Urban industry configuration method and device based on space chain and storage medium

Abstract

The invention discloses an urban industry configuration method based on a space chain, urban industry configuration equipment based on the space chain and a storage medium, and belongs to the technical field of urban planning. The method comprises the following steps: acquiring enterprise data of an enterprise of a target city and associated data related to the enterprise, wherein the associated data comprises geographic space data of a region where the enterprise is located, industrial chain information data and industrial development planning data of the target city; determining current industry chain information matched with the enterprise according to the enterprise data and the associated data; predicting future industry chain information of enterprises of the target city according to the current industry chain information and an industry chain prediction model; and according to the future industrial chain information, carrying out industrial configuration on the target city, and carrying out industrial optimization configuration based on a space chain structure rule, thereby realizing matching between the urban industrial chain layout and the actual demand of the industrial chain.

Description

Technical Field

[0001] The present invention relates to the field of urban planning, and in particular to an urban industry configuration method based on a space chain, an urban industry configuration device based on a space chain, and a storage medium. Background Art

[0002] When cities are being updated, designed and planned, they need to make a master plan, and on the basis of the master plan, they need to make traffic planning, environmental planning, social planning, economic planning, etc. In this process, they often refer to the planning of some cities of the same type, but this planning method often fails to deeply explore the industrial needs of urban planning development and the needs of industrial chain development, resulting in insufficient or excessive supporting industrial land after urban planning, which leads to a waste of urban land resources, or insufficient industrial allocation, that is, the problem of mismatch between the layout of the urban industrial chain and the actual needs of the industrial chain.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide an urban industry configuration method based on spatial chain, an urban industry configuration system based on spatial chain, an urban industry configuration device and a storage medium based on spatial chain, aiming to achieve the matching of urban industrial chain layout with the actual needs of the industrial chain.

[0005] To achieve the above object, the present invention provides a method for configuring urban industries based on a space chain, and the method for configuring urban industries based on a space chain comprises the following steps:

[0006] Acquire enterprise data of enterprises in the target city and associated data related to the enterprises, wherein the associated data includes: geographic space data of the region where the enterprises are located, industrial chain information data, and industrial development planning data of the target city;

[0007] Determine the current industrial chain information matching the enterprise according to the enterprise data and the associated data;

[0008] Predicting the future industrial chain information of enterprises in the target city based on the current industrial chain information and the industrial chain prediction model;

[0009] Carry out industrial configuration for the target city based on the future industrial chain information.

[0010] Optionally, the enterprise data includes: enterprise name, enterprise address, industry category, business scope and number of employees; the geographic space data includes: at least one of road network data, building data, land use data and POI data in the area where the enterprise is located; the development planning data includes: at least one of current industry operation data, industry development trend data and industry policy data; the step of determining the current industrial chain information matching the enterprise according to the enterprise data and the associated data includes:

[0011] Extracting text information of the enterprise data, and generating first tag information corresponding to the enterprise according to the text information;

[0012] generating second tag information corresponding to the enterprise according to the associated data;

[0013] The current industrial chain information matching the enterprise is determined according to the first tag information and the second tag information.

[0014] Optionally, the step of determining the current industrial chain information matching the enterprise according to the first tag information and the second tag information includes:

[0015] Generate a label vector according to the first label information and the second label information, wherein the label vector includes a plurality of label data;

[0016] Calculate the cosine similarity between the label vector and multiple industry chain information vectors to obtain multiple cosine similarities;

[0017] The industrial chain information vector corresponding to the highest cosine similarity is selected from the multiple cosine similarities as a matching vector, and the corresponding current industrial chain information is determined according to the matching vector.

[0018] Optionally, the step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model includes:

[0019] Determine link information between each sub-industry chain in the current industry chain information according to the current industry chain information, and generate an edge list according to the link information;

[0020] Generate node feature data based on the current industrial chain information and the spatial features of the enterprise;

[0021] The edge list, the node feature data and the prediction target are input into the industrial chain prediction model, and the future industrial chain information is output.

[0022] Optionally, before the step of generating feature data of a node according to the current industrial chain information and the spatial features of the enterprise, the step further includes:

[0023] Obtain city element information within a preset distance, wherein the city element information includes: population data, economic data, land data, infrastructure data, and road data.

[0024] The urban element weight of the urban element information is determined according to the first industry information, and the spatial feature is calculated according to the urban element weight and the urban element information.

[0025] Optionally, before the step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model, the step further includes:

[0026] Acquire sample data of industrial chain development of sample cities, the sample data including: industrial chain sample data corresponding to different time periods, city sample element data, and sample association data related to sample enterprises in sample cities;

[0027] The industrial chain prediction model is trained according to the sample data and the machine learning model, and the machine learning model is graph representation learning.

[0028] Optionally, the step of training the industrial chain prediction model according to the sample data and the machine learning model includes:

[0029] According to the industrial chain sample data, the city sample element data and the sample association data are classified respectively to obtain first city sample element data, second city sample element data, first sample association data and second sample association data, wherein the first city sample element data and the first sample association data are respectively associated with the industrial chain sample data at a degree greater than or equal to a preset association degree; and the second city sample element data and the second sample association data are respectively associated with the industrial chain sample data at a degree less than a preset association degree;

[0030] Determine a sample edge list and sample node feature data according to the industrial chain sample data, the first city sample element data, and the first sample association data;

[0031] The industrial chain prediction model is trained according to the sample edge list, the sample node feature data and the machine learning model.

[0032] In addition, to achieve the above purpose, the present invention also provides an urban industry configuration system based on space chain, and the urban industry configuration system based on space chain includes:

[0033] An acquisition module is used to acquire enterprise data of enterprises in a target city and associated data related to the enterprises, wherein the associated data includes: geographic space data of the region where the enterprises are located, industrial chain information data, and industrial development planning data of the target city;

[0034] A matching module, used to determine the current industrial chain information matching the enterprise according to the enterprise data and the associated data;

[0035] A prediction module, used to predict the future industrial chain information of the enterprises in the target city based on the current industrial chain information and the industrial chain prediction model;

[0036] A configuration module is used to configure the industry of the target city according to the future industrial chain information.

[0037] In addition, to achieve the above-mentioned objectives, the present invention also provides an urban industry configuration device based on spatial chain, and the urban industry configuration device based on spatial chain includes: a memory, a processor, and an urban industry configuration program based on spatial chain stored in the memory and executable on the processor, and the urban industry configuration program based on spatial chain is configured to implement the steps of any of the above-mentioned urban industry configuration methods based on spatial chain.

[0038] In addition, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a city industry configuration program based on a spatial chain is stored. When the city industry configuration program based on a spatial chain is executed by a processor, the steps of any of the above-mentioned city industry configuration methods based on a spatial chain are implemented.

[0039] The present invention proposes a method for urban industrial configuration based on a spatial chain. The method obtains enterprise data and enterprise-related associated data of enterprises in a target city, and determines the current industrial chain information matching the enterprises based on the enterprise data and the associated data, thereby determining the specific situation of the enterprises in the target city on the industrial chain, and predicting the future industrial chain information of the enterprises in the target city based on the current industrial chain information and the industrial chain prediction model, thereby predicting the development of the industrial chain of the enterprises in the target city based on the current industrial chain information based on the prediction model, thereby realizing the prediction of the industry, and configuring the industry of the target city based on the future industrial chain information, optimizing the urban industrial layout, and avoiding the problem of mismatch between the urban industrial chain layout and the actual demand of the industrial chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a structural diagram of a space chain-based urban industry configuration device in a hardware operating environment involved in an embodiment of the present invention;

[0041] Figure 2 It is a flowchart of the first embodiment of the city industry configuration method based on space chain of the present invention;

[0042] Figure 3 It is a flow chart of the second embodiment of the urban industry configuration method based on space chain of the present invention;

[0043] Figure 4 It is a flowchart of the third embodiment of the urban industry configuration method based on space chain of the present invention;

[0044] Figure 5 This is a flow chart of the fourth embodiment of the urban industry configuration method based on space chain of the present invention.

[0045] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0047] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of urban industry configuration equipment based on space chain in the hardware operating environment involved in the embodiment of the present invention.

[0048] like Figure 1 As shown, the urban industry configuration device based on the space chain may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The interactive device 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional interactive device 1003 may also be connected to the communication bus through a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the urban industrial configuration equipment based on the space chain, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0050] like Figure 1As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and an urban industry configuration program based on a space chain.

[0051] exist Figure 1 In the urban industry configuration device based on space chain shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the urban industry configuration device based on space chain of the present invention can be set in the urban industry configuration device based on space chain, and the urban industry configuration device based on space chain calls the urban industry configuration program based on space chain stored in the memory 1005 through the processor 1001, and executes the urban industry configuration method based on space chain provided in an embodiment of the present invention.

[0052] The embodiment of the present invention provides a method for configuring urban industries based on a space chain, referring to Figure 2 , Figure 2 This is a flow chart of a first embodiment of a method for configuring urban industries based on a space chain according to the present invention. In this embodiment, the method for configuring urban industries based on a space chain includes:

[0053] Step S1, obtaining enterprise data of enterprises in a target city and associated data related to the enterprises, wherein the associated data includes: geographic space data of the region where the enterprises are located, industrial chain information data, and industrial development planning data of the target city;

[0054] The spatial chain here refers to the mutual connection and dependency between different functional areas within a city or region. In this embodiment, the industrial configuration of the target city is optimized through the spatial chain and the industrial chain. The enterprise data here can be the data generated by the enterprise in production and operation, such as: the raw material data purchased by the enterprise, the product data produced, the business scope, the enterprise scale data, the enterprise's partners, the enterprise's subsidiary data, the enterprise's branch data, the enterprise's location data, and the enterprise's industry type, etc.

[0055] Step S2, determining the current industrial chain information matching the enterprise according to the enterprise data and the associated data;

[0056] In this embodiment, the current industrial chain information or the industrial chain information to be determined in the future is generated based on the enterprise data and the associated data. And the enterprise here can be a single enterprise, such as a group enterprise, involving multiple industrial chains. It can also be multiple enterprises, and the relationship between enterprises is not limited. It can be enterprises on the same industrial chain or enterprises on adjacent industrial chains. Preferably, enterprises on the same industrial chain can be selected, and the industrial chain information here can be stored in the database. The industrial chain information here is specifically composed of multiple sub-industry chain information. Specifically, the current industrial chain information that matches the enterprises in the target city is determined by data matching.

[0057] Step S3, predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model;

[0058] The future industrial chain information here is predicted by the industrial chain prediction model. Specifically, the input parameters required by the industrial chain prediction model are determined, and the target input data is determined in the first industrial chain according to the input parameters, and the target input data is input into the industrial chain prediction model, and the industrial chain prediction model outputs the future industrial chain information. Of course, in this embodiment, parameters such as the predicted time are required, and specifically, the prediction is made by year.

[0059] Step S4, performing industrial configuration on the target city according to the future industrial chain information.

[0060] The development status of enterprises in the future target city in the industrial chain is determined based on the future industrial chain information, so that the industrial configuration of the target city can be adjusted by modifying planning policies, etc.

[0061] In this embodiment, by acquiring the enterprise data and enterprise-related associated data of the enterprises in the target city, and determining the current industrial chain information matching the enterprises based on the enterprise data and the associated data, the specific situation of the enterprises in the target city in the industrial chain can be determined, and the future industrial chain information of the enterprises in the target city can be predicted based on the current industrial chain information and the industrial chain prediction model, so that the development of the industrial chain of the enterprises in the target city can be predicted based on the current industrial chain information based on the prediction model, thereby realizing the prediction of the industry, and configuring the industry of the target city based on the future industrial chain information, optimizing the urban industrial layout, and avoiding the problem of mismatch between the urban industrial chain layout and the actual demand of the industrial chain.

[0062] Further, based on the first embodiment, a second embodiment of the urban industry configuration method based on the space chain of the present invention is proposed. In this embodiment, referring to Figure 3The enterprise data includes: enterprise name, enterprise address, industry category, business scope and number of employees; the geographic space data includes: at least one of road network data, building data, land use data and POI data in the area where the enterprise is located; the development planning data includes: at least one of current industry operation data, industry development trend data and industry policy data; the step of determining the current industrial chain information matching the enterprise according to the enterprise data and the associated data includes:

[0063] Step S21, extracting text information of the enterprise data, and generating first tag information corresponding to the enterprise according to the text information;

[0064] The method of extracting text information is not limited here. For data in a standardized format, the corresponding text information can be obtained by matching the enterprise data through regular expressions. Optionally, the text information is determined by a keyword extraction method, which optionally includes: a method based on word frequency statistics, a recognition method based on a professional dictionary, a keyword extraction algorithm based on deep learning, etc.

[0065] Step S22, generating second tag information corresponding to the enterprise according to the associated data;

[0066] The second tag information here is generated by the associated data, the point of interest (P o in t o f In t eres t， POI) may include corresponding urban industrial supporting facilities, such as docks, railway stations, and airports. It should be noted that the data here is generally standardized data. Therefore, in this embodiment, the second tag information corresponding to the enterprise can be directly generated through the associated data without extracting text information. Of course, in some embodiments, there are also non-standard data, and the second tag information can also be determined by extracting text information.

[0067] Step S23: determining the current industrial chain information matching the enterprise according to the first tag information and the second tag information.

[0068] A vector for matching is generated according to the first label information and the second label information, and then the current industrial chain information is determined through the vector.

[0069] In this embodiment, the text information of the enterprise data is extracted, and the first label information corresponding to the enterprise is generated according to the text information; and the second label information corresponding to the enterprise is generated according to the associated data; the enterprise and the industrial chain can be associated with each other by the first label information and the second label information, and the current industrial chain information matching the enterprise is determined according to the first label information and the second label information, thereby establishing a corresponding relationship between the enterprise and the industrial chain, and improving the accuracy of subsequent predictions.

[0070] Further, based on the second embodiment, a third embodiment of the urban industry configuration method based on the space chain of the present invention is proposed. In this embodiment, referring to Figure 4 The step of determining the current industrial chain information matching the enterprise according to the first tag information and the second tag information includes:

[0071] Step S231, generating a label vector according to the first label information and the second label information, wherein the label vector includes a plurality of label data;

[0072] It should be noted that the label data here includes the data in the first label information and the data in the second label. The label vector here needs to have the same dimension and element type as the industrial chain information vector. And the text information needs to be vectorized, which can generally be vectorized through the word embedding vector model (Word2Vec), bidirectional encoder representation from transformer (Bidirectional Encoder Representations from Transformers, BERT), etc.

[0073] Step S232, calculating the cosine similarity between the label vector and the plurality of industrial chain information vectors to obtain a plurality of cosine similarities;

[0074] The label vector and the industrial chain information vector are standardized, and the dot product of the two vectors is calculated, and the cosine similarity is calculated based on the dot product. The cosine similarity value obtained ranges from -1 to 1. The closer the value is to 1, the more similar the texts are; the closer the value is to -1, the less similar the texts are; when the value is 0, it means that the texts are orthogonal, that is, there are no common features. The industrial chain information vector here can include part of the industrial chain information that can be used for matching.

[0075] Step S233 , selecting the industrial chain information vector corresponding to the highest cosine similarity from the multiple cosine similarities as a matching vector, and determining the corresponding current industrial chain information according to the matching vector.

[0076] Specifically, in this embodiment, since the maximum value of the cosine similarity is 1, the industrial chain information vector corresponding to the value closest to 1 is selected as the matching vector. In other embodiments, it can be first determined whether the data of the same element type in the first tag information and the second tag information are the same or similar. Determine whether to execute step S232 based on the determination result.

[0077] In this embodiment, a label vector is generated by using the first label information and the second label information, and then the label vector is matched with the industrial chain information vector, thereby determining the corresponding current industrial chain information.

[0078] Further, based on any of the above embodiments, a fourth embodiment of the urban industry configuration method based on space chain of the present invention is proposed. In this embodiment, referring to Figure 5 The step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model includes:

[0079] Step S31, determining link information between each sub-industry chain in the current industry chain information according to the current industry chain information, and generating an edge list according to the link information;

[0080] Specifically, the edge list here is a list containing node pairs, each node pair is composed of two node identifiers, indicating that there is an edge between them. Of course, in other embodiments, it can also be a two-dimensional array, and the elements of the two-dimensional array represent the edges between nodes and the weights of the edges.

[0081] Step S32, generating node feature data according to the current industrial chain information and the spatial features of the enterprise;

[0082] The characteristic data here may include the production capacity of the node, the number of enterprises corresponding to the node, and the number of employees corresponding to the node. Of course, in some embodiments, it may also include the supporting facilities corresponding to the node.

[0083] Step S33, inputting the edge list, the node feature data and the prediction target into the industrial chain prediction model, and outputting the future industrial chain information.

[0084] The prediction target here is the prediction time, which is in years in this embodiment. For example, the secondary industry information in 5 years can be predicted, and the secondary industry information in 10 years can also be predicted. The edge list, the node feature data and the prediction target are input into the industrial chain prediction model to output the prediction result.

[0085] In this embodiment, an edge list is generated through the link information and corresponding feature data is generated according to the spatial features, so as to obtain standardized input model data, thereby realizing the prediction of the industry.

[0086] Furthermore, before the step of generating feature data of a node according to the current industrial chain information and the spatial features of the enterprise, the step further includes:

[0087] Obtain city element information within a preset distance, wherein the city element information includes: population data, economic data, land data, infrastructure data, and road data.

[0088] The urban element weight of the urban element information is determined according to the first industry information, and the spatial feature is calculated according to the urban element weight and the urban element information.

[0089] It should be noted that different industrial chains have different demands for different types of resources. For example, for the heavy industry industrial chain, the factor weight of docks and railway stations is greater than that of airports. In addition, the factor weight of energy resources and mining resources is greater than that of forestry resources and fishery resources. On the contrary, for the tourism industrial chain, the factor weight of airports is greater than that of docks and railway stations, and the factor weight of infrastructure such as accommodation, catering and transportation is greater than that of energy resources and mining resources. For enterprises in different industrial chains in the same target city, even if the city factor information is the same, due to the difference in city factor weights, the calculated spatial characteristics will be different. For the same industrial chain, since the corresponding city factor information of different cities is also different, the larger the value of the spatial feature here, the more suitable it is to develop the corresponding industrial chain in the target city.

[0090] In this embodiment, urban element information within a preset distance is obtained, and the urban element weight of the urban element information is determined according to the first industrial information, and the spatial feature is calculated according to the urban element weight and the urban element information. According to the size of the spatial feature, it can be reflected whether the target city is suitable for developing the corresponding industrial chain.

[0091] Further, based on any of the above embodiments, a fifth embodiment of the city industry configuration method based on the space chain of the present invention is proposed. In this embodiment, before the step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model, it also includes:

[0092] Acquire sample data of industrial chain development of sample cities, the sample data including: industrial chain sample data corresponding to different time periods, city sample element data, and sample association data related to sample enterprises in sample cities;

[0093] The industrial chain prediction model is trained according to the sample data and the machine learning model, and the machine learning model is graph representation learning.

[0094] In this embodiment, the industrial chain data of the sample city in different years are input into the machine learning model. Of course, other types of machine learning models can also be used in other embodiments. When other types of machine learning models are used, the industrial chain sample data, city sample element data, and sample association data related to sample enterprises in the sample city need to be converted into corresponding data training formats.

[0095] Furthermore, the industrial chain sample data also includes: attribute labels corresponding to the industrial chain, and the attribute labels include: a dominant industrial chain label, an auxiliary industrial chain label, and a planned industrial chain label.

[0096] It should be noted that the sample cities may have different industrial chains in the same year, but the revenue generated by different industrial chains, the competitiveness of the industrial chains, and the impact of the industrial chains on the development of enterprises are different. Therefore, it is necessary to distinguish whether the industrial chain is a leading industrial chain or an auxiliary industrial chain. In addition, it should be noted that in other embodiments, in addition to the basic data, the industrial chain sample data may also include further extracted feature data, which may include the length of the industrial chain, the number of isolated industrial sites in the industrial chain space, the average distance between industrial chain links, etc.

[0097] Furthermore, the step of training the industrial chain prediction model according to the sample data and the machine learning model includes:

[0098] According to the industrial chain sample data, the city sample element data and the sample association data are classified respectively to obtain first city sample element data, second city sample element data, first sample association data and second sample association data, wherein the first city sample element data and the first sample association data are respectively associated with the industrial chain sample data at a degree greater than or equal to a preset association degree; and the second city sample element data and the second sample association data are respectively associated with the industrial chain sample data at a degree less than a preset association degree;

[0099] Determine a sample edge list and sample node feature data according to the industrial chain sample data, the first city sample element data, and the first sample association data;

[0100] The industrial chain prediction model is trained according to the sample edge list, the sample node feature data and the machine learning model.

[0101] In this embodiment, a preset correlation degree is set as a threshold, the city sample element data and the sample association data are classified, and the corresponding sample edge list and sample node feature data are determined based on the obtained first city sample element data and the first sample association data.

[0102] In this embodiment, the sample edge list and sample node feature data are determined according to the industrial chain sample data, the first city sample element data and the first sample association data, and the industrial chain prediction model is trained according to the sample edge list, the sample node feature data and the machine learning model, so that the industrial chain model of the target city can be used as a model based on the changes in the sample city in the industrial chain for evolution and prediction, thereby realizing the prediction of the industry, and configuring the industry for the target city according to the future industrial chain information, thereby optimizing the urban industrial layout and avoiding the problem of mismatch between the urban industrial chain layout and the actual demand of the industrial chain.

[0103] In addition, an embodiment of the present invention also proposes an urban industry configuration device based on a spatial chain, and the urban industry configuration device based on a spatial chain includes: a memory, a processor, and an urban industry configuration program based on a spatial chain stored in the memory and executable on the processor, and the urban industry configuration program based on a spatial chain is configured to implement the steps of an embodiment of the urban industry configuration method based on a spatial chain as described above.

[0104] In addition, an embodiment of the present invention further proposes a storage medium, on which a city industry configuration program based on a spatial chain is stored. When the city industry configuration program based on a spatial chain is executed by a processor, the steps of any of the above-mentioned embodiments of the city industry configuration method based on a spatial chain are implemented.

[0105] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0106] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0108] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for urban industry configuration based on space chain, characterized in that: The urban industry configuration method based on space chain includes the following steps: Acquire enterprise data of enterprises in the target city and associated data related to the enterprises, wherein the associated data includes: geographic space data of the region where the enterprises are located, industrial chain information data, and industrial development planning data of the target city; Determine the current industrial chain information matching the enterprise according to the enterprise data and the associated data; Predicting the future industrial chain information of enterprises in the target city based on the current industrial chain information and the industrial chain prediction model; Carry out industrial configuration for the target city based on the future industrial chain information.

2. The urban industry configuration method based on space chain according to claim 1, characterized in that: Before the step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model, the method further includes: Acquire sample data of industrial chain development in sample cities, the sample data including: industrial chain sample data corresponding to different time periods, city sample element data, and sample association data related to sample enterprises in sample cities; The industrial chain prediction model is trained according to the sample data and the machine learning model, and the machine learning model is graph representation learning.

3. The urban industry configuration method based on space chain as claimed in claim 2, characterized in that: The industrial chain sample data also includes: attribute labels corresponding to the industrial chain, and the attribute labels include: a dominant industrial chain label, an auxiliary industrial chain label, and a planned industrial chain label.

4. The urban industry configuration method based on space chain as claimed in claim 2, characterized in that: The step of training the industrial chain prediction model according to the sample data and the machine learning model includes: According to the industrial chain sample data, the city sample element data and the sample association data are classified respectively to obtain first city sample element data, second city sample element data, first sample association data and second sample association data, wherein the first city sample element data and the first sample association data are respectively associated with the industrial chain sample data at a degree greater than or equal to a preset association degree; and the second city sample element data and the second sample association data are respectively associated with the industrial chain sample data at a degree less than a preset association degree; Determine a sample edge list and sample node feature data according to the industrial chain sample data, the first city sample element data, and the first sample association data; The industrial chain prediction model is trained according to the sample edge list, the sample node feature data and the machine learning model.

5. The urban industry configuration method based on space chain according to claim 1, characterized in that: The enterprise data includes: enterprise name, enterprise address, industry category, business scope and number of employees; the geographic space data includes: at least one of road network data, building data, land use data and POI data in the area where the enterprise is located; the development planning data includes: at least one of current industry operation data, industry development trend data and industry policy data; the step of determining the current industrial chain information matching the enterprise based on the enterprise data and the associated data includes: Extracting text information of the enterprise data, and generating first tag information corresponding to the enterprise according to the text information; generating second tag information corresponding to the enterprise according to the associated data; The current industrial chain information matching the enterprise is determined according to the first tag information and the second tag information.

6. The urban industry configuration method based on space chain according to claim 5 is characterized in that: The step of determining the current industrial chain information matching the enterprise according to the first tag information and the second tag information includes: Generate a label vector according to the first label information and the second label information, wherein the label vector includes a plurality of label data; Calculate the cosine similarity between the label vector and multiple industry chain information vectors to obtain multiple cosine similarities; The industrial chain information vector corresponding to the highest cosine similarity is selected from the multiple cosine similarities as a matching vector, and the corresponding current industrial chain information is determined according to the matching vector.

7. The urban industry configuration method based on space chain according to claim 1, characterized in that: The step of predicting the future industrial chain information of the enterprises in the target city according to the current industrial chain information and the industrial chain prediction model comprises: Determine link information between each sub-industry chain in the current industry chain information according to the current industry chain information, and generate an edge list according to the link information; Generate node feature data based on the current industrial chain information and the spatial features of the enterprise; The edge list, the node feature data and the prediction target are input into the industrial chain prediction model, and the future industrial chain information is output.

8. The urban industry configuration method based on space chain according to claim 7, characterized in that: Before the step of generating feature data of a node according to the current industrial chain information and the spatial features of the enterprise, the step further includes: Obtain city element information within a preset distance, wherein the city element information includes: population data, economic data, land data, infrastructure data, and road data. The urban element weight of the urban element information is determined according to the first industry information, and the spatial feature is calculated according to the urban element weight and the urban element information.

9. An urban industry configuration device based on space chain, characterized in that: The urban industry configuration device based on spatial chain includes: a memory, a processor, and an urban industry configuration program based on spatial chain stored in the memory and executable on the processor. The urban industry configuration program based on spatial chain is configured to implement the steps of the urban industry configuration method based on spatial chain as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a city industry configuration program based on the space chain, and when the city industry configuration program based on the space chain is executed by the processor, the steps of the city industry configuration method based on the space chain as described in any one of claims 1 to 7 are implemented.

Images