A Smart City Venue Recommendation Method and System Based on the Internet of Things

Abstract

This specification provides an embodiment of a smart city location recommendation method and system based on the Internet of Things (IoT), executed by a management platform of the smart city location recommendation IoT system. The method includes acquiring location information and pedestrian flow information for at least one location; wherein, the location information includes the number of locations, the distance between locations, and the control measures for entrances and exits and passageways in each location; the control measures include whether the entrances and exits and passageways in each location are closed; based on the location information and pedestrian flow information of at least one location, determining multiple candidate control schemes for at least one location; and based on the multiple candidate control schemes, determining a target control scheme for at least one location.

Description

Technical Field

[0001] This specification relates to the fields of intelligent algorithms and the Internet of Things (IoT), and in particular to a smart city location recommendation method and system based on the Internet of Things. Background Technology

[0002] During periods of high foot traffic, such as peak tourist seasons or holidays, it is necessary to implement relevant control measures in crowded places to appropriately reduce the flow of people, thereby reducing the risk of epidemic transmission and minimizing safety hazards.

[0003] Typically, before determining control measures, it is necessary to first determine or predict the pedestrian flow at a location. For example, patent CN201911360825.3 discloses a pedestrian flow prediction method that uses a Long Short-Term Memory (LSTM) network model and a fully connected neural network model to determine the target pedestrian flow for the time period to be predicted. As another example, patent CN202011310784.X discloses a pedestrian flow control method that constructs a pedestrian flow heatmap based on a heatmap algorithm.

[0004] However, the flow of people varies from place to place, and the control measures also differ to some extent. Therefore, how to apply different control measures to different places in a targeted manner and control the flow of people in these places more accurately is an urgent problem to be solved. Summary of the Invention

[0005] This specification provides one or more embodiments of a smart city location recommendation method based on the Internet of Things (IoT), executed by a management platform of a smart city location recommendation IoT system. The method includes: acquiring location information and pedestrian flow information for at least one location; wherein the location information includes the number of locations, the distance between locations, and control measures for entrances / exits and passageways in each location; the control measures include whether entrances / exits and passageways in each location are closed; determining multiple candidate control schemes for the at least one location based on the location information and pedestrian flow information; and determining a target control scheme for the at least one location based on the multiple candidate control schemes.

[0006] This specification provides one or more embodiments of a smart city location recommendation IoT system. The system includes a management platform configured to perform the following operations: acquiring location information and pedestrian flow information for at least one location; wherein the location information includes the number of locations, the distance between locations, and control measures for entrances / exits and passageways in each location; the control measures include whether entrances / exits and passageways in each location are closed; determining multiple candidate control schemes for the at least one location based on the location information and pedestrian flow information; and determining a target control scheme for the at least one location based on the multiple candidate control schemes.

[0007] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the Internet of Things-based smart city location recommendation method. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 These are exemplary schematic diagrams of a smart city location recommendation Internet of Things system according to some embodiments of this specification;

[0010] Figure 2 This is an exemplary flowchart of a smart city location recommendation method according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart illustrating the determination of candidate control schemes according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart illustrating the determination of a target control scheme according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary flowchart illustrating the determination of evaluation values ​​according to some embodiments of this specification;

[0014] Figure 6 This is an exemplary schematic diagram of a pedestrian flow map according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] Unless the context clearly indicates an exception, words such as "a," "an," "a kind," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0019] Figure 1 This is an exemplary structural diagram of a smart city location recommendation Internet of Things system according to some embodiments of this specification.

[0020] An Internet of Things (IoT) system is an information processing system that includes some or all of the following platforms: a user platform, a service platform, a management platform, a sensor network platform, and an object platform. The user platform is a functional platform that enables the acquisition of user-sensed information and the generation of control information. The service platform connects the management platform and the user platform, providing services for sensing and control information communication. The management platform coordinates and manages the connections and collaboration between various functional platforms (such as the user platform and the service platform). The management platform aggregates information from the IoT operating system and provides sensing and control management functions. The sensor network platform is a functional platform that manages sensor communication. In some embodiments, the sensor network platform can connect the management platform and the object platform, enabling sensing and control information communication. The object platform is a functional platform for generating sensing information.

[0021] Information processing in an IoT system can be divided into user-perceived information processing and control information processing. Control information can be generated based on user-perceived information. In some embodiments, control information may include user-demand control information, and user-perceived information may include user query information. The processing of perception information involves the object platform acquiring the perception information and transmitting it to the management platform via the sensor network platform. User-demand control information is transmitted from the management platform to the user platform via the service platform, thereby controlling the sending of prompt information.

[0022] In some embodiments, when an IoT system is applied to urban management, it can be referred to as a smart city IoT system.

[0023] In some embodiments, such as Figure 1As shown, the recommended IoT system 100 for smart city locations may include a user platform 110, a service platform 120, a management platform 130, a sensor network platform 140, and an object platform 150.

[0024] User platform 110 can be a platform for interacting with users. Users can be administrators, tourists, etc. In some embodiments, user platform 110 can be configured as a terminal device. For example, the terminal device can include a mobile device, a tablet computer, etc., or any combination thereof. In some embodiments, user platform 110 can be used to receive user input requests and / or instructions. For example, user platform 110 can obtain user query requests regarding pedestrian flow and pedestrian flow control plans in multiple areas of the city through the terminal device. In some embodiments, user platform 110 can provide feedback to users through the terminal device. For example, user platform 110 can display pedestrian flow control plans for multiple areas of the city to users through the terminal device (e.g., a display). In some embodiments, user platform 110 can send user input requests and / or instructions to service platform 120 and can obtain feedback information from service platform 120.

[0025] Service platform 120 can be a platform for conveying user needs and control information, connecting user platform 110 and management platform 130. In some embodiments, service platform 120 may include processing equipment and other components. The processing equipment may be a server or a group of servers. In some embodiments, service platform 120 may be centrally located. Centralized location means that service platform 120 uniformly receives, sends, and processes data. For example, service platform 120 can send a user's query command for crowd control plans for multiple areas of a city to management platform 130. As another example, service platform 120 can send crowd control plans for multiple areas of a city generated by management platform 130 to user platform 110.

[0026] The management platform 130 can refer to a platform that coordinates and manages the connections and collaboration between various functional platforms, gathers all the information of the Internet of Things (IoT), and provides sensing, management, and control functions for the IoT operating system. For example, the management platform 130 can obtain pedestrian traffic information (e.g., pedestrian traffic at multiple entrances and exits of the locations) from the sensor network platform 140, and determine a pedestrian traffic control plan based on the pedestrian traffic information of multiple locations within the target area. In some embodiments, the management platform 130 can interact with the service platform 120. For example, the management platform 130 can send pedestrian traffic control plans for each location to the service platform 120. In some embodiments, the management platform 130 may include processing equipment and other components. The processing equipment may be a server or a server group. In some embodiments, the management platform 130 may be a remote platform controlled by administrators, artificial intelligence, or preset rules.

[0027] In some embodiments, the management platform 130 may adopt a front-distributed layout. A front-distributed layout may refer to the management platform including a central database and multiple independent sub-platforms. Each sub-platform stores, processes, and / or transmits corresponding data based on different data sources. Each sub-platform can further aggregate the processed data into the central database. The management platform 130 can analyze and process the aggregated data, store it, and then transmit the data to the service platform 120 through the central database. In some embodiments, the multiple sub-platforms included in the management platform 130 can be determined based on preset areas within a city. For example, the management platform 130 may include multiple sub-platforms such as Area A Management Sub-platform, Area B Management Sub-platform, and Area C Management Sub-platform.

[0028] In some embodiments, in response to a user's query request for a pedestrian flow control plan, the management platform 130 can obtain pedestrian flow information for locations within a corresponding area from the sensor network platform 140, and then determine a pedestrian flow control plan. For example, the management platform 130 can store, analyze, and process pedestrian flow-related information for locations in areas A, B, and C of the city through area A management sub-platforms, and upload it to the management platform 130's overall database; the management platform 130 can also further analyze and process the pedestrian flow-related data in the overall database to obtain a pedestrian flow control plan, and then upload the pedestrian flow control plan to the service platform 120 through the overall database.

[0029] The sensor network platform 140 can be a functional platform for managing sensor communication. In some embodiments, the sensor network platform 140 can connect the management platform 130 and the object platform 150 to realize the functions of sensing communication for perceptual information and sensing communication for control information. In some embodiments, the sensor network platform 140 may include multiple sensor network sub-platforms.

[0030] In some embodiments, the sensor network platform 140 may be deployed independently. Independent deployment refers to the sensor network platform 140 using different sub-platforms for data storage, processing, and / or transmission of data of different types or from different data sources. In some embodiments, the multiple sub-platforms included in the sensor network platform 140 may be determined based on preset areas within a city, and may correspond to the sub-platforms of the management platform 130. For example, the sensor network platform 140 may set up a sensor network sub-platform for area A, a sensor network sub-platform for area B, and a sensor network sub-platform for area C, corresponding to the management sub-platforms for areas A, B, and C, respectively.

[0031] In some embodiments, in response to a pedestrian flow query command issued by a sub-platform of the management platform 130, the sensor network platform 140 obtains the pedestrian flow of the venue from the monitoring equipment (e.g., camera equipment) in the object platform 150 through the corresponding sub-platform of the sensor network platform 140, and uploads it to the corresponding sub-platform of the management platform 130.

[0032] The object platform 150 can be a functional platform for generating sensing information. In some embodiments, the object platform 150 may include a device configured as at least one monitoring device. For example, the monitoring device may be deployed at entrances and exits or passageways of locations in various areas of a city. In some embodiments, the object platform 150 may include multiple sub-platforms, each corresponding to a sub-platform of the sensor network platform 140. In some embodiments, the object platform 150 may be used to acquire relevant information about various locations within a target area. For example, the object platform 150 may acquire pedestrian flow information at multiple entrances and exits or passageways of a location based on monitoring devices (e.g., camera devices). In some embodiments, the object platform 150 may send the acquired relevant information about various locations within the target area to the sub-platforms of the sensor network platform 140.

[0033] It should be noted that the Smart City Location Recommended IoT System 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art will be able to make various modifications or variations based on the description in this specification. For example, the Smart City Location Recommended IoT System 100 may include one or more other suitable components to achieve similar or different functions. However, these variations and modifications will not depart from the scope of this specification.

[0034] Figure 2 This is an exemplary flowchart recommended for smart city locations based on some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by management platform 130.

[0035] Step 210: Obtain location information and pedestrian flow information for at least one location.

[0036] In some embodiments, venue information may refer to information about the venue itself and / or information related to the foot traffic at that venue. For example, venue information may include the number of venues at least one location, the distance between venues, entrances and exits within the venues, passageways, and their control measures. For methods of obtaining venue information, please refer to [link to relevant documentation]. Figure 1 The relevant description in the document.

[0037] In some embodiments, the number of venues may refer to the total number of venues within a certain area. For example, the number of venues may be determined based on the total number of venues within a preset distance range (e.g., 3km, 5km, etc.) from venue A. Alternatively, the number of venues may be determined based on the total number of venues in the street or neighborhood to which venue B belongs. Yet another example is that the number of venues may be determined based on the total number of venues (e.g., merchants in venue C) within venue C (e.g., a shopping mall).

[0038] In some embodiments, the distance between locations can refer to the distance between two locations. For example, the distance between locations can be the straight-line distance between two locations or the shortest commuting distance between two locations.

[0039] In some embodiments, an entrance or exit in a venue can refer to an entrance or exit in the venue used for access to the outside world. For example, an entrance or exit in a venue can include the entrance or exit of a scenic spot, the entrance or exit of a shopping mall, etc.

[0040] In some embodiments, a passageway may indicate a road or route between entrances. For example, a passageway may include a road between two locations, or a route between entrances and exits within a location.

[0041] In some embodiments, control measures may refer to measures implemented to control the flow and density of people in places where people gather. For example, closing off a certain entrance or exit of the place, implementing one-way traffic between two entrances or exits of the place, or placing a certain length of isolation fence or isolation strip at a certain entrance or exit of the place.

[0042] In some embodiments, pedestrian flow information may refer to the number of people entering the venue per unit time (e.g., 50 people / minute). For example, the management platform can count the pedestrian flow at all locations within the venue (e.g., entrances, exits, passageways, etc.) to obtain the pedestrian flow information for that venue. For methods of obtaining pedestrian flow information, please refer to [link to relevant documentation]. Figure 1 The relevant description in the document.

[0043] Step 220: Based on the location information and pedestrian flow information of at least one location, determine the candidate control plan.

[0044] In some embodiments, a candidate control scheme may refer to a set of control measures corresponding to at least one location. For example, a management platform may determine all candidate control measures that can be taken for multiple locations based on location information and pedestrian flow information, thereby obtaining multiple candidate control schemes.

[0045] In some embodiments, candidate control schemes can be determined by the management platform. For example, the management platform can determine candidate control schemes based on algorithms or models.

[0046] In some embodiments, the management platform can construct vectors based on pre-control pedestrian flow information, match these vectors against a historical data vector database to obtain candidate vectors, and then aggregate the control measures corresponding to these candidate vectors into candidate control schemes. For more information on determining candidate control schemes, please refer to [link to relevant documentation]. Figure 3 The relevant description in the document.

[0047] Step 230: Determine the target control scheme based on the candidate control schemes.

[0048] In some embodiments, the target control scheme may refer to the final control scheme determined from the candidate control schemes. For example, the management platform may use candidate control schemes that meet preset conditions as the target control scheme.

[0049] In some embodiments, the target control scheme can be determined by the management platform. For example, the management platform can determine the target control scheme based on algorithms or models.

[0050] In some embodiments, when the number of locations in at least one location exceeds a preset threshold, the management platform can iteratively update the candidate control schemes multiple times until the preset conditions are met, thus determining the target control scheme. For more information on determining the target control scheme, please refer to [link to relevant documentation]. Figure 4 The relevant description in the document.

[0051] In some embodiments of this specification, multiple candidate control schemes are determined based on pedestrian flow information of at least one location, and the final target control scheme is determined based on the multiple candidate control schemes. This can recommend corresponding control schemes for different locations, more accurately control pedestrian flow, save control resources, improve control efficiency, and achieve reasonable control of locations.

[0052] It should be noted that the above description of process 200 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 200 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0053] Figure 3This is an exemplary flowchart illustrating the determination of candidate control schemes according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by management platform 130.

[0054] Step 310: Construct a first feature vector corresponding to at least one location based on the location information and pedestrian flow information of at least one location.

[0055] In some embodiments, the pedestrian traffic information of a venue may refer to the pedestrian traffic information of the venue before the implementation of the target control plan. In some embodiments, the first feature vector refers to a feature vector that characterizes the attributes or characteristics of the venue (e.g., venue information, pedestrian traffic information, etc.).

[0056] In some embodiments, a feature of a location corresponds to an element of a first feature vector, and each element value of the first feature vector can represent the feature value of its corresponding feature. For example, the first feature vector can be (a, b, c, d, e, f), where a can represent the number of locations, b can represent the distance between locations, c can represent entrances and exits in the locations, d can represent passageways, e can represent control measures, and f can represent pedestrian flow information. In some embodiments, the values ​​of the elements in the first feature vector can be the actual values ​​of the features; for example, the element value a = 30 can represent that there are 30 locations. In other embodiments, the actual situation of the features can be classified according to a preset correspondence, and the classified values ​​can be used as the values ​​of the elements in the location feature vector. For example, the preset correspondence of control measure e can be: e = 0 indicates that the control measure is in an uncontrolled state, e = 1 indicates that the control measure adopted by the location is the first control measure, e = 2 indicates that the control measure adopted by the location is the second control measure, etc., where the first control measure and the second control measure are any two different preset control measures, and this specification does not limit them.

[0057] The vector database includes historical data vectors from multiple locations. In some embodiments, the management platform 130 acquires historical data from multiple locations, constructs multiple historical data vectors based on the historical data, and forms a vector database.

[0058] In some embodiments, a historical data vector may refer to a historical feature vector of a venue constructed by the management platform 130 based on the venue's historical data. The construction of the historical data vector can refer to the methods for constructing venue vectors described above. In some embodiments, historical data may refer to data related to the venue's historical foot traffic. For example, historical data may include historical foot traffic information and corresponding historical control measures, historical control plans, etc.

[0059] Step 320: Based on the first feature vector, perform vector retrieval in the vector database and select vectors in the vector database whose vector distance from the first feature vector is less than a preset distance threshold as candidate vectors.

[0060] In some embodiments, the candidate vector can refer to a historical data vector in the quantitative database that has a certain degree of similarity to the first feature vector of the location.

[0061] In some embodiments, the management platform 130 can determine the vector distance between the first feature vector and each historical data vector in the vector database, and select vectors in the vector database whose vector distance to the first feature vector is less than a preset distance threshold as candidate vectors. The vector distance includes, but is not limited to, Euclidean distance, cosine distance, Mahalanobis distance, Chebyshev distance, and / or Manhattan distance.

[0062] Step 330: Determine the control measures corresponding to the candidate vectors as candidate control measures.

[0063] In some embodiments, a candidate control measure may refer to the control measure corresponding to a candidate vector. For example, in a candidate vector (a,b,c,d,e,f), if the value of the element e represents a control measure, then the management platform 130 will determine e as the candidate control measure for that candidate vector.

[0064] Step 340: Summarize the candidate control measures for the entrances and exits and passages of each of at least one location into multiple candidate control schemes.

[0065] A candidate control scheme can refer to a collection of multiple candidate control measures. In some embodiments, the management platform 130 can summarize candidate control measures for entrances, exits, passages, etc. of multiple locations into a candidate control scheme based on preset summarization rules. For example, it can summarize according to the feature values ​​of the first feature vector (e.g., control measure e, etc.), or directly summarize all candidate control schemes in the form of a matrix or table, etc.

[0066] In some embodiments of this specification, by constructing a first feature vector of the location and a vector database, the first feature vector is retrieved from the vector database to obtain candidate control schemes, thereby eliminating unreasonable control measures, improving computational efficiency, and simplifying the computational workload of subsequently determining the target control scheme.

[0067] Figure 4 This is a schematic flowchart illustrating the determination of a target control scheme according to some embodiments of this specification. In some embodiments, process 400 may be executed by the management platform 130. Figure 4 As shown, process 400 may include the following steps:

[0068] In some embodiments, when the number of locations at at least one location exceeds a preset number threshold, the management platform 130 can determine a target control scheme through a preset algorithm.

[0069] The preset quantity threshold can be the number of locations pre-set based on experience. For example, the preset quantity threshold could be 50, 100, etc.

[0070] Preset algorithms can refer to methods that use modeling or various analytical algorithms to deduce and determine target control schemes. For example, management platform 130 can generate multiple candidate control schemes based on the combination of the open or closed states of multiple control measures in multiple locations, analyze each candidate control scheme one by one to determine the optimal control scheme, and determine the open or closed state of control measures in each location based on the optimal control scheme.

[0071] In some embodiments, the management platform 130 may perform multiple rounds of iterative updates on multiple candidate control schemes based on a preset algorithm until the preset conditions are met, at which point the target control scheme is determined.

[0072] Preset conditions can refer to the termination conditions for multiple rounds of iterative updates. See the description below for details.

[0073] In some embodiments, each round of iterative updates of multiple candidate control schemes based on a preset algorithm by the management platform 130 may include the following steps:

[0074] Step 410: Determine the evaluation value of each first candidate control scheme. When the number of iterations is 1, the first candidate control scheme is the initial multiple candidate control schemes. When the number of iterations is greater than 1, the first candidate control scheme is the multiple candidate control schemes selected in the previous iteration.

[0075] In some embodiments, the management platform 130 may set an iteration counter to determine whether the number of iteration rounds is greater than 1. When the number of iteration rounds is 1, the first candidate control scheme is the initial pool of candidate control schemes. For more information on the initial pool of candidate control schemes, see [link to relevant documentation]. Figure 2 and Figure 3 Related content.

[0076] In some embodiments, the management platform 130 may encode each of the initial multiple candidate control schemes based on preset encoding rules.

[0077] Preset coding rules can refer to rules used to characterize the open / closed status of control measures in various locations within a candidate control scheme. For example, preset coding rules characterize multiple combinations of open or closed statuses of different entrances / exits and passageways in various locations. Coding rules can be represented in various forms, such as binary coding and symbolic coding. In some embodiments, 1 and 0 can be used to represent the open and closed statuses of control measures, respectively.

[0078] In some embodiments, multiple candidate control schemes encoded based on preset encoding rules can be in the form of vectors or matrices. For example, for venues A, B, C, and D, where venue A has 3 entrances a1, a2, and a3, venue B has 2 entrances b1 and b2, venue C is an open gathering place (without entrances), and venue D has 1 entrance d1, the candidate control scheme can be ((1, 0, 1), (1, 0), (1), (0)), where the first element (1, 0, 1) represents the control method of venue A, and the other elements are similar.

[0079] An evaluation value can refer to a value used to determine whether each candidate control plan meets the requirements. For example, an evaluation value can be a value within the range [0, 1], with a larger value indicating that the corresponding candidate control plan is more compliant with the requirements. The evaluation value can be determined based on the pedestrian flow of the candidate control plan.

[0080] In some embodiments, the management platform 130 may count the number of people in each location after the control measures for each location are turned on / off according to the candidate control scheme, and determine the evaluation coefficient of each location based on the relationship between the number of people in each location and the corresponding preset number of people in each location, and determine the evaluation value of the candidate control scheme based on the evaluation coefficients of all locations in the candidate control scheme.

[0081] The evaluation coefficient characterizes whether the pedestrian flow at a certain location in the candidate control plan meets the requirements. The evaluation coefficient can be a value within the range [0, 1], with a larger value indicating better pedestrian flow control at the corresponding location. For example, when the pedestrian flow at a location in the candidate control plan after the adjustment of control measures (e.g., the total pedestrian flow at that entrance / exit / passage) is close to the location's preset pedestrian flow threshold, the evaluation coefficient is set to 1. The management platform 130 can reduce the evaluation coefficient proportionally (e.g., 0.02) based on the difference between the pedestrian flow after the adjustment of control measures and the location's preset pedestrian flow threshold (e.g., the absolute value of the difference). For example, the preset difference threshold can be 200 people. When the difference is 200 people, the evaluation coefficient is 1 - 0.02 = 0.98; when the difference is 400 people, the evaluation coefficient is reduced to 1 - 0.02 * 2 = 0.96.

[0082] In some embodiments, after obtaining the evaluation coefficients of all locations in the candidate control scheme, the management platform 130 can use the value obtained by calculating the mean square error of all evaluation coefficients as the evaluation value of the candidate control scheme.

[0083] It is understandable that the flow of people in different locations within the candidate control plan will change after adjustments to the control measures. The plan is more effective when the flow of people in each location fluctuates around its preset threshold.

[0084] In some embodiments, the assessment value can be determined based on a pedestrian flow prediction model; see [link to relevant documentation] for more details. Figure 5 And its description.

[0085] Step 420: Based on the evaluation values ​​of each first candidate control scheme, determine the second candidate control scheme from the first candidate control schemes.

[0086] The second candidate control scheme can refer to multiple candidate control schemes selected from the first candidate control scheme. The number can be a pre-set number or proportion. For example, 4 or 8 can be selected, or they can be selected according to the proportion of the first candidate control scheme (for example, 10%).

[0087] In some embodiments, the management platform 130 can determine a second candidate scheme based on the probability of selection of each scheme in the first candidate control scheme using a preset selection function. The selection function can be various preset selection operators. For example, the selection function can be a roulette wheel selection operator, an expected value selection operator, a uniform sorting operator, etc.

[0088] In some embodiments, the probability of each first candidate control scheme being selected as a second candidate control scheme can be determined based on the ratio of the evaluation value of each first candidate control scheme to the total evaluation value. The total evaluation value can be the sum of the evaluation values ​​of all first candidate control schemes. The higher the ratio of the evaluation value of a candidate control scheme to the total evaluation value, the greater its probability of being selected by the selection function.

[0089] Step 430: Transform the second candidate control scheme to determine the third candidate control scheme. The third candidate control scheme may include the new candidate control scheme generated after transforming the second candidate scheme.

[0090] Transformation can refer to a method of processing candidate control schemes based on preset rules to generate new control schemes. For example, transformation may include recombining the open / closed states of control measures for a certain location in a candidate control scheme. For instance, in a second candidate control scheme, exit a1 of location A is changed from open to closed, and exit a2 is changed from closed to open, thereby generating a third candidate control scheme.

[0091] In some embodiments, the management platform 130 may process the third candidate control scheme to determine its evaluation value. It is understood that the higher the evaluation value of the third candidate control scheme, the higher the probability that the third candidate control scheme will be selected for transformation in the next iteration.

[0092] It should be noted that the third candidate control scheme is a set of candidate control schemes. It includes the selected second candidate control scheme, new candidate control schemes generated by transforming the second candidate control scheme, and also candidate control schemes from the first candidate control scheme that were not selected. It can be understood that, based on the first candidate control scheme, new candidate control schemes will be added as the transformation process progresses.

[0093] In some embodiments, the transformation includes a first transformation and a second transformation. The management platform 130 generates multiple third candidate control schemes through the transformation.

[0094] The first transformation may be a processing method that selects two second candidate control schemes from a plurality of second candidate control schemes and exchanges the control measures of one or more locations in the two second candidate control schemes to generate one or more third candidate pairing schemes.

[0095] In some embodiments, for the two selected second candidate control schemes, the management platform 130 can exchange the control measures for the locations with higher evaluation coefficients to generate two third candidate control schemes.

[0096] For example, the two selected second candidate control schemes P1 and P2 are ((1,0,1), (1,0), (1), (0)) and ((1,1,0), (1,1), (1), (0)) respectively. Among them, the evaluation coefficient of venue A in the second candidate control scheme P1 is the highest, and the evaluation coefficient of venue B in the second candidate control scheme P2 is the highest. Then, the management platform 130 can replace the control measures (1,1,0) of venue A in the second candidate control scheme P2 with the control measures (1,0,1) of venue A in the second candidate control scheme P1 to generate the third candidate control scheme ((1,0,1), (1,1), (1), (0)); at the same time, the control measures (1,1) of venue B in the second candidate control scheme P2 can replace the control measures (1,0) of venue B in the second candidate control scheme P1 to generate the third candidate control scheme ((1,0,1), (1,1), (1), (0)). That is, based on the exchange of control measures in the above-mentioned situations with high evaluation coefficients, two new third candidate control schemes P3 and P4 are generated, namely ((1,0,1), (1,1), (1), (0)) and ((1,1,0), (1,1), (1), (0)).

[0097] It is understandable that exchanging the control measures for venues with high evaluation coefficients in the second candidate scheme can help retain and disseminate the control methods with better crowd control effects in the second candidate scheme to the new candidate scheme.

[0098] In some embodiments, the management platform 130 may select multiple pairs of second candidate control schemes for first transformation processing based on a preset first transformation quantity threshold (e.g., 3 pairs) or a preset first transformation ratio (e.g., 20%) to generate multiple pairs of third candidate control schemes. For example, if there are 20 first candidate control schemes, the management platform 130 may select 20 * 20% = 4 second candidate control schemes from the first candidate control schemes based on a preset selection function, and perform the first transformation to generate 4 third candidate control schemes accordingly.

[0099] In some embodiments, the management platform 130 can process a plurality of third candidate control schemes generated based on the first transformation to determine the evaluation value of the plurality of third candidate control schemes.

[0100] The second transformation can refer to a processing method that adjusts the open / closed status of at least one control measure for one or more locations from the third candidate control scheme generated after the first transformation.

[0101] In some embodiments, the management platform 130 can adjust one or more control measures for the location with the lowest evaluation coefficient in the third candidate control scheme. For example, it can change one or more entrances / exits of the location with the lowest evaluation coefficient from a closed state to an open state, or from an open state to a closed state, thereby generating a new third candidate control scheme.

[0102] For example, for the third candidate control scheme P3((1,0,1),(1,1),(1),(0)) generated based on the first transformation, if the evaluation coefficient of venue B is the lowest, the management platform 130 can adjust the control measures (1,1) of venue B.

[0103] In some embodiments, the management platform 130 can obtain the pedestrian flow data (e.g., pedestrian flow data of multiple entrances and exits) of all control measures for the location with the lowest evaluation coefficient in the third candidate scheme, and adjust the control measures whose pedestrian flow data does not meet the preset pedestrian flow threshold. For example, the open state (i.e., "1") of the first element of the control method (1, 1) of location B in P3 can be set to closed. Wherein, the pedestrian flow of the control measure corresponding to the first element does not meet the preset pedestrian flow threshold, then the generated third candidate control scheme is ((1, 1, 0), (0, 1), (1), (0)). It should be noted that this is only an example, and the second transformation can also be carried out in other reasonable ways. For example, the second transformation can be to adjust the control measures of the location with the lowest evaluation coefficient in the third candidate control scheme according to a preset adjustment ratio (e.g., randomly select 50% of the entrances and exits to change from open to closed) to generate a new candidate control scheme.

[0104] In some embodiments, the management platform 130 can select multiple third candidate control schemes based on a preset second transformation ratio (e.g., 5%) and perform a second transformation process to generate multiple third candidate control schemes. For example, if there are 20 third candidate control schemes, 20 * 5% = 1 third candidate control scheme can be selected from the third candidate control schemes based on a preset second transformation ratio of 5% and a preset selection function, and then the second transformation can be performed to generate a new third candidate control scheme.

[0105] Some embodiments in this specification generate a third candidate control scheme through a first transformation and a second transformation, which can improve the efficiency of iteration and help to obtain the optimal control scheme more quickly.

[0106] In some embodiments, the management platform 130 may screen the third candidate control schemes based on the evaluation values ​​of each third candidate control scheme, and determine the screened candidate control schemes as candidate control schemes to enter the next round of iteration or as the target control scheme.

[0107] For example, the management platform 130 can sort the third candidate control schemes from highest to lowest according to their evaluation values ​​and remove the lower-ranked third candidate control schemes. For instance, the management platform 130 can remove the lower-ranked third candidate control schemes according to a preset percentage (e.g., 5%) or a preset number (e.g., 8). Other suitable methods can also be used for filtering; for example, the management platform 130 can obtain the number n of newly generated third candidate control schemes in this iteration and then remove the n candidate control schemes with the lowest evaluation values. This specification does not limit the filtering method.

[0108] Step 440: Repeat the above iterative process until the preset conditions are met.

[0109] In some embodiments, the management platform 130 may repeat the process of steps 420 to 430 to iteratively update the third candidate pairing scheme until the preset conditions are met and the iteration stops.

[0110] The preset condition can be that the number of iterations is greater than the preset maximum number of iterations (e.g., 50 times, 100 times). Another example is that the preset condition can be that the evaluation value of the candidate control scheme reaches a preset expected value (e.g., 1, 0.98). Yet another example is that the preset condition can be that the maximum evaluation value of the candidate control scheme remains unchanged after n iterations, or that the difference between the maximum evaluation values ​​of the candidate control schemes in two adjacent iterations is lower than a preset difference threshold (e.g., 0.02, 0.03). It should be noted that the preset condition can be one or more combinations of the above, and this specification does not limit it.

[0111] Step 450: Determine the target control scheme from the third candidate control schemes obtained from multiple rounds of iteration.

[0112] In some embodiments, the management platform 130 may select the third candidate control scheme with the highest evaluation value from the third candidate control schemes obtained from multiple iterations as the target control scheme. For example, the management platform 130 may sort the third candidate control schemes from largest to smallest according to their evaluation values ​​and determine the third candidate control scheme with the highest ranking as the target control scheme.

[0113] In some embodiments, the management platform 130 can adjust the opening or closing status of the control measures for each location corresponding to the target control plan based on the target control plan.

[0114] Some embodiments in this specification obtain the optimal crowd control scheme through preset algorithms, thereby determining the open or closed status of control settings in multiple locations, which can reduce the manpower and time costs caused by manual calculation.

[0115] Figure 5This is an exemplary flowchart illustrating the determination of evaluation values ​​according to some embodiments of this specification. Figure 5 As shown, process 500 includes the following steps. In some embodiments, process 500 may be executed by management platform 130.

[0116] Step 510: Construct the graph structure.

[0117] The graph structure can be called a pedestrian flow graph. A pedestrian flow graph can refer to a graph constructed based on relevant information of multiple locations within a region. A pedestrian flow graph can represent the pedestrian flow relationships between multiple locations within a region. In some embodiments, the management platform 130 can construct a pedestrian flow graph based on the basic information of multiple locations within the region and the on / off status of control measures at each location. A pedestrian flow graph can include multiple nodes and multiple edges.

[0118] Nodes include one or more of the following: venues, available entrances and exits of venues, passageways, and areas where people gather in open spaces. For example... Figure 6 As shown, the nodes of the pedestrian flow map 600 include location A, location B, location C, location D, as well as entrance a1, exit a2, entrance a3, entrance b1, entrance b2, and entrance c1.

[0119] Node characteristics include node type, current pedestrian traffic over a given period, and control measures.

[0120] Node types can be used to distinguish different nodes in a pedestrian flow map. For example, node types can include locations, entrances / exits, passageways, and areas where people gather in open spaces (e.g., plazas, open areas). Figure 6 As shown, the pedestrian flow map 600 includes location nodes: location A node, location B node, location C node; entrance / exit nodes: entrance / exit a1 node, exit a2 node, entrance a3 node, etc.

[0121] Node types can also be pre-defined based on experience to characterize locations with strong correlation to traffic flow. For example, nodes could be bar nodes, shopping mall nodes, cinema nodes, etc. For instance, location A node in the pedestrian flow map 600 could be a shopping mall (not shown in the figure).

[0122] The current period of pedestrian traffic can be a preset time period ending at the current point in time. For example, the pedestrian traffic of the previous week, the pedestrian traffic of the previous month, etc.

[0123] Control measures include open / closed status. This indicates whether entry is permitted. For example, whether a venue, entrance / exit, or open area gatherings are closed (whether movement of people is permitted). For more information on control measures, see [link to relevant documentation]. Figure 1 And its description.

[0124] The edges of a pedestrian flow graph can be formed by connecting nodes whose distances meet a preset distance threshold. In some embodiments, the edges of the pedestrian flow graph can be directed edges, which can be used to represent the direction of pedestrian flow between nodes. For example, a node of type entrance / exit, when the entrance / exit is a one-way entrance (e.g., exit or entrance), other nodes are connected to this node, and the arrows point to the directed edges formed by this node, indicating that pedestrian flow is flowing in from other nodes and no pedestrian flow is flowing out. Figure 6 As shown, the edges of the pedestrian flow graph 600 include: the edge generated by connecting the location node A to the entrance / exit node a1 (which can be entered or exited) is a bidirectional edge; the edge generated by connecting the location A to the exit node a2 (which can only be exited) is a unidirectional edge.

[0125] Edge features include distance. This can characterize the relative distance between nodes. For example, distance can be determined based on the distance (e.g., straight-line distance, walking distance, etc.) between the two actual locations corresponding to two location nodes.

[0126] Edge features also include feature differences. Feature differences can be used to characterize the difference in relevance between the two nodes connected by the edge. For example, feature differences can be the difference in the node types of the two nodes. For instance, if a bar is near a bookstore and a nightclub, the bar is more relevant to the nightclub than to the bookstore. Consequently, the probability of foot traffic moving from the bar to the nightclub is higher than to the bookstore. Feature differences can also be related to the distance between the two nodes. For example, if there are many places in an area, but the distance between them is large, the feature differences will also be large.

[0127] In some embodiments, the management platform 130 can construct a pedestrian flow map 600 based on relevant information of multiple locations within a target area and historical pedestrian flow data obtained from the management sub-platform and / or the total database of the management platform 130. For example, the pedestrian flow map 600 can be constructed based on relevant information of multiple locations in city A and the control measures for each location.

[0128] Step 520: Input the graph structure into the evaluation model, output the pedestrian flow of all nodes in the graph structure within a preset future period, and obtain the evaluation value of the candidate control scheme.

[0129] The evaluation model can refer to the model used to process pedestrian flow maps. The evaluation model can be a pre-trained machine learning model. The evaluation model can include any one or a combination of other models, such as recurrent neural network models, convolutional neural network models, or other custom model structures.

[0130] In some embodiments, the evaluation model can be a graph neural network model. The management platform 130 can input the pedestrian flow map 600 into the evaluation model, and based on the processing of the evaluation model, output the pedestrian flow for a preset future period of time for all nodes of the pedestrian flow map 600.

[0131] In some embodiments, the evaluation model can be trained using multiple labeled training samples. The training samples can be multiple sample pedestrian flow maps constructed based on relevant information and historical control measures for multiple locations within multiple sample areas. The labels can be the historical pedestrian flow corresponding to the sample pedestrian flow maps after the implementation of historical control measures. These historical pedestrian flow labels can be determined by summing the pedestrian flow of all locations corresponding to the sample pedestrian flow maps. Labels can be manually labeled. During training, multiple labeled training samples can be input into the initial evaluation model. A loss function is constructed using the labels and the output of the initial evaluation model. The parameters of the evaluation model are iteratively updated based on the loss function. Training is complete when the loss function of the initial evaluation model converges or the number of iterations reaches a threshold, resulting in a trained evaluation model.

[0132] In some embodiments, different control measures in the pedestrian flow map 600 can correspond to different candidate control schemes. Based on the processing of the pedestrian flow map 600 using the evaluation model, the evaluation value of each candidate control scheme among multiple candidate control schemes can be obtained.

[0133] For example, the management platform 130 can obtain the historical pedestrian traffic data of the locations corresponding to all nodes. After obtaining the predicted pedestrian traffic for a future period of time for all nodes output by the pedestrian traffic map 600, the evaluation coefficient of all nodes is determined based on the relationship between the pedestrian traffic output by the nodes and the historical pedestrian traffic data, and then the evaluation value of the candidate control scheme is determined.

[0134] For information regarding evaluation coefficients and assessment values, please refer to [link / reference]. Figure 4 And its description.

[0135] In some embodiments, the management platform 130 can determine the pedestrian flow of a node based on the control method of a certain location in the candidate control scheme. The pedestrian flow of a node can be determined based on a formula. Specifically, if the location corresponding to the node is a closed node, the pedestrian flow of the closed node is zero; if the location corresponding to the node is a non-closed node, the pedestrian flow of the non-closed node can be determined based on a formula, wherein the parameters of the formula are related to the pedestrian flow of the non-closed node before it is closed to its adjacent closed nodes.

[0136] In some embodiments, the management platform 130 may determine the visitor flow of a node based on the following formula.

[0137] V` i=p*V i +d∑ k＝1 (V k *R*Q) (1)

[0138] In formula (1), V` i V represents the pedestrian flow of a non-closed node after the pedestrian flow graph update of 600. i This represents the pedestrian flow before the update of the pedestrian flow graph 600. i > 0, indicating the i-th non-closed node in the pedestrian flow graph 600. p and d are preset weight coefficients, for example, p = 0.3, d = 0.5.

[0139] V k To be with node V i The value of a connected node that changed from an open node to a closed node in the current pedestrian flow graph update 600 represents the pedestrian flow before the node was closed. k is greater than or equal to 1.

[0140] It is understandable that, with non-closed node V i When a connected node changes from open to closed, the flow of people from that node will move to its adjacent open node. Here, Q represents the flow of people from V... k Flow to (transfer to) V i The probability value of Q can be preset, for example, Q = 0.3. It should be noted that the value of Q represents the probability of pedestrian flow shifting, and it can also be determined based on the characteristic differences of the edges of the nodes. It can be understood that when two nodes are similar in type, the value of Q is larger.

[0141] The value of R in formula (1) can be determined based on the distance and / or feature difference values ​​of the edge features. Non-closed node V i People flow in the updated People Flow Map 600 V` i The value of R is positively correlated with the value of R. It is understandable that the value of R is larger when two nodes are of similar types (e.g., bars and nightclubs) or are close to each other.

[0142] In some embodiments, see Figure 4 Among the multiple candidate control schemes determined by the preset algorithm, as a new candidate control scheme is generated, the management platform 130 can refer to the control method of the newly generated candidate control scheme to update the control method of the corresponding node in the pedestrian flow map 600 (e.g., update the whether the node is closed). At the same time, the pedestrian flow of the non-closed nodes in the pedestrian flow map 600 is updated by formula (1). Finally, the updated pedestrian flow map 600 is processed by the evaluation model to obtain the evaluation value of each newly generated candidate control scheme.

[0143] Some embodiments in this specification process pedestrian flow maps based on evaluation models to obtain evaluation values ​​for candidate control schemes. This helps to quickly obtain evaluation values ​​for newly generated candidate control schemes, enabling more efficient determination of the optimal candidate control scheme. Furthermore, incorporating pedestrian flow data from adjacent nodes before closure and considering the probability of pedestrian flow direction after closure also makes the obtained node pedestrian flow data more accurate.

[0144] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0145] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0146] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0147] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0148] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0149] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0150] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart city location recommendation method based on the Internet of Things (IoT), executed by a management platform of a smart city location recommendation IoT system, the method comprising: Obtain venue information and pedestrian flow information for at least one location; wherein, the venue information includes the number of locations, the distance between locations, and the control measures for entrances and exits and passageways in each location; the control measures include whether the entrances and exits and passageways in each location are closed; Based on the location information and pedestrian flow information of the at least one location, multiple candidate control schemes are determined for the at least one location, including: Construct a first feature vector corresponding to the at least one location based on the location information and pedestrian flow information; Based on the first feature vector, a vector retrieval is performed in the vector database, and vectors in the vector database whose vector distance from the first feature vector is less than a preset distance threshold are selected as candidate vectors. The control measures corresponding to the candidate vectors are determined as candidate control measures; The candidate control measures corresponding to the at least one location are summarized into the multiple candidate control schemes; The candidate control schemes include a vector consisting of control measures for each location, and each candidate control scheme has one or more evaluation values; In response to a number of locations exceeding a preset threshold, a target control plan is determined using a preset algorithm, including: The multiple candidate control schemes are iteratively updated in multiple rounds until the target control scheme is determined when the preset conditions are met, including: The evaluation value of the first candidate control scheme is determined. When the number of iteration rounds is 1, the first candidate control scheme is the initial multiple candidate control schemes; when the number of iteration rounds is greater than 1, the first candidate control scheme is the multiple candidate control schemes selected in the previous iteration. Based on the evaluation value, a second candidate control scheme is determined from the first candidate control scheme; The second candidate control scheme is transformed to determine the third candidate control scheme, wherein the transformation includes a first transformation and a second transformation; The first transformation includes: selecting two second candidate control schemes from the plurality of second candidate control schemes, and exchanging the control measures of one or more locations in the two second candidate control schemes to generate one or more third candidate control schemes; The second transformation includes: adjusting the open / closed status of at least one control measure for one or more locations in the third candidate control scheme; Repeat the above iterative process until the preset condition is met; The target control scheme is determined from the third candidate control scheme obtained from multiple rounds of iteration.

2. The method according to claim 1, wherein the smart city location recommendation IoT system further comprises a user platform, a service platform, a sensor network platform, and an object platform; The user platform obtains the user's query instruction for the crowd control plan of at least one venue, and transmits the query instruction to the management platform via the service platform; The location information and the pedestrian flow information are obtained based on the object platform and transmitted to the management platform based on the sensor network platform; The method further includes: The target management plan is transmitted to the user platform based on the service platform.

3. A smart city location recommendation IoT system, characterized in that, The system includes a management platform configured to perform the following operations: Obtain venue information and pedestrian flow information for at least one location; wherein, the venue information includes the number of locations, the distance between locations, and the control measures for entrances and exits and passageways in each location; the control measures include whether the entrances and exits and passageways in each location are closed; Based on the location information and pedestrian flow information of the at least one location, multiple candidate control schemes are determined for the at least one location, including: Construct a first feature vector corresponding to the at least one location based on the location information and pedestrian flow information; Based on the first feature vector, a vector retrieval is performed in the vector database, and vectors in the vector database whose vector distance from the first feature vector is less than a preset distance threshold are selected as candidate vectors. The control measures corresponding to the candidate vectors are determined as candidate control measures; The candidate control measures corresponding to the at least one location are summarized into the multiple candidate control schemes; The candidate control schemes include a vector consisting of control measures for each location, and each candidate control scheme has one or more evaluation values; In response to a number of locations exceeding a preset threshold, a target control plan is determined using a preset algorithm, including: The multiple candidate control schemes are iteratively updated in multiple rounds until the target control scheme is determined when the preset conditions are met, including: The evaluation value of the first candidate control scheme is determined, wherein when the number of iteration rounds is 1, the first candidate control scheme is the initial multiple candidate control schemes; when the number of iteration rounds is greater than 1, the first candidate control scheme is the multiple candidate control schemes selected in the previous iteration. Based on the evaluation value, a second candidate control scheme is determined from the first candidate control scheme; The second candidate control scheme is transformed to determine the third candidate control scheme, wherein the transformation includes a first transformation and a second transformation; The first transformation includes: selecting two second candidate control schemes from the plurality of second candidate control schemes, and exchanging the control measures of one or more locations in the two second candidate control schemes to generate one or more third candidate control schemes; The second transformation includes: adjusting the open / closed status of at least one control measure for one or more locations in the third candidate control scheme; Repeat the above iterative process until the preset condition is met; The target control scheme is determined from the third candidate control scheme obtained from multiple rounds of iteration.

4. The system according to claim 3, characterized in that, The system also includes a user platform, a service platform, a sensor network platform, and an object platform; The user platform obtains the user's query instruction for the crowd control plan of at least one venue, and transmits the query instruction to the management platform via the service platform; The location information and the pedestrian flow information are obtained based on the object platform and transmitted to the management platform based on the sensor network platform; The target management plan is transmitted to the user platform based on the service platform.

Images