A method for constructing a digital twin for urban planning

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a method for constructing a digital twin for urban planning, including: obtaining the daily output of each industrial element; obtaining a time-delay consistency coefficient according to the consistency of the output changes between industrial elements and other industrial elements and the difference in time lag under the condition of consistent output; obtaining all upstream industrial elements of each downstream industrial element based on the time-delay consistency coefficient; obtaining the consistency of output changes according to the covariation relationship of the output between upstream industrial elements when they are raw materials in the same link; obtaining a number of industrial system elements according to the consistency of output changes and the time-delay consistency coefficient; constructing an urban industrial system network based on all industrial system elements, and obtaining a number of digital twins for urban planning. The present invention aims to solve the problem that multiple links and products in the urban industrial system are interrelated, so that the divided urban industrial systems do not interfere with each other.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a method for constructing a digital twin for urban planning. Background Art

[0002] A digital twin city refers to combining the physical space and digital space of a city through information technology and intelligent devices to construct a city information model. Through digital twin technology, urban planners can more accurately simulate the future development of a city, predict possible problems, and formulate more scientific planning schemes. Digital twin technology is mainly used in urban planning by simulating the production capacity and consumption of a city, and then predicting the future trend of the city. Among them, the economic lifelines affecting the city are usually multiple industrial chains. Therefore, by analyzing and predicting the production capacity of each industrial chain in the future, the future trend of the city can be obtained, and then the future urban planning can be adjusted.

[0003] The industrial system of a city has multiple complete industrial chains, which are sequentially related from raw materials to semi-finished products, from semi-finished products to finished products, from semi-finished products to new semi-finished products, and from raw materials to finished products. When analyzing the future trend of a city, due to the existence of local industries, outbound industries, and processing industries in the city, it is necessary to separate different industrial chains and then construct a digital twin model. However, in the separation process, affected by the time mismatch of different industrial chains and the fact that one product is used in multiple links of the industrial system, the upstream and downstream relationships of some links of the industrial system are hidden, which reduces the accuracy of the digital twin model in predicting the future of the city. Summary of the Invention

[0004] The present invention provides a method for constructing a digital twin for urban planning to solve the existing problems.

[0005] A method for constructing a digital twin for urban planning according to the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides a method for constructing a digital twin for urban planning, and the method includes the following steps. The system includes the following modules:

[0007] Obtain the daily output of each industrial element on a preset date sequence;

[0008] Obtain the time-lag consistency coefficient of each industrial element and other industrial elements according to the consistency of the output change of each industrial element and other industrial elements and the difference in time lag under the consistent output;

[0009] Screen the downstream industrial elements of each industrial element based on the time-lag consistency coefficient to obtain all the upstream industrial elements of each downstream industrial element;

[0010] Obtain the yield change consistency of each upstream industrial element under each downstream industrial element according to the covariance relationship of the yields in the case of the same-link raw materials among all upstream industrial elements of each downstream industrial element;

[0011] According to the yield change consistency of each upstream industrial element under the downstream industrial element, and combining with the time-delay consistency coefficient of the corresponding industrial element, obtain a number of industrial system elements;

[0012] Construct an urban industrial system network based on all industrial system elements, obtain a number of industrial communities after community division of the urban industrial system network, and obtain a number of digital twins for urban planning based on each industrial community.

[0013] Preferably, the specific steps for obtaining the time-delay consistency coefficient include:

[0014] For the i-th industrial element, obtain all production date segments of the i-th industrial element, and all matching production date segments in the m-th suspected downstream industrial element of the i-th industrial element;

[0015] The time-delay consistency coefficient between the i-th industrial element and the m-th suspected downstream industrial element is calculated as follows:

[0016]

[0017] where represents the variance function; is the exponential function with the natural constant as the base; is the date median of the k-th production date segment of the i-th industrial element, is the date median of the k-th matching production date segment in the m-th suspected downstream industrial element of the i-th industrial element.

[0018] Preferably, the specific steps for obtaining the production date segment include:

[0019] Use the dynamic time warping algorithm to perform dynamic warping matching on the daily production of the i-th industrial element and the j-th industrial element other than the i-th industrial element, and obtain the production matching days of the i-th industrial element on each day in the j-th industrial element;

[0020] If the date sequence value of the production matching day of the second day of the i-th industrial element is greater than or equal to 2, record the j-th industrial element as the suspected downstream industrial element of the i-th industrial element;

[0021] Obtain all the minimum values of the sequence formed by the daily output of the $i$-th industrial element, and denote the date sequence formed by all the dates between two adjacent minimum values and including the first minimum value among the two minimum values as a production date segment of the $i$-th industrial element.

[0022] Preferably, the specific steps for obtaining the matching production date segment include:

[0023] Denote the production matching date of the first date in the $k$-th production date segment of the $i$-th industrial element in the date sequence of the $m$-th suspected downstream industrial element of the $i$-th industrial element as the first day of the $k$-th matching production date segment in the $m$-th suspected downstream industrial element of the $i$-th industrial element;

[0024] Denote the production matching date of the last date in the $k$-th production date segment in the date sequence of the $m$-th suspected downstream industrial element of the $i$-th industrial element as the last day of the $k$-th matching production date segment in the $m$-th suspected downstream industrial element of the $i$-th industrial element;

[0025] Denote the sequence formed by all the dates between the first day and the last day of the $k$-th matching production date segment in the $m$-th suspected downstream industrial element as the $k$-th matching production date segment in the $m$-th suspected downstream industrial element of the $i$-th industrial element.

[0026] Preferably, the specific steps for obtaining the upstream industrial element include:

[0027] Preset a time lag consistency threshold. When the time lag consistency coefficient between the $i$-th industrial element and the $m$-th suspected downstream industrial element is greater than or equal to the time lag consistency threshold, denote the $m$-th suspected downstream industrial element of the $i$-th industrial element as the downstream industrial element of the $i$-th industrial element;

[0028] For the $n$-th downstream industrial element of the $i$-th industrial element, denote the $i$-th industrial element as the th upstream industrial element of the $n$-th downstream industrial element.

[0029] Preferably, the specific steps for obtaining the production change consistency include:

[0030] Denote the time lag consistency coefficient between the $i$-th industrial element and the $n$-th downstream industrial element of the $i$-th industrial element as the time lag consistency coefficient between the $n$-th downstream industrial element and the th upstream industrial element of the $n$-th downstream industrial element;

[0031] Among the date sequences of each covariant contribution industrial element of the th upstream industrial element of the $n$-th downstream industrial element, obtain the one that is the same as the The sequence segment with the same production date segment of the k-th production date of the upstream industrial element is denoted as the k-th production date segment under each covariant contribution industrial element of the upstream industrial element;

[0032] Under the n-th downstream industrial element The production change consistency of the upstream industrial element is calculated as follows:

[0033]

[0034] where is a function to obtain the Pearson correlation coefficient;

[0035] is the number of covariant contribution industrial elements of the -th upstream industrial element of the n-th downstream industrial element, is the number of production date segments of the -th upstream industrial element of the n-th downstream industrial element;

[0036] is the sequence of production compositions of the k-th production date segment of the -th upstream industrial element of the n-th downstream industrial element, is the sequence of production compositions of the covariant contribution industrial elements of the -th upstream industrial element of the n-th downstream industrial element in the k-th production date segment.

[0037] Preferably, the specific steps for obtaining the covariant contribution industrial element include:

[0038] Among all the upstream industrial elements of the n-th downstream industrial element, except for the -th upstream industrial element, the other upstream industrial elements are denoted as the covariant contribution industrial elements of the -th upstream industrial element of the n-th downstream industrial element.

[0039] Preferably, the specific steps for obtaining the industrial system element include:

[0040] Obtain the industrial system correlation coefficients of all upstream industrial elements under the n-th downstream industrial element, perform linear normalization on the industrial system correlation coefficients of all upstream industrial elements under the n-th downstream industrial element to obtain the normalized values of the industrial system correlation coefficients of each upstream industrial element under the n-th downstream industrial element, use the Otsu threshold algorithm to perform maximum differential segmentation on the normalized values of the industrial system correlation coefficients, and take all the upstream industrial elements in the largest part after segmentation as several upwardly associated industrial elements of the n-th downstream industrial element;

[0041] Take the industrial system correlation coefficient of the upstream industrial element corresponding to each upwardly associated industrial element of the nth downstream industrial element as the industrial system correlation coefficient of each upwardly associated industrial element of the nth downstream industrial element; each downstream industrial element and each of its upwardly associated industrial elements form an industrial system element.

[0042] Preferably, the specific steps for obtaining the industrial system correlation coefficient include:

[0043] For the nth downstream industrial element, the industrial system correlation coefficient of the th upstream industrial element is calculated as follows:

[0044]

[0045] where is the time-delay consistency coefficient between the nth downstream industrial element and the th upstream industrial element of the nth downstream industrial element, and is the production change consistency of the th upstream industrial element under the nth downstream industrial element.

[0046] Preferably, the steps of constructing an urban industrial system network based on all industrial system elements, performing community division on the urban industrial system network to obtain several industrial communities, and obtaining several digital twins for urban planning based on each industrial community include:

[0047] Construct an urban industrial system network based on a relational network structure. The urban industrial system network is a topological structure. Each node in the urban industrial system network represents the first industrial element. If two nodes can form an industrial system element, take the industrial system correlation coefficient between the downstream industrial element and the upwardly associated industrial element in this industrial system element as the degree of the urban industrial system network;

[0048] Perform community division on the urban industrial system network through the Louvain algorithm to obtain several industrial communities. Take the production of industrial elements in each community on all dates as the data basis for generating a digital twin, and obtain several digital twins for urban planning.

[0049] The beneficial effects of the technical solution of the present invention are as follows: This application obtains the daily output of each industrial element on a preset date sequence; according to the consistency of the output changes between each industrial element and other industrial elements and the difference in time lag when the output is consistent, the time-lag consistency coefficient between each industrial element and other industrial elements is obtained; through the time-lag consistency coefficient, the consistency of the output changes of different industrial elements and the time-lag effect of the output changes during different batches of production between the upstream and downstream links in the industrial system are highlighted; based on the time-lag consistency coefficient, the downstream industrial elements of each industrial element are screened to obtain all the upstream industrial elements of each downstream industrial element; according to the covariance relationship of the output between all the upstream industrial elements of each downstream industrial element when they are used as raw materials in the same link, the consistency of the output changes of each upstream industrial element under each downstream industrial element is obtained; by analyzing the simultaneous change situations among all the upstream industrial elements of the same downstream industrial element, the consistency of the output changes among different upstream industrial elements in the same upstream link is analyzed, thereby avoiding the problem that the different proportions of different industrial elements in the same upstream link have different degrees of influence on the downstream industrial link, resulting in a decrease in the time-lag consistency coefficient; according to the consistency of the output changes of each upstream industrial element under the downstream industrial element and combining with the time-lag consistency coefficient of the corresponding industrial element, several industrial system elements are obtained; according to all the industrial system elements, an urban industrial system network is constructed, and after community division of the urban industrial system network, several industrial communities are obtained, and several digital twins for urban planning are obtained based on each industrial community; the different industrial elements are divided into systems, so that the different industrial systems after division are independent of each other, and when conducting urban planning, only all the industrial elements in one industrial system need to be analyzed, avoiding the interference of other industrial elements. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a flowchart of the steps of a method for constructing a digital twin for urban planning according to the present invention;

[0052] Figure 2 It is a matching schematic diagram of the daily output of different industrial elements in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a method for constructing a digital twin for urban planning proposed according to the present invention, including its specific implementation manner, structure, features, and effects, as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0055] The following specifically describes, in conjunction with the accompanying drawings, the specific solution of a method for constructing a digital twin for urban planning provided by the present invention.

[0056] Please refer to Figure 1 , which shows a flowchart of the steps of a method for constructing a digital twin for urban planning provided by an embodiment of the present invention. The method includes the following steps:

[0057] Step S001: Obtain the daily output of each industrial element on the preset date sequence.

[0058] It should be noted that there are multiple complete industrial system chains in the city. The purpose of the digital twin constructed in this embodiment is to accurately divide multiple industrial system chains, and then use each industrial system chain as the data basis of a digital twin, so that the constructed digital twins do not affect each other, and each digital twin only contains all industrial elements of all links in one industrial system chain.

[0059] Furthermore, it should be noted that there are multiple links in an industrial system chain, and the previous link will affect the subsequent link. The main manifestation of the influence is the consistency of the output changes of each link in different industrial system chains. Therefore, in this embodiment, the output of all links in the city is first collected, and different links of different industrial systems are used as an industrial element to obtain the daily output of each link.

[0060] Preferably, the specific steps for obtaining the daily output of each industrial element are as follows:

[0061] Preset the length of the date sequence, obtain the daily production quantity of each industrial element on the date sequence according to the public data of the urban industrial data statistics department, and then perform maximum-minimum normalization on the production quantity to obtain the daily output of each industrial element. The set composed of all industrial elements is the urban industrial system set.

[0062] It should be noted that the length segment of the date sequence in this embodiment is described by taking one year as an example. Among them, the industrial elements are the products produced by each factory in the city, and the production quantity is the total quantity of the same product produced in the city. As an example, the industrial elements in this embodiment are described by taking raw materials such as ores and agricultural products, semi-finished raw materials after processing of raw materials such as pig iron and kerosene, and power generation, industrial water output, sewage discharge, etc. as examples.

[0063] It should be especially noted that the public data of the urban industrial data statistics department in this embodiment is collected by taking the public data of the industrial statistics department under the Municipal Bureau of Statistics as an example. The Municipal Bureau of Statistics organizes and implements national economic accounting and input-output surveys, and provides national economic accounting materials after compiling the gross domestic product within the city.

[0064] Step S002: Obtain the time-lag consistency coefficient of each industrial element and other industrial elements according to the consistency of the output changes of each industrial element and other industrial elements and the difference in time lag under the condition of consistency of output.

[0065] It should be noted that since industrial production needs to ensure that the cost is as low as possible, placing the same industrial system in one city can reduce the transportation cost to the greatest extent. The conditions of the city where the industrial system is placed are usually the place of origin of raw materials or low energy consumption cost. Therefore, cities with low raw material origin or low energy consumption cost can attract more industries. That is, one kind of raw material or one kind of energy consumption can affect multiple industrial chains. Then, when constructing a digital twin, because it is limited by the influence of the same upstream link, these multiple industrial chains need to be combined for analysis.

[0066] Furthermore, it should be noted that the time limits of different links of the same industrial system are different. Then, the changes in the upstream link will affect the next link after a certain period of time. Therefore, it is first necessary to perform similarity analysis and time-lag analysis on the current industrial element and other industrial elements to obtain the time-lag consistency coefficient of the current industrial element and each other industrial element.

[0067] Preferably, the specific steps to obtain the time-lag consistency coefficient of the current industrial element and each other industrial element according to the difference in time lag between the current industrial element and other industrial elements are as follows:

[0068] It should be noted that since the previous link in different links of an industrial system will affect the subsequent links, the entire complete industrial system is manifested as a tree structure presented with the convergence of links. Moreover, in this tree structure, the output change of the industrial element corresponding to the previous link will affect the industrial element corresponding to the subsequent link after a certain period of time, and the influence difference is small and the influence feedback time is similar. Therefore, in this embodiment, dynamic time warping is used to match each industrial element, and then the time-delay consistency and change similarity of different influences are analyzed to obtain the time-delay consistency coefficient between each industrial element and other industrial elements.

[0069] Specifically, the dynamic time warping algorithm is used to perform dynamic warping matching on the daily output of the i-th industrial element and the j-th industrial element except the i-th industrial element, and obtain the output matching days of the i-th industrial element on the j-th industrial element every day. The output matching days are the dates with the smallest interval from the date of the i-th industrial element every day and the least output difference.

[0070] It should be noted that the dynamic time warping algorithm is a well-known existing technology, and will not be elaborated in this embodiment. As Figure 2 shown, Figure 2 It is a matching schematic diagram of the daily output of different industrial elements, specifically representing the schematic diagram after the daily output of the i-th industrial element and the j-th industrial element is matched by the dynamic time warping algorithm.

[0071] Furthermore, if the date sequence value of the output matching day of the second day of the i-th industrial element is greater than or equal to 2, the j-th industrial element is recorded as the suspected downstream industrial element of the i-th industrial element.

[0072] It should be noted that the dynamic time warping algorithm will match the elements with the same numerical value in the two sequences. Then, if the outputs are similar, they will be matched as a pair. If the i-th industrial element is the upstream industrial element and the j-th industrial element is the downstream industrial element, due to the time lag phenomenon in the output influence of the i-th industrial element on the j-th industrial element, the dynamic time warping algorithm will take the previous several days of the j-th industrial element as the output matching days of the first day of the i-th industrial element. At this time, it is considered that the j-th industrial element may be the downstream industrial element of the i-th industrial element.

[0073] Furthermore, similarly, all the suspected downstream industrial elements of the i-th industrial element are obtained.

[0074] It should be noted that the above-mentioned suspected downstream industrial elements affected by the i-th industrial element are initially obtained through the dynamic time warping algorithm, without considering the intensity of the influence correlation. Therefore, it is necessary to further analyze the consistency of the influence time lag between each industrial element and its suspected downstream industrial elements to obtain the time lag consistency coefficient of each suspected downstream industrial element of the industrial element, and then screen the suspected downstream industrial elements to obtain the downstream industrial elements of each industrial element.

[0075] Preferably, the specific steps for obtaining the time lag consistency coefficient of each suspected downstream industrial element of the industrial element according to the daily output matching relationship between the industrial element and its suspected downstream industrial elements are as follows:

[0076] It should be noted that the quantity that the downstream of the industrial system ultimately needs to produce reflects the daily output change of the upstream link in the upstream link, and the more the peaks in this change can reflect the degree of demand in the downstream link. Therefore, in order to highlight the influence time lag relationship between the industrial element and its suspected downstream industrial elements, in this embodiment, the date sequence of the industrial element is first segmented according to the fluctuation of the output data, and then based on the production matching days of the industrial element in the suspected downstream industrial elements every day, after matching the date sequences of the industrial element and its suspected downstream industrial elements, several production date segments of the industrial element and the matching production date segments of its suspected downstream industrial elements are obtained.

[0077] Specifically, all the minimum values of the sequence formed by the daily output of the i-th industrial element are obtained, and the date sequence formed by all the dates between two adjacent minimum values and including the first minimum value of the two minimum values is recorded as a production date segment of the i-th industrial element. Similarly, all the production date segments of the i-th industrial element are obtained.

[0078] Furthermore, for the k-th production date segment of the i-th industrial element, the production matching day of the first date in the k-th production date segment in the date sequence of the m-th suspected downstream industrial element of the i-th industrial element is recorded as the first day of the k-th matching production date segment of the m-th suspected downstream industrial element of the i-th industrial element; the production matching day of the last date in the k-th production date segment in the date sequence of the m-th suspected downstream industrial element of the i-th industrial element is recorded as the last day of the k-th matching production date segment of the m-th suspected downstream industrial element of the i-th industrial element. The sequence formed by all the dates between the first day and the last day of the k-th matching production date segment of the m-th suspected downstream industrial element is recorded as the k-th matching production date segment of the m-th suspected downstream industrial element of the i-th industrial element.

[0079] Similarly, each production date segment of the i-th industrial element is obtained, as well as the corresponding matching production date segments in each suspected downstream industrial element of the i-th industrial element.

[0080] It should be noted that if the m-th suspected downstream industrial element is a downstream industrial element of the i-th industrial element, then when the production of the i-th industrial element changes, the time lag relationship of the change of the m-th suspected downstream industrial element is consistent. This time lag is caused by the need for operations such as transportation and transfer during the process from the upstream link to the downstream link of the industrial element. Therefore, in this embodiment, according to the consistency of the time difference between the production date segment and the corresponding matching production date segment, the time lag consistency coefficient between each industrial element and its suspected downstream industrial element is obtained.

[0081] Preferably, the time lag consistency coefficient between the i-th industrial element and the m-th suspected downstream industrial element is calculated as follows:

[0082]

[0083] where represents the variance function; is the exponential function with the natural constant as the base; is the date median of the k-th production date segment of the i-th industrial element, is the date median of the k-th matching production date segment in the m-th suspected downstream industrial element of the i-th industrial element.

[0084] It should be noted that variance can reflect the magnitude of a value. Therefore, in this embodiment, is used to reflect the consistency of the time difference between the production date segment and the corresponding matching production date segment in the suspected downstream industrial element. The more consistent this value is, the more consistent the time lag effect of the i-th industrial element on the m-th suspected downstream industrial element is, and the more likely the m-th suspected downstream industrial element is a downstream industrial element of the i-th industrial element.

[0085] Similarly, the time lag consistency coefficients between each industrial element and other industrial elements are obtained.

[0086] Step S003: Based on the time lag consistency coefficients, screen the downstream industrial elements of each industrial element to obtain all the upstream industrial elements of each downstream industrial element. According to the covariance relationship of the production among all the upstream industrial elements of each downstream industrial element when they are raw materials in the same link, obtain the production change consistency of each upstream industrial element under each downstream industrial element. According to the production change consistency of each upstream industrial element under the downstream industrial element, combined with the time lag consistency coefficient of the corresponding industrial element, obtain several industrial system elements.

[0087] A preset time-delay consistency threshold value. In this embodiment, 0.4 is taken as an example for description. When the time-delay consistency coefficient between the $i$-th industrial element and the $m$-th suspected downstream industrial element is greater than or equal to the time-delay consistency threshold value, the $m$-th suspected downstream industrial element of the $i$-th industrial element is recorded as the downstream industrial element of the $i$-th industrial element.

[0088] It should be noted that each link in the industrial system of the city presents a tree structure, that is, the production of one industrial element may be affected by multiple industrial elements. Then, there will be an interrelated relationship between multiple industrial elements that produce the same industrial element. Then, when the downstream industrial element changes, the changes in its upstream industrial elements are not obvious, or because the industrial element accounts for a small proportion in the production of the next industrial element, which leads to a mismatch in production volume. Then, when performing dynamic time warping, due to the dissimilarity of the changes, there are errors in the warping, and then the accuracy of the time-delay consistency coefficient is relatively low. Therefore, the above-mentioned time-delay consistency threshold value is preset to be relatively small.

[0089] Furthermore, it should be noted that since the proportion of industrial elements as raw materials is different when producing the same industrial element, the time-delay consistency coefficient of the industrial element with a larger proportion is more accurate than the numerical consistency coefficient of the industrial element with a smaller proportion. And as raw material industrial elements have similar demands, the change ranges of the production volumes of raw material industrial elements are similar. Therefore, in this embodiment, the industrial system correlation coefficient between each downstream industrial element and its upstream industrial element is obtained by combining the time-delay consistency coefficient with the production volume change consistency of the upstream industrial element of the downstream industrial element.

[0090] Preferably, for the $n$-th downstream industrial element of the $i$-th industrial element, the $i$-th industrial element is recorded as the $n$-th upstream industrial element of the $n$-th downstream industrial element, and the time-delay consistency coefficient between the $i$-th industrial element and the $n$-th downstream industrial element of the $i$-th industrial element is recorded as the time-delay consistency coefficient between the $n$-th downstream industrial element and the $n$-th upstream industrial element of the $n$-th downstream industrial element.

[0091] Similarly, all upstream industrial elements of the $n$-th downstream industrial element and the time-delay consistency coefficients between the $n$-th downstream industrial element and all upstream industrial elements are obtained.

[0092] Furthermore, for the $k$-th production date segment of the $n$-th upstream industrial element of the $n$-th downstream industrial element, the $k$-th production date segment of the $n$-th upstream industrial element is the same as the $k$-th production date segment of the $i$-th upstream industrial element; among all upstream industrial elements of the $n$-th downstream industrial element, except for the Other upstream industrial elements except the first upstream industrial element are denoted as the covariant contribution industrial elements of the nth downstream industrial element from the first upstream industrial element.

[0093] Furthermore, in the date sequence of each covariant contribution industrial element of the first upstream industrial element of the nth downstream industrial element, a sequence segment identical to the kth production date segment date of the first upstream industrial element is obtained and denoted as the kth production date segment under each covariant contribution industrial element of the first upstream industrial element of the nth downstream industrial element.

[0094] Furthermore, according to the consistency of the production volume change between the kth production date segment of the first upstream industrial element of the nth downstream industrial element and the kth covariant contribution date segment of each covariant contribution industrial element under the first upstream industrial element of the nth downstream industrial element, and combined with the time lag consistency coefficient between the nth downstream industrial element and the first upstream industrial element of the nth downstream industrial element, the specific steps to obtain the industrial system correlation degree coefficient of the first upstream industrial element of the nth downstream industrial element are as follows:

[0095] The calculation method of the production volume change consistency of the first upstream industrial element under the nth downstream industrial element is as follows:

[0096]

[0097] Wherein, is a function for calculating the Pearson correlation coefficient; is the number of covariant contribution industrial elements of the first upstream industrial element of the nth downstream industrial element, is the number of production date segments of the first upstream industrial element of the nth downstream industrial element; is the sequence of the production volume composition of the kth production date segment of the first upstream industrial element of the nth downstream industrial element, is the sequence of the production volume composition of the covariant contribution industrial elements of the first upstream industrial element of the nth downstream industrial element in the kth production date segment.

[0098] Used to measure the consistency of the output changes of upstream industrial elements and their covariant contribution industrial elements at the same time. The larger the value, the more likely it is that both the element and its covariant contribution industrial elements are used as raw materials for the downstream industrial element. Therefore, the th upstream industrial element is more likely to form a link in an industrial system with the nth downstream industrial element.

[0099] Furthermore, based on the consistency of the output changes of the th upstream industrial element under the nth downstream industrial element, the time-delay consistency coefficient between the nth downstream industrial element and the th upstream industrial element of the nth downstream industrial element is corrected to obtain the industrial system correlation coefficient of the th upstream industrial element under the nth downstream industrial element. The calculation method is as follows:

[0100]

[0101] Wherein, is the time-delay consistency coefficient between the nth downstream industrial element and the th upstream industrial element of the nth downstream industrial element, is the consistency of the output changes of the th upstream industrial element under the nth downstream industrial element.

[0102] Furthermore, obtain the industrial system correlation coefficients of all upstream industrial elements under the nth downstream industrial element, perform linear normalization on the industrial system correlation coefficients of all upstream industrial elements under the nth downstream industrial element to obtain the normalized values of the industrial system correlation coefficients of each upstream industrial element under the nth downstream industrial element, use the Otsu threshold algorithm to perform maximum-difference segmentation on the normalized values of the industrial system correlation coefficients, and take all the upstream industrial elements in the largest part after segmentation as several upward-related industrial elements of the nth downstream industrial element. Take the industrial system correlation coefficient of the upstream industrial element corresponding to each upward-related industrial element of the nth downstream industrial element as the industrial system correlation coefficient of each upward-related industrial element of the nth downstream industrial element; each downstream industrial element and each of its upward-related industrial elements form an industrial system element.

[0103] It should be noted that in this embodiment, the maximum-minimum normalization algorithm is used to normalize the industrial system correlation coefficient; the Otsu threshold algorithm is a well-known existing technology, and will not be elaborated in this embodiment.

[0104] Step S004: Construct a urban industrial system network based on all industrial system elements. After partitioning the urban industrial system network into communities, several industrial communities are obtained. Based on each industrial community, several digital twins for urban planning are acquired.

[0105] It should be noted that after obtaining all industrial system elements composed of all downstream industrial elements and their respective upward-related industrial elements, one industrial system element represents the relationship between two adjacent links of an industrial system in the city. And all industrial systems in the city are connected due to this kind of association. Then, by constructing a urban industrial system network based on the relationship network structure with all industrial system elements, and then partitioning the urban industrial system network, several industrial communities are obtained. Furthermore, digital twins are constructed for each industrial community, and several digital twins for urban planning are obtained.

[0106] Specifically, construct a urban industrial system network based on the relationship network structure. The urban industrial system network is a topological structure. Each node in the urban industrial system network represents the first industrial element. If two nodes can form an industrial system element, then the industrial system correlation coefficient between the downstream industrial element and the upward-related industrial element in this industrial system element is used as the degree of the urban industrial system network.

[0107] It should be noted that the industrial system referred to in this embodiment is a unidirectional industrial system. Therefore, the two nodes presenting industrial system elements in the urban industrial system network point from the upstream link to the downstream link. Thus, the degree of the node is unique and has a direction.

[0108] Furthermore, in this embodiment, the Louvain algorithm is used to partition the urban industrial system network into communities, obtaining several industrial communities. The historical output of industrial elements in each community on all dates is used as the data basis for generating a digital twin, and several digital twins for urban planning are obtained. The industrial relationships between the digital twins do not interfere with each other.

[0109] It should be noted that the Louvain algorithm described in this embodiment is a well-known existing technology and will not be elaborated in this embodiment.

[0110] It should be noted that the model used in this embodiment only represents a negative correlation relationship and restricts the output result of the model to be within the interval, where is the input of this model. In specific implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description and is not specifically limited.

[0111] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for constructing a digital twin for urban planning, characterized in that: The method comprises the following steps: Get the daily output of each industrial element in the preset date sequence; According to the consistency of the output change of each industrial element with other industrial elements and the difference of time lag in the output under the consistency condition, the time lag consistency coefficient of each industrial element with other industrial elements is obtained; Based on the time-lag consistency coefficient, the downstream industrial elements of each industrial element are screened to obtain all the upstream industrial elements of each downstream industrial element; According to the covariation relationship of the output between all the upstream industrial elements of each downstream industrial element as the raw materials of the same link, the consistency of the output change of each upstream industrial element under each downstream industrial element is obtained; According to the consistency of the output change of each upstream industrial element under the downstream industrial element, combined with the time-lag consistency coefficient of the corresponding industrial element, several industrial system elements are obtained; Construct an urban industrial system network based on all industrial system elements, divide the urban industrial system network into communities to obtain several industrial communities, and obtain several digital twins for urban planning based on each industrial community; The specific steps of obtaining the time-lag consistency coefficient include: For the i-th industrial element, obtain all production date segments of the i-th industrial element and all matching production date segments in the m-th suspected downstream industrial element of the i-th industrial element; The time-lag consistency coefficient between the i-th industrial element and the m-th suspected downstream industrial element The calculation method is: in, represents the variance function; is an exponential function with a natural constant as base; is the median date of the k-th production date segment of the i-th industrial element, The median date of the kth matching production date segment in the mth suspected downstream industrial element of the i-th industrial element; The specific steps for obtaining the consistency of the output change include: The time-lag consistency coefficient between the ith industrial element and the nth downstream industrial element of the ith industrial element is recorded as the time-lag consistency coefficient between the nth downstream industrial element and the nth downstream industrial element. The time-lag consistency coefficient of the upstream industrial elements; In the nth downstream industrial element In the date sequence of each covariant contributing industrial element of the upstream industrial element, obtain the date sequence of the first The sequence segment with the same production date segment date as the kth production date segment of the nth downstream industrial element is recorded as the The k-th production date segment under each covariant contributing industrial element of the upstream industrial elements; The nth downstream industrial element Consistency of production changes of upstream industrial elements The calculation method is: in, To find the function of Pearson correlation coefficient; The nth downstream industrial element The number of covariant contributing industrial elements of the upstream industrial elements, The nth downstream industrial element The number of production date segments of each upstream industrial element; The nth downstream industrial element The sequence of the production of the kth production date segment of the upstream industrial elements, The nth downstream industrial element The sequence of the covariant contributions of the upstream industrial elements and the production of the industrial elements in the k-th production date segment.

2. A method for constructing a digital twin for urban planning according to claim 1, characterized in that: The specific steps of obtaining the production date segment include: Use the dynamic time warping algorithm to dynamically match the daily output of the i-th industrial element with the j-th industrial element except the i-th industrial element, and obtain the daily output matching day of the i-th industrial element on the j-th industrial element; If the date sequence value of the second day's output matching day of the i-th industrial element is greater than or equal to 2, the j-th industrial element is recorded as the suspected downstream industrial element of the i-th industrial element; Obtain all the minimum values ​​of the sequence composed of the daily output of the ith industrial element, and record the date sequence composed of all dates between two adjacent minimum values ​​and including the first minimum value of the two minimum values ​​as a production date segment of the ith industrial element.

3. A method for constructing a digital twin for urban planning according to claim 2, characterized in that: The specific steps of obtaining the matching production date segment include: The first date in the k-th production date segment of the i-th industrial element, the production matching date in the date sequence of the m-th suspected downstream industrial element of the i-th industrial element, is recorded as the first day of the k-th matching production date segment in the m-th suspected downstream industrial element of the i-th industrial element; The last date in the k-th production date segment, the production matching date in the date sequence of the m-th suspected downstream industrial element of the i-th industrial element, is recorded as the last day of the k-th matching production date segment in the m-th suspected downstream industrial element of the i-th industrial element; The sequence consisting of all dates between the first day and the last day of the kth matching production date segment in the mth suspected downstream industrial element is recorded as the kth matching production date segment in the mth suspected downstream industrial element of the ith industrial element.

4. A method for constructing a digital twin for urban planning according to claim 1, characterized in that: The specific steps of obtaining the upstream industrial elements include: A time lag consistency threshold is preset, and when the time lag consistency coefficient between the ith industrial element and the mth suspected downstream industrial element is greater than or equal to the time lag consistency threshold, the mth suspected downstream industrial element of the ith industrial element is recorded as the downstream industrial element of the ith industrial element; For the nth downstream industrial element of the ith industrial element, the ith industrial element is recorded as the nth downstream industrial element. An upstream industrial element.

5. A method for constructing a digital twin for urban planning according to claim 1, characterized in that: The specific steps of obtaining the covariant contribution industrial elements include: Among all the upstream industrial elements of the nth downstream industrial element, except the The other upstream industrial elements except the first upstream industrial element are recorded as the nth downstream industrial element. The covariant contribution of upstream industrial elements to industrial elements.

6. A method for constructing a digital twin for urban planning according to claim 1, characterized in that: The specific steps of obtaining the industrial system elements include: Obtain the industrial system correlation coefficients of all upstream industrial elements under the nth downstream industrial element, perform linear normalization on the industrial system correlation coefficients of all upstream industrial elements under the nth downstream industrial element to obtain the normalized value of the industrial system correlation coefficient of each upstream industrial element under the nth downstream industrial element, use the Otsu threshold algorithm to perform maximum difference segmentation on the normalized value of the industrial system correlation coefficient, and use all upstream industrial elements in the largest part of the two after the segmentation as several upwardly associated industrial elements of the nth downstream industrial element; The industrial system correlation coefficient of the upstream industrial element corresponding to each upwardly associated industrial element of the nth downstream industrial element is used as the industrial system correlation coefficient of each upwardly associated industrial element of the nth downstream industrial element; each downstream industrial element and each of its upwardly associated industrial elements constitute an industrial system element.

7. A method for constructing a digital twin for urban planning according to claim 6, characterized in that: The specific steps of obtaining the industrial system correlation coefficient include: The nth downstream industrial element Industrial system correlation coefficient of upstream industrial elements The calculation method is: in, The relationship between the nth downstream industrial element and the nth downstream industrial element The time-lag consistency coefficient of the upstream industrial elements, For the nth downstream industrial element The consistency of output changes of upstream industrial elements.

8. A method for constructing a digital twin for urban planning according to claim 1, characterized in that: The urban industrial system network is constructed according to all industrial system elements, and a number of industrial communities are obtained after the urban industrial system network is divided into communities. A number of digital twins for urban planning are obtained based on each industrial community, including: Constructing an urban industrial system network based on a relational network structure, wherein the urban industrial system network is a topological structure, wherein each node in the urban industrial system network represents the first industrial element, and if two nodes can constitute an industrial system element, the industrial system correlation coefficient between the downstream industrial element and the upwardly associated industrial element in the industrial system element is used as the degree of the urban industrial system network; The urban industrial system network is divided into communities through the Leuven algorithm to obtain several industrial communities. The output of industrial elements in each community on all dates is used as the data basis for generating a digital twin, thus obtaining several digital twins for urban planning.

Images