Smart city evaluation method and system based on artificial intelligence

Abstract

The invention relates to the technical field of smart city evaluation, in particular to a smart city evaluation method and system based on artificial intelligence. The method comprises the following steps: acquiring a smart city evaluation index, acquiring a city ground environment image through a satellite image acquisition system, analyzing the city ground environment image, an appearance evaluation index and an appearance index weight coefficient, and generating an appearance characterization value of the smart city; to-be-evaluated city data of the smart city are obtained, the to-be-evaluated city data comprise city network data, city logistics data, city community data and city traffic data, the to-be-evaluated city data, the non-appearance evaluation indexes and the non-appearance index weight coefficients, and non-appearance characterization values of the smart city are generated; and determining the smart city grade corresponding to the to-be-evaluated smart city according to the appearance characterization value and the non-appearance characterization value. The smart city evaluation method and device can improve the accuracy of smart city evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of smart city evaluation, and particularly relates to a smart city evaluation method and system based on artificial intelligence. Background Art

[0002] With the acceleration of the urbanization process, the concept of smart city has gradually gained popularity and become an important means to improve urban management efficiency and residents' living quality. Smart cities integrate advanced technologies such as information and communication technology, Internet, Internet of Things, and artificial intelligence to achieve intelligent management and optimization of urban infrastructure. However, how to scientifically and effectively evaluate the construction achievements of smart cities has become a major challenge in current urban management.

[0003] However, there are still many deficiencies in the existing smart city evaluation methods based on artificial intelligence. For example, some methods only focus on the evaluation of a single field or aspect, lacking comprehensiveness and systematicness; some methods have limited data processing and analysis capabilities and are difficult to deeply explore the potential value of urban data; some methods are too complex and not easy to be applied and promoted in practice.

[0004] Therefore, there is an urgent need for a smart city evaluation method and system based on artificial intelligence to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a smart city evaluation method and system based on artificial intelligence: to solve the technical problem that the existing technology lacks comprehensiveness and systematicness in the evaluation of smart cities, resulting in inaccurate evaluation.

[0006] The purpose of the present invention can be achieved by the following technical solutions: On the one hand, a smart city evaluation method based on artificial intelligence, the method includes: Obtain smart city evaluation indicators, where the smart city evaluation indicators include appearance evaluation indicators and non-appearance evaluation indicators; Collect urban ground environment images through a satellite image acquisition system, analyze the urban ground environment images, appearance evaluation indicators, and appearance index weight coefficients to generate an appearance characterization value of the smart city; Obtain the to-be-evaluated urban data of the smart city, where the to-be-evaluated urban data includes urban network data, urban logistics data, urban community data, and urban traffic data, and generate a non-appearance characterization value of the smart city for the to-be-evaluated urban data, non-appearance evaluation indicators, and non-appearance index weight coefficients; Generate a smart level characteristic value of the to-be-evaluated smart city according to the appearance characterization value and the non-appearance characterization value, and determine the corresponding smart city level of the to-be-evaluated smart city based on the smart level characteristic value.

[0007] Further, obtaining the appearance index weight coefficient specifically includes the following process: Obtain m objects to be evaluated in the urban ground environment image. The number of appearance evaluation indicators is n, and an original data matrix of the corresponding evaluation indicators of the objects to be evaluated is formed : ; Among them, is the evaluation value of the jth object to be evaluated under the ith appearance evaluation indicator, where i = 1, 2, 3, …, n; j = 1, 2, 3, …, m; Calculate the proportion of the index value of the jth object to be evaluated under the ith appearance evaluation indicator ; Calculate the entropy value of the ith appearance evaluation indicator , where ; Calculate the weight coefficient of the ith appearance evaluation indicator .

[0008] Further, parsing the urban ground environment image, appearance evaluation indicators, and appearance index weight coefficients to generate the appearance representation value of the smart city specifically includes the following process: Generate multiple urban appearance detection nodes based on the urban ground environment image, and obtain information of multiple urban appearance detection nodes. Among them, the urban appearance detection nodes and appearance evaluation indicators correspond one by one; Obtain the first urban appearance detection node information, the second urban appearance detection node information, and so on until the Gth urban appearance detection node information corresponding to the urban ground environment image. Among them, the first urban appearance detection node information includes the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure. The Gth urban appearance detection node information includes the number of the Gth information infrastructure, the number of the Gth transportation infrastructure, and the number of the Gth environmental protection infrastructure. The number of information infrastructure is the total number of the existence of data centers and Internet of Things sensors. The number of transportation infrastructure is the total number of the existence of intelligent transportation systems, intelligent traffic lights, and intelligent traffic monitoring systems. The environmental protection infrastructure is the total number of the existence of intelligent garbage sorting systems, air quality monitoring stations, and water quality monitoring systems; Sum the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure to obtain the first node representation coefficient until the Gth node representation coefficient is obtained; Multiply the appearance index weight coefficient by the corresponding node representation coefficient, and find the sum value of all products. Denote this sum value as the appearance representation value of the smart city.

[0009] Further, generating multiple urban appearance detection nodes based on the urban ground environment image specifically includes the following process: Segment the urban ground environment image into several partial images, use the position of the center point of each partial image as the detection node, count the number of information infrastructure, transportation infrastructure, and environmental protection infrastructure corresponding to the urban ground environment image, and form the urban appearance detection node information accordingly.

[0010] Further, obtaining the non-appearance index weight coefficient specifically includes the following process: Establish a hierarchical model with a hierarchical structure, where the levels include the target layer, criterion layer, and measure layer; Determine the number h of relevant influencing factors at each level, and construct a set of non-appearance influencing factors , , where is a subset of the urban network completeness rate, is a subset of the urban logistics connectivity rate, is a subset of the urban community information intercommunication rate, is a subset of the urban traffic processing efficiency. Among them, the urban network completeness rate is the degree of connection and interaction between various elements within the city and between the city and the external environment. The urban logistics connectivity rate is the degree of connectivity between nodes in the urban logistics network. The urban community information intercommunication rate is the degree of information transmission and sharing between urban communities. The urban traffic processing efficiency is the efficiency of improving traffic flow under the coordinated action of various traffic modes, traffic facilities, and traffic management measures in the urban traffic system; Take out two subsets at the same level from the set for comparison, use to represent the ratio of importance, and assign the corresponding importance according to a preset ratio. Combine the importance of each layer to form a judgment matrix; Calculate the maximum eigenvalue of the judgment matrix: ; Among them, is the matrix obtained by normalizing each column vector of the judgment matrix, the value of is 1, 2...h, is the matrix obtained by adding the elements of matrix row by row, and then normalizing the resulting vector. is the matrix obtained by adding the elements of matrix column by column, and then normalizing the resulting vector; Calculate the consistency index : ; Among them, represents the order of the judgment matrix, and mark the value as the non-appearance index weight coefficient.

[0011] Further, for the urban data to be evaluated, non-appearance evaluation indicators, and non-appearance indicator weight coefficients, generating the non-appearance representation value of the smart city specifically includes the following process: Obtain the standard urban network completeness rate based on the non-appearance evaluation indicators, obtain the urban network completeness rate of the smart city to be evaluated based on the urban network data, and calculate the difference A between the urban network completeness rate and the standard urban network completeness rate; Obtain the standard urban logistics connectivity rate based on the non-appearance evaluation indicators, obtain the urban logistics connectivity rate of the smart city to be evaluated based on the urban network data, and calculate the difference B between the urban logistics connectivity rate and the standard urban logistics connectivity rate; Obtain the standard urban community information intercommunication rate based on the non-appearance evaluation indicators, obtain the urban community information intercommunication rate of the smart city to be evaluated based on the urban network data, and calculate the difference C between the urban community information intercommunication rate and the standard urban community information intercommunication rate; Obtain the standard urban traffic processing efficiency based on the non-appearance evaluation indicators, obtain the urban traffic processing efficiency of the smart city to be evaluated based on the urban network data, and calculate the difference D between the standard urban traffic processing efficiency and the urban traffic processing efficiency; Substitute the differences A, B, C, D, and the non-appearance indicator weight coefficients into the calculation formula for the non-appearance representation value of the smart city to calculate the non-appearance representation value LMS of the smart city. The calculation formula is as follows: ; where, 、 、 、 4 are the urban network completeness rate coefficient, urban logistics connectivity rate coefficient, urban community information intercommunication rate coefficient, and urban traffic processing efficiency coefficient respectively.

[0012] Further, generating the smart level characteristic value of the smart city to be evaluated according to the appearance representation value and the non-appearance representation value specifically includes the following process: Obtain the appearance representation value and non-appearance representation value generated in each management period. Construct a rectangular coordinate system with the execution time of the management period as the X-axis and the appearance representation value and non-appearance representation value as the Y-axis. Mark all the appearance representation values and non-appearance representation values as points in the rectangular coordinate system. Connect the adjacent points of the appearance representation value and the adjacent points of the non-appearance representation value in the rectangular coordinate system respectively to generate an appearance representation value curve and a non-appearance representation value curve. Draw perpendicular lines from both ends of the appearance representation value curve and the non-appearance representation value curve to the X-axis to obtain four starting and ending line segments. The closed figure is formed by the appearance representation value curve, the non-appearance representation value curve, the four starting and ending line segments, and the X-axis. Calculate the total area of the formed closed figure, and record the total area as the smart level characteristic value of the smart city to be evaluated.

[0013] Further, the process of determining the corresponding smart city level of the smart city to be evaluated based on the smart level characteristic value specifically includes the following: Query the value range corresponding to the smart level characteristic value, and determine the smart city level based on the value range. Among them, each smart city level corresponds to a smart city level.

[0014] On the other hand, a smart city evaluation system based on artificial intelligence, the system includes: An evaluation index acquisition module, used to acquire smart city evaluation indexes. Among them, the smart city evaluation indexes include appearance evaluation indexes and non-appearance evaluation indexes; An appearance characterization value calculation module, used to collect urban ground environment images through a satellite image acquisition system, analyze the urban ground environment images, appearance evaluation indexes and appearance index weight coefficients, and generate the appearance characterization value of the smart city; A non-appearance characterization value calculation module, used to acquire the data of the city to be evaluated in the smart city. Among them, the data of the city to be evaluated includes urban network data, urban logistics data, urban community data and urban traffic data, and generate the non-appearance characterization value of the smart city for the data of the city to be evaluated, non-appearance evaluation indexes and non-appearance index weight coefficients; A smart city level evaluation module, used to generate the smart level characteristic value of the smart city to be evaluated according to the appearance characterization value and the non-appearance characterization value, and determine the corresponding smart city level of the smart city to be evaluated based on the smart level characteristic value.

[0015] Compared with the existing solutions, the beneficial effects achieved by the present invention are: Improvement in comprehensiveness and accuracy: This method not only considers intuitive appearance factors such as the urban ground environment, but also deeply analyzes non-appearance data such as urban networks, logistics, communities and traffic, ensuring the comprehensiveness and in-depthness of the evaluation. The comprehensive calculation of the appearance characterization value and the non-appearance characterization value makes the evaluation result more accurate and can more truly reflect the construction level and actual effectiveness of the smart city.

[0016] Enhancement of intelligence and automation: The satellite image acquisition system is used to automatically acquire urban ground environment images, and artificial intelligence technology is combined for image analysis and data analysis, significantly improving the intelligence and automation level of the evaluation process. This not only reduces the burden of manual evaluation, but also improves the evaluation efficiency and accuracy, providing efficient technical support for smart city evaluation.

[0017] The decision-making support is remarkable: by generating the intelligent level characteristic values, the present invention provides an intuitive evaluation of the smart city level for urban managers, which helps managers better understand the current situation and potential of smart city construction and provides a strong basis for formulating scientific and reasonable urban development strategies. At the same time, targeted improvement suggestions are put forward for the weak links found in the evaluation, providing directional guidance for the continuous optimization of smart city construction. Brief Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is the flowchart of the first artificial intelligence-based smart city evaluation method in the embodiments of the present invention; Figure 2 is the flowchart of the second artificial intelligence-based smart city evaluation method in the embodiments of the present invention; Figure 3 is the flowchart of the third artificial intelligence-based smart city evaluation method in the embodiments of the present invention; Figure 4 is the system block diagram of an artificial intelligence-based smart city evaluation in the embodiments of the present invention. Detailed Embodiments

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more example embodiments. In the following description, many specific details are provided to give a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, steps, etc. can be adopted. In other cases, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0022] This embodiment provides an artificial intelligence-based smart city evaluation method. Figure 1is the flowchart of the first artificial intelligence-based smart city evaluation method according to an embodiment of the present invention, as shown in Figure 1 shown, the method includes the following steps: Step S101: Obtain smart city evaluation indicators, where the smart city evaluation indicators include appearance evaluation indicators and non-appearance evaluation indicators; Step S102: Collect urban ground environment images through a satellite image acquisition system, analyze the urban ground environment images, appearance evaluation indicators, and appearance index weight coefficients to generate an appearance characterization value of the smart city; Step S103: Obtain the data of the city to be evaluated for the smart city, where the data of the city to be evaluated includes urban network data, urban logistics data, urban community data, and urban traffic data, and generate a non-appearance characterization value of the smart city for the data of the city to be evaluated, non-appearance evaluation indicators, and non-appearance index weight coefficients; Step S104: Generate a smart level characteristic value of the smart city to be evaluated according to the appearance characterization value and the non-appearance characterization value, and determine the corresponding smart city level of the smart city to be evaluated based on the smart level characteristic value.

[0023] In summary, the method of the present invention not only considers intuitive appearance factors such as the urban ground environment, but also deeply analyzes non-appearance data such as urban networks, logistics, communities, and traffic, ensuring the comprehensiveness and in-depthness of the evaluation. The comprehensive calculation of the appearance characterization value and the non-appearance characterization value makes the evaluation result more accurate and can more truly reflect the construction level and actual effectiveness of the smart city. Automatically obtaining urban ground environment images using a satellite image acquisition system and combining artificial intelligence technology for image analysis and data analysis significantly improves the intelligence and automation level of the evaluation process. This not only reduces the burden of manual evaluation, but also improves the evaluation efficiency and accuracy, providing efficient technical support for smart city evaluation.

[0024] In some embodiments, obtaining the appearance index weight coefficient specifically includes the following process: Obtain m objects to be evaluated in the urban ground environment image, and the number of appearance evaluation indicators is n, forming an original data matrix of the corresponding evaluation indicators of the objects to be evaluated : ; where is the evaluation value of the jth object to be evaluated under the ith appearance evaluation indicator, i = 1, 2, 3,..., n; j = 1, 2, 3,..., m; Calculate the proportion of the index value of the jth object to be evaluated under the ith appearance evaluation indicator ; Calculate the entropy value of the ith appearance evaluation indicator , where ; Calculate the weight coefficient of the i-th appearance evaluation index .

[0025] It should be noted that the evaluation value of the j-th object to be evaluated under the i-th appearance evaluation index may include: according to the preprocessed data and the determined evaluation criteria, quantitatively scoring the j-th object to be evaluated under the i-th appearance evaluation index, and the quantitative scoring includes: Scoring system: Assign a score to each feature of the object to be evaluated, and then add or weighted average these scores to obtain the final evaluation value.

[0026] Grading system: Divide the performance of the object to be evaluated into different grades, such as excellent, good, general, poor, etc., and assign a corresponding numerical value or range to each grade.

[0027] Continuous numerical representation: Directly use continuous numerical values to represent the performance of the object to be evaluated under the appearance evaluation index, such as using percentages, decimals or integers, etc.

[0028] In some embodiments Figure 2 is the workflow diagram of the second artificial intelligence-based smart city evaluation method of the embodiments of the present invention. As Figure 2 shown, parsing the urban ground environment image, appearance evaluation index and appearance index weight coefficient to generate the appearance characterization value of the smart city specifically includes the following steps: Step S201: Generate multiple urban appearance detection nodes according to the urban ground environment image, and obtain multiple urban appearance detection node information, where the urban appearance detection nodes and the appearance evaluation indexes correspond one by one; Step S202: Obtain the first urban appearance detection node information, the second urban appearance detection node information until the G-th urban appearance detection node information corresponding to the urban ground environment image; Among them, the first urban appearance detection node information includes the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure, and the G-th urban appearance detection node information includes the number of the G-th information infrastructure, the number of the G-th transportation infrastructure, and the number of the G-th environmental protection infrastructure. The number of information infrastructure is the total number of data centers and Internet of Things sensors, the number of transportation infrastructure is the total number of intelligent transportation systems, intelligent traffic lights and intelligent traffic monitoring systems, and the environmental protection infrastructure is the total number of intelligent waste sorting systems, air quality monitoring stations, and water quality monitoring systems; Step S203: Sum the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure to obtain the first node characterization coefficient until the G-th node characterization coefficient is obtained; Step S204: Multiply the appearance index weight coefficient by the corresponding node characterization coefficient, and obtain the sum of all products, and record this sum value as the appearance characterization value of the smart city.

[0029] In some embodiments, generating a plurality of urban appearance detection nodes according to the urban ground environment image specifically includes the following process: Segment the urban ground environment image into several partial images, use the position of the center point of each partial image as the detection node, count the number of information infrastructure, transportation infrastructure, and environmental protection infrastructure corresponding to the urban ground environment image, and form urban appearance detection node information accordingly.

[0030] In some embodiments, obtaining the non-appearance index weight coefficient specifically includes the following process: Establish a hierarchical model with a hierarchical structure, where the hierarchy includes an objective layer, a criterion layer, and a measure layer; Determine the number h of relevant influencing factors at each level, and construct a set of non-appearance influencing factors , , where is a subset of the urban network completeness rate, is a subset of the urban logistics connectivity rate, is a subset of the urban community information intercommunication rate, is a subset of the urban traffic processing efficiency, where the urban network completeness rate is the degree of connection and interaction between various elements within the city and between the city and the external environment, the urban logistics connectivity rate is the degree of connectivity between nodes in the urban logistics network, the urban community information intercommunication rate is the degree of information transmission and sharing between urban communities, and the urban traffic processing efficiency is the efficiency of improving traffic flow under the coordinated action of various traffic modes, traffic facilities, and traffic management measures in the urban traffic system; Take out two subsets at the same level from the set for comparison, and use to represent the ratio of importance, and assign the corresponding importance according to a preset ratio, and combine the importance of each layer to form a judgment matrix; Calculate the maximum eigenvalue : ; where is the matrix obtained by normalizing each column vector of the judgment matrix, the value of is 1, 2... h, is the matrix obtained by adding the elements of matrix row by row, and then normalizing the obtained vector, is the matrix obtained by adding the elements of matrix column by column, and then normalizing the obtained vector; Calculate the consistency index : ; wherein, represents the order of the judgment matrix, and marks the value as the weight coefficient of non-appearance indicators.

[0031] In some embodiments, Figure 3 is the workflow diagram of the third artificial intelligence-based smart city evaluation method according to the embodiments of the present invention. As shown in Figure 3 , generating the non-appearance representation value of the smart city for the city data to be evaluated, non-appearance evaluation indicators, and non-appearance indicator weight coefficients specifically includes the following steps: Step S301: Obtain the standard urban network completeness rate based on non-appearance evaluation indicators, obtain the urban network completeness rate of the smart city to be evaluated based on urban network data, and calculate the difference A between the urban network completeness rate and the standard urban network completeness rate; Step S302: Obtain the standard urban logistics connectivity rate based on non-appearance evaluation indicators, obtain the urban logistics connectivity rate of the smart city to be evaluated based on urban network data, and calculate the difference B between the urban logistics connectivity rate and the standard urban logistics connectivity rate; Step S303: Obtain the standard urban community information interchange rate based on non-appearance evaluation indicators, obtain the urban community information interchange rate of the smart city to be evaluated based on urban network data, and calculate the difference C between the urban community information interchange rate and the standard urban community information interchange rate; Step S304: Obtain the standard urban traffic processing efficiency based on non-appearance evaluation indicators, obtain the urban traffic processing efficiency of the smart city to be evaluated based on urban network data, and calculate the difference D between the standard urban traffic processing efficiency and the urban traffic processing efficiency; Step S305: Substitute the differences A, B, C, D, and the non-appearance indicator weight coefficient into the calculation formula of the non-appearance representation value of the smart city, and calculate the non-appearance representation value LMS of the smart city. The calculation formula is as follows: ; Wherein, , , , 4 are respectively the urban network completeness rate coefficient, urban logistics connectivity rate coefficient, urban community information interchange rate coefficient, and urban traffic processing efficiency coefficient.

[0032] Further, generating the smart level characteristic value of the smart city to be evaluated according to the appearance representation value and the non-appearance representation value specifically includes the following process: Obtain the appearance characterization values and non-appearance characterization values generated in each management period. Construct a rectangular coordinate system with the execution time of the management period as the X-axis and the appearance characterization values and non-appearance characterization values as the Y-axis. Mark all the appearance characterization values and non-appearance characterization values as points in the rectangular coordinate system. Connect the adjacent points of the appearance characterization values and the adjacent points of the non-appearance characterization values in the rectangular coordinate system respectively to generate an appearance characterization value curve and a non-appearance characterization value curve. Draw perpendicular lines from both ends of the appearance characterization value curve and the non-appearance characterization value curve to the X-axis to obtain four starting and ending line segments. A closed figure is formed by the appearance characterization value curve, the non-appearance characterization value curve, the four starting and ending line segments, and the X-axis. Calculate the total area of the formed closed figure, and record the total area as the smart city level characteristic value to be evaluated.

[0033] In some embodiments, determining the smart city level corresponding to the smart city to be evaluated based on the smart city level characteristic value specifically includes the following process: Query the value range corresponding to the smart city level characteristic value, and determine the smart city level based on the value range, where each smart city level corresponds to a smart city grade.

[0034] In some embodiments, Figure 4 is a system block diagram of an artificial intelligence-based smart city evaluation system according to an embodiment of the present invention, as Figure 4 shown, the system includes: An evaluation index acquisition module, configured to acquire smart city evaluation indexes, where the smart city evaluation indexes include appearance evaluation indexes and non-appearance evaluation indexes; An appearance characterization value calculation module, configured to collect urban ground environment images through a satellite image acquisition system, analyze the urban ground environment images, appearance evaluation indexes, and appearance index weight coefficients, and generate the appearance characterization values of the smart city; A non-appearance characterization value calculation module, configured to acquire the data of the city to be evaluated of the smart city, where the data of the city to be evaluated includes urban network data, urban logistics data, urban community data, and urban traffic data, and generate the non-appearance characterization values of the smart city for the data of the city to be evaluated, non-appearance evaluation indexes, and non-appearance index weight coefficients; A smart city level evaluation module, configured to generate the smart city level characteristic value of the smart city to be evaluated according to the appearance characterization value and the non-appearance characterization value, and determine the smart city level corresponding to the smart city to be evaluated based on the smart city level characteristic value.

[0035] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0036] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0037] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0038] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only for some logical function divisions. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0039] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0040] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An artificial intelligence-based evaluation method for smart cities, characterized in that the method Including: Obtain the evaluation indicators of a smart city. Among them, the evaluation indicators of a smart city include appearance evaluation indicators and non - appearance evaluation indicators; Collect the urban ground environment images through a satellite image acquisition system, analyze the urban ground environment images, appearance evaluation indicators, and appearance indicator weight coefficients to generate the appearance characterization value of the smart city; Obtain the data of the city to be evaluated for the smart city. Among them, the data of the city to be evaluated includes urban network data, urban logistics data, urban community data, and urban traffic data. Analyze the data of the city to be evaluated, non - appearance evaluation indicators, and non - appearance indicator weight coefficients to generate the non - appearance characterization value of the smart city; Generate the smart - level characteristic value of the smart city to be evaluated based on the appearance characterization value and the non - appearance characterization value, and determine the corresponding smart - city level of the smart city to be evaluated based on the smart - level characteristic value.

2. The method for evaluating a smart city based on artificial intelligence according to claim 1, wherein Obtaining the appearance indicator weight coefficient specifically includes the following process: Obtain m objects to be evaluated in the urban ground environment image, where the number of appearance evaluation indicators is n, and form the original data matrix of the corresponding evaluation indicators of the objects to be evaluated : ； Among them, is the evaluation value of the jth object to be evaluated under the ith appearance evaluation index, where i = 1, 2, 3, …, n; j = 1, 2, 3, …, m; Calculate the proportion of the index value of the j-th object to be evaluated under the i-th appearance evaluation index ; Calculate the entropy value of the i-th appearance evaluation index , where ; Calculate the weight coefficient of the i-th appearance evaluation index .

3. The method for evaluating a smart city based on artificial intelligence according to claim 2, wherein Analyzing the urban ground environment images, appearance evaluation indicators, and appearance indicator weight coefficients to generate the appearance characterization value of the smart city specifically includes the following process: Generate multiple urban appearance detection nodes based on the urban ground environment images, and obtain the information of multiple urban appearance detection nodes. Among them, the urban appearance detection nodes and the appearance evaluation indicators are in one - to - one correspondence; Obtain the first urban appearance detection node information, the second urban appearance detection node information until the G - th urban appearance detection node information corresponding to the urban ground environment image. Among them, the first urban appearance detection node information includes the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure. The G - th urban appearance detection node information includes the number of the G - th information infrastructure, the number of the G - th transportation infrastructure, and the number of the G - th environmental protection infrastructure. The number of information infrastructure is the total number of the existence of data centers and Internet of Things sensors. The number of transportation infrastructure is the total number of the existence of intelligent transportation systems, intelligent traffic lights, and intelligent traffic monitoring systems. The environmental protection infrastructure is the total number of the existence of intelligent waste sorting systems, air quality monitoring stations, and water quality monitoring systems; Sum the number of the first information infrastructure, the number of the first transportation infrastructure, and the number of the first environmental protection infrastructure to obtain the first node characterization coefficient until obtaining the G - th node characterization coefficient; Multiply the appearance indicator weight coefficient by the corresponding node characterization coefficient, and calculate the sum of all products. Denote this sum as the appearance characterization value of the smart city.

4. The method for evaluating a smart city based on artificial intelligence according to claim 3, wherein Generating multiple urban appearance detection nodes based on the urban ground environment images specifically includes the following process: Segment the urban ground environment image into several partial images. Take the position of the center point of each partial image as the detection node, count the number of information infrastructure, transportation infrastructure, and environmental protection infrastructure corresponding to the urban ground environment image, and form the urban appearance detection node information accordingly.

5. The method for evaluating a smart city based on artificial intelligence according to claim 1, wherein Obtaining the non - appearance indicator weight coefficient specifically includes the following process: Establish a hierarchical model with a hierarchical structure. Among them, the levels include the target layer, the criterion layer, and the measure layer; Determine the number \(h\) of relevant influencing factors at each level, and construct a set of non-aesthetic influencing factors , , where is a subset of the urban network completeness rate, is a subset of the urban logistics connectivity rate, is a subset of the urban community information interchange rate, is a subset of the urban traffic processing efficiency. Among them, the urban network completeness rate refers to the degree of connection and interaction among various elements within the city and between the city and the external environment. The urban logistics connectivity rate refers to the degree of connectivity among nodes in the urban logistics network. The urban community information interchange rate refers to the degree of information transmission and sharing among urban communities. The urban traffic processing efficiency refers to the efficiency of improving traffic flow under the combined action of various traffic modes, traffic facilities, and traffic management measures in the urban traffic system; Select two subsets at the same level from the set for comparison, use to represent the ratio of importance, and assign the corresponding importance according to a preset ratio. Combine the importance of each layer to form a judgment matrix; Calculate the maximum eigenvalue of the judgment matrix : ； Among them, is the matrix obtained by normalizing each column vector of the judgment matrix, The value of h is 1, 2... h, is the matrix After adding the elements of each row to obtain a vector and then normalizing the matrix, is the matrix After adding the elements of each column to obtain a vector and then normalizing the matrix; calculate the consistency index : Among them, represents the order of the judgment matrix, and The value is marked as the weight coefficient of non-appearance indicators.

6. The method for evaluating a smart city based on artificial intelligence according to claim 5, wherein Analyzing the data of the city to be evaluated, non - appearance evaluation indicators, and non - appearance indicator weight coefficients to generate the non - appearance characterization value of the smart city specifically includes the following process: Obtain the complete rate of the standard urban network based on non-appearance evaluation indicators, obtain the complete rate of the urban network of the smart city to be evaluated based on urban network data, and calculate the difference A between the complete rate of the urban network and the complete rate of the standard urban network; Obtain the standard urban logistics connection rate based on non-appearance evaluation indicators, obtain the urban logistics connection rate of the smart city to be evaluated based on urban network data, and calculate the difference B between the urban logistics connection rate and the standard urban logistics connection rate; Obtain the standard urban community information interchange rate based on non-appearance evaluation indicators, obtain the urban community information interchange rate of the smart city to be evaluated based on urban network data, and calculate the difference C between the urban community information interchange rate and the standard urban community information interchange rate; Obtain the standard urban traffic processing efficiency based on non-appearance evaluation indicators, obtain the urban traffic processing efficiency of the smart city to be evaluated based on urban network data, and calculate the difference D between the standard urban traffic processing efficiency and the urban traffic processing efficiency; Substitute the difference A, difference B, difference C, difference D and the non-appearance index weight coefficient into the non-appearance characterization value calculation formula of the smart city, and calculate the non-appearance characterization value LMS of the smart city. The calculation formula is as follows: ； Among them, , , , 4 are the urban network completeness rate coefficient, the urban logistics connectivity rate coefficient, the urban community information intercommunication rate coefficient, and the urban traffic processing efficiency coefficient respectively.

7. The method for evaluating a smart city based on artificial intelligence according to claim 1, wherein, Generate the smart city level characteristic value of the smart city to be evaluated according to the appearance characterization value and the non-appearance characterization value. The specific process includes the following: Obtain the appearance characterization value and the non-appearance characterization value generated in each management period. Construct a rectangular coordinate system with the execution time of the management period as the X-axis and the appearance characterization value and the non-appearance characterization value as the Y-axis. Mark all the appearance characterization values and non-appearance characterization values in the rectangular coordinate system in the form of points. Connect the adjacent points of the appearance characterization values and the adjacent points of the non-appearance characterization values in the rectangular coordinate system respectively to generate an appearance characterization value curve and a non-appearance characterization value curve. Draw perpendicular lines from both ends of the appearance characterization value curve and the non-appearance characterization value curve to the X-axis to obtain four starting and ending line segments. The closed figure is formed by the appearance characterization value curve, the non-appearance characterization value curve, the four starting and ending line segments and the X-axis. Calculate the total area of the formed closed figure, and record the total area as the smart city level characteristic value of the smart city to be evaluated.

8. An artificial intelligence-based smart city evaluation method according to claim 1, characterized in that Determine the smart city level corresponding to the smart city to be evaluated based on the smart city level characteristic value. The specific process includes the following: Query the value range corresponding to the smart city level characteristic value, and determine the smart city level based on the value range. Among them, each smart city level corresponds to a smart city level.

9. An artificial intelligence-based smart city evaluation system, characterized in that, Applicable to an artificial intelligence-based smart city evaluation method described in any one of claims 1 to 8. The system includes: An evaluation index acquisition module for acquiring smart city evaluation indicators, where the smart city evaluation indicators include appearance evaluation indicators and non-appearance evaluation indicators; An appearance characterization value calculation module for collecting urban ground environment images through a satellite image acquisition system, analyzing the urban ground environment images, appearance evaluation indicators and appearance index weight coefficients, and generating the appearance characterization value of the smart city; The non-appearance characterization value calculation module is used to obtain the urban data to be evaluated for the smart city. Among them, the urban data to be evaluated includes urban network data, urban logistics data, urban community data, and urban traffic data, and generates the non-appearance characterization value of the smart city for the urban data to be evaluated, non-appearance evaluation indicators, and non-appearance indicator weight coefficients; The smart city level evaluation module is used to generate the smart level characteristic value of the smart city to be evaluated based on the appearance characterization value and the non-appearance characterization value, and determine the corresponding smart city level of the smart city to be evaluated based on the smart level characteristic value.

Images