Data analysis method, device, equipment, storage medium and computer program product

Abstract

This application discloses a data analysis method, apparatus, device, storage medium, and computer program product to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic economic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two at the data level, thus failing to provide direct decision support for precise intervention in urban governance. The method includes: spatially aligning collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; acquiring noise data corresponding to each geographic grid; determining the association topology between the geographic grids based on the noise data; generating an association matrix based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and generating a management strategy for each geographic grid based on the association matrix.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a data analysis method, apparatus, device, storage medium, and computer program product. Background Technology

[0002] In urban management, noise level monitoring and economic operation analysis are usually carried out as separate processes. Existing technologies can separately collect and assess noise data and perform statistical processing of economic indicators.

[0003] However, existing solutions are clearly insufficient when a deeper understanding of the dynamic and complex interrelationship between urban noise and economic activity is required. Current technologies lack a method to accurately match and quantify discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic connection between the two at the data level, thus failing to provide direct decision support for precise interventions in urban governance.

[0004] Therefore, how to effectively correlate urban noise data with economic operation data to provide scientific and real-time decision support for urban managers has become an urgent technical problem to be solved in the field of urban governance. Summary of the Invention

[0005] This application provides a data analysis method to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0006] This application also provides a data analysis device to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0007] This application also provides a data analysis device to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0008] This application also provides a computer-readable storage medium to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic economic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0009] A computer program product is designed to address the problem that existing data analysis methods cannot accurately match and quantify discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0010] The embodiments of this application adopt the following technical solutions: A data analysis method includes: spatially aligning collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; acquiring noise data corresponding to each geographic grid; determining the association topology between the geographic grids based on the noise data; generating an association matrix to determine the correlation between noise data and economic data based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and generating a management strategy for each geographic grid based on the association matrix.

[0011] A data analysis device includes: an economic data acquisition unit, configured to spatially align collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; a noise acquisition unit, configured to acquire noise data corresponding to each of the geographic grids; an association unit, configured to determine the association topology between the geographic grids based on the noise data; an association matrix generation unit, configured to generate an association matrix for determining the correlation between noise data and economic data based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and a strategy generation unit, configured to generate a management strategy for each geographic grid based on the association matrix.

[0012] A data analysis device, comprising: The processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: spatially aligning collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; acquiring noise data corresponding to each geographic grid; determining the association topology between the geographic grids based on the noise data; generating an association matrix for determining the correlation between noise data and economic data based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and generating a management strategy for each geographic grid based on the association matrix.

[0013] A computer-readable storage medium stores one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the following operations: spatially aligning collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; acquiring noise data corresponding to each geographic grid; determining the association topology between the geographic grids based on the noise data; generating an association matrix for determining the correlation between the noise data and the economic data based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and generating a management strategy for each geographic grid based on the association matrix.

[0014] A computer program product includes a computer program that, when executed by a processor, performs the following: spatial alignment of collected economic data according to a preset geographic grid to determine the economic data corresponding to each geographic grid; acquiring noise data corresponding to each geographic grid; determining the association topology between the geographic grids based on the noise data; generating an association matrix for determining the correlation between the noise data and the economic data based on the temporal changes of the economic data corresponding to each geographic grid and the association topology; and generating a management strategy for each geographic grid based on the association matrix.

[0015] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: Using the data analysis method provided in this application, when joint analysis based on urban noise data and economic operation data is required, the collected economic data can first be spatially aligned according to a preset geographic grid to determine the economic data corresponding to each geographic grid. At the same time, the noise data corresponding to each geographic grid can be obtained, and the association topology between geographic grids can be determined based on the noise data. Then, based on the temporal changes of the economic data corresponding to each geographic grid and the association topology, an association matrix for determining the correlation between noise data and economic data can be generated. Finally, a management strategy for each geographic grid can be generated based on the association matrix. The data analysis method provided in this application solves the problem of inconsistent data sources, formats, and precision in traditional methods by uniformly mapping economic data to a preset geographic grid and acquiring noise data within the corresponding grid. Simultaneously, the grid-based alignment provides a unified and standardized analysis unit and data foundation for subsequent spatiotemporal correlation calculations, significantly improving the standardization and feasibility of multi-source data fusion. Furthermore, this solution can infer the correlation topology between various geographic grids from noise data and then analyze it in conjunction with the temporal changes in economic data. Through this dual analysis mode of temporal change and spatial topology, the coupling relationship between the spatial propagation path of noise and the temporal fluctuation pattern of economic data can be more accurately identified, generating a correlation matrix that reflects the intrinsic connection between the two. This overcomes the limitations of traditional methods that can only perform surface statistical analysis or isolated spatiotemporal analysis, greatly improving the data analysis capabilities for different phenomena in urban operations and providing crucial data support for urban governance. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram of the specific structure of a data analysis system provided in this application embodiment. Figure 2 This is a schematic diagram illustrating a specific process of a data analysis method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the specific structure of a data analysis device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the specific structure of a data analysis device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] This application provides a data analysis method to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance.

[0019] The execution subject of the data analysis method provided in this application embodiment may be, but is not limited to, at least one of a city management server, a data analysis server, and a city governance server; in addition, the execution subject of the method may also be the system or application (APP) itself running on these servers.

[0020] For ease of description, the following description uses a data analysis system as the execution subject to illustrate the implementation of this method. It should be understood that using a data analysis system as the execution subject is merely an illustrative example and should not be construed as a limitation of the method.

[0021] In one implementation, the specific structure of the data analysis system provided in this application embodiment can be as follows: Figure 1 As shown, it mainly includes: a data fusion layer, an intelligent analysis layer, and a collaborative control layer.

[0022] The data fusion layer, located at the city's edge and the cloud, primarily comprises heterogeneous data gateways and edge computing nodes. The heterogeneous data gateways are used to access data from IoT sensors, APIs, text work orders, and other sources using different protocols (e.g., HTTP, CoAP, MQTT) and formats, performing initial cleaning and format unification. Edge computing nodes can be deployed in regional centers to perform real-time preprocessing and aggregation of sensor data.

[0023] The intelligent analysis layer, the core computational layer, mainly comprises a dynamic association engine and a policy knowledge base. The dynamic association engine encapsulates models such as the spatiotemporal graph convolutional network and dynamic weighted LSTM described in S104, used to perform association analysis and generate association matrices. The policy knowledge base stores historical policy rules and performance evaluation data, supporting policy optimization and iteration.

[0024] The collaborative control layer, serving as both the output and interaction layer, primarily includes a RESTful API interface and a command distribution module. The RESTful API interface allows external systems to query results or receive policies. The command distribution module pushes policy commands generated via protocols such as MQTT to a wide range of terminal devices.

[0025] In this embodiment of the application, the layers of the data analysis system communicate with each other through an internal high-speed network to jointly complete all the functions of the following data analysis.

[0026] Based on the above Figure 1 The data analysis system shown in this application, and the specific implementation flowchart of the data analysis method provided in this application are illustrated in the figure below. Figure 2 As shown, the main steps include the following: Step 11: Based on the preset geographic grid, spatially align the collected economic data to determine the economic data corresponding to each geographic grid. It should be noted that, in this embodiment of the application, the target urban area can be divided into continuous and uniform geographic grid units according to urban management needs and data analysis accuracy requirements. For example, a square grid with a side length of 500 meters can be used to cover the entire analysis area. Each geographic grid has a unique geographic code (such as latitude and longitude range or grid ID), and the center coordinates of each geographic grid can be used as the spatial representative location of that geographic grid.

[0027] In this embodiment of the application, the data analysis system can obtain macroeconomic data such as GDP, total corporate tax payment, and industrial distribution of various administrative regions (e.g., districts and streets) by calling the application programming interfaces of official agencies such as statistical departments and tax departments.

[0028] It is also possible to obtain microeconomic data such as transaction records from commercial POS machines through business system interfaces or data sharing protocols. Each transaction record contains information such as transaction time, transaction amount, and merchant number.

[0029] In this embodiment, the acquired macroeconomic data can be linked from administrative regions to corresponding geographic grids. Specifically, the data analysis system first identifies the enterprise entity corresponding to the macroeconomic data, then queries the first location information representing the geographical location of the enterprise entity, such as the business registration address and operating address, and then uses geocoding technology to parse the first location information of the enterprise entity into latitude and longitude coordinates. Based on the latitude and longitude coordinates, the system determines the geographic grid unit to which the enterprise entity belongs, and allocates or proportionally distributes the corresponding macroeconomic data of the enterprise entity to that grid.

[0030] Furthermore, based on the acquired microeconomic data, the data analysis system can determine the merchant's secondary location information, such as the merchant's registered address or store GPS coordinates, according to the merchant's ID. Then, through geocoding and spatial judgment, each transaction is assigned to a specific geographic grid. It should be noted that, in this embodiment, the data analysis system can aggregate transaction flows within a grid over a certain time period (e.g., daily or weekly) to obtain microeconomic indicators such as the grid's total transaction amount and transaction frequency.

[0031] Through the above processing, the data analysis system can ultimately generate a series of economic indicator data sequences corresponding to each geographic grid, thereby completing the spatial alignment of economic data.

[0032] Step 12: Obtain the noise data corresponding to each geographic grid. Specifically, in the embodiments of this application, noise data can be acquired in the following two ways: 1. Acquisition of structured noise data: Specifically, Internet of Things (IoT) noise sensors can be deployed at key locations throughout the city to form a sensing network. Each sensor continuously collects noise decibel values ​​(such as equivalent sound level Leq), along with a high-precision timestamp and GPS coordinates. The sensors then report the collected data to the data center in real time or periodically via a wireless network. Based on the sensor's GPS coordinates, the data analysis system can directly correlate the noise data collected by the sensor with its corresponding geographic grid.

[0033] 2. Analysis and identification of unstructured noise data: Specifically, the data analysis system obtains noise complaint forms from platforms such as the city's citizen service hotline. These forms contain unstructured information such as the complaint time, approximate location, and noise type. The system then uses Natural Language Processing (NLP) technology to parse these noise complaint forms, automatically extracting key structured information, which may include: Time: The time or period during which the complaint occurred.

[0034] Location: The location described in the text, such as "southeast corner of the intersection of XX Road and YY Road" or "near Building 3 of ZZ Community", can then be converted into latitude and longitude coordinates through address standardization and geocoding technology.

[0035] Event type: such as "construction noise", "commercial advertising noise", "traffic noise" and other category tags.

[0036] Ultimately, the data analysis system can associate the analyzed noise events with the corresponding geographic grid based on their geographic coordinates.

[0037] Step 13: Determine the association topology between geographic grids based on the noise data collected by performing Step 12; In this embodiment of the application, the data analysis system can construct a spatial topology graph based on the spatial association between different geographic grids caused by noise propagation or related events. In this spatial topology graph, the nodes are geographic grids, and the weights of the edges represent the degree of association between the geographic grids in the noise dimension.

[0038] In this embodiment of the application, the data analysis system can determine the associated topology between geographic grids according to the following sub-steps, including: Sub-step 1301: Determine the time similarity based on the timestamps of the noise data and the economic data; Specifically, in the embodiments of this application, the data analysis system can determine the temporal similarity between two geographic grids by comparing the synchronicity of noise events in the temporal distribution of the two geographic grids. For example, the correlation coefficient of the frequency of noise events occurring in the same time period of the two grids can be calculated, or the temporal similarity of a pair of specific events can be calculated using the following formula [1]: T sim =1 - |t complaint - t sensor | / T range [1] Among them, t complaint and t sensor T represents the time of the complaint and the time when the sensor detected the abnormal noise, respectively. range This represents the normalized time range (e.g., 24 hours). In this embodiment, T sim The closer the value is to 1, the more synchronized the two geographic grids are in time.

[0039] Sub-step 1302: Determine the spatial similarity based on the location information of the noise data and the center location information of the corresponding geographic grid. Specifically, in the embodiments of this application, based on the spatial distance attenuation effect, the closer the geographical grids are, the greater the possibility of their noise influencing each other. Therefore, the data analysis system can calculate the spatial similarity based on the distance between the grid center points according to the following formula [2]: S dist =1-distance(l complaint grid center ) / grid radius [2] Where distance represents the geographic distance between the center points of the geographic grid, grid radius This represents the distance attenuation factor, which is set according to the urban environment and noise type. S dist The value of is between 0 and 1, and the closer the distance, the closer the value is to 1.

[0040] Sub-step 1303: Determine the matching relationship between geographic grids based on the temporal similarity and spatial similarity determined by executing sub-step 1302; Specifically, in the embodiments of this application, the data analysis system can perform weighted fusion of temporal similarity and spatial similarity based on the following formula [3] to obtain the final matching score: Match Score (A, B) = α × sim +β×S dist [3] Where α and β represent weighting coefficients, and α + β = 1. Furthermore, in this embodiment, the weighting coefficients α and β can be dynamically adjusted according to the functional characteristics of the region where the grid is located. For example: For commercial area grids: economic activities and noise (such as pedestrian traffic and advertising) are highly correlated in time, so we can set α=0.7 and β=0.3 to focus more on time correlation.

[0041] For grids near industrial areas or major transportation routes: noise propagation is more significantly affected by spatial distance, so α=0.3 and β=0.7 can be set to focus more on spatial correlation.

[0042] Sub-step 1304: Based on the matching relationships determined by executing sub-step 1303, construct the spatial topological relationships between geographic grids.

[0043] Specifically, the data analysis system can use all geographic grids as nodes, and if there is a match between two grids... Score If the threshold is exceeded, an edge is established between them, and the Match is set. Score This serves as the weight of the edge. This constructs a spatial topological graph describing the relationships between noise components.

[0044] Step 14: Based on the temporal changes of economic data corresponding to each geographic grid and the aforementioned correlation topology, generate a correlation matrix to determine the correlation between noise data and economic data; In this embodiment of the application, the data analysis system can construct the association matrix according to the following sub-steps: Sub-step 1401: Input the temporal variation and spatial topological relationship into the preset deep learning model; In this embodiment of the application, the data analysis system can pre-build a deep learning model that integrates spatiotemporal features. This deep learning model mainly includes two modules: a spatiotemporal graph convolutional network module and a long short-term memory network module.

[0045] The spatiotemporal graph convolutional network module takes the time series of noise data and the spatial topological adjacency matrix as the main input. Through graph convolution operations, the model can capture how noise propagates and spreads on the spatial topological network, learning that the noise characteristics of each grid depend not only on its own history but also on the influence of its topological neighbors. This effectively models the spatial propagation characteristics of noise.

[0046] The Long Short-Term Memory (LSTM) module is used with time series economic data as the primary input. The LSTM module can capture long-term dependencies and periodic and trend changes in economic indicators, learning the temporal dynamic characteristics of economic activities. In a preferred embodiment, the LSTM module employs a dynamic weighting mechanism, meaning its internal gating weights or attention weights can adaptively adjust according to the current pattern of the input economic sequence to better focus on key time points.

[0047] Finally, the two modules are exchanged and merged through a shared layer or a fusion layer, enabling the model to simultaneously consider "how the economy changes over time" and "how noise propagates in spatially interconnected networks," thereby learning the coupling relationship between the two.

[0048] It should be noted that before inputting the temporal variations and spatial topological relationships into this deep learning model, the data analysis system can first preprocess the data, including: The data analysis system can organize the economic data of each geographic grid obtained by executing step 11 into a time series format, and also organize the noise data of each geographic grid obtained by executing step 12 into a time series format. The association topology graph constructed by executing step 13 is transformed into an adjacency matrix A, where the element A[i][j] represents the matching degree weight between geographic grid i and geographic grid j.

[0049] Sub-step 1402: Based on the deep learning model, determine the changes in economic data over time and the propagation data of noise based on spatial topological relationships; Sub-step 1403: Based on the change data and the propagation data, construct a correlation matrix that characterizes the degree of correlation between the economic data and the noise data corresponding to each geographic grid.

[0050] Specifically, the data analysis system can input preprocessed economic time-series data, noisy time-series data, and topological adjacency matrix into a trained deep learning model. The deep learning model outputs a correlation score R for each pair (grid, economic indicator type, noise indicator type). The correlation matrix is ​​obtained by organizing the R values ​​of all geographic grids and all indicator pairs in matrix form.

[0051] In this correlation matrix, the rows and columns can represent different geographical grids or different indicators. The value of the matrix element R(i,j) represents the degree of correlation between an economic indicator in the i-th grid and a noise indicator in the j-th grid. Positive values ​​indicate a positive correlation, meaning that active economic activity is accompanied by increased noise; negative values ​​indicate a negative correlation, and the larger the absolute value, the stronger the correlation.

[0052] Step 15: Based on the correlation matrix obtained by performing Step 14, generate management strategies for each geographic grid.

[0053] In this embodiment, a strategy knowledge base can be built into the data analysis system according to business needs, storing several strategy rules in the form of "IF-THEN". Each rule defines the triggering condition and the execution action. For example: Rule 1: If the correlation between the "average nighttime noise level" and the "total nighttime transaction volume" of a certain commercial area grid is greater than 0.8, then the following strategy is generated: "It is recommended to extend the business hours of core merchants in the area to 24:00 and simultaneously activate the smart light pole noise reduction broadcast system."

[0054] Rule 2: If the correlation R between the "frequency of noise complaints" and the "industrial output of the grid and the adjacent grid upwind" of a certain industrial zone grid is greater than 0.7, and the complaints are concentrated at night, then the generation strategy is: "Send an early warning to the environmental law enforcement system, suggesting that the area be patrolled at night and that the patrol route parameters of the law enforcement vehicle be optimized."

[0055] In this embodiment, the data analysis system can scan the association matrix in real time or periodically, matching the matrix element values ​​with conditions in the policy rule base. Once a match is successful, the corresponding policy instruction is automatically generated.

[0056] Additionally, it should be noted that the data analysis system can distribute the generated strategy commands through standardized interfaces, for example: For policies that need to be linked with other government systems (such as urban management and environmental protection platforms), the policy instructions are pushed to the corresponding system's interface through RESTful API calls.

[0057] For strategies that require direct control of IoT terminal devices (such as broadcasting systems, information screens, and vehicle-mounted terminals in law enforcement vehicles), a lightweight MQTT protocol is used to publish instructions to the corresponding topics, which are then received and executed by devices that have subscribed to those topics.

[0058] Using the data analysis method provided in this application, when joint analysis based on urban noise data and economic operation data is required, the collected economic data can first be spatially aligned according to a preset geographic grid to determine the economic data corresponding to each geographic grid. At the same time, the noise data corresponding to each geographic grid can be obtained, and the association topology between geographic grids can be determined based on the noise data. Then, based on the temporal changes of the economic data corresponding to each geographic grid and the association topology, an association matrix for determining the correlation between noise data and economic data can be generated. Finally, a management strategy for each geographic grid can be generated based on the association matrix. The data analysis method provided in this application solves the problem of inconsistent data sources, formats, and precision in traditional methods by uniformly mapping economic data to a preset geographic grid and acquiring noise data within the corresponding grid. Simultaneously, the grid-based alignment provides a unified and standardized analysis unit and data foundation for subsequent spatiotemporal correlation calculations, significantly improving the standardization and feasibility of multi-source data fusion. Furthermore, this solution can infer the correlation topology between various geographic grids from noise data and then analyze it in conjunction with the temporal changes in economic data. Through this dual analysis mode of temporal change and spatial topology, the coupling relationship between the spatial propagation path of noise and the temporal fluctuation pattern of economic data can be more accurately identified, generating a correlation matrix that reflects the intrinsic connection between the two. This overcomes the limitations of traditional methods that can only perform surface statistical analysis or isolated spatiotemporal analysis, greatly improving the data analysis capabilities for different phenomena in urban operations and providing crucial data support for urban governance.

[0059] In one embodiment, this application also provides a data analysis device to address the problem that existing data analysis methods cannot accurately match and quantitatively correlate discrete noise events with continuous, macroeconomic indicators within a unified spatiotemporal framework. This makes it difficult to scientifically reveal the intrinsic relationship between the two from a data perspective, thus failing to provide direct decision support for precise intervention in urban governance. A schematic diagram of the specific structure of this data analysis device is shown below. Figure 3 As shown, it includes: an economic data acquisition unit 31, a noise acquisition unit 32, a correlation unit 33, a correlation matrix generation unit 34, and a strategy generation unit 35.

[0060] Among them, the economic data acquisition unit 31 is used to spatially align the collected economic data according to the preset geographic grid and determine the economic data corresponding to each geographic grid. The noise acquisition unit 32 is used to acquire noise data corresponding to each of the geographic grids. Association unit 33 is used to determine the association topology between the geographic grids based on the noise data; The correlation matrix generation unit 34 is used to generate a correlation matrix for determining the correlation between noise data and economic data based on the temporal changes of economic data corresponding to each geographic grid and the correlation topology. The strategy generation unit 35 is used to generate management strategies for each geographic grid based on the correlation matrix.

[0061] In one embodiment, the noise acquisition unit 32 is specifically used to: collect structured noise data within the geographic grid through an Internet of Things sensor; and / or, parse unstructured complaint text through natural language processing technology to extract noise event information corresponding to the geographic grid.

[0062] In one embodiment, the economic data acquisition unit 31 is specifically used for: acquiring macroeconomic data and transaction flow data; determining the enterprise entity corresponding to the macroeconomic data, and determining the first location information corresponding to the macroeconomic data based on the registration information of the enterprise entity; determining the second location information corresponding to the transaction flow data; and determining the geographic grid corresponding to the economic data based on the first location information and the second location information.

[0063] In one implementation, the association unit 33 is specifically used for: determining temporal similarity based on the timestamps of the noise data and the economic data; determining spatial similarity based on the location information of the noise data and the center location information of the corresponding geographic grid; determining the matching relationship between the geographic grids based on the temporal similarity and spatial similarity; and constructing the spatial topological relationship between the geographic grids based on the matching relationship.

[0064] In one implementation, the correlation matrix generation unit 34 is specifically used for: inputting the temporal changes and the spatial topological relationship into a preset deep learning model; determining the changes in economic data over time and the propagation data of noise based on the spatial topological relationship according to the deep learning model; and constructing a correlation matrix characterizing the degree of correlation between economic data and noise data corresponding to each geographic grid according to the changes and the propagation data.

[0065] In one implementation, the deep learning model includes a spatiotemporal graph convolutional network module and a long short-term memory network module; wherein the spatiotemporal graph convolutional network module is configured to model the spatial propagation characteristics of noise data based on the spatial topological relationship; and the long short-term memory network module is configured to model the temporal changes.

[0066] Using the data analysis apparatus provided in this application embodiment, when joint analysis based on urban noise data and economic operation data is required, the collected economic data can first be spatially aligned according to a preset geographic grid to determine the economic data corresponding to each geographic grid. At the same time, the noise data corresponding to each geographic grid is obtained, and the association topology between geographic grids is determined based on the noise data. Then, based on the temporal changes of the economic data corresponding to each geographic grid and the association topology, an association matrix for determining the correlation between noise data and economic data is generated. Finally, a management strategy for each geographic grid can be generated based on the association matrix. The data analysis device provided in this application solves the problem of inconsistent data sources, formats, and precision in traditional methods by uniformly mapping economic data to a preset geographic grid and acquiring noise data within the corresponding grid. Simultaneously, the grid-based alignment provides a unified and standardized analysis unit and data foundation for subsequent spatiotemporal correlation calculations, significantly improving the standardization and feasibility of multi-source data fusion. Furthermore, this solution can infer the correlation topology between various geographic grids from noise data and then analyze it in conjunction with the temporal changes in economic data. Through this dual analysis mode of temporal change and spatial topology, the coupling relationship between the spatial propagation path of noise and the temporal fluctuation pattern of economic data can be more accurately identified, generating a correlation matrix that reflects the intrinsic connection between the two. This overcomes the limitations of traditional methods that can only perform surface statistical analysis or isolated spatiotemporal analysis, greatly improving the data analysis capabilities for different phenomena in urban operations and providing crucial data support for urban governance.

[0067] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0068] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0069] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0070] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a data analysis device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: Based on a preset geographic grid, the collected economic data is spatially aligned to determine the economic data corresponding to each geographic grid; noise data corresponding to each geographic grid is obtained; based on the noise data, the association topology between the geographic grids is determined; based on the temporal changes of the economic data corresponding to each geographic grid and the association topology, an association matrix is ​​generated to determine the correlation between noise data and economic data; based on the association matrix, a management strategy for each geographic grid is generated.

[0071] The above is as stated in this application. Figure 4The data analysis electronic device disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0072] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0073] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 1 The data analysis method shown in the embodiment is specifically used to perform the following operations: Based on a preset geographic grid, the collected economic data is spatially aligned to determine the economic data corresponding to each geographic grid; noise data corresponding to each geographic grid is obtained; based on the noise data, the association topology between the geographic grids is determined; based on the temporal changes of the economic data corresponding to each geographic grid and the association topology, an association matrix is ​​generated to determine the correlation between noise data and economic data; based on the association matrix, a management strategy for each geographic grid is generated.

[0074] It should be understood that the training and prediction processes of the AI ​​models involved in the various embodiments of this specification all adhere to multiple legal and compliant principles, including legal data sources, compliant data content, compliant data governance, compliant training objectives and schemes, compliant training processes, compliant training environments and tools, and compliant ethical verification of training results, and comply with the requirements of Article 5 of the Patent Law. Among them: Data source legitimacy: All datasets used for AI model training were obtained through legal means, covering three categories: publicly authorized data, data authorized by partners, and self-collected compliant data. Publicly authorized data comes from compliant data sources following open-source licenses such as Apache 2.0, with complete copyright attribution and authorization scope clearly marked, and no unauthorized open-source code or data reuse. Data authorized by partners has been subject to formal data usage agreements, clearly defining the scope, duration, and confidentiality obligations, and possessing a complete authorization chain. For self-collected data involving personal information, strict informed consent procedures have been followed, and anonymization processes (including but not limited to field masking, feature anonymization, and differential privacy technology applications) have been implemented to remove personally identifiable information, fully complying with the requirements of relevant laws and regulations such as the "Interim Measures for the Administration of Generative Artificial Intelligence Services" and the "Personal Information Protection Law."

[0075] Data content compliance: The AI ​​model's dataset undergoes multiple screenings and cleaning processes to remove all content that may violate social morality or harm public interests. It contains no obscene, pornographic, violent, discriminatory, or information that endangers national or public safety, nor does it involve the illegal acquisition or use of genetic resources. For data in sensitive fields (such as healthcare and finance), an additional privacy-preserving computation module (including federated learning and secure multi-party computation technologies) ensures that the data is "usable but not visible," avoiding compliance risks during the original data transmission process and ensuring that the data application scenarios and uses comply with public order and good morals and industry regulatory requirements.

[0076] Data governance norms: A complete data traceability system is established during the AI ​​model training process to automatically record the source, collection time, annotation process, cleaning rules, and permission allocation of training data, generating traceable compliance reports to ensure that the data is verifiable throughout its entire lifecycle. The dataset annotation process for AI models is completed by a professional human R&D team, clearly defining the proportion of human creative contributions and avoiding reliance on AI-generated data that has not undergone substantial human modification, thus meeting the examination requirements for "human main contributions" in AI patent applications.

[0077] Training objectives and plans are compliant: The AI ​​model training objective focuses on the analysis and learning of the spatial propagation characteristics of noise and the temporal changes of economic data. The training scheme and the final output results do not violate any mandatory provisions of laws and administrative regulations, do not harm the public interest or the legitimate rights and interests of others, and do not pose any potential risks of being used for illegal activities, infringing on privacy, or undermining public safety. It strictly adheres to the ethical principle of "intelligent for good".

[0078] Training process compliance: A closed-loop training framework is adopted to ensure compliance and controllability of the training process. The specific process is as follows: First, training samples are obtained through compliant data sources. After the aforementioned data cleaning and desensitization, they are input into the neural network model to generate preliminary training results. Second, an expert system is introduced to verify the preliminary results. Based on preset rules and human expert experience, the feasibility of the results is evaluated, and outputs that may pose ethical risks or compliance hazards are corrected (such as removing decision-making logic that violates public order and good morals, and adjusting model parameters that do not comply with safety regulations). Finally, the loss function weights are dynamically optimized based on expert system feedback to strengthen the model's learning of compliant results, avoid overfitting errors or non-compliant labels, and form a closed-loop control of "data input - model training - expert verification - parameter optimization - result feedback" to ensure that the entire training process complies with A5 ethical review requirements.

[0079] Training environment and tool compliance: AI model training is implemented using nationally licensed chips and a compliant training platform. All open-source frameworks and components used in the training process have obtained their corresponding licenses, and copyright statements and patent citation information are fully retained, with no instances of infringement or reuse. The training environment is built using virtual devices (containers / virtual machines) with fixed random seeds and initial parameter configurations to ensure the reproducibility of the training process. Furthermore, through access control and operation log recording, risks such as data leakage and parameter tampering during training are prevented, ensuring the security and compliance of the training process.

[0080] Training results ethical verification compliance: After the model is trained, it undergoes additional third-party ethical compliance assessment and algorithm filing review to verify that the model output does not violate social morality or harm public interests. For potentially sensitive scenarios (such as public services and intelligent decision-making), a special result verification mechanism is established to ensure that the model always complies with Article 5 of the Patent Law and relevant laws and regulations in practical applications.

[0081] In summary, the data and training process used in the AI ​​model of this specification strictly comply with the relevant provisions of Article 5 of the Patent Law and the Patent Examination Guidelines (2023 Edition), and there are no violations of laws, social ethics, public interests, or illegal use of genetic resources. It fully meets the compliance requirements for patent authorization.

[0082] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0087] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0088] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0089] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0090] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data analysis method, characterized in that, include: Based on the preset geographic grid, the collected economic data is spatially aligned to determine the economic data corresponding to each geographic grid. Obtain the noise data corresponding to each of the aforementioned geographic grids; Based on the noise data, determine the associated topology between the geographic grids; Based on the temporal changes of economic data corresponding to each geographic grid and the aforementioned correlation topology, a correlation matrix is ​​generated to determine the correlation between noisy data and economic data. Based on the correlation matrix, management strategies are generated for each geographic grid.

2. The method according to claim 1, characterized in that, The acquisition of noise data corresponding to each of the geographic grids specifically includes: Structured noise data within the geographic grid is collected via IoT sensors; and / or, Unstructured complaint text is parsed using natural language processing techniques to extract noise event information corresponding to the geographic grid.

3. The method according to claim 1, characterized in that, The spatial alignment of economic data according to a preset geographic grid specifically includes: Obtain macroeconomic data and transaction flow data; Identify the enterprise entity corresponding to the macroeconomic data, and determine the first location information corresponding to the macroeconomic data based on the registration information of the enterprise entity; Determine the second location information corresponding to the transaction flow data; Based on the first location information and the second location information, the geographic grid corresponding to the economic data is determined.

4. The method according to claim 1, characterized in that, The step of determining the association topology between the geographic grids based on the noise data specifically includes: Determine the time similarity based on the timestamps of the noise data and the economic data; The spatial similarity is determined based on the location information of the noise data and the center location information of the corresponding geographic grid. The matching relationship between the geographic grids is determined based on the temporal similarity and spatial similarity. Based on the matching relationship, construct the spatial topological relationship between the geographic grids.

5. The method according to claim 4, characterized in that, The step of generating an association matrix based on the temporal changes of economic data corresponding to each geographic grid and the associated topology specifically includes: The temporal changes and spatial topological relationships are input into a preset deep learning model; Based on the deep learning model, the changes in the economic data over time and the propagation of noise based on the spatial topology are determined; Based on the change data and the propagation data, a correlation matrix is ​​constructed to characterize the degree of correlation between the economic data and the noise data corresponding to each geographic grid.

6. The method according to claim 5, characterized in that, The deep learning model includes a spatiotemporal graph convolutional network module and a long short-term memory network module; The spatiotemporal graph convolutional network module is configured to model the spatial propagation characteristics of noise data based on the spatial topology. The long short-term memory network module is configured to model the temporal changes.

7. A data analysis device, characterized in that, include: The economic data acquisition unit is used to spatially align the collected economic data according to a preset geographic grid and determine the economic data corresponding to each geographic grid. A noise acquisition unit is used to acquire noise data corresponding to each of the geographic grids. An association unit is used to determine the association topology between the geographic grids based on the noise data; The correlation matrix generation unit is used to generate a correlation matrix for determining the correlation between noise data and economic data based on the temporal changes of economic data corresponding to each geographic grid and the correlation topology. The strategy generation unit is used to generate management strategies for each geographic grid based on the correlation matrix.

8. A data analysis device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: Based on the preset geographic grid, the collected economic data is spatially aligned to determine the economic data corresponding to each geographic grid. Obtain the noise data corresponding to each of the aforementioned geographic grids; Based on the noise data, determine the associated topology between the geographic grids; Based on the temporal changes of economic data corresponding to each geographic grid and the aforementioned correlation topology, a correlation matrix is ​​generated to determine the correlation between noisy data and economic data. Based on the correlation matrix, management strategies are generated for each geographic grid.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the data analysis method as described in any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the data analysis method as described in any one of claims 1-6.

Images