Region identification method and device, equipment and storage medium

Abstract

The invention discloses a region identification method and device, equipment and a storage medium. The method comprises the following steps: obtaining target region characteristics based on base station data in a target region and user data associated with the base station data; analyzing the features of the target region by using the trained classification model, and identifying the region attribute of each base station in the target region; determining a target base station group according to a plurality of base stations with the same area attribute, the area where the target base station group is located being an area to be identified; and according to the geographic position of the target base station group, drawing the boundary of the to-be-identified area, and determining the area attribute of the target base station group as the area attribute of the to-be-identified area. Through the method provided by the invention, a dynamic region without a clear identifier or boundary can be effectively identified and labeled, the comprehensiveness of map data is perfected, and the map can more accurately reflect a region activity mode based on crowd characteristics.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to a region identification method, device, equipment and storage medium. Background Art

[0002] Modern map applications usually display specific geographic information on demand, such as buildings, roads, and points of interest.

[0003] However, existing maps often rely on building boundaries or fixed geographic ranges when drawing areas, which has strong limitations. This method cannot accurately reflect the actual area and scope of use of certain areas, such as areas without fixed buildings or clear boundaries (such as construction sites, temporary facilities) and unfixed activity areas (such as actual consumer activity areas around shopping malls). The absence or inaccuracy of these areas not only affects the integrity of the map, but may also lead to analytical bias or decision-making errors in areas such as urban planning, base station layout and environmental monitoring due to the lack of comprehensive geographic information.

[0004] Therefore, how to break through the limitations of traditional map drawing and accurately present these dynamic and blurred-boundary areas has become a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a region identification method, apparatus, device and computer storage medium, which can identify regions with high mobility or instability to improve map data.

[0006] In a first aspect, an embodiment of the present application provides a region recognition method, the method comprising:

[0007] Obtaining target area characteristics based on base station data within the target area and user data associated with the base station data;

[0008] Analyze the characteristics of the target area using the trained classification model to identify the regional attributes of each base station in the target area. The classification model is trained using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels.

[0009] According to multiple base stations with the same regional attributes, a target base station group is determined, and the area where the target base station group is located is the area to be identified;

[0010] According to the geographical location of the target base station group, the boundary of the area to be identified is drawn, and the area attribute of the target base station group is determined as the area attribute of the area to be identified.

[0011] In a possible implementation manner of the first aspect, drawing a boundary of the to-be-identified area according to the geographical location of the target base station group includes:

[0012] Obtaining location information of each base station in the target base station group;

[0013] Using the convex hull algorithm, according to the location information, the target base station is selected from the target base station group, and the target base station is determined as the contour point of the area to be identified;

[0014] Connect the contour points to obtain a closed figure, which is the boundary of the area to be identified.

[0015] In a possible implementation manner of the first aspect, determining a target base station group according to multiple base stations with the same area attribute includes:

[0016] Obtain location information of multiple base stations with the same area attributes, and calculate the distance between any two of the multiple base stations;

[0017] Based on the distance between any two base stations, multiple base stations are divided into base station groups to obtain at least one target base station group, and the distance between any two base stations in the at least one target base station group is less than a preset distance.

[0018] In a possible implementation manner of the first aspect, acquiring base station data in a target area and user data associated with the base station data to obtain characteristics of the target area includes:

[0019] The regional population characteristic model is used to analyze the base station data and the user data associated with the base station data, and the base station attribute characteristics, user signaling residence characteristics and user portrait characteristics are extracted to form the characteristics of the target area.

[0020] In a possible implementation manner of the first aspect, the base station data includes base station configuration data and base station residence day detailed data, the user data associated with the base station data includes multiple tag data of the user, and the base station data and the user data associated with the base station data are analyzed by using a regional population feature model to extract base station attribute features, user signaling residence features, and user portrait features, including:

[0021] Extracting base station attribute features according to base station configuration data;

[0022] Based on the detailed data of base station residence day, the predefined time visitor characteristics, predefined date characteristics, resident population characteristics, residence duration and frequency characteristics are extracted to form the user signaling residence characteristics;

[0023] User portrait features are extracted based on the user's various label data.

[0024] In a possible implementation manner of the first aspect, the method further includes:

[0025] Acquire base station data samples, user data samples associated with the base station data samples, and area attribute labels corresponding to each base station in the base station data samples;

[0026] According to the base station data sample and the user data sample associated with the base station data sample, sample features are obtained, where the sample features include base station attribute features, user signaling residence features, and user portrait features;

[0027] The classification model is used to analyze the sample features to obtain the prediction results, which are the predicted regional attributes of each base station corresponding to the sample features;

[0028] Calculate the loss value based on the difference between the predicted regional attributes and the regional attribute labels;

[0029] Adjust the parameters of the classification model according to the loss value;

[0030] When the training stop condition is met, the classification model is output;

[0031] When the training stop condition is not met, continue to execute the step of obtaining the prediction result according to the input sample features.

[0032] In a possible implementation manner of the first aspect, the method further includes:

[0033] Analyze each feature in the sample features to determine the importance of each feature, and the importance is used for classification prediction of the classification model.

[0034] In a possible implementation manner of the first aspect, the method further includes:

[0035] The map display interface displays the area information of the area to be identified, which includes the center point coordinates, contour point sequence and area attributes.

[0036] In a possible implementation manner of the first aspect, the method further includes:

[0037] The base station attribute label of each contour point of the area to be identified is displayed on the map display interface, and the base station attribute label includes a base station identifier and area attributes.

[0038] In a second aspect, an embodiment of the present application provides a region identification device, the device comprising:

[0039] Obtaining target area characteristics based on base station data within the target area and user data associated with the base station data;

[0040] Analyzing the characteristics of the target area using a trained classification model to identify the regional attributes of each base station in the target area, wherein the classification model is trained using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels;

[0041] Determine a target base station group according to multiple base stations with the same area attribute, and the area where the target base station group is located is the area to be identified;

[0042] According to the geographical location of the target base station group, the boundary of the area to be identified is drawn, and the area attribute of the target base station group is determined as the area attribute of the area to be identified.

[0043] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement any one of the methods in the first aspect above.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the method of any one of the above-mentioned first aspects is implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements any one of the methods in the above-mentioned first aspect.

[0046] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0047] The regional identification method provided in the embodiment of the present application is based on base station data and user data associated with the base station data, deeply analyzes the regional population characteristics in the target area, and uses a classification model to identify the regional attributes of each base station in the target area, and classifies the base stations with the same regional attributes into a base station group. The area covered by this base station group is the area to be identified, and the contour boundary of the area is further drawn based on the base station group. By combining the geographical boundaries and population characteristics of the target area, this method can not only complete the missing areas in the traditional map, but also dynamically update the map information, especially in the identification of highly mobile or unstable areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application.

[0049] Figure 1 It is a flowchart of a region identification method provided in an embodiment of the present application;

[0050] Figure 2 It is a flowchart of a region identification method provided in an embodiment of the present application;

[0051] Figure 3It is a flow chart of a classification model training method provided in an embodiment of the present application;

[0052] Figure 4 is a structural schematic diagram of a region identification device provided in an embodiment of the present application;

[0053] Figure 5 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make those of ordinary skill in the art better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples consistent with some aspects of the present application as detailed in the attached claims.

[0056] Geographic resource information is an important part of spatiotemporal big data. Geographic resource information covers a wide range of geographical areas and a variety of geographical features, and the data volume is huge. Geographic resource information has important application value in many fields, such as urban planning, natural resource management, environmental monitoring, weather forecasting, agricultural production, etc., which require the collection, storage, processing and analysis of geographic resource information. Among them, how to improve the accuracy and completeness of regional attribute locations is the difficulty of geographic layer collection.

[0057] As mentioned in the background technology section, existing maps often lack clear identification and corresponding information for areas without fixed buildings or clear boundaries, as well as areas where the range of human activities is not fixed. This deficiency not only affects the integrity of map data, but may also cause problems in areas such as urban planning and base station layout. In particular, in analysis work that requires human activity orientation, the lack of geographic information in these areas can easily lead to biased analysis results or wrong decisions.

[0058] However, existing mapping or geographic information acquisition methods have various defects and cannot efficiently and accurately identify these unlabeled areas and obtain their detailed geographic information.

[0059] In order to solve this technical problem, the embodiments of the present application provide a region identification method, device, equipment and computer storage medium.

[0060] The region identification method provided in the embodiment of the present application is described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0061] Figure 1 A schematic flow chart of a region identification method provided in one embodiment of the present application is shown.

[0062] like Figure 1 As shown, the method may include the following steps.

[0063] S110 : Obtain characteristics of the target area based on base station data in the target area and user data associated with the base station data.

[0064] The target area may refer to an area to be analyzed selected by a user, or a pre-set area to be analyzed.

[0065] In one implementation, in response to user input, a range of the target area is determined on a map display interface.

[0066] For example, the user input may include: a user clicking on any one of a plurality of preset regions in the map, or a user drawing a polygon on the map. For example, the target region may be a pre-set administrative region, such as a town, township or other clearly defined administrative area.

[0067] It should be understood that the present application does not limit the specific type and range of the target area, and it can be preset according to actual needs in practical applications. However, the target area must contain at least one area to be identified.

[0068] The area to be identified may refer to an area that is not clearly marked in existing maps, an area without fixed boundaries, or an area whose characteristics change dynamically.

[0069] For example, the areas to be identified may include the following types:

[0070] Areas lacking fixed buildings or clear boundaries, such as construction sites, temporary facilities, makeshift markets, etc.

[0071] Areas with dynamic activity ranges, such as actual consumption activity areas around shopping malls, specific activity areas in parks, etc., have high mobility of people and boundaries that change with activities.

[0072] Areas with fixed locations but extended functional areas, such as schools, hospitals, or campuses, which, although clearly identified on maps, may have services or impacts beyond the boundaries marked on traditional maps.

[0073] Specific areas with high population density or mobility, such as areas around stations, exhibition venues, or large-scale events, usually have obvious dynamic properties.

[0074] Temporary or unmarked areas, such as shelters formed due to disasters or temporary needs, temporary construction areas, etc., cannot be directly obtained through traditional map data.

[0075] Base station data refers to the multi-dimensional data of all base stations in the target area.

[0076] Exemplarily, the base station data may include base station configuration data, base station residence day detailed data, and the like.

[0077] Base station configuration data refers to data such as the location, coverage, and device status of the base station.

[0078] Base station daily detailed data refers to the data on the user's stay at a certain base station within a specified time period, which may include the time the user stays in the base station coverage area, the frequency of stay, and other related behavior information.

[0079] The user data associated with the base station data refers to the user data for communication using the base station in the target area.

[0080] Exemplarily, user data may include various tag data of the user, such as user behavior data, demographic attribute data, residence time, access frequency, etc.

[0081] In one implementation, the method for obtaining base station data in the target area and user data associated with the base station data may be: obtaining multi-dimensional data including base station identification, geographic location, signal coverage, operation status, etc. from the base stations in the target area. Collecting user communication data through the base stations in the target area, including user identity tags, residence time, access frequency, demographic characteristics, etc. The base station data is associated with the user data to form a multi-dimensional data set.

[0082] The embodiment of the present application constructs a regional population characteristic model for analyzing base station data in a target area and user data associated with the base station data.

[0083] It should be noted that the regional population characteristic model is not a machine learning model, but a model based on mathematical and analytical methods, which can reflect the characteristics of base stations based on user characteristics.

[0084] In one embodiment, a regional population characteristic model is used to analyze base station data and user data associated with the base station data, extract base station attribute characteristics, user signaling residence characteristics, and user portrait characteristics to form target area characteristics.

[0085] Base station attribute features refer to the static and dynamic information describing the base stations in the target area. These features are usually provided by the configuration data of the base station and are mainly used to describe the basic location and status of the base stations in the target area.

[0086] User signaling residence characteristics refer to extracting user activity information at each base station by analyzing the communication signaling data of users in the target area. These characteristics mainly describe the behavior patterns of users in the base station coverage area.

[0087] Exemplarily, user signaling residence characteristics include, but are not limited to, predefined time visitor characteristics, predefined date characteristics, resident population characteristics, residence duration and frequency characteristics, etc.

[0088] The predefined time visitor feature refers to the dwell time data in a predefined time period (such as 18:00 to 21:00 on Friday), which reflects the user's activities in a specific time period.

[0089] Predefined date features refer to the dwell time data on predefined dates (such as holidays or weekends), reflecting the activity trends of users on specific dates.

[0090] Resident population characteristics refer to the data on the permanent situation of users in the base station coverage area, which can be classified according to residence or work type.

[0091] The dwell time and frequency characteristics refer to the dwell time data of users in different time periods (such as daytime and nighttime), or the characteristic data of the number of days users stay on weekends and weekdays.

[0092] User portrait features refer to data that describes the basic characteristics of a user based on his or her personal information.

[0093] Exemplarily, the base station data includes base station configuration data and base station residence day detailed data, and the user data associated with the base station data includes user multiple tag data. The above embodiment is implemented by including the following steps:

[0094] S111. Extract base station attribute features according to base station configuration data.

[0095] The base station attribute characteristics may include, for example: base station identification, longitude, latitude, geographic location of the base station and other auxiliary information.

[0096] S112. Extract the visitor characteristics of the predefined time, the predefined date characteristics, the resident population characteristics, the residence duration and the frequency characteristics according to the detailed data of the base station residence day to form the user signaling residence characteristics.

[0097] The method for extracting visitor features at a predefined time period may be: in a specified time period (e.g., 18:00 to 21:00 on Friday), count the length of time that users stay in the time period, filter records with a length of time greater than 30 minutes, and count by base station. Similarly, similar statistics may be performed for other specific time periods (e.g., 18:00 to 21:00 on Thursday).

[0098] The predefined date feature may be, for example, a holiday feature. The method for extracting the holiday feature may be: based on the data of a specific date (such as a weekend or a holiday), the user's residence time on that date is counted. For example, the weekend daytime data may be selected to calculate the total residence time during working hours; or the weekend night data may be selected to calculate the total residence time during residential time.

[0099] The method for extracting the resident population characteristics may be: according to the resident type of users, they are divided into two categories: residence and work, and the number of users in each category is counted according to the base station groups.

[0100] The method for extracting the residence time and frequency characteristics can be: segmenting the user residence time according to time periods (such as daytime and nighttime) and accumulating the total monthly residence time; or counting the monthly residence days according to weekends and weekdays; and segmenting the number of users according to the average monthly daytime residence time.

[0101] S113. Extract user portrait features based on the user's various tag data.

[0102] The method for extracting user portrait features is: based on the user's various label data (such as gender, age, occupation, education level, etc.), the number of people in each type of user portrait data is counted by base station group.

[0103] S114: Combine the above-extracted base station attribute features, user signaling residence features and user portrait features to form target area features.

[0104] By constructing a regional population characteristic model, based on the base station data in the target area and the user data associated with it, we extract multi-dimensional information including base station attribute characteristics, user signaling residence characteristics and user portrait characteristics, thus achieving a comprehensive analysis of the population activity patterns, base station coverage characteristics and user group portraits in the target area.

[0105] S120: Analyze the characteristics of the target area using the trained classification model to identify the regional attributes of each base station in the target area.

[0106] The classification model is trained using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels.

[0107] Regional attributes refer to classification labels that describe the functions and characteristics of geographic regions.

[0108] It should be understood that the area can be pre-defined based on multiple dimensions such as the area's usage nature, function, population activity pattern, etc., and this application does not limit this.

[0109] Examples of regional attributes include, but are not limited to: tourist attractions, industrial parks, shopping mall areas, residential areas, construction areas, park activity areas, rural markets, etc.

[0110] That is, the classification model is used to analyze the characteristics of the target area and identify which of the preset regional attributes each base station in the target area belongs to. For example, if there are multiple base stations in the target area, the classification model can be trained to identify that the regional attribute of base station A is "shopping area", the regional attribute of base station B is "industrial park", and the regional attribute of base station C is "residential area".

[0111] In one implementation, base station data samples and user data samples associated with them in different regions can be collected to construct a data set. The features in the data set include the geographical location of the base station, the length of user stay, demographic characteristics, etc., and each base station is assigned a corresponding regional attribute label. These sample data are trained using traditional classification algorithms, such as decision trees or random forests. During the training process, the model learns the relationship between the input features and the regional attribute labels in the data samples, and gradually optimizes the classification decision boundary. After the model training is completed, the performance of each classification algorithm is evaluated using cross-validation and other techniques, and the algorithm with the best performance is selected as the final classification model. Finally, the new base station data in the target area is classified and analyzed using the selected classification model to identify accurate regional attribute labels for each base station. The advantage of this method lies in its simplicity of implementation and the universal applicability of the algorithm, which is suitable for relatively simple data sets and analysis tasks.

[0112] In one implementation, base station data samples and user data samples associated with them in different regions can be prepared to construct a feature-rich data set. The data set contains features such as the geographic coordinates of the base station, the length of stay of the user, the population density, and the regional attribute labels corresponding to each base station. Then, the XGBoost (eXtreme GradientBoosting) classification algorithm is used to train the data set. XGBoost is based on the gradient boosting tree method, which maximizes the prediction performance of the model by gradually building multiple weak classifiers and combining them into a strong classifier. During the model training process, XGBoost can adaptively adjust the attributes of each base station to accurately classify the region. In order to optimize the performance of the model, the hyperparameters of XGBoost (such as the depth of the tree, the learning rate, the regularization parameter, etc.) are adjusted using techniques such as random search algorithms, and the accuracy, recall rate, and other indicators of the model are evaluated through cross-validation. Finally, the XGBoost model with the best performance is selected for regional attribute analysis of base stations in the target area. The advantage of this method is that XGBoost can handle more complex data sets, has strong generalization ability and high accuracy, and is suitable for large-scale data analysis and more sophisticated regional attribute recognition tasks.

[0113] S130. Determine a target base station group based on multiple base stations with the same area attribute, and the area where the target base station group is located is the area to be identified.

[0114] Base stations in the target area are classified into different regional attribute categories according to the characteristics of the target area, such as "shopping area", "industrial park", "residential area", etc. Each base station has an associated regional attribute label, which reflects the type of area where the base station is located.

[0115] When multiple base stations have the same regional attributes, they can be classified into a "target base station group". This target base station group represents a collection of base stations with similar attributes in the target area, that is, the areas where these base stations are located have the same characteristics and can therefore be considered to be the same type of area.

[0116] The area covered by the target base station group is determined as the "area to be identified". That is, by identifying that the regional attributes of multiple base stations are the same and classifying them into a target base station group, the overall attributes of the area where these base stations are located can be inferred.

[0117] In this step, the regional attributes of multiple base stations in the target area are analyzed to identify a group of base stations with the same regional attributes, and the area where the base station group is located is defined as the area to be identified.

[0118] For example, suppose that in a city, there are multiple base stations distributed around a large shopping mall. All these base stations have the same regional attributes. By clustering these base stations, the area where these base stations are located (i.e. the area around the shopping mall) can be used as a target base station group. This area can be defined as a "shopping mall area", even if this area is not clearly marked in traditional maps. In this way, different functional areas can be dynamically identified, especially those that are temporary or have no clear building boundaries.

[0119] S140: Draw the boundary of the area to be identified according to the geographical location of the target base station group, and determine the area attribute of the target base station group as the area attribute of the area to be identified.

[0120] By identifying the regional attributes of the target base station group, the spatial scope of the area to be identified can be determined according to the geographical locations of these base stations.

[0121] The boundary of the area to be identified can be obtained by clustering or boundary fitting the geographical location of the target base station group, thereby obtaining an area covering these base stations. This area will be given the regional attribute label of the target base station group, that is, the area to be identified will inherit the regional attributes of the target base station group.

[0122] In one implementation, the geographic location information (such as longitude and latitude coordinates) of the target base station group is obtained, and the target base stations are spatially clustered using a clustering algorithm. Base stations with similar geographical locations are grouped together to define a "clustering area".

[0123] The clustering results can be used to draw the region boundary through the minimum enclosing rectangle, convex hull or other geometric algorithms. Once the boundary is determined, the regional attributes of the target base station group will be assigned to the entire area to be identified.

[0124] This implementation is suitable for situations where the spatial distribution between base stations is relatively dispersed or irregular.

[0125] In one implementation, geographical location information of the target base station group is obtained, and a polygon including all target base stations is drawn based on the geographical location information to determine the boundary of the area.

[0126] By calculating the boundaries of the polygon or correcting it according to the existing geographic information, the boundaries of the area to be identified are ensured to be complete. Then, the regional attributes of the target base station group are assigned to all areas within the boundaries of this area, and finally the attributes of the area to be identified are determined.

[0127] This implementation method is suitable for scenarios where base stations are distributed relatively regularly and area boundaries need to be finely divided.

[0128] The area identification method provided in the embodiment of the present application deeply analyzes the regional population characteristics in the target area based on base station data and user data associated with the base station data, and uses a classification model to identify the regional attributes of each base station in the target area, and classifies the base stations with the same regional attributes into a base station group. The area covered by this base station group is the area to be identified, and the outline boundary of the area is further drawn based on the base station group.

[0129] Traditional map data often relies on fixed, clearly marked geographic features, such as buildings, roads, and scenic spots. However, for some dynamic areas without fixed boundaries (such as construction sites, temporary activity areas, consumer areas around shopping malls, etc.), traditional maps may not accurately display or lack sufficient information. This method combines base station data, user flow data, and crowd characteristics to dynamically identify and draw the boundaries of these areas, and classify them according to the attributes of the crowd in the area, providing a richer and more detailed supplement to ordinary map data.

[0130] By combining the geographic boundaries and population characteristics of the target area, this method can not only complete the missing areas in traditional maps, but also dynamically update map information, especially in the identification of highly mobile or unstable areas. For example, based on the distribution of base stations in the area and user activity patterns, the actual geographic scope of shopping malls, schools, scenic spots, temporary activity areas, etc. is identified to reflect the actual use and function of these areas, avoiding the static limitations of traditional map data. This makes the map more realistic and real-time, supports efficient decision-making in areas such as urban planning, resource allocation, and public safety, and improves the overall accuracy and usability of the map.

[0131] Figure 2 A schematic flow chart of a region identification method provided in an embodiment of the present application is shown.

[0132] It should be understood that Figure 2 The illustrated embodiment can be viewed as Figure 1 An example of step S140 in the embodiment.

[0133] like Figure 2 As shown, the method may include the following steps.

[0134] S210: Obtain location information of each base station in the target base station group.

[0135] The location information may include the longitude and latitude coordinates of the base station.

[0136] Exemplarily, the location information of each base station may be obtained from a base station database or a base station configuration file.

[0137] S220 , using a convex hull algorithm, based on the location information, select a target base station from the target base station group, and determine the target base station as a contour point of the area to be identified.

[0138] The convex hull algorithm is used to select a set of key "contour points" from the target base station group based on the base station location data. The core idea of ​​the convex hull algorithm is to find the outermost points of a set of points that form a minimum convex polygon that surrounds all base station points.

[0139] In this way, the “boundary” point set of the target base station cluster is determined, providing key data for subsequent boundary drawing.

[0140] S230 , connecting the contour points to obtain a closed figure, where the closed figure is the boundary of the area to be identified.

[0141] The contour points selected in step S220 are connected in sequence to obtain a closed figure, the outer area of ​​which is the boundary of the area to be identified.

[0142] Since the convex hull algorithm ensures that the selected point set is the outermost points, the graph connected by these points can most accurately surround the target base station group and define the spatial scope of the area to be identified.

[0143] The method of this embodiment uses a convex hull algorithm to accurately filter out contour points from the target base station group and connect them into a closed figure, thereby accurately drawing the boundary of the area to be identified. It can efficiently and automatically calculate the area boundary, avoid errors caused by manual drawing, and has strong adaptability and can handle irregularly distributed base station groups.

[0144] In one embodiment, Figure 1 Step S130 in the embodiment can be implemented by the following method:

[0145] S131. Obtain location information of multiple base stations with the same area attribute, and calculate the distance between any two base stations among the multiple base stations.

[0146] Exemplarily, a distance calculation method of a geographic coordinate system may be used to calculate the physical distance between any two base stations in the target base station group to determine the spatial relationship between the base stations.

[0147] S132. Divide the multiple base stations into base station groups based on the distance between any two base stations to obtain at least one target base station group.

[0148] According to the calculated distances between base stations, these base stations are divided into several base station groups using a certain clustering method or a simple division strategy based on a distance threshold.

[0149] Exemplarily, each target base station group is characterized in that the distance between all base stations in the group is less than a preset threshold, which is usually set through experiments or based on the characteristics of the target area, and the present application does not limit its specific value.

[0150] After the division, one or more target base station groups may be obtained, each of which is composed of base stations whose distances to each other are less than a preset value.

[0151] The method of this embodiment calculates the distances between multiple base stations with the same regional attributes and effectively divides the base stations based on a preset distance threshold, thereby identifying the target base station group. The base stations in each base station group have a high spatial density and can accurately reflect the geographical characteristics of the target area. Through the division of the base station group, the area to be identified can be better defined.

[0152] Figure 3 A schematic flow chart of a region identification method provided in an embodiment of the present application is shown.

[0153] It should be understood that Figure 3 The illustrated embodiment can be viewed as Figure 1 An example of the classification model training process in the embodiment.

[0154] like Figure 3 As shown, the training method of the classification model may include the following steps.

[0155] S310, obtaining base station data samples, user data samples associated with the base station data samples, and area attribute labels corresponding to each base station in the base station data samples.

[0156] S320. Obtain sample features according to the base station data sample and the user data sample associated with the base station data sample.

[0157] Sample characteristics include base station attribute characteristics, user signaling residence characteristics and user portrait characteristics.

[0158] S330: Analyze the sample features using the classification model to obtain a prediction result, where the prediction result is a predicted regional attribute of each base station corresponding to the sample features.

[0159] S340: Calculate a loss value according to the difference between the predicted regional attribute and the regional attribute label.

[0160] S350. Adjust the parameters of the classification model according to the loss value.

[0161] S360: when the training stop condition is met, output the classification model;

[0162] S370: When the training stop condition is not met, continue to execute the step of obtaining a prediction result based on the input sample features.

[0163] In one embodiment, the classification model training method may further include the following steps:

[0164] Each feature in the sample features is analyzed to determine the importance of each feature, which is used for classification prediction of the classification model.

[0165] During the training process of the classification model, by evaluating each feature in the training data set, the contribution of each feature to the prediction results of the classification model can be quantified.

[0166] Exemplarily, the importance of a feature can be determined by calculating the contribution of each feature to a splitting node in a decision tree based on a decision tree model. It should be understood that the more times a feature is used as a splitting node in the tree, the more important the feature is in the model.

[0167] Exemplarily, the importance of a feature can also be evaluated by calculating the split frequency of the feature in all trees or the contribution to the improvement of model performance based on the random forest and XGBoost methods.

[0168] The method of this embodiment can analyze the importance of each sample feature to clarify which features are most critical in classification prediction. In this way, the model can focus more computing resources on important features, thereby improving classification effect and prediction accuracy.

[0169] In one embodiment, after the regional attributes and regional boundaries of the area to be identified in the target area are identified using the method of the present application, the relevant information of the area to be identified can also be displayed in a digitized map.

[0170] In one implementation, the area information of the area to be identified is displayed on a map display interface, and the area information includes center point coordinates, contour point sequence, and area attributes.

[0171] In one implementation, a base station attribute label of each contour point of the area to be identified is displayed on a map display interface, and the base station attribute label includes a base station identifier and area attributes.

[0172] For example, digital maps can be obtained manually and using GIS (Geographic Information System) tools.

[0173] For example, a third-party map manufacturer may be used to obtain a digitized map.

[0174] For example, crawler technology may be used to obtain digitized maps from websites that provide public digitized maps.

[0175] The method of this embodiment stores the information of the identified area to be identified and the base station information constituting the area to be identified in the digital map, which can be called for display when needed, for easy subsequent viewing and use.

[0176] The above mainly introduces a method for identifying a region in an embodiment of the present application in conjunction with the accompanying drawings. At the same time, it should be understood that although the steps in the flowcharts involved in the embodiments described above are displayed in sequence, these steps are not necessarily performed in sequence in the order shown in the figure. Unless otherwise specified in this document, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least a part of the steps or stages in other steps. A region identification device in an embodiment of the present application is introduced below in conjunction with the accompanying drawings. For the sake of brevity, appropriate omissions will be made when introducing the device below, and the relevant content can refer to the relevant description in the method above, and will not be repeated.

[0177] Corresponding to the method described in the above embodiment, Figure 5 A structural block diagram of a region identification device 500 provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0178] like Figure 4 As shown, the device 1000 may include:

[0179] A feature acquisition module 1001 is used to obtain target area features based on base station data in the target area and user data associated with the base station data;

[0180] A model processing module 1002 is used to analyze the characteristics of the target area using a trained classification model to identify the regional attributes of each base station in the target area, wherein the classification model is trained using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels;

[0181] An analysis module 1003 is used to determine a target base station group according to multiple base stations with the same area attribute, and the area where the target base station group is located is the area to be identified;

[0182] The drawing module 1004 is used to draw the boundary of the area to be identified according to the geographical location of the target base station group, and determine the area attribute of the target base station group as the area attribute of the area to be identified.

[0183] Figure 5 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application is shown.

[0184] The computer device may include a processor 7001 and a memory 7002 storing computer program instructions.

[0185] Specifically, the processor 7001 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0186] The memory 7002 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 7002 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 7002 may include a removable or non-removable (or fixed) medium, or the memory 7002 is a non-volatile solid-state memory. The memory 7002 may be inside or outside the integrated gateway disaster recovery device.

[0187] In one example, the memory 7002 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0188] The processor 7001 reads and executes the computer program instructions stored in the memory 7002 to implement Figure 1 The region identification method in the illustrated embodiment.

[0189] In one example, the computer device may further include a communication interface 7003 and a bus 7004. Figure 5 As shown, the processor 7001, the memory 7002, and the communication interface 7003 are connected via a bus 7004 and communicate with each other.

[0190] The communication interface 7003 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0191] Bus 7004 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, Memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 7004 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0192] In addition, in combination with the region identification method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any region identification method in the above embodiment is implemented.

[0193] An embodiment of the present application also provides a computer program product, including a computer program, which implements any one of the region recognition methods in the above embodiments when the computer program is processed and executed.

[0194] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0195] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0196] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0197] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A region recognition method, characterized in that: include: Obtaining target area characteristics based on base station data within the target area and user data associated with the base station data; Analyzing the characteristics of the target area using a trained classification model to identify the regional attributes of each base station in the target area, wherein the classification model is trained using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels; Determine a target base station group according to multiple base stations with the same area attribute, and the area where the target base station group is located is the area to be identified; According to the geographical location of the target base station group, the boundary of the area to be identified is drawn, and the area attribute of the target base station group is determined as the area attribute of the area to be identified.

2. The method according to claim 1, characterized in that Drawing the boundary of the to-be-identified area according to the geographical location of the target base station group includes: Acquire location information of each base station in the target base station group; Using a convex hull algorithm, according to the location information, a target base station is screened out from the target base station group, and the target base station is determined as a contour point of the area to be identified; The contour points are connected to obtain a closed figure, where the closed figure is the boundary of the area to be identified.

3. The method according to claim 1, characterized in that The step of determining a target base station group according to a plurality of base stations having the same area attribute includes: Acquire location information of multiple base stations with the same area attribute, and calculate the distance between any two base stations among the multiple base stations; Based on the distance between any two base stations, the multiple base stations are divided into base station groups to obtain at least one target base station group, and the distance between any two base stations in the at least one target base station group is less than a preset distance.

4. The method according to any one of claims 1 to 3, characterized in that The step of acquiring base station data in the target area and user data associated with the base station data to obtain characteristics of the target area includes: The base station data and the user data associated with the base station data are analyzed by using a regional population characteristic model, and base station attribute characteristics, user signaling residence characteristics and user portrait characteristics are extracted to form the target area characteristics.

5. The method according to claim 4, characterized in that The base station data includes base station configuration data and base station residence day detailed data, the user data associated with the base station data includes user multiple label data, and the regional population feature model is used to analyze the base station data and the user data associated with the base station data to extract base station attribute features, user signaling residence features and user portrait features, including: Extracting attribute characteristics of the base station according to the base station configuration data; Extracting visitor characteristics at predefined time, characteristics of predefined date, characteristics of permanent population, and characteristics of residence duration and frequency according to the detailed data of base station residence day to form the user signaling residence characteristics; The user portrait features are extracted based on the user's various tag data.

6. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Acquire a base station data sample, a user data sample associated with the base station data sample, and an area attribute label corresponding to each base station in the base station data sample; Obtaining sample features according to the base station data sample and the user data sample associated with the base station data sample, wherein the sample features include base station attribute features, user signaling residence features, and user portrait features; Analyzing the sample features using the classification model to obtain a prediction result, where the prediction result is a predicted regional attribute of each base station corresponding to the sample features; Calculating a loss value according to a difference between the predicted regional attribute and the regional attribute label; According to the loss value, adjusting parameters of the classification model; When the training stop condition is met, outputting the classification model; If the training stop condition is not met, continue to execute the steps of acquiring base station data samples, user data samples associated with the base station data samples, and area attribute labels corresponding to each base station in the base station data samples.

7. The method according to claim 6, characterized in that The method further comprises: Each feature in the sample features is analyzed to determine the importance of each feature, and the importance is used for classification prediction of the classification model.

8. The method according to claim 2 or 3, characterized in that: The method further comprises: The area information of the area to be identified is displayed on the map display interface, and the area information includes center point coordinates, contour point sequence and area attributes.

9. The method according to claim 8, characterized in that The method further comprises: The base station attribute label of each contour point of the to-be-identified area is displayed on the map display interface, and the base station attribute label includes a base station identifier and an area attribute.

10. A region recognition device, characterized in that: include: A feature acquisition module, used to obtain target area features based on base station data in the target area and user data associated with the base station data; A model processing module, used to analyze the characteristics of the target area by using a trained classification model to identify the regional attributes of each base station in the target area, wherein the classification model is trained by using base station data samples, user data samples associated with the base station data samples, and corresponding regional attribute labels; An analysis module, used to determine a target base station group according to multiple base stations with the same regional attributes, where the area where the target base station group is located is the area to be identified; The drawing module is used to draw the boundary of the area to be identified according to the geographical location of the target base station group, and determine the area attribute of the target base station group as the area attribute of the area to be identified.

11. A computer device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of a computer device, the computer device is caused to perform the method according to any one of claims 1 to 9.

Images