AIGC-based regional management method and related product

Abstract

The invention provides an AIGC-based area management method and a related product. The method comprises the following steps: collecting behavior data, video monitoring data and environment data of a user in a target area through front-end image acquisition equipment or Internet of Things equipment; and matching the behavior data of the users in the target area with the user data of the users in the target area to obtain comprehensive data of the users in the target area. And processing the comprehensive data by using a machine learning algorithm to obtain user group classification data. And performing multi-modal fusion on the video monitoring data, the comprehensive data and the environment data to obtain a multi-modal fusion result. And determining a target area management strategy based on the multi-modal fusion result and the user group classification data. According to the method provided by the invention, the intelligent level of regional management and the pertinence of decision making can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a regional management method based on AIGC and related products. Background Art

[0002] With the continuous development of science and technology, communities are also moving towards intelligence. When managing a region, existing technologies will train management models with data from different dimensions and generate management strategies through management models. However, existing technologies are also insufficient in the depth of user behavior analysis. Many traditional systems cannot effectively use machine learning or deep learning algorithms for data mining, resulting in a one-sided understanding of user groups. The classification and prediction of user behavior are often based on simple rules, but lack in-depth data-driven analysis, and cannot accurately capture user needs and behavior patterns. This greatly reduces the pertinence and effectiveness of management measures. Therefore, how to conduct more targeted management measurements on target areas has become a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0003] Based on the above problems, this application provides a regional management method based on AIGC to improve the pertinence of production management strategies.

[0004] The present application provides a regional management method based on AIGC, the method comprising the following steps:

[0005] Collect user behavior data, video surveillance data, and environmental data in the target area through front-end image acquisition devices or IoT devices;

[0006] Matching the behavior data of the target area users with the user data of the target area users to obtain the comprehensive data of the target area users;

[0007] Processing the comprehensive data using a machine learning algorithm to obtain user group classification data;

[0008] Performing multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result;

[0009] A target area management strategy is determined based on the multimodal fusion result and the user group classification data.

[0010] In a possible implementation, the collecting of the behavior data, video surveillance data and environmental data of users in the target area by a front-end image acquisition device or an Internet of Things device includes:

[0011] Marking the behavior of users in the target area by using a drone, a camera or the IoT device to obtain a marking result;

[0012] Generate activity trajectory data, residence time data and interaction behavior data based on the marking results;

[0013] Processing the activity trajectory data, the residence time data, and the interaction behavior data using a machine learning algorithm to obtain behavior data of users in a target area;

[0014] Video surveillance data and environmental data are collected through drones, cameras or the IoT devices.

[0015] In a possible implementation, the using a machine learning algorithm to process the comprehensive data to obtain user group classification data includes:

[0016] Clustering the comprehensive data based on a deep learning clustering model to obtain a clustering result, wherein the clustering result is used to represent the user's behavior category;

[0017] User group classification data is determined based on the clustering results.

[0018] In a possible implementation, performing multimodal fusion on the video surveillance data, the comprehensive data, and the environmental data to obtain a multimodal fusion result includes:

[0019] Based on the weather data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under weather factors to obtain a first modal fusion result;

[0020] Based on the time data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under the time factor to obtain a second modal fusion result;

[0021] The first modal fusion result and the second modal fusion result are modally fused to obtain a multimodal fusion result.

[0022] The present application also provides an AIGC-based regional management device, which includes the following modules:

[0023] An acquisition module is used to collect behavior data, video surveillance data, and environmental data of users in the target area through a front-end image acquisition device or an IoT device;

[0024] A matching module, used for matching the behavior data of the target area users with the user data of the target area users to obtain the comprehensive data of the target area users;

[0025] A processing module, used to process the comprehensive data using a machine learning algorithm to obtain user group classification data;

[0026] A fusion module, used for performing multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result;

[0027] A decision module is used to determine a target area management strategy based on the multimodal fusion result and the user group classification data.

[0028] In a possible implementation, the acquisition module is specifically used to:

[0029] Marking the behavior of users in the target area by using a drone, a camera or the IoT device to obtain a marking result;

[0030] Generate activity trajectory data, residence time data and interaction behavior data based on the marking results;

[0031] Processing the activity trajectory data, the residence time data, and the interaction behavior data using a machine learning algorithm to obtain behavior data of users in a target area;

[0032] Video surveillance data and environmental data are collected through drones, cameras or the IoT devices.

[0033] In a possible implementation manner, the processing module is specifically configured to:

[0034] Clustering the comprehensive data based on a deep learning clustering model to obtain a clustering result, wherein the clustering result is used to represent the user's behavior category;

[0035] User group classification data is determined based on the clustering results.

[0036] In a possible implementation, the fusion module is specifically used to:

[0037] Based on the weather data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under weather factors to obtain a first modal fusion result;

[0038] Based on the time data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under the time factor to obtain a second modal fusion result;

[0039] The first modal fusion result and the second modal fusion result are modally fused to obtain a multimodal fusion result.

[0040] The present application also provides an electronic device, the electronic device comprising a processor and a memory:

[0041] The memory is used to store a computer program and transmit the computer program to the processor;

[0042] The processor is used to execute the steps of the above-mentioned AIGC-based area management method according to the instructions in the computer program.

[0043] The present application also provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program, and when the computer program is executed by an electronic device, the steps of the above-mentioned AIGC-based regional management method are implemented.

[0044] Compared with the prior art, this application has the following beneficial effects:

[0045] The method provided in the present application collects the behavior data, video surveillance data and environmental data of the users in the target area through a front-end image acquisition device or an Internet of Things device. Then, the behavior data of the users in the target area is matched with the user data of the users in the target area to obtain the comprehensive data of the users in the target area. The comprehensive data is processed by a machine learning algorithm to obtain user group classification data. The video surveillance data, comprehensive data and environmental data are multimodally fused to obtain a multimodal fusion result. The target area management strategy is determined based on the multimodal fusion result and the user group classification data.

[0046] First of all, this application has significantly improved data processing and analysis capabilities. By introducing machine learning and deep learning algorithms, the system can efficiently process large-scale, multi-dimensional data streams. This capability enables the system to quickly respond to changes in user behavior, thereby improving the timeliness and effectiveness of management decisions. Based on the analysis of real-time data streams, managers can obtain more accurate insights into user behavior and provide a scientific basis for regional management.

[0047] Secondly, this application also performs well in the depth of user behavior analysis. By comprehensively utilizing machine learning algorithms, the system can conduct comprehensive data mining and accurately identify and classify user groups. This data-driven analysis method can deeply capture user needs and behavior patterns, helping managers to formulate more targeted management strategies, thereby improving the efficiency and effectiveness of governance.

[0048] To sum up, the AIGC-based regional management method of this application has significant advantages in flexibility, data processing capabilities, depth of user behavior analysis and dynamic feedback mechanism, which can effectively improve the intelligence level of regional management and the targeted decision-making, and meet the needs of modern urban management. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0050] Figure 1 A flow chart of a regional management method based on AIGC provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of an AIGC-based regional management device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] As described above, when managing a region, existing technologies train management models with data from different dimensions and generate management strategies through management models. However, existing technologies are also insufficient in terms of the depth of user behavior analysis. Many traditional systems cannot effectively use machine learning or deep learning algorithms for data mining, resulting in a one-sided understanding of user groups. The classification and prediction of user behavior are often based on simple rules, but lack in-depth data-driven analysis, and cannot accurately capture user needs and behavior patterns. This greatly reduces the pertinence and effectiveness of management measures.

[0053] After research, it was found that the existing technology has many shortcomings in regional management and user behavior analysis, which limits its effectiveness and flexibility in practical applications.

[0054] First, traditional video surveillance systems usually rely on static cameras and manual monitoring, which makes the system lack flexibility and adaptability. Since these systems are often fixed in a specific location, they cannot dynamically adjust the monitoring range, resulting in an inability to fully cover user behavior in complex environments. In addition, static monitoring is easily affected by environmental changes (such as lighting, weather, etc.), which reduces the accuracy and reliability of data collection.

[0055] Secondly, existing technologies are relatively weak in data processing and analysis capabilities. Traditional methods mostly rely on statistical analysis and cannot effectively process large-scale, multi-dimensional data, especially in the face of real-time data streams. This limitation makes it difficult for the system to quickly respond to changes in user behavior, resulting in delayed decision-making and failure to meet management needs in a rapidly changing environment.

[0056] In addition, existing technologies are also insufficient in the depth of user behavior analysis. Many traditional systems cannot effectively use machine learning or deep learning algorithms for data mining, resulting in a one-sided understanding of user groups. The classification and prediction of user behavior are often based on simple rules, but lack in-depth data-driven analysis, and cannot accurately capture user needs and behavior patterns. This greatly reduces the pertinence and effectiveness of management measures.

[0057] Finally, existing technologies often lack dynamic feedback mechanisms and cannot monitor and adjust management strategies in real time. Even if a certain amount of data is collected, it is often not possible to convert it into effective management measures in a timely manner, resulting in waste of resources and decision-making errors. This information island phenomenon makes it difficult for urban managers to form a comprehensive understanding of regional conditions, thus affecting governance effectiveness.

[0058] In summary, the existing technology has significant shortcomings in terms of flexibility, data processing capabilities, depth of user behavior analysis, and dynamic feedback mechanisms, which limit its effective application in regional management. In contrast, the regional management method based on AIGC proposed in this application can better solve these problems and improve the level of intelligent management and the scientific nature of decision-making.

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] It is understandable that the method provided in the present application can be applied to a processing device, which is a processing device that can perform regional management, such as a terminal device or a server that can perform regional management. The method provided in the present application can be executed independently by a terminal device or a server, or can be applied to a network scenario in which a terminal device and a server communicate, and is executed by the cooperation of a terminal device and a server. Among them, the terminal device can be a computer, a mobile phone and other devices. The server can be understood as an application server or a Web server. In actual deployment, the server can be a stand-alone server or a cluster server.

[0061] Figure 1 A flowchart of a regional management method based on AIGC provided in this application, the method comprises the following steps:

[0062] S101: Collecting user behavior data, video surveillance data, and environmental data in the target area through a front-end image acquisition device or an IoT device.

[0063] The processing device collects the user's behavior data, video surveillance data, and environmental data in the target area through the front-end image acquisition device or the Internet of Things device. The processing device can use advanced front-end image acquisition devices (such as drones, cameras) and Internet of Things devices to collect a variety of information in the target area. Specifically, first, the front-end image acquisition device captures the user's behavior data in real time through the camera or drone installed in the target area. These devices can mark the user's activities in a specific area, such as walking, staying, interacting, and other behaviors. This real-time monitoring lays the foundation for subsequent data processing.

[0064] In one possible implementation, the collected behavior data can be processed by artificial intelligence algorithms to generate more detailed activity trajectory data, residence time data, and interaction behavior data. Activity trajectory data represents the user's movement path in the target area, residence time data records the length of time the user stays in a specific location, and interaction behavior data involves the interaction between the user and the environment or other users. Accurate extraction of this information is crucial to understanding user behavior patterns, thereby providing data support for regional management.

[0065] The collection of environmental data is equally important. IoT devices can collect environmental information in the target area, such as temperature, humidity, light, noise level, etc. These environmental data will provide background information for subsequent multimodal fusion, helping to more fully understand the relationship between user behavior and the environment. By combining behavioral data and environmental data, it is possible to more deeply analyze the behavioral characteristics of users under specific environmental conditions, providing an important basis for the formulation of management strategies.

[0066] S102: Match the behavior data of the target area users with the user data of the target area users to obtain comprehensive data of the target area users.

[0067] The processing device needs to match the behavior data of users in the target area with the user data of the user to form comprehensive data. The key to this process lies in the integration and association of data. User data may include basic information of the user, such as age, gender, occupation, interests, etc., which combined with the behavior data can form a panoramic view of the user. Through this integration, the system can more comprehensively understand the user's behavior patterns and the motivations behind them.

[0068] The matching process usually requires data preprocessing to ensure the consistency and accuracy of behavioral data and user data. This involves steps such as data cleaning, standardization, and deduplication to eliminate data noise and redundant information. Through efficient data matching algorithms, user behavior can be quickly associated with its basic information to form a detailed user portrait.

[0069] The comprehensive data obtained not only includes basic information and behavior data of users, but can also be used to analyze user preferences and needs. This comprehensive view lays the foundation for subsequent classification of user groups, allowing managers to formulate more personalized management strategies based on the characteristics of different users. At the same time, the generation of comprehensive data also provides rich data resources for the training of subsequent machine learning models, improving the accuracy of classification and prediction.

[0070] S103: Process the comprehensive data using a machine learning algorithm to obtain user group classification data.

[0071] The processing device processes the comprehensive data through a machine learning algorithm and finally obtains user group classification data. The processing device divides users into different groups by analyzing their behaviors and characteristics for subsequent management and services. First, the comprehensive data is analyzed using deep learning and clustering algorithms. The clustering model can divide users into groups with similar characteristics based on their behavioral characteristics and basic information. For example, some users may show high-frequency visit behaviors, while others may prefer to stay for a short time.

[0072] This process can use unsupervised learning methods to perform cluster analysis, and the clustering results can clearly show the user's behavior categories. By extracting features from the data, the system can automatically identify potential user groups and help managers understand the needs and behavior patterns of different groups. This analysis not only helps improve management efficiency, but also provides managers with more targeted decision-making basis.

[0073] In addition, user group classification data can be continuously updated and optimized through subsequent feedback mechanisms. As data increases and user behavior changes, machine learning models can be retrained on new data to adapt to new trends and patterns. This dynamic update capability enables regional management to reflect changes in user behavior in real time and adjust management strategies in a timely manner.

[0074] S104: Perform multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result.

[0075] The processing equipment fuses data from different sources in a multi-modal manner to form a more comprehensive and accurate analysis result. The fusion of video surveillance data, comprehensive data, and environmental data can provide a richer information perspective for regional management. First, based on the weather data in the environmental data, the modal fusion of video surveillance data and comprehensive data under weather factors is performed. This process can reveal the impact of weather changes on user behavior. For example, on rainy days, users' activity patterns may be different, and this change needs to be considered in the regional management strategy.

[0076] Secondly, based on the time data in the environmental data, the video surveillance data and the comprehensive data are modally fused under the time factor. This process can help managers understand the differences in user behavior in different time periods, thereby optimizing resource allocation and management strategies. By analyzing user activities in different time periods, peak and trough periods can be identified, providing managers with a basis for dynamic adjustments.

[0077] Finally, the first modal fusion result and the second modal fusion result are modally fused to obtain a comprehensive multimodal fusion result. This result not only covers the user's behavior pattern, but also takes into account the influence of environmental factors, providing more comprehensive support for the management strategy of the target area. Through this multi-dimensional data analysis, managers can formulate more scientific and effective management plans and improve the pertinence of regional management.

[0078] S105: Determine a target area management strategy based on the multimodal fusion result and the user group classification data.

[0079] The processing device determines the target area management strategy based on the multimodal fusion results and the user group classification data.

[0080] The method provided in the present application collects the behavior data, video surveillance data and environmental data of the users in the target area through a front-end image acquisition device or an Internet of Things device. Then, the behavior data of the users in the target area is matched with the user data of the users in the target area to obtain the comprehensive data of the users in the target area. The comprehensive data is processed by a machine learning algorithm to obtain user group classification data. The video surveillance data, comprehensive data and environmental data are multimodally fused to obtain a multimodal fusion result. The target area management strategy is determined based on the multimodal fusion result and the user group classification data.

[0081] First of all, this application has significantly improved data processing and analysis capabilities. By introducing machine learning and deep learning algorithms, the system can efficiently process large-scale, multi-dimensional data streams. This capability enables the system to quickly respond to changes in user behavior, thereby improving the timeliness and effectiveness of management decisions. Based on the analysis of real-time data streams, managers can obtain more accurate insights into user behavior and provide a scientific basis for regional management.

[0082] Secondly, this application also performs well in the depth of user behavior analysis. By comprehensively utilizing machine learning algorithms, the system can conduct comprehensive data mining and accurately identify and classify user groups. This data-driven analysis method can deeply capture user needs and behavior patterns, helping managers to formulate more targeted management strategies, thereby improving the efficiency and effectiveness of governance.

[0083] To sum up, the AIGC-based regional management method of this application has significant advantages in flexibility, data processing capabilities, depth of user behavior analysis and dynamic feedback mechanism, which can effectively improve the intelligence level of regional management and the targeted decision-making, and meet the needs of modern urban management.

[0084] This application also provides a Figure 2 The structural diagram of a regional management device based on AIGC is shown, and the regional management device based on AIGC 200 includes the following modules:

[0085] The acquisition module 201 is used to collect the behavior data, video surveillance data and environmental data of users in the target area through a front-end image acquisition device or an Internet of Things device;

[0086] A matching module 202, used to match the behavior data of the target area users with the user data of the target area users to obtain the comprehensive data of the target area users;

[0087] A processing module 203 is used to process the comprehensive data using a machine learning algorithm to obtain user group classification data;

[0088] A fusion module 204 is used to perform multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result;

[0089] The decision module 205 is used to determine a target area management strategy based on the multimodal fusion result and the user group classification data.

[0090] In a possible implementation, the acquisition module is specifically used to:

[0091] Marking the behavior of users in the target area by using a drone, a camera or the IoT device to obtain a marking result;

[0092] Generate activity trajectory data, residence time data and interaction behavior data based on the marking results;

[0093] Processing the activity trajectory data, the residence time data, and the interaction behavior data using a machine learning algorithm to obtain behavior data of users in a target area;

[0094] Video surveillance data and environmental data are collected through drones, cameras or the IoT devices.

[0095] In a possible implementation manner, the processing module is specifically configured to:

[0096] Clustering the comprehensive data based on a deep learning clustering model to obtain a clustering result, wherein the clustering result is used to represent the user's behavior category;

[0097] User group classification data is determined based on the clustering results.

[0098] In a possible implementation, the fusion module is specifically used to:

[0099] Based on the weather data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under weather factors to obtain a first modal fusion result;

[0100] Based on the time data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under the time factor to obtain a second modal fusion result;

[0101] The first modal fusion result and the second modal fusion result are modally fused to obtain a multimodal fusion result.

[0102] The device provided by the present application collects the behavior data, video surveillance data and environmental data of the users in the target area through the front-end image acquisition device or the Internet of Things device. Then, the behavior data of the users in the target area is matched with the user data of the users in the target area to obtain the comprehensive data of the users in the target area. The comprehensive data is processed by a machine learning algorithm to obtain the user group classification data. The video surveillance data, the comprehensive data and the environmental data are multimodally fused to obtain the multimodal fusion result. The target area management strategy is determined based on the multimodal fusion result and the user group classification data.

[0103] First of all, this application has significantly improved data processing and analysis capabilities. By introducing machine learning and deep learning algorithms, the system can efficiently process large-scale, multi-dimensional data streams. This capability enables the system to quickly respond to changes in user behavior, thereby improving the timeliness and effectiveness of management decisions. Based on the analysis of real-time data streams, managers can obtain more accurate insights into user behavior and provide a scientific basis for regional management.

[0104] Secondly, this application also performs well in the depth of user behavior analysis. By comprehensively utilizing machine learning algorithms, the system can conduct comprehensive data mining and accurately identify and classify user groups. This data-driven analysis method can deeply capture user needs and behavior patterns, helping managers to formulate more targeted management strategies, thereby improving the efficiency and effectiveness of governance.

[0105] To sum up, the AIGC-based regional management method of this application has significant advantages in flexibility, data processing capabilities, depth of user behavior analysis and dynamic feedback mechanism, which can effectively improve the intelligence level of regional management and the targeted decision-making, and meet the needs of modern urban management.

[0106] An embodiment of the present application also provides an AIGC-based regional management device, wherein the device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device performs the steps of the AIGC-based regional management method described in any embodiment of the present application.

[0107] In practical applications, the computer-readable storage medium may be any combination of one or more computer-readable media, which may be a computer-readable signal medium or a computer-readable storage medium.

[0108] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0109] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0111] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely schematic, in which the unit described as a separate component may or may not be physically separated, and the component prompted as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0113] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A regional management method based on AIGC, characterized in that: include: Collect user behavior data, video surveillance data, and environmental data in the target area through front-end image acquisition devices or IoT devices; Matching the behavior data of the target area users with the user data of the target area users to obtain the comprehensive data of the target area users; Processing the comprehensive data using a machine learning algorithm to obtain user group classification data; Performing multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result; A target area management strategy is determined based on the multimodal fusion result and the user group classification data.

2. The method according to claim 1, characterized in that The collecting of the behavior data, video surveillance data and environmental data of users in the target area by the front-end image acquisition device or the Internet of Things device includes: Marking the behavior of users in the target area by using a drone, a camera or the IoT device to obtain a marking result; Generate activity trajectory data, residence time data and interaction behavior data based on the marking results; Processing the activity trajectory data, the residence time data, and the interaction behavior data using a machine learning algorithm to obtain behavior data of users in a target area; Video surveillance data and environmental data are collected through drones, cameras or the IoT devices.

3. The method according to claim 1, characterized in that The method of processing the comprehensive data using a machine learning algorithm to obtain user group classification data includes: Clustering the comprehensive data based on a deep learning clustering model to obtain a clustering result, wherein the clustering result is used to represent the user's behavior category; User group classification data is determined based on the clustering results.

4. The method according to claim 1, characterized in that: The multimodal fusion of the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result includes: Based on the weather data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under weather factors to obtain a first modal fusion result; Based on the time data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under the time factor to obtain a second modal fusion result; The first modal fusion result and the second modal fusion result are modally fused to obtain a multimodal fusion result.

5. A regional management device based on AIGC, characterized in that: include: An acquisition module is used to collect behavior data, video surveillance data, and environmental data of users in the target area through a front-end image acquisition device or an IoT device; A matching module, used for matching the behavior data of the target area users with the user data of the target area users to obtain the comprehensive data of the target area users; A processing module, used to process the comprehensive data using a machine learning algorithm to obtain user group classification data; A fusion module, used for performing multimodal fusion on the video surveillance data, the comprehensive data and the environmental data to obtain a multimodal fusion result; A decision module is used to determine a target area management strategy based on the multimodal fusion result and the user group classification data.

6. The device according to claim 5, characterized in that The acquisition module is specifically used for: Marking the behavior of users in the target area by using a drone, a camera or the IoT device to obtain a marking result; Generate activity trajectory data, residence time data and interaction behavior data based on the marking results; Processing the activity trajectory data, the residence time data, and the interaction behavior data using a machine learning algorithm to obtain behavior data of users in a target area; Video surveillance data and environmental data are collected through drones, cameras or the IoT devices.

7. The device according to claim 5, characterized in that The processing module is specifically used for: Clustering the comprehensive data based on a deep learning clustering model to obtain a clustering result, wherein the clustering result is used to represent the user's behavior category; User group classification data is determined based on the clustering results.

8. The device according to claim 5, characterized in that The fusion module is specifically used for: Based on the weather data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under weather factors to obtain a first modal fusion result; Based on the time data in the environmental data, modal fusion is performed on the video surveillance data and the comprehensive data under the time factor to obtain a second modal fusion result; The first modal fusion result and the second modal fusion result are modally fused to obtain a multimodal fusion result.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store the computer program; The processor is used to execute the computer program to implement the AIGC-based area management method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the AIGC-based area management method according to any one of claims 1 to 4 is implemented.

Images