Digital Twin Target Category Determination Method, Device, Medium and Electronic Device

Abstract

The present application provides a method, apparatus, medium and electronic device for determining the digital twin target category, which relates to the field of digital twin technology, and includes: collecting the basic data of each preset area of the actual target corresponding to the digital twin target to obtain a basic data list set S; obtaining an attribute expected value list set X according to S and an attribute classification model; obtaining a target category influence value Z corresponding to the digital twin target according to X; obtaining the category corresponding to the digital twin target according to Z and a preset category determination interval. The present application not only saves computing power and reduces calculation time, but also improves calculation accuracy. Considering the different requirements of different types and degrees for each ability, different weights are set for them, and the evaluation results obtained are more objective and accurate.

Description

Background Art

[0002] Digital twin is a technical means that maps, interacts bidirectionally, and deeply integrates a physical entity with its virtual digital model in real time, and is widely used in many fields such as manufacturing, smart cities, transportation, and energy management. By building a digital twin platform, enterprises and organizations can achieve all-round digital presentation, simulation analysis, and optimized decision-making support for physical assets, processes, systems, etc. With the rapid development of digital twin technology, more and more physical institutions have built their own digital twin platforms, aiming to improve operational efficiency, reduce costs, and improve product quality with its powerful functions.

[0003] Digital twin platforms have multiple capability interfaces, and each capability interface is used to implement certain functions. Different application scenarios, different developers, and different users have their own different understandings and factors to consider when evaluating the quality of digital twin platforms. For example, manufacturing enterprises may be more concerned about the accuracy and effectiveness of digital twin platforms in production process simulation and equipment failure prediction; while managers in the field of smart cities focus on the accuracy and timeliness of the platform's simulation of urban resource allocation and emergency response. The existing evaluation methods for digital twin platforms lack a unified standard, making it difficult to conduct objective and fair horizontal comparisons between different digital twin platforms, and it is also not conducive to users accurately judging the actual value of the platforms they use and finding directions for improvement.

[0004] In view of the many deficiencies in the above-mentioned existing technologies, how to establish a set of scientific, comprehensive, and objective evaluation systems and methods to accurately evaluate the digital twin platforms that have been built has become an important technical problem to be solved urgently. Summary of the Invention

[0005] In view of the above technical problems, the present application provides a method, device, medium, and electronic device for determining digital twin target categories, which at least partially solve the problems existing in the prior art.

[0006] In the first aspect of the present application, a method for determining digital twin target categories is provided. The method includes the following steps:

[0007] S100, collect the basic data of each preset area of the actual target corresponding to the digital twin target to obtain a basic data list set S = (S 1 , S 2 , …, S i , …, S n ); i = 1, 2, …, n; where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area;

[0008] S200, based on S and the attribute classification model, obtain the set of attribute expected value lists X = (X 1 , X 2 , …, X i , …, X n ); where X i is the list of attribute expected values corresponding to the i-th preset area; X i = (X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, …, m; m is the number of attributes of the digital twin target; X i，j is the attribute expected value of the j-th attribute corresponding to the i-th preset area;

[0009] S300, based on X, obtain the target category influence value Z = Σ m j=1 (G j × N j ); where N j is the attribute matching degree corresponding to the j-th attribute of the digital twin target; and N j is determined according to the target attribute category and the actual attribute category of the j-th attribute of the digital twin target; G j is the comprehensive expected value corresponding to the j-th attribute of the digital twin target; G j = Σ n i=1 (X i，j × M i ); M i is the area matching degree corresponding to the i-th preset area;

[0010] S400, based on Z and the preset category determination interval, obtain the category of the digital twin target.

[0011] In the second aspect of the present application, there is provided a digital twin target category determination device, and the device includes:

[0012] An acquisition unit, configured to acquire the basic data of each preset area of the actual target corresponding to the digital twin target, so as to obtain a set of basic data lists S = (S 1 , S 2 , …, S i , …, S n ); i = 1, 2, …, n; where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area;

[0013] An expected value determination unit, configured to obtain a set of attribute expected value lists X = (X 1, X 2 , …, X i , …, X n ); where, X i is the list of expected attribute values corresponding to the i-th preset area; X i = (X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, …, m; m is the number of attributes of the digital twin target; X i，j is the expected attribute value of the j-th attribute corresponding to the i-th preset area;

[0014] The influence value determination unit is used to obtain the target category influence value Z = Σ m j=1 (G j ×N j ) according to X; where, N j is the attribute matching degree corresponding to the j-th attribute of the digital twin target; and N j is determined according to the target attribute category and the actual attribute category of the j-th attribute of the digital twin target; G j is the comprehensive expected value corresponding to the j-th attribute of the digital twin target; G j = Σ n i=1 (X i，j ×M i ); M i is the area matching degree corresponding to the i-th preset area;

[0015] The category determination unit obtains the category of the digital twin target according to Z and the preset category determination interval.

[0016] In the third aspect of the present application, a non-transitory computer-readable storage medium is provided, and at least one instruction or at least one program segment is stored in the storage medium, and at least one instruction or at least one program segment is loaded and executed by a processor to implement the foregoing digital twin target category determination method.

[0017] In the fourth aspect of the present application, an electronic device is provided, including a processor and the foregoing non-transitory computer-readable storage medium.

[0018] The present application has at least the following beneficial effects:

[0019] The digital twin target category determination method provided by this application obtains the basic data of the actual target corresponding to the constructed digital twin target, obtains the demand degree of the actual target for each attribute (ability) required for constructing the digital twin target, and then evaluates the constructed digital twin target according to the actual utility degree of each attribute (ability) in the constructed digital twin target and the demand degree (the actual usage degree that should be achieved) of each attribute (ability) required for constructing the digital twin target. On the one hand, considering that different types of digital twin cities have different demand degrees for different attributes (abilities), by dividing the actual target into smaller regions, the demand degree of the actual target for each attribute (ability) is judged, and then the comprehensive demand degree of the entire city for each ability is obtained, which not only saves computing power, reduces computing time, but also improves computing accuracy. Considering the different demands of different types for each ability, different weights are set for them, and the evaluation results obtained are more objective and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of this application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this application, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of the digital twin target category determination method provided by the embodiment of this application;

[0022] Figure 2 It is a structural block diagram of the digital twin target category determination device provided by the embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings in the embodiments of this application. Obviously, the described embodiments are only some embodiments of this application, rather than all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is only illustrative. Based on this application, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0026] Please refer to Figure 1 As shown, an embodiment of this application provides a method for determining a digital twin target category. The method includes the following steps:

[0027] S100, collect the basic data of each preset area of the actual target corresponding to the digital twin target to obtain a basic data list set S=(S 1 , S 2 , …, S i , …, S n ); i = 1, 2, …, n; where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area.

[0028] Specifically, in this embodiment, the digital twin target is a digital twin city that has been constructed. The digital twin city includes an application layer, a capability component layer, and a twin body layer. Among them, the capability component layer is various capabilities required to build a digital twin city, including: Internet of Things perception and control capability, 3D model construction capability, visualization rendering capability, data fusion and supply capability, spatio-temporal analysis and calculation capability, simulation and deduction capability, virtual-real fusion interaction capability, self-learning and self-optimization capability, and mass innovation and extended application capability. These capabilities are used to process and analyze the collected data.

[0029] It should be noted that for different digital twin cities, due to different demand emphases, the demand degrees for each ability are different. As an example, for heavy traffic cities and heavy industrial cities, the demands for abilities are different when constructing digital twin cities. And the demand for abilities is reflected in the ability levels. Each ability has a corresponding level. The higher the level, the more mature and perfect the ability is, and the higher the application frequency, etc.

[0030] In this embodiment, the actual target corresponding to the digital twin target is the actual city corresponding to the digital twin city. In the construction of the digital twin platform, data collection is the foundation. Here, the actual city corresponding to the digital twin city is divided into several preset regions. Here, the division of the preset regions can be carried out according to the preset region shapes to obtain grid-like regions. Among them, the regions close to the city edge may not fill the corresponding grid-like regions completely. It can also be divided according to other region division methods. Then, according to each divided preset region, data collection is carried out respectively to obtain the basic data list set S. Here, it can be understood that the data included in the basic data list is all the data to be collected for the actual city corresponding to the digital twin city.

[0031] S200, according to S and the attribute classification model, obtain the attribute expected value list set X=(X 1 , X 2 , …, X i , …, X n ); where X i is the attribute expected value list corresponding to the i-th preset region; X i =(X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, …, m; m is the number of attributes corresponding to the digital twin target; X i，j is the attribute expected value of the j-th attribute corresponding to the i-th preset region.

[0032] Specifically, the attribute classification model is used to obtain the demand values, that is, the attribute expected values, of the input data of each preset region for each type of ability. As an example: Encode S i to obtain the corresponding feature vector, and then input it into the attribute classification model to obtain X i =(X i，1 , X i，2 , …, X i，j , …, X i，m ); where X i，jThe expected value of the j-th attribute corresponding to the i-th preset area is the degree of demand of the i-th preset area for the j-th ability required to build a digital twin city. Since the data characteristics and features of each preset area are different, the corresponding output degree of demand for each ability is different. Thus, it reflects the degree of demand for the corresponding ability of each preset area in building a digital twin city.

[0033] S300. According to X, obtain the target category influence value Z = Σ m j=1 (G j ×N j ) ; where N j is the attribute matching degree corresponding to the j-th attribute of the digital twin target; and N j is determined according to the target attribute category and the actual attribute category of the j-th attribute of the digital twin target; G j is the comprehensive expected value corresponding to the j-th attribute of the digital twin target; G j = Σ n i=1 (X i，j ×M i ) ; M i is the area matching degree corresponding to the i-th preset area.

[0034] Specifically, first, according to the actual demand degree of each preset area of the actual city for each ability required to build a digital twin city, obtain the demand degree of the actual city for each ability when building a digital twin city. Here, each preset area has a corresponding area matching degree, and the area matching degree represents the importance of this area compared to other areas for the actual city. If the importance is greater, when calculating the demand degree of the actual city for each ability when building a digital twin city, the proportion it occupies is greater, which means the weight (area matching degree) corresponding to this area is higher. In this way, the final obtained demand degree of the actual city for each ability when building a digital twin city takes into account the importance of each preset area, and the obtained demand degree of the actual city for each ability when building a digital twin city is more accurate.

[0035] Furthermore, after obtaining the demand degree of the actual city for each ability when building a digital twin city, in order to accurately evaluate the already built digital twin city, it is necessary to evaluate whether the application of each ability of the already built digital twin city is appropriate according to the actual application situation (actual attribute category) of each ability in the already built digital twin city and the demand degree of the actual city corresponding to the already built digital twin city for each ability when building a digital twin city (target attribute category) obtained by collecting data. In this embodiment, the target category influence value Z = Σ mj=1 (G j ×N j ); N j is determined according to the target attribute category and the actual attribute category of the j-th attribute of the digital twin target. That is, through N j weights are assigned to the actual demand degrees of each preset area of the actual city for each ability required to build a digital twin city, so that the obtained target category influence value of the built digital twin city is more accurate. Here, if the actual attribute category of a certain attribute (ability) is equal to or greater than the target attribute category, it means that when building a digital twin city, the application degree of this attribute (ability) meets the standard, and the functions that can be realized based on this attribute (ability) are accurate and perfect enough. As an example, for the spatio-temporal analysis function interface, the corresponding actual attribute category is the fifth category (where the categories include a total of five categories: the first category, the second category, the third category, the fourth category, and the fifth category). The higher the corresponding category, the higher the usage frequency and usage accuracy of this ability. And the demand level for the spatio-temporal analysis function interface when building a digital twin city deduced from the basic data of the actual city collected through steps S100 to S300 of this application is the fourth level. Then, it can be known that the usage degree of the built digital twin city for the spatio-temporal analysis function interface is higher than it should be, that is, the usage degree meets the standard. On the contrary, if the actual attribute category of a certain attribute (ability) is less than the target attribute category, it means that when building a digital twin city, the application degree of this attribute (ability) does not meet the standard. Then, the functions that can be realized by the corresponding attribute (ability) of the built digital twin city may not be perfect enough.

[0036] In this embodiment, the target category influence value is determined by the total demand degree of each attribute (ability) of the digital twin city, and corresponding weights are assigned to each attribute (ability). And this weight is obtained according to the actual usage situation (actual attribute category) of each ability in the built digital twin city and the demand degree (target attribute category) of the actual city corresponding to the built digital twin city for each ability obtained by collecting data, so that the obtained target category influence value takes into account the actual usage degree of each attribute (ability) and more accurately reflects the actual usage situation of the built digital twin city for each attribute (ability).

[0037] S400. Determine an interval according to Z and the preset category to obtain the category corresponding to the digital twin target.

[0038] Specifically, the preset category determination interval is used to rate the influence value of the target category. As an example, the preset category determination interval is as follows: 0 - 30 is the first category, 30 - 60 is the second category, 60 - 80 is the third category, and 80 - 100 is the fourth category. According to the above method for determining the influence value of the target category, the larger the influence value of the target category, the higher the score of the digital twin target, the better its effect, and the more reasonable and accurate the use of each ability. Conversely, the smaller the influence value of the target category, the lower the score of the digital twin target, the worse the simulation effect on the actual city, and the use of one or some abilities may not be accurate enough. Thus, the larger the corresponding preset category determination interval, the better the digital twin target effect.

[0039] In this embodiment, by obtaining the basic data of the actual target corresponding to the constructed digital twin target, obtaining the demand degree of the actual target for each attribute (ability) required for constructing the digital twin target, and then evaluating the constructed digital twin target according to the actual practical degree of each attribute (ability) in the constructed digital twin target and the demand degree (the actual usage degree that should be achieved) of each attribute (ability) required for constructing the digital twin target. On the one hand, considering that different types of digital twin cities have different demand degrees for different attributes (abilities), by dividing the actual target into smaller regions to judge the demand degree of the actual target for each attribute (ability), and then obtaining the comprehensive demand degree of the entire city for each ability, which not only saves computing power, reduces calculation time, but also improves calculation accuracy. Considering the different demands of different types for each ability, different weights are set for them, and the obtained evaluation results are more objective and accurate.

[0040] In an exemplary embodiment of the present application, N j is determined according to the following steps:

[0041] S310, according to G j and the preset attribute category determination interval, obtain the target attribute category MG j corresponding to G j .

[0042] S320, obtain the actual attribute category JG j of the jth attribute corresponding to the digital twin target.

[0043] S330, if JG j ≥MG j , then N j =1.

[0044] S340, if JG j <MG j , then N j =JGj / MG j 。

[0045] In this embodiment, if JG j ≥MG j , that is, the actual attribute category is equal to or greater than the target attribute category, it indicates that when constructing the digital twin city, the application degree of this attribute (ability) meets the standard, and the functions that can be realized based on this attribute (ability) are accurate and perfect enough. At this time, set its corresponding weight to 1. On the contrary, if JG j <MG j , the actual attribute category is less than the target attribute category, it indicates that when constructing the digital twin city, the application degree of this attribute (ability) does not meet the standard. Then, the functions that can be realized by the corresponding attribute (ability) of the constructed digital twin city may not be perfect enough. At this time, the corresponding weight is less than 1, and the more the actual attribute category is less than the target attribute category, the smaller the corresponding weight, that is, the lower the score corresponding to this attribute (ability), and it will further lead to a lower score of the digital twin target.

[0046] In an exemplary embodiment of the present application, M i is determined according to the following steps:

[0047] S350. Obtain the floating population quantity of each preset area to obtain a floating population quantity list L = (L 1 , L 2 , …, L i , …, L n ); where L i is the floating population quantity corresponding to the i-th preset area.

[0048] S360. According to L, obtain M i ; where M i meets the following conditions: M i =L i / MAX(L); MAX() is a preset maximum value determination function.

[0049] In this embodiment, the regional matching degree of each preset area is determined according to the floating population quantity of each preset area. Here, the more the floating population quantity, the more important the area is, and the higher the corresponding weight. M i =L i / MAX(L), that is, the weight of the preset area with the largest floating population is 1, and it is the most important compared with other preset areas. For other preset areas, the weights are all less than 1, and the more the floating population quantity, the greater the weight. Taking this as the regional matching degree of each preset area reflects the importance degree of each preset area and makes the obtained comprehensive expected value more accurate.

[0050] In an exemplary embodiment of the present application, after step S100, the method further includes:

[0051] S500, obtaining m attribute classification sub-models corresponding to the digital twin target; wherein each attribute classification sub-model has a corresponding attribute; and the attributes corresponding to any two attribute classification sub-models are different.

[0052] S600, according to S and the m attribute classification sub-models, obtaining a key attribute expected value list set X'=(X 1 ', X 2 ', …, X i ', …, X n '); wherein X i ' is the key attribute expected value list corresponding to the i-th preset area; X i '=(X i，1 ', X i，2 ', …, X i，j ', …, X i，m '); X i，j ' is the key attribute expected value of the j-th attribute corresponding to the i-th preset area obtained according to the j-th attribute classification sub-model.

[0053] S700, according to X', obtaining a target category influence value Z'=Σ m j=1 (G j '×N j ); wherein G j ' is the key comprehensive expected value corresponding to the j-th attribute of the digital twin target; G j '=Σ n i=1 (X i，j '×M i ).

[0054] S800, according to Z' and a preset category determination interval, obtaining the category corresponding to the digital twin target.

[0055] In this embodiment, there are multiple classification models, that is, for each attribute (ability), a corresponding attribute classification sub-model is trained. Compared with the requirement degree of using only one attribute classification model to obtain each attribute (ability), the requirement degree of the attribute (ability) output by the attribute classification sub-model trained in the vertical field for each attribute (ability) is more accurate.

[0056] It can be understood that in use, S i is respectively input into the m attribute classification sub-models to obtain X i '=(X i，1 ', X i，2 ', …, Xi，j ’, …, X i，m ’). X i，j ’ is the key attribute expected value of the j-th attribute corresponding to the i-th preset region obtained by inputting S i into the j-th attribute classification sub-model.

[0057] In an exemplary embodiment of the present application, the preset region can be determined according to the following steps:

[0058] S110, obtain the population density distribution map corresponding to the actual target; wherein, the pixel value of each pixel point in the population density distribution map represents the population density of the physical region corresponding to the pixel point.

[0059] S120, segment the population density distribution map according to the superpixel segmentation algorithm to obtain a number of preset sub-regions; wherein, the difference between any two pixel values within each preset sub-region is less than a preset first pixel value difference threshold.

[0060] Specifically, the superpixel algorithm aims to over-segment the image into multiple relatively uniform and small regions (superpixels) with similar features. Compared with traditional pixel-level processing, it can greatly reduce the amount of data processed by subsequent algorithms while retaining the main structure and feature information of the image. Therefore, the difference between any two pixel values within each preset sub-region is less than a preset first pixel value difference threshold. Further, in this embodiment, the superpixel algorithm can be the SLIC algorithm, that is, the Simple Linear Iterative Clustering algorithm.

[0061] S130, perform region merging according to the watershed algorithm to obtain a number of preset intermediate regions; wherein, the difference between any two pixel values within each preset intermediate region is less than a preset second pixel value difference threshold; the second pixel value difference threshold is greater than the first pixel value difference threshold.

[0062] Specifically, the watershed algorithm first constructs a color difference gradient map (virtual terrain), that is, calculates the color difference between superpixels: traverse each superpixel region, calculate the color difference between it and adjacent superpixel regions, and the color distance calculation formula in the corresponding color mode can also be used (such as the Euclidean distance calculation method based on the differences of each color component in the RGB mode). Take this color difference value as the basis for measuring the "height difference" between superpixels. Just like constructing the height change of the terrain based on grayscale values in the traditional watershed algorithm, here a virtual terrain height situation is constructed based on color differences. Secondly, generate a gradient map: According to the calculation results of the color differences between superpixels, assign corresponding "gradient values" (i.e., color difference values) to the pixel points on the boundary of each superpixel, thereby constructing a gradient map that reflects the degree of color change between superpixel regions. Where the gradient value is large, it indicates a large color change, equivalent to a steep slope in the terrain, and where the gradient value is small, the color change is gentle, similar to flat ground in the terrain. This gradient map will be used as the "virtual terrain" for subsequent simulation of water flow convergence. After that, mark the seed regions (initial regions). Then, select the seed regions based on superpixel features, that is, from the existing superpixel regions, select some as seed regions for marking according to features such as the area size and color uniformity of the superpixels. For example, an area threshold can be set, and superpixel regions with an area larger than the threshold and relatively small internal color differences (measured by calculating statistical indicators such as the variance of pixel colors within the superpixel) are marked and given different marking values (such as using different integers to identify different seed regions). These marking values will guide the division and expansion of regions during the subsequent simulation of the water flow process. Finally, based on the constructed color difference gradient map (virtual terrain), simulate the water flow convergence process according to the principle of the watershed algorithm. Starting from the marked seed regions, let the "water flow" (which can be understood as the expansion trend of the region) flow along the direction with small color differences (that is, similar colors), and gradually divide into different connected regions. During this process, since the seed regions have been marked and the water flow tends to flow along the direction of similar colors, it will naturally move in the direction of dividing pixel points with similar colors together and separating from adjacent regions with large color differences, and finally form multiple connected regions.

[0063] S140, obtain the area of each preset intermediate region.

[0064] S150, if the area of the preset intermediate region Y p is less than the preset intermediate region area threshold, then obtain each preset intermediate region adjacent to Y p to obtain an adjacent region list J = (J p，1 , J p，2 , …, J p，e , …, J p，f ); e = 1, 2, …, f; where f is the number of regions adjacent to Yp The number of adjacent preset intermediate regions; J p，e For Y p The region identifier Y of the e-th preset intermediate region adjacent to Y e .

[0065] S160. Obtain the list BYC of absolute differences in average pixel values according to J p =(BYC p，1 , BYC p，2 , …, BYC p，e , …, BYC p，f ); where BYC p，e is the absolute difference in average pixel values between Y p and Y e ; BYC p，e =|BY e -BY P |; BY e is the regional average pixel value corresponding to Y e ; BY P is the regional average pixel value corresponding to Y p .

[0066] S170. If BYC p，e =MIN(BYC p ), and BYC p，e is less than the preset average pixel value difference threshold, then fuse Y p and Y e to obtain n preset regions; where MIN() is a preset minimum value determination function.

[0067] Specifically, after the watershed algorithm, there may still be some small connected regions that do not meet the final requirements and need to be fused into adjacent large connected regions to further optimize the segmentation result. Then, obtain the adjacent intermediate regions of the preset intermediate regions with smaller areas. If the average pixel value difference threshold between them is the smallest and less than the preset average pixel value difference threshold, then perform fusion.

[0068] In this embodiment, n preset regions are obtained according to the population density. There is a certain difference in population density between any two preset regions. Each preset region is formed according to the population density. Compared with the relatively uniform physical regions divided manually, the method for determining the preset regions provided in this embodiment can better reflect the population distribution, and then assign different region matching degrees to them, which can better reflect the importance of each preset region and make the final evaluation result more accurate and objective.

[0069] Please refer to Figure 2 shown. An embodiment of the present application provides a digital twin target category determination device 100, and the device includes:

[0070] The acquisition unit 110 is configured to acquire the basic data of each preset area of the actual target corresponding to the digital twin target, so as to obtain a basic data list set S = (S 1 , S 2 , …, S i , …, S n ); i = 1, 2, …, n; where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area.

[0071] The expected value determination unit 120 is configured to obtain an attribute expected value list set X = (X 1 , X 2 , …, X i , …, X n ) according to S and the attribute classification model; where X i is the attribute expected value list corresponding to the i-th preset area; X i = (X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, …, m; m is the number of attributes of the digital twin target; X i，j is the attribute expected value of the j-th attribute corresponding to the i-th preset area.

[0072] The influence value determination unit 130 is configured to obtain the target category influence value Z = Σ m j=1 (G j × N j ) according to X; where N j is the attribute matching degree corresponding to the j-th attribute of the digital twin target; and N j is determined according to the target attribute category and the actual attribute category of the j-th attribute of the digital twin target; G j is the comprehensive expected value corresponding to the j-th attribute of the digital twin target; G j = Σ n i=1 (X i，j × M i ); M i is the area matching degree corresponding to the i-th preset area.

[0073] The category determination unit 140 obtains the category corresponding to the digital twin target according to Z and the preset category determination interval.

[0074] Embodiments of the present application also provide a computer program product, which includes program code. When the program product runs on an electronic device, the program code is used to cause the electronic device to execute the steps in the methods according to various exemplary embodiments of the present application described above in this specification.

[0075] In addition, although the steps of the methods in the present application are described in a specific order in the drawings, this does not require or imply that these steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0076] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the methods according to the embodiments of the present application.

[0077] In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0078] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method, or a program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuitry", "module", or "system" here.

[0079] An electronic device according to this embodiment of the present application. The electronic device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0080] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: at least one of the above-mentioned processors, at least one of the above-mentioned memories, and a bus connecting different system components (including the memory and the processor).

[0081] Among them, the memory stores program code, and the program code can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present application described in the above "Exemplary Methods" section of this specification.

[0082] The memory may include a readable medium in the form of volatile memory such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0083] The memory may also include program / utility with a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of or some combination of these examples may include the implementation of a network environment.

[0084] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures.

[0085] The electronic device may also communicate with one or more external devices (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device, and / or communicate with any device that enables the electronic device to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be through an input / output (I / O) interface. And, the electronic device may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through the bus. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0086] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on the network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0087] In an exemplary embodiment of the present application, a computer-readable storage medium is further provided, on which a program product capable of implementing the above methods in this specification is stored. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0088] The program product can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0089] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0090] The program code included on the readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0091] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0092] In addition, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0093] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0094] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining a digital twin target category, characterized in that: The method comprises: S100, collecting basic data of each preset area of ​​the actual target corresponding to the digital twin target to obtain a basic data list set S=(S1, S2, ..., S i , …, S n ), i=1, 2, ..., n, where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area; S200, based on S and the attribute classification model, obtain the attribute expected value list set X=(X1, X2, …, X i , …, X n ), where X i is the attribute expected value list corresponding to the i-th preset area; X i =(X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, ..., m; m is the number of attributes corresponding to the digital twin target; X i，j is the expected value of the jth attribute corresponding to the i-th preset area; S300, based on X, obtain the target category impact value Z=Σ corresponding to the digital twin target m j=1 (G j ×N j ); where N j is the attribute matching degree corresponding to the jth attribute of the digital twin target; and N j It is determined based on the target attribute category and actual attribute category of the jth attribute of the digital twin target; G j is the comprehensive expected value corresponding to the jth attribute of the digital twin target; G j =Σ n i=1 (X i，j ×M i ); M i is the area matching degree corresponding to the i-th preset area; S400, determining an interval according to Z and a preset category, and obtaining a category corresponding to the digital twin target; M i Follow these steps to determine: S350, obtaining the number of floating population in each preset area to obtain a floating population list L=(L1, L2, ..., L i , …, L n ), where L i is the number of floating population corresponding to the i-th preset area; S360, according to L, get M i ; Among them, M i Meet the following conditions: M i =L i / MAX(L); MAX() is the preset maximum value determination function; N j Follow these steps to determine: S310, according to G j And the preset attribute category determines the interval, and G j Corresponding target attribute category MG j ; S320, obtaining the actual attribute category JG of the jth attribute corresponding to the digital twin target j ; S330, if JG j ≥MG j , then N j =1; After step S320, the method further includes: S340, if JG j <MG j , then N j =JG j / MG j .

2. The method for determining the target category of a digital twin according to claim 1, characterized in that: After step S100, the method further includes: S500, obtaining m attribute classification sub-models corresponding to the digital twin target; wherein each attribute classification sub-model has corresponding attributes; and the attributes corresponding to any two attribute classification sub-models are different; S600, based on S and m attribute classification sub-models, obtain a list set of expected values ​​of key attributes X'=(X1', X2', ..., X i ', ..., X n '); where X i ' is the expected value list of key attributes corresponding to the i-th preset area; X i '=(X i，1 ', X i，2 ', ..., X i，j ', ..., X i，m ');X i，j ' is the expected value of the key attribute of the jth attribute corresponding to the i-th preset area obtained according to the j-th attribute classification sub-model; S700, according to X', obtain the target category impact value Z'=Σ m j=1 (G j '×N j ); where G j ' is the key comprehensive expected value corresponding to the jth attribute of the digital twin target; G j '=Σ n i=1 (X i，j '×M i ); S800, determine the interval according to Z' and the preset category, and obtain the category corresponding to the digital twin target.

3. The method for determining the target category of a digital twin according to claim 1, characterized in that: The preset area is determined according to the following steps: S110, obtaining a population density distribution map corresponding to the actual target; wherein the pixel value of each pixel point in the population density distribution map represents the population density of the physical area corresponding to the pixel point; S120, segmenting the population density distribution map according to a superpixel segmentation algorithm to obtain a plurality of preset sub-regions; wherein the difference between any two pixel values ​​in each preset sub-region is less than a preset first pixel value difference threshold; S130, performing region merging according to a watershed algorithm to obtain a plurality of preset intermediate regions; wherein the difference between any two pixel values ​​in each preset intermediate region is less than a preset second pixel value difference threshold; and the second pixel value difference threshold is greater than the first pixel value difference threshold; S140, obtaining the area of ​​each preset middle area; S150, if the middle area Y is preset p The area of ​​the region is smaller than the preset middle area threshold, then the p Each adjacent preset middle area, to obtain the adjacent area list J = (J p，1 , J p，2 , …, J p，e , …, J p，f ), e=1, 2, ..., f, where f is the p The number of adjacent preset intermediate areas; J p，e For Y p The region identifier Y of the adjacent e-th preset middle region e ; S160, according to J, obtain the average pixel value absolute difference list BYC p =(BYC p，1 , BYC p，2 ,…,BYC p，e ,…,BYC p，f ); Among them, BYC p，e Y p With Y e The average absolute difference of pixel values ​​between p，e =|BY e -BY P | BY e Y e The corresponding area average pixel value; BY P Y p The corresponding area average pixel value; S170, if BYC p，e =MIN(BYC p ), and BYC p，e If the average pixel value difference is less than the preset threshold, Y p With Y e Perform regional fusion to obtain n preset regions; wherein MIN() is a preset minimum value determination function.

4. The method for determining the digital twin target category according to claim 3 is characterized in that: After step S110, the method further includes: S001, normalize the pixel values ​​of the population density distribution map.

5. A digital twin target category determination device, characterized in that: The device comprises: The acquisition unit is used to collect the basic data of each preset area of ​​the actual target corresponding to the digital twin target to obtain a basic data list set S=(S1, S2, ..., S i , …, S n ), i=1, 2, ..., n, where n is the number of preset areas; S i is the basic data list corresponding to the i-th preset area; The expected value determination unit is used to obtain the attribute expected value list set X=(X1, X2, …, X i , …, X n ), where X i is the attribute expected value list corresponding to the i-th preset area; X i =(X i，1 , X i，2 , …, X i，j , …, X i，m ); j = 1, 2, ..., m; m is the number of attributes corresponding to the digital twin target; X i，j is the expected value of the jth attribute corresponding to the i-th preset area; The influence value determination unit is used to obtain the target category influence value Z=Σ corresponding to the digital twin target according to X. m j=1 (G j ×N j ); where N j is the attribute matching degree corresponding to the jth attribute of the digital twin target; and N j It is determined based on the target attribute category and actual attribute category of the jth attribute of the digital twin target; G j is the comprehensive expected value corresponding to the jth attribute of the digital twin target; G j =Σ n i=1 (X i，j ×M i ); M i is the area matching degree corresponding to the i-th preset area; A category determination unit determines the interval according to Z and the preset category to obtain the category corresponding to the digital twin target; M i Follow these steps to determine: Get the number of floating population in each preset area to obtain a floating population list L=(L1, L2, ..., L i , …, L n ), where L i is the number of floating population corresponding to the i-th preset area; According to L, we get M i ; Among them, M i Meet the following conditions: M i =L i / MAX(L); MAX() is the preset maximum value determination function; N j Follow these steps to determine: S310, according to G j And the preset attribute category determines the interval, and G j Corresponding target attribute category MG j ; S320, obtaining the actual attribute category JG of the jth attribute corresponding to the digital twin target j ; S330, if JG j ≥MG j , then N j =1; After step S320, the method further includes: S340, if JG j <MG j , then N j =JG j / MG j .

6. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method as claimed in any one of claims 1 to 4.

7. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 6.

Images