determined. For the land use of the target sub-block, a neighborhood size is set. The clustering range of the target sub-block is set according to the neighborhood size, and the shortest distance from the boundary of the clustering range to the target sub-block is less than the neighborhood size. It is determined whether the land use of other sub-blocks in the clustering range is consistent with the target block. If so, when the area ratio of other sub-blocks falling into the clustering range is greater than the preset area ratio, the other sub-blocks are incorporated into the cluster cluster of the target sub-block.

[0076] Step 302: Obtain the development intensity of each location in the target block.

[0077] The development intensity is the intensity of development activities per unit area. Optionally, the development intensity includes at least one of building density, population density, unit investment capital, traffic rate, and volume ratio.

[0078] Step 303: Divide the target block according to the development intensity to obtain the development intensity distribution of the target block.

[0079] Exemplarily, several development intensity intervals are set, each of which has the same length and is connected. The development intensity of each location in the target block is matched with the aforementioned several development intensity intervals to obtain the corresponding development intensity intervals of each location in the target block. A spatial clustering operation is performed on the land in the target block according to the development intensity interval to obtain the development intensity distribution of the target block.

[0080] Step 304: Update the division optimization result with reference to the spatial pattern distribution and the development intensity distribution.

[0081] Exemplarily, a first partition difference between the spatial pattern distribution and the partition optimization result is obtained. A second partition difference between the development intensity distribution and the partition optimization result is obtained. The spatial partition optimization model is called to perform data processing on the first partition difference to obtain a first optimization result. The development intensity partition optimization model is called to perform data processing on the second partition difference to obtain a second optimization result. The first optimization result and the second optimization result are integrated to obtain an updated partition optimization result.

[0082] By adopting the above technical solution, the division optimization results are updated according to the spatial pattern distribution and the development intensity distribution, so that the division optimization results integrate multiple factors and improve the credibility of the division optimization results.

[0083] In the following embodiments, in one implementation, the land information of the sub-block includes location information and development potential. For the development potential, it is necessary to process it in combination with the actual situation of the sub-block to ensure the accuracy of the development potential. Therefore, the embodiment of the present application discloses a method for obtaining land information. Figure 4 , the method comprising: Step 401: Acquire building information in a sub-block of a target block, where the building information includes the number of buildings and building types.

[0084] Optionally, building types include commercial buildings, agricultural buildings, residential buildings, public buildings, transportation buildings, other buildings, and no buildings.

[0085] Step 402: According to the building information, the current development direction of the sub-block is obtained.

[0086] Exemplarily, according to the number of buildings, the target building type with the largest number in the sub-block is determined, and according to the development direction corresponding to the target building type, the current development direction is obtained.

[0087] Exemplarily, according to the building information, the quantity change of the building types in the sub-block is obtained. The rising building types showing an upward trend in the quantity change are selected. The target rising building type with the largest rising rate is determined among the rising building types. The development direction corresponding to the rising building type is set as the current development direction.

[0088] In some other embodiments, the current development direction of the sub-block may be obtained without using the building information, for example, by obtaining the current development direction through the land use of the sub-block.

[0089] Step 403: extract the target current development direction of the sub-block and the nearby current development directions of the nearby blocks of the sub-block, and obtain the industrial development information of the sub-block.

[0090] A neighboring block refers to a block that has the same boundary as a sub-block. A neighboring block is one of the sub-blocks of the target block.

[0091] Industrial development information refers to the structure, trend, dynamics and various factors and data related to a certain industry or sector in the sub-block. Optionally, industrial development information includes at least one of industry type, industrial development status and total industry value.

[0092] Step 404: Call the development prediction model, perform development prediction according to the industry development information, the current development direction of the target and the current development direction of the vicinity, and obtain the development potential of the sub-block.

[0093] Optionally, feature extraction is performed on the industrial development information, the current development direction of the target, and the current development direction of the nearby areas to obtain a development feature matrix. The development prediction model is called to perform development prediction on the development feature matrix to obtain the development potential of the sub-block.

[0094] Step 405: Integrate the location information and development potential of the sub-block to obtain the land information of the sub-block.

[0095] Exemplarily, the location information and development potential of the sub-block are combined to obtain the land information of the sub-block.

[0096] By adopting the above technical solution, the land information of the target block is obtained according to the location information and development potential of the sub-block, so that the land information can represent the main information of the target block, which is conducive to improving the accuracy of subsequent land division.

[0097] The present application embodiment discloses a training method for a partition optimization model. Figure 5 , the method comprising: Step 501: Set a condition function according to the global condition of the target block to obtain a global constraint.

[0098] In this step, a macro-level analysis of the target block is required, wherein the global conditions include but are not limited to at least one of environmental regulations within the target block, restrictions on the total amount of land, total population capacity, regional development goals, and the total carrying capacity of infrastructure.

[0099] Based on these global conditions, appropriate conditional functions are set to quantify these restrictions. For example, if a certain area has fixed ecological protection areas, the conditional function may restrict land use in the area to ensure that the planning does not exceed the carrying capacity or legal constraints of these areas. These global constraints are crucial to ensure the feasibility of the planning scheme.

[0100] Step 502: Obtain a neighborhood constraint based on the association between the target block and the blocks near the target block.

[0101] The target block and nearby blocks will influence each other, and the neighborhood constraint describes the degree of influence between the aforementioned target block and nearby blocks.

[0102] In some embodiments, the economic correlation between the target block and the nearby blocks is calculated, and the economic correlation is used as a domain constraint. For example, the circulation trade volume between the target block and the nearby blocks, as well as the first trade volume of the target block and the second trade volume of the nearby blocks are calculated, and the sum of the first trade volume and the second trade volume is calculated to obtain the total trade volume. The ratio of the circulation trade volume to the total trade volume is calculated to obtain the economic correlation.

[0103] Step 503: Based on the land information of the target block, classify and regress the natural factors, traffic factors and economic factors to obtain local constraints.

[0104] Natural factors include natural conditions such as topography, climate, vegetation, and water sources. For example, some areas may be prone to waterlogging due to low-lying terrain, or they may need to avoid overdevelopment due to special ecological environments.

[0105] Traffic factors refer to the status of the transportation network, such as the carrying capacity of roads, traffic flow, distribution of public transportation facilities, etc. Traffic factors will affect the accessibility of land and thus the development potential of the block.

[0106] Economic factors include the market value of the land, the surrounding industrial layout, the economic development level of the region, etc. Different economic factors will affect the land use of the target block, such as industrial land, commercial land or residential land.

[0107] Step 504: Integrate the global constraint, the neighborhood constraint, and the local constraint to obtain a constraint factor.

[0108] Exemplarily, the global constraint, the domain constraint and the local constraint are put into a matrix of a preset size to obtain the constraint factor, wherein if the length requirement of the aforementioned matrix is ​​not met, zero padding is performed at the end.

[0109] Step 505: Obtain a loss function based on the land information of the target block.

[0110] Furthermore, the loss function is retrieved according to the land division strategy of the target block, wherein the corresponding relationship between the land division strategy and the loss function is preset.

[0111] Step 506: Use the constraint factors and loss function to train the partition optimization model.

[0112] Exemplarily, the parameters in the partition optimization model are optimized through an error back propagation algorithm to achieve training of the partition optimization model.

[0113] By adopting the above technical solution, the partition optimization model is trained using constraint factors and loss functions to ensure the quality of the partition optimization model. Moreover, the setting of constraint factors and loss functions can improve the generalization ability, stability and efficiency of the partition optimization model.

[0114] In the following embodiments, for the edge area in the sub-block, the factor of residents needs to be further considered. Therefore, the embodiment of the present application discloses a method for optimizing the division of the edge area. Figure 6 , the method comprising: Step 601: In response to receiving an input operation of the living conditions of residents in the edge area of ​​a sub-block in a target block, the living conditions of the residents are obtained, where the living conditions of the residents include the living location, the number of residents and the occupations of the residents.

[0115] The edge region refers to the region inside the sub-block where the shortest distance to the ion-block boundary is less than the distance threshold.

[0116] In some other embodiments, the resident living conditions are obtained by retrieving server data.

[0117] Step 602: Count residents' travel situations based on their living conditions.

[0118] Residents’ travel conditions include at least one of travel routes, travel frequency, travel purpose, travel time, travel distance, and travel mode.

[0119] For example, the resident's work location is generated according to the resident's occupation. A first candidate moving route between the residential location and the resident's work location and a first travel mode corresponding to the first candidate moving route are counted. The first candidate moving route and the first travel mode are recorded in the resident's travel situation.

[0120] Exemplarily, public service facilities whose distance from the residential location is less than a preset distance threshold are counted. Second candidate movement routes between the residential location and the resident's work location and second travel modes corresponding to the second candidate movement routes are counted. The second candidate movement routes and the second travel modes are recorded in the resident's travel situation.

[0121] Step 603: Perform feature extraction operations on the residents’ living conditions and residents’ travel conditions to obtain the residents’ living characteristics in the edge area.

[0122] In some embodiments, a feature extraction operation is performed on the resident's living conditions to obtain a first resident's living characteristic. A feature extraction operation is performed on the resident's travel conditions to obtain a second resident's living characteristic. The first resident's living characteristic and the second resident's living characteristic are concatenated to obtain the resident's living characteristic of the marginal area.

[0123] Step 604: Call the partition optimization model to update the sub-block division range according to the residential characteristics of the residents.

[0124] The working process and related contents of the partition optimization model can be referred to step 106 or Figure 2 The embodiment shown.

[0125] By adopting the above technical solution, the division range of the target block is updated according to the living conditions of residents in the marginal area, so that the division range is more in line with the interests of the residents and the rationality of the division optimization results is improved.

[0126] In the following embodiments, the relationship between the edge area and the target block can be updated and adjusted according to the mobility of residents to determine whether the edge area should be divided into sub-blocks. Therefore, the embodiment of the present application discloses a second method for optimizing the division of the edge area. Figure 7 , the method comprising: Step 701: Collect public facility information in the edge area, where the public facility information includes the location, type and quantity of the public facilities.

[0127] Exemplarily, public service facilities whose distance from the residential location is less than a preset distance threshold are counted. The locations, types and quantities of the aforementioned public service facilities are counted to obtain public facility information.

[0128] Step 702: Obtain the flow tendency of residents in the edge area based on the public facility information.

[0129] Optionally, a flow tendency model is constructed based on the types and number of public facilities. The flow tendency model is used to simulate the attractiveness of different types of public facilities to resident flows. For example, hospitals and schools usually attract more flows, while sports facilities and commercial facilities may present different proportions of attractiveness based on residents' consumption and leisure needs. Furthermore, GIS technology is used to analyze the relationship between public facilities and surrounding population density to identify flow hotspots. For example, if there are multiple schools and hospitals in a certain area, it may attract more resident flows.

[0130] For example, based on the density of transportation networks, public facilities and the living needs of residents, the flow trend of residents in the marginal area is predicted to obtain the flow tendency of residents.

[0131] Step 703: Weight the resident mobility tendency according to the land information to obtain the resident mobility weight tendency.

[0132] Different land uses will have different effects on residents' mobility tendency. For example, residential areas usually have higher resident mobility, but commercial areas may attract longer stays. Therefore, obtain the land use in the edge area. Combined with the transportation network information of the edge area, evaluate the traffic accessibility of each area. According to the land use type and traffic accessibility, assign a weight value to each flow tendency area. According to the weight value, get the weighted tendency of residents' mobility.

[0133] Step 704: Update the division relationship between the edge area and the target block according to the residents' mobility weight tendency.

[0134] For example, if the weight of resident mobility tends to be directed from the edge area to the target block, the edge area is kept in the target block. If the weight of resident mobility tends to be directed from the edge area to other blocks, the edge area is divided into other blocks.

[0135] By adopting the above technical solution, the division relationship between the marginal area and the target block is updated according to the weight tendency of residents' mobility, making the aforementioned division relationship more accurate and effectively meeting the needs of residents in the marginal area.

[0136] Based on the same inventive concept, the present application embodiment provides a land division optimization system on a network platform, please refer to Figure 8 , the system comprises: The acquisition module 801 is used to obtain query information, land information, partition optimization model, spatial clustering operation, development intensity, building information, development prediction model, global conditions, loss function, and resident living conditions; Memory 802, used to store a program of any of the above-mentioned methods for optimizing land division on a network platform; Processor 803, the program in the memory can be loaded and executed by the processor to implement any of the above-mentioned land division optimization methods for the network platform.

[0137] By adopting the above technical solution, the division range of the target block is optimized according to the query information input by the relevant personnel, and the division optimization result of the target block is obtained. Not only can the land division be updated according to the specified requirements to improve the quality of the land division, but also convenient land division result query is provided to simplify the operation.

[0138] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0139] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a land division optimization method for a network platform.

[0140] Computer storage media include, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0141] Based on the same inventive concept, an embodiment of the present application provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a land division optimization method of a network platform.

[0142] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0143] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A land division optimization method for a network platform, characterized in that: The method comprises: In response to the input operation of the query information, the land information of the target block is counted, wherein the land information includes land division rule restrictions, land division strategy and the location of the target block; Extracting the division basis of the target block according to the land information of the target block and the query information; Performing a feature extraction operation on the land information to obtain land features; According to the division basis, weighting operation is performed on the land characteristics to obtain input characteristics; In response to the parameter input operation, obtaining model parameters of the partition optimization model, and inputting the model parameters into the partition optimization model; Calling the partition optimization model, optimizing the partition range of the target block according to the input features, and obtaining a partition optimization result of the target block; The division optimization result is visualized to obtain a land division chart, and the land division chart is displayed.

2. The land division optimization method of the network platform according to claim 1 is characterized in that: The calling of the partition optimization model to optimize the partition range of the target block according to the land characteristics to obtain the partition optimization result of the target block includes: Executing an optimization step, the optimization step comprising: calling the partition optimization model, optimizing the i-th partition range of the target block according to the land characteristics, and obtaining the i+1-th partition range of the target block, where i is a positive integer and the initial value of i is 1; Executing a comparison step, the comparison step comprising: comparing the difference between the i-th division range and the i+1-th division range to obtain a change in the i-th division range, and storing the change data corresponding to the i-th division range in a local memory; Executing a display step, the display step comprising: displaying the change of the i-th division range in an animation form; Update i to i+1, repeat the optimization step, the comparison step and the display step until the land division rule restrictions are met, and take the i+1th division range as the division optimization result.

3. The land division optimization method of the network platform according to claim 2 is characterized in that: The method further comprises: According to the land information, a spatial clustering operation is performed on the target block to obtain a spatial pattern distribution of the target block, wherein the spatial pattern distribution represents the spatial distribution of land use in the target block; Obtaining the development intensity of each location within the target block; Dividing the target block according to the development intensity to obtain the development intensity distribution of the target block; The division optimization result is updated with reference to the spatial pattern distribution and the development intensity distribution.

4. The land division optimization method of the network platform according to claim 2 is characterized in that: The method further comprises: Acquire building information in a sub-block of the target block, wherein the building information includes the number of buildings and the type of buildings; According to the building information, the current development direction of the sub-block is obtained; Extracting the target current development direction of the sub-block and the nearby current development directions of the nearby blocks of the sub-block, and obtaining the industrial development information of the sub-block; Calling a development prediction model to perform development prediction according to the industrial development information, the current development direction of the target and the current development direction of nearby areas, and obtaining the development potential of the sub-block; The location information and development potential of the sub-block are integrated to obtain the land information of the sub-block.

5. The land division optimization method of the network platform according to claim 2 is characterized in that: The method further comprises: Setting a condition function according to the global condition of the target block to obtain a global constraint; Obtaining a neighborhood constraint according to a relationship between the target block and blocks near the target block; According to the land information of the target block, natural factors, traffic factors and economic factors are classified and regressed to obtain local constraints; Integrating the global constraint, the neighborhood constraint and the local constraint to obtain a constraint factor; Obtaining a loss function based on land information of the target block; The partition optimization model is trained using the constraint factor and the loss function.

6. The land division optimization method of the network platform according to claim 1 is characterized in that: The method further comprises: In response to receiving an input operation of the living conditions of residents in the edge area of ​​the sub-block in the target block, obtaining the living conditions of the residents, wherein the living conditions of the residents include the living location, the number of residents and the occupation of the residents; According to the residential conditions of the residents, statistics on the residents' travel conditions; Performing feature extraction operations on the residential conditions of the residents and the travel conditions of the residents to obtain residential characteristics of the residents in the marginal area; The partition optimization model is called to update the partition range of the sub-block according to the residential characteristics of the residents.

7. The land division optimization method of the network platform according to claim 6 is characterized in that: The method further comprises: Collecting public facility information of the edge area, wherein the public facility information includes the location, type and quantity of the public facilities; Obtaining the flow tendency of residents in the marginal area according to the public facilities information; Weighting the resident mobility tendency according to the land information to obtain the resident mobility weight tendency; The division relationship between the edge area and the target block is updated according to the resident flow weight tendency.

8. A land division optimization system on a network platform, characterized in that: The system comprises: The acquisition module is used to obtain query information, land information, partition optimization model, spatial clustering operation, development intensity, building information, development prediction model, global conditions, loss function, and resident living conditions; A memory, used to store a program of a land division optimization method for a network platform according to any one of claims 1 to 7; The program in the processor memory can be loaded and executed by the processor to implement the land division optimization method of the network platform as described in any one of claims 1 to 7.

9. An intelligent terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images