CN118590832A - User work and residence identification method, electronic device and storage medium - Google Patents

Abstract

The invention relates to the technical field of information processing, in particular to a user location identification method, electronic equipment and a storage medium, and aims to solve the technical problem that the accuracy of a location obtained by the existing location identification method is low. To this end, the user job place identification method of the present invention includes: acquiring terminal state information of a user terminal; determining a first stop point cluster sequence based on the terminal state information; clustering is carried out based on the second stay point cluster sequence, so that a stay clustering point cluster is obtained; the user's job site is identified based on the stay cluster. Thus, a job site with higher accuracy is obtained.

Description

Translated fromChinese

用户职住地识别方法、电子设备及存储介质User work and residence identification method, electronic device and storage medium

技术领域Technical Field

本发明涉及信息处理技术领域，具体提供一种用户职住地识别方法、电子设备及存储介质。The present invention relates to the field of information processing technology, and specifically provides a method for identifying a user's workplace and residence, an electronic device, and a storage medium.

背景技术Background Art

目前，职住地识别主要分为两种方案，第一种是收集用户的手机信令数据，并利用其时空信息获得用户的职住地，该方法需要基于基站位置、覆盖范围等信息，获得它们有一定的成本，且获得的职住地的精度较低。第二种是获取用户的位置轨迹，通过对定位信息进行时空分析得到用户的职住地，该方法需要频繁请求用户的定位信息，因耗电大不适合智能设备上部署，而且室内场景的定位失败率较高。另外，上述两种方案提供的职住地信息比较单一，基于其构建的职住地围栏不够精准。At present, there are two main schemes for workplace identification. The first is to collect the user's mobile phone signaling data and use its spatiotemporal information to obtain the user's workplace. This method requires information such as base station location and coverage, which has a certain cost, and the accuracy of the workplace obtained is low. The second is to obtain the user's location trajectory and obtain the user's workplace by performing spatiotemporal analysis on the positioning information. This method requires frequent requests for the user's positioning information. Due to its high power consumption, it is not suitable for deployment on smart devices, and the positioning failure rate in indoor scenes is high. In addition, the workplace information provided by the above two schemes is relatively simple, and the workplace fence constructed based on it is not accurate enough.

相应地，本领域需要一种新的用户职住地识别方案来解决上述问题。Accordingly, the art needs a new user work and residence identification solution to solve the above problems.

发明内容Summary of the invention

为了克服上述缺陷，提出了本发明，以提供解决或至少部分地解决上述技术问题。本发明提供了一种用户职住地识别方法、电子设备及存储介质。In order to overcome the above defects, the present invention is proposed to solve or at least partially solve the above technical problems. The present invention provides a method for identifying a user's workplace and residence, an electronic device and a storage medium.

在第一方面，本发明提供一种用户职住地识别方法，所述方法包括：获取用户终端的终端状态信息；基于所述终端状态信息确定第一停留点簇序列；基于第二停留点簇序列进行聚类，得到停留聚类点簇，所述第二停留点簇序列包括所述第一停留点簇序列；基于所述停留聚类点簇识别所述用户职住地。In a first aspect, the present invention provides a method for identifying a user's workplace and residence, the method comprising: obtaining terminal status information of a user terminal; determining a first stay point cluster sequence based on the terminal status information; clustering based on a second stay point cluster sequence to obtain a stay cluster point cluster, the second stay point cluster sequence including the first stay point cluster sequence; identifying the user's workplace and residence based on the stay cluster point cluster.

在一个实施方式中，所述获取用户终端的终端状态信息，包括：在预设时间设置k个采样点，其中k为正整数；在每个所述采样点采集用户终端的终端状态信息。In one embodiment, the acquiring the terminal status information of the user terminal includes: setting k sampling points at a preset time, where k is a positive integer; and collecting the terminal status information of the user terminal at each sampling point.

在一个实施方式中，所述终端状态信息至少包括所述终端连接的基站编号信息、连接的WIFI信息、扫描到的WIFI列表和位置信息；所述基于所述终端状态信息确定第一停留点簇序列，包括：基于所述预设时间的第一采样点构建第一停留点簇；判断第n采样点是否属于所述第一停留点簇，n为正整数，1＜n≤k；若是，基于所述第n采样点的终端状态信息更新所述第一停留点簇；若否，基于所述第n采样点构建第m停留点簇，判断第n+1采样点是否属于所述第m停留点簇，m为正整数，1＜m；直至将所有采样点分配至对应的停留点簇；基于所述停留点簇得到所述第一停留点簇序列。In one embodiment, the terminal status information includes at least the base station number information connected to the terminal, the connected WIFI information, the scanned WIFI list and the location information; the determining of the first stay point cluster sequence based on the terminal status information includes: constructing a first stay point cluster based on the first sampling point of the preset time; judging whether the nth sampling point belongs to the first stay point cluster, n is a positive integer, 1＜n≤k; if so, updating the first stay point cluster based on the terminal status information of the nth sampling point; if not, constructing the mth stay point cluster based on the nth sampling point, judging whether the n+1th sampling point belongs to the mth stay point cluster, m is a positive integer, 1＜m; until all sampling points are assigned to corresponding stay point clusters; and obtaining the first stay point cluster sequence based on the stay point cluster.

在一个实施方式中，所述基于所述预设时间的第一采样点构建第一停留点簇，包括：将所述第一采样点连接的基站编号信息添加至所述第一停留点簇的基站编号序列；将所述第一采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列；将所述第一采样点扫描到的WIFI列表添加至所述第一停留点簇的第二WIFI序列；将所述第一采样点位置信息作为所述第一停留点簇的位置信息；将所述第一采样点的序号添加至所述第一停留点簇的采样点序列。In one embodiment, the first sampling point based on the preset time constructs a first stay point cluster, including: adding the base station number information connected to the first sampling point to the base station number sequence of the first stay point cluster; adding the WIFI information connected to the first sampling point to the first WIFI sequence of the first stay point cluster; adding the WIFI list scanned by the first sampling point to the second WIFI sequence of the first stay point cluster; using the location information of the first sampling point as the location information of the first stay point cluster; and adding the sequence number of the first sampling point to the sampling point sequence of the first stay point cluster.

在一个实施方式中，所述判断第n采样点是否属于所述第一停留点簇，包括：In one embodiment, the determining whether the nth sampling point belongs to the first stay point cluster includes:

S11.判断所述第一停留点簇的基站编号序列是否包含所述第n采样点连接的基站编号信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S12；S11. Determine whether the base station number sequence of the first stay point cluster contains the base station number information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S12;

S12.判断所述第一停留点簇的第一WIFI序列是否包含所述第n采样点连接的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S13；S12. Determine whether the first WIFI sequence of the first stay point cluster contains the WIFI information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S13;

S13.判断所述第一停留点簇的第二WIFI序列与所述第n采样点扫描到的WIFI列表是否至少有一个相同的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S14；S13. Determine whether the second WIFI sequence of the first stay point cluster and the WIFI list scanned by the nth sampling point have at least one identical WIFI information; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S14;

S14.基于所述第一停留点簇的位置信息与所述第n采样点对应终端的位置信息确定第一距离，判断所述第一距离是否小于第一阈值，若是，则确定所述第n采样点属于所述第一停留点簇，若否，确定所述第n采样点不属于所述第一停留点簇。S14. Determine a first distance based on the location information of the first stay point cluster and the location information of the terminal corresponding to the nth sampling point, and determine whether the first distance is less than a first threshold; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, determine that the nth sampling point does not belong to the first stay point cluster.

在一个实施方式中，所述基于所述第n采样点的终端状态信息更新所述第一停留点簇，包括：在所述第一停留点簇的基站编号序列不包含所述第n采样点的基站编号信息的情况下，将所述第n采样点的基站编号信息添加至所述第一停留点簇的基站编号序列中；在所述第一停留点簇的第一WIFI序列不包含所述第n采样点连接的WIFI信息的情况下，将所述第n采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列中；在所述第一停留点簇的第二WIFI序列不包含所述第n采样点扫描到的WIFI列表的至少一个WIFI信息的情况下，将所述第n采样点扫描到的WIFI列表的至少一个WIFI信息添加至所述第一停留点簇的第二WIFI序列中；基于所述第一停留点簇的位置信息与所述第n采样点的位置信息对所述第一停留点簇的位置信息进行更新；将所述第n采样点的序号添加至所述第一停留点簇的采样点序列。In one embodiment, the updating of the first stay point cluster based on the terminal status information of the nth sampling point includes: when the base station number sequence of the first stay point cluster does not include the base station number information of the nth sampling point, adding the base station number information of the nth sampling point to the base station number sequence of the first stay point cluster; when the first WIFI sequence of the first stay point cluster does not include the WIFI information connected to the nth sampling point, adding the WIFI information connected to the nth sampling point to the first WIFI sequence of the first stay point cluster; when the second WIFI sequence of the first stay point cluster does not include at least one WIFI information in the WIFI list scanned by the nth sampling point, adding at least one WIFI information in the WIFI list scanned by the nth sampling point to the second WIFI sequence of the first stay point cluster; updating the position information of the first stay point cluster based on the position information of the first stay point cluster and the position information of the nth sampling point; and adding the sequence number of the nth sampling point to the sampling point sequence of the first stay point cluster.

在一个实施方式中，所述基于第二停留点簇序列进行聚类，得到停留聚类点簇，包括：确定所述第二停留点簇序列中任意两个停留点簇之间的距离；基于所述任意两个停留点簇之间的距离得到距离矩阵；基于所述距离矩阵对所述第二停留点簇序列中的停留点簇进行聚类，得到多个聚类簇；融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇。In one embodiment, clustering is performed based on the second stay point cluster sequence to obtain stay cluster point clusters, including: determining the distance between any two stay point clusters in the second stay point cluster sequence; obtaining a distance matrix based on the distance between the any two stay point clusters; clustering the stay point clusters in the second stay point cluster sequence based on the distance matrix to obtain multiple cluster clusters; and fusing the stay point clusters in each of the cluster clusters to obtain the stay cluster point cluster.

在一个实施方式中，所述确定所述第二停留点簇序列中任意两个停留点簇之间的距离，包括：In one embodiment, determining the distance between any two stay point clusters in the second stay point cluster sequence includes:

S21.判断所述任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述任意两个停留点簇之间的距离为第一预设距离；若否，执行S22；S21. Determine whether there is the same base station number in the base station number sequence of any two stay point clusters; if so, determine that the distance between the any two stay point clusters is a first preset distance; if not, execute S22;

S22.判断所述任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息，若是，则确定所述任意两个停留点簇之间的距离为第二预设距离；若否，基于所述任意两个停留点簇的位置信息确定所述任意两个停留点簇之间的距离。S22. Determine whether the first WIFI sequences of any two stay point clusters have the same WIFI information. If so, determine that the distance between the any two stay point clusters is a second preset distance; if not, determine the distance between the any two stay point clusters based on the location information of the any two stay point clusters.

在一个实施方式中，所述停留聚类点簇包括停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列、位置信息和采样点序列；所述融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇，包括：对每个所述聚类簇中所有停留点簇的基站编号序列、第一WIFI序列和第二WIFI序列分别取并集，得到所述停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列；对每个所述聚类簇中所有停留点簇的位置信息进行加权平均，得到所述停留聚类点簇的位置信息；对每个所述聚类簇中所有停留点簇的采样点序列进行合并，得到所述停留聚类点簇的采样点序列。In one embodiment, the stay cluster point cluster includes a base station numbering sequence, a first WIFI sequence and a second WIFI sequence, location information and a sampling point sequence of the stay cluster point cluster; the fusion of the stay point clusters in each of the clusters to obtain the stay cluster point cluster includes: taking the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of all the stay point clusters in each of the clusters to obtain the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of the stay cluster point cluster; performing weighted averaging on the location information of all the stay point clusters in each of the clusters to obtain the location information of the stay cluster point cluster; merging the sampling point sequences of all the stay point clusters in each of the clusters to obtain the sampling point sequence of the stay cluster point cluster.

在一个实施方式中，所述基于所述停留聚类点簇识别所述用户的职住地，包括：获取所述停留聚类点簇的采样点序列中每个采样点对应的第一权重和第二权重，其中所述第一权重为所述采样点对应用户居住地的权重，所述第二权重为所述采样点对应用户工作地的权重；基于所述第一权重和所述第二权重，分别确定所述停留聚类点簇作为用户居住地对应的第一置信度和作为用户工作地对应的第二置信度；基于所述第一置信度和所述第二置信度确定用户居住地和用户工作地。In one embodiment, identifying the user's residence and workplace based on the stay clustering point cluster includes: obtaining a first weight and a second weight corresponding to each sampling point in the sampling point sequence of the stay clustering point cluster, wherein the first weight is the weight of the sampling point corresponding to the user's residence, and the second weight is the weight of the sampling point corresponding to the user's workplace; based on the first weight and the second weight, determining a first confidence level corresponding to the stay clustering point cluster as the user's residence and a second confidence level corresponding to the user's workplace, respectively; and determining the user's residence and the user's workplace based on the first confidence level and the second confidence level.

在一个实施方式中，所述方法还包括：从识别为用户居住地的所述停留聚类点簇中获取用户居住地信息；和/或从识别为用户工作地的所述停留聚类点簇中获取用户工作地信息。In one embodiment, the method further includes: obtaining user residence information from the stay clustering point cluster identified as the user's residence; and/or obtaining user workplace information from the stay clustering point cluster identified as the user's workplace.

在一个实施方式中，在基于所述终端状态信息确定第一停留点簇序列之后，以及基于第二停留点簇序列进行聚类得到停留聚类点簇之前，所述方法还包括：判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇；若是，对所述第一停留点簇序列中包含同一区域的停留点簇进行融合；将融合后的所有停留点簇按照采样点序列的长度进行排序；将所述采样点序列的长度小于动态长度阈值的停留点簇从所述第一停留点簇序列中删除。In one embodiment, after determining the first stay point cluster sequence based on the terminal status information, and before clustering to obtain a stay point cluster based on the second stay point cluster sequence, the method further includes: determining whether there are stay point clusters containing the same area in the first stay point cluster sequence; if so, merging the stay point clusters containing the same area in the first stay point cluster sequence; sorting all the fused stay point clusters according to the length of the sampling point sequence; and deleting the stay point clusters whose lengths of the sampling point sequences are less than a dynamic length threshold from the first stay point cluster sequence.

在一个实施方式中，所述判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇，包括：In one embodiment, determining whether there is a stay point cluster including the same area in the first stay point cluster sequence includes:

S31.判断所述第一停留点簇序列的任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S32；S31. Determine whether there are the same base station numbers in the base station number sequences of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there are stay point clusters containing the same area in the first stay point cluster sequence; if not, execute S32;

S32.判断所述第一停留点簇序列的任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S33；S32. Determine whether there is the same WIFI information in the first WIFI sequence of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there is a stay point cluster containing the same area in the first stay point cluster sequence; if not, execute S33;

S33.基于所述第一停留点簇序列中任意两个停留点簇的位置信息确定第二距离，判断所述第二距离是否小于第二阈值，若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，则确定所述第一停留点簇序列中不存在包含同一区域的停留点簇。S33. Determine a second distance based on the position information of any two stay point clusters in the first stay point cluster sequence, and judge whether the second distance is less than a second threshold value. If so, determine that there are stay point clusters covering the same area in the first stay point cluster sequence; if not, determine that there are no stay point clusters covering the same area in the first stay point cluster sequence.

在第二方面，提供一种电子设备，该电子设备包括至少一个处理器和至少一个存储装置，所述存储装置适于存储多条程序代码，所述程序代码适于由所述处理器加载并运行以执行前述任一项所述的用户职住地识别方法。In a second aspect, an electronic device is provided, which includes at least one processor and at least one storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute any of the user work and residence identification methods described above.

在第三方面，提供一种计算机可读存储介质，该计算机可读存储介质其中存储有多条程序代码，所述程序代码适于由处理器加载并运行以执行前述任一项所述的用户职住地识别方法。In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute any of the aforementioned user work and residence identification methods.

方案1.一种用户职住地识别方法，其特征在于，所述方法包括：Solution 1. A method for identifying a user's workplace and residence, characterized in that the method comprises:

获取用户终端的终端状态信息；Obtain terminal status information of the user terminal;

基于所述终端状态信息确定第一停留点簇序列；Determine a first stay point cluster sequence based on the terminal state information;

基于第二停留点簇序列进行聚类，得到停留聚类点簇，所述第二停留点簇序列包括所述第一停留点簇序列；Perform clustering based on a second stay point cluster sequence to obtain a stay point cluster, wherein the second stay point cluster sequence includes the first stay point cluster sequence;

基于所述停留聚类点簇识别所述用户职住地。The user's workplace and residence are identified based on the stay cluster point clusters.

方案2.根据方案1所述的用户职住地识别方法，其特征在于，所述获取用户终端的终端状态信息，包括：Solution 2. The method for identifying a user's workplace and residence according to Solution 1, wherein the step of obtaining the terminal status information of the user terminal comprises:

在预设时间设置k个采样点，其中k为正整数；Set k sampling points at a preset time, where k is a positive integer;

在每个所述采样点采集用户终端的终端状态信息。The terminal status information of the user terminal is collected at each sampling point.

方案3.根据方案2所述的用户职住地识别方法，其特征在于，所述终端状态信息至少包括所述终端连接的基站编号信息、连接的WIFI信息、扫描到的WIFI列表和位置信息；所述基于所述终端状态信息确定第一停留点簇序列，包括：Solution 3. The user's workplace and residence identification method according to Solution 2 is characterized in that the terminal status information at least includes the base station number information connected to the terminal, the connected WIFI information, the scanned WIFI list and the location information; and the determining of the first stay point cluster sequence based on the terminal status information includes:

基于所述预设时间的第一采样点构建第一停留点簇；Constructing a first stay point cluster based on the first sampling point at the preset time;

判断第n采样点是否属于所述第一停留点簇，n为正整数，1＜n≤k；Determine whether the nth sampling point belongs to the first stay point cluster, where n is a positive integer, 1＜n≤k;

若是，基于所述第n采样点的终端状态信息更新所述第一停留点簇；If so, updating the first stay point cluster based on the terminal status information of the nth sampling point;

若否，基于所述第n采样点构建第m停留点簇，判断第n+1采样点是否属于所述第m停留点簇，m为正整数，1＜m；If not, construct an mth stay point cluster based on the nth sampling point, and determine whether the n+1th sampling point belongs to the mth stay point cluster, where m is a positive integer and 1<m;

直至将所有采样点分配至对应的停留点簇；Until all sampling points are assigned to the corresponding stay point clusters;

基于所述停留点簇得到所述第一停留点簇序列。The first stay point cluster sequence is obtained based on the stay point cluster.

方案4.根据方案3所述的用户职住地识别方法，其特征在于，所述基于所述预设时间的第一采样点构建第一停留点簇，包括：Solution 4. The user's workplace and residence identification method according to Solution 3 is characterized in that the first sampling point based on the preset time is used to construct a first stay point cluster, comprising:

将所述第一采样点连接的基站编号信息添加至所述第一停留点簇的基站编号序列；Adding the base station number information connected to the first sampling point to the base station number sequence of the first stay point cluster;

将所述第一采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列；Adding the WIFI information of the first sampling point connection to the first WIFI sequence of the first stay point cluster;

将所述第一采样点扫描到的WIFI列表添加至所述第一停留点簇的第二WIFI序列；Add the WIFI list scanned by the first sampling point to the second WIFI sequence of the first stay point cluster;

将所述第一采样点位置信息作为所述第一停留点簇的位置信息；Using the first sampling point location information as the location information of the first stay point cluster;

将所述第一采样点的序号添加至所述第一停留点簇的采样点序列。The sequence number of the first sampling point is added to the sampling point sequence of the first stay point cluster.

方案5.根据方案3所述的用户职住地识别方法，其特征在于，所述判断第n采样点是否属于所述第一停留点簇，包括：Solution 5. The user's workplace and residence identification method according to Solution 3 is characterized in that the step of determining whether the nth sampling point belongs to the first stay point cluster comprises:

S11.判断所述第一停留点簇的基站编号序列是否包含所述第n采样点连接的基站编号信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S12；S11. Determine whether the base station number sequence of the first stay point cluster contains the base station number information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S12;

S12.判断所述第一停留点簇的第一WIFI序列是否包含所述第n采样点连接的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S13；S12. Determine whether the first WIFI sequence of the first stay point cluster contains the WIFI information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S13;

S13.判断所述第一停留点簇的第二WIFI序列与所述第n采样点扫描到的WIFI列表是否至少有一个相同的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S14；S13. Determine whether the second WIFI sequence of the first stay point cluster and the WIFI list scanned by the nth sampling point have at least one identical WIFI information; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S14;

S14.基于所述第一停留点簇的位置信息与所述第n采样点对应终端的位置信息确定第一距离，判断所述第一距离是否小于第一阈值，若是，则确定所述第n采样点属于所述第一停留点簇，若否，确定所述第n采样点不属于所述第一停留点簇。S14. Determine a first distance based on the location information of the first stay point cluster and the location information of the terminal corresponding to the nth sampling point, and determine whether the first distance is less than a first threshold; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, determine that the nth sampling point does not belong to the first stay point cluster.

方案6.根据方案3所述的用户职住地识别方法，其特征在于，所述基于所述第n采样点的终端状态信息更新所述第一停留点簇，包括：Solution 6. The user's workplace and residence identification method according to Solution 3 is characterized in that the updating of the first stay point cluster based on the terminal status information of the nth sampling point comprises:

在所述第一停留点簇的基站编号序列不包含所述第n采样点的基站编号信息的情况下，将所述第n采样点的基站编号信息添加至所述第一停留点簇的基站编号序列中；If the base station number sequence of the first stay point cluster does not include the base station number information of the nth sampling point, adding the base station number information of the nth sampling point to the base station number sequence of the first stay point cluster;

在所述第一停留点簇的第一WIFI序列不包含所述第n采样点连接的WIFI信息的情况下，将所述第n采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列中；When the first WIFI sequence of the first stay point cluster does not include the WIFI information of the n-th sampling point connection, adding the WIFI information of the n-th sampling point connection to the first WIFI sequence of the first stay point cluster;

在所述第一停留点簇的第二WIFI序列不包含所述第n采样点扫描到的WIFI列表的至少一个WIFI信息的情况下，将所述第n采样点扫描到的WIFI列表的至少一个WIFI信息添加至所述第一停留点簇的第二WIFI序列中；If the second WIFI sequence of the first stay point cluster does not include at least one WIFI information in the WIFI list scanned by the n-th sampling point, add at least one WIFI information in the WIFI list scanned by the n-th sampling point to the second WIFI sequence of the first stay point cluster;

基于所述第一停留点簇的位置信息与所述第n采样点的位置信息对所述第一停留点簇的位置信息进行更新；updating the position information of the first stay point cluster based on the position information of the first stay point cluster and the position information of the nth sampling point;

将所述第n采样点的序号添加至所述第一停留点簇的采样点序列。The sequence number of the nth sampling point is added to the sampling point sequence of the first stay point cluster.

方案7.根据方案1所述的用户职住地识别方法，其特征在于，所述基于第二停留点簇序列进行聚类，得到停留聚类点簇，包括：Solution 7. The user's workplace and residence identification method according to Solution 1 is characterized in that clustering based on the second stay point cluster sequence to obtain the stay point clustering clusters includes:

确定所述第二停留点簇序列中任意两个停留点簇之间的距离；Determining the distance between any two stay point clusters in the second stay point cluster sequence;

基于所述任意两个停留点簇之间的距离得到距离矩阵；Obtaining a distance matrix based on the distance between any two stay point clusters;

基于所述距离矩阵对所述第二停留点簇序列中的停留点簇进行聚类，得到多个聚类簇；Clustering the stay point clusters in the second stay point cluster sequence based on the distance matrix to obtain a plurality of cluster clusters;

融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇。The stay point clusters in each of the clusters are fused to obtain the stay point clusters.

方案8.根据方案7所述的用户职住地识别方法，其特征在于，所述确定所述第二停留点簇序列中任意两个停留点簇之间的距离，包括：Solution 8. The user's workplace and residence identification method according to Solution 7 is characterized in that determining the distance between any two stay point clusters in the second stay point cluster sequence comprises:

S21.判断所述任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述任意两个停留点簇之间的距离为第一预设距离；若否，执行S22；S21. Determine whether there is the same base station number in the base station number sequence of any two stay point clusters; if so, determine that the distance between the any two stay point clusters is a first preset distance; if not, execute S22;

S22.判断所述任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息，若是，则确定所述任意两个停留点簇之间的距离为第二预设距离；若否，基于所述任意两个停留点簇的位置信息确定所述任意两个停留点簇之间的距离。S22. Determine whether the first WIFI sequences of any two stay point clusters have the same WIFI information. If so, determine that the distance between the any two stay point clusters is a second preset distance; if not, determine the distance between the any two stay point clusters based on the location information of the any two stay point clusters.

方案9.根据方案7所述的用户职住地识别方法，其特征在于，所述停留聚类点簇包括停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列、位置信息和采样点序列；所述融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇，包括：Solution 9. The user's workplace and residence identification method according to Solution 7 is characterized in that the stay cluster point cluster includes a base station number sequence, a first WIFI sequence and a second WIFI sequence, location information and a sampling point sequence of the stay cluster point cluster; the fusion of the stay point clusters in each of the clusters to obtain the stay cluster point cluster includes:

对每个所述聚类簇中所有停留点簇的基站编号序列、第一WIFI序列和第二WIFI序列分别取并集，得到所述停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列；Taking the union of the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of all the stay point clusters in each of the clusters, respectively, to obtain the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of the stay point cluster;

对每个所述聚类簇中所有停留点簇的位置信息进行加权平均，得到所述停留聚类点簇的位置信息；Performing weighted averaging on the location information of all the stop point clusters in each of the clusters to obtain the location information of the stop point clusters;

对每个所述聚类簇中所有停留点簇的采样点序列进行合并，得到所述停留聚类点簇的采样点序列。The sampling point sequences of all the stop point clusters in each of the clusters are merged to obtain the sampling point sequence of the stop point cluster.

方案10.根据方案1所述的用户职住地识别方法，其特征在于，所述基于所述停留聚类点簇识别所述用户职住地，包括：Solution 10. The method for identifying a user's workplace and residence according to Solution 1, wherein the step of identifying the user's workplace and residence based on the stay cluster point clusters comprises:

获取所述停留聚类点簇的采样点序列中每个采样点对应的第一权重和第二权重，其中所述第一权重为所述采样点对应用户居住地的权重，所述第二权重为所述采样点对应用户工作地的权重；Obtaining a first weight and a second weight corresponding to each sampling point in the sampling point sequence of the stay cluster point cluster, wherein the first weight is the weight of the sampling point corresponding to the user's residence, and the second weight is the weight of the sampling point corresponding to the user's workplace;

基于所述第一权重和所述第二权重，分别确定所述停留聚类点簇作为用户居住地对应的第一置信度和作为用户工作地对应的第二置信度；Based on the first weight and the second weight, respectively determining a first confidence level corresponding to the stay cluster as a user's residence and a second confidence level corresponding to the user's workplace;

基于所述第一置信度和所述第二置信度确定用户居住地和用户工作地。The user's residence and the user's work place are determined based on the first confidence level and the second confidence level.

方案11.根据方案10所述的用户职住地识别方法，其特征在于，所述方法还包括：从识别为用户居住地的所述停留聚类点簇中获取用户居住地信息；和/或从识别为用户工作地的所述停留聚类点簇中获取用户工作地信息。Scheme 11. The user's workplace and residence identification method according to Scheme 10 is characterized in that the method also includes: obtaining the user's residence information from the stay clustering point cluster identified as the user's residence; and/or obtaining the user's workplace information from the stay clustering point cluster identified as the user's workplace.

方案12.根据方案3所述的用户职住地识别方法，其特征在于，在基于所述终端状态信息确定第一停留点簇序列之后，以及基于第二停留点簇序列进行聚类得到停留聚类点簇之前，所述方法还包括：Solution 12. The user's workplace and residence identification method according to Solution 3 is characterized in that after determining the first stay point cluster sequence based on the terminal status information and before clustering the stay point clusters based on the second stay point cluster sequence, the method further includes:

判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇；Determining whether there is a stay point cluster including the same area in the first stay point cluster sequence;

若是，对所述第一停留点簇序列中包含同一区域的停留点簇进行融合；If so, merging the stay point clusters in the first stay point cluster sequence that contain the same area;

将融合后的所有停留点簇按照采样点序列的长度进行排序；Sort all the fused stay point clusters according to the length of the sampling point sequence;

将所述采样点序列的长度小于动态长度阈值的停留点簇从所述第一停留点簇序列中删除。The stay point clusters whose length of the sampling point sequence is less than a dynamic length threshold are deleted from the first stay point cluster sequence.

方案13.根据方案12所述的用户职住地识别方法，其特征在于，所述判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇，包括：Solution 13. The user's workplace and residence identification method according to Solution 12 is characterized in that the step of determining whether there is a stay point cluster including the same area in the first stay point cluster sequence comprises:

S31.判断所述第一停留点簇序列的任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S32；S31. Determine whether there are the same base station numbers in the base station number sequences of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there are stay point clusters containing the same area in the first stay point cluster sequence; if not, execute S32;

S32.判断所述第一停留点簇序列的任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S33；S32. Determine whether there is the same WIFI information in the first WIFI sequence of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there is a stay point cluster containing the same area in the first stay point cluster sequence; if not, execute S33;

S33.基于所述第一停留点簇序列中任意两个停留点簇的位置信息确定第二距离，判断所述第二距离是否小于第二阈值，若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，则确定所述第一停留点簇序列中不存在包含同一区域的停留点簇。S33. Determine a second distance based on the position information of any two stay point clusters in the first stay point cluster sequence, and judge whether the second distance is less than a second threshold value. If so, determine that there are stay point clusters covering the same area in the first stay point cluster sequence; if not, determine that there are no stay point clusters covering the same area in the first stay point cluster sequence.

方案14.一种电子设备，包括至少一个处理器和至少一个存储装置，所述存储装置适于存储多条程序代码，其特征在于，所述程序代码适于由所述处理器加载并运行以执行方案1至13中任一项所述的用户职住地识别方法。Scheme 14. An electronic device comprising at least one processor and at least one storage device, wherein the storage device is suitable for storing multiple program codes, and wherein the program codes are suitable for being loaded and run by the processor to execute the user work and residence identification method described in any one of Schemes 1 to 13.

方案15.一种计算机可读存储介质，其中存储有多条程序代码，其特征在于，所述程序代码适于由处理器加载并运行以执行方案1至13中任一项所述的用户职住地识别方法。Solution 15. A computer-readable storage medium storing a plurality of program codes, characterized in that the program codes are suitable for being loaded and run by a processor to execute the user's workplace and residence identification method described in any one of Solutions 1 to 13.

本发明上述一个或多个技术方案，至少具有如下一种或多种有益效果：The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

本发明中的用户职住地识别方法，获取预设时间用户终端的终端状态信息；基于终端状态信息确定第一停留点簇序列；基于第二停留点簇序列进行聚类，得到停留聚类点簇，第二停留点簇序列包括第一停留点簇序列；基于停留聚类点簇识别用户的职住地。如此，解决了现有技术中职住地的识别对用户位置信息的依赖问题，提高了职住地的精确度。The user's workplace and residence identification method of the present invention obtains the terminal status information of the user terminal at a preset time; determines a first stay point cluster sequence based on the terminal status information; performs clustering based on a second stay point cluster sequence to obtain a stay cluster point cluster, wherein the second stay point cluster sequence includes the first stay point cluster sequence; and identifies the user's workplace and residence based on the stay cluster point cluster. In this way, the problem of the prior art that the identification of workplace and residence depends on the user's location information is solved, and the accuracy of the workplace and residence is improved.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

参照附图，本发明的公开内容将变得更易理解。本领域技术人员容易理解的是：这些附图仅仅用于说明的目的，而并非意在对本发明的保护范围组成限制。此外，图中类似的数字用以表示类似的部件，其中：The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

图1是根据本发明的一个实施例的用户职住地识别方法的主要步骤流程示意图；FIG1 is a flow chart showing the main steps of a method for identifying a user's workplace and residence according to an embodiment of the present invention;

图2是一个实施例中基于停留点簇得到第一停留点簇序列的流程示意图；FIG2 is a schematic diagram of a process of obtaining a first stay point cluster sequence based on a stay point cluster in an embodiment;

图3是一个实施例中基于第二停留点簇序列进行聚类得到停留聚类点簇的流程示意图；FIG3 is a schematic diagram of a process of clustering a stay point cluster based on a second stay point cluster sequence in one embodiment;

图4是一个实施例中基于停留聚类点簇识别用户的职住地的流程示意图；FIG4 is a schematic diagram of a process for identifying a user's workplace and residence based on a stay clustering point cluster in one embodiment;

图5是一个实施例中电子设备的结构示意图。FIG. 5 is a schematic structural diagram of an electronic device in an embodiment.

具体实施方式DETAILED DESCRIPTION

下面参照附图来描述本发明的一些实施方式。本领域技术人员应当理解的是，这些实施方式仅仅用于解释本发明的技术原理，并非旨在限制本发明的保护范围。Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

在本发明的描述中，“模块”、“处理器”可以包括硬件、软件或者两者的组合。一个模块可以包括硬件电路，各种合适的感应器，通信端口，存储器，也可以包括软件部分，比如程序代码，也可以是软件和硬件的组合。处理器可以是中央处理器、微处理器、图像处理器、数字信号处理器或者其他任何合适的处理器。处理器具有数据和/或信号处理功能。处理器可以以软件方式实现、硬件方式实现或者二者结合方式实现。非暂时性的计算机可读存储介质包括任何合适的可存储程序代码的介质，比如磁碟、硬盘、光碟、闪存、只读存储器、随机存取存储器等等。术语“A和/或B”表示所有可能的A与B的组合，比如只是A、只是B或者A和B。术语“至少一个A或B”或者“A和B中的至少一个”含义与“A和/或B”类似，可以包括只是A、只是B或者A和B。单数形式的术语“一个”、“这个”也可以包含复数形式。In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and/or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and/or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

目前，职住地识别主要分为两种方案，第一种是收集用户的手机信令数据，并利用其时空信息获得用户的职住地，该方法需要基于基站位置、覆盖范围等信息，获得它们有一定的成本，且获得的职住地的精度较低。第二种是获取用户的位置轨迹，通过对定位信息进行时空分析得到用户的职住地，该方法需要频繁请求用户的定位信息，因耗电大不适合智能设备上部署，而且室内场景的定位失败率较高。另外，上述两种方案提供的职住地信息比较单一，基于其构建的职住地围栏不够精准。At present, there are two main schemes for workplace identification. The first is to collect the user's mobile phone signaling data and use its spatiotemporal information to obtain the user's workplace. This method requires information such as base station location and coverage, which has a certain cost, and the accuracy of the workplace obtained is low. The second is to obtain the user's location trajectory and obtain the user's workplace by performing spatiotemporal analysis on the positioning information. This method requires frequent requests for the user's positioning information. Due to its high power consumption, it is not suitable for deployment on smart devices, and the positioning failure rate in indoor scenes is high. In addition, the workplace information provided by the above two schemes is relatively simple, and the workplace fence constructed based on it is not accurate enough.

为此，本申请提出了一种用户职住地识别方法、电子设备及存储介质，获取用户终端的终端状态信息；基于终端状态信息确定第一停留点簇序列；基于第二停留点簇序列进行聚类，得到停留聚类点簇，第二停留点簇序列包括第一停留点簇序列；基于停留聚类点簇识别用户的职住地。如此，解决了现有技术中职住地的识别对用户位置信息的依赖问题，提高了职住地的精确度。To this end, the present application proposes a method, electronic device and storage medium for identifying a user's workplace and residence, which obtains the terminal status information of the user terminal; determines a first stay point cluster sequence based on the terminal status information; performs clustering based on a second stay point cluster sequence to obtain a stay cluster point cluster, wherein the second stay point cluster sequence includes the first stay point cluster sequence; and identifies the user's workplace and residence based on the stay cluster point cluster. In this way, the problem of the dependence of the identification of workplace and residence on the user's location information in the prior art is solved, and the accuracy of the workplace and residence is improved.

参阅附图1，图1是根据本发明的一个实施例的用户职住地识别方法的主要步骤流程示意图。Please refer to FIG1 , which is a flowchart showing the main steps of a method for identifying a user's workplace and residence according to an embodiment of the present invention.

如图1所示，本发明实施例中的用户职住地识别方法主要包括下列步骤S101-步骤S104。As shown in FIG. 1 , the method for identifying a user's workplace and residence in an embodiment of the present invention mainly includes the following steps S101 to S104 .

步骤S101：获取用户终端的终端状态信息。Step S101: Acquire terminal status information of a user terminal.

步骤S102：基于所述终端状态信息确定第一停留点簇序列。Step S102: Determine a first stay point cluster sequence based on the terminal status information.

步骤S103：基于第二停留点簇序列进行聚类，得到停留聚类点簇，所述第二停留点簇序列包括所述第一停留点簇序列。Step S103: performing clustering based on the second stay point cluster sequence to obtain a stay point cluster, wherein the second stay point cluster sequence includes the first stay point cluster sequence.

步骤S104：基于所述停留聚类点簇识别所述用户职住地。Step S104: Identify the user's workplace and residence based on the stay clustering point clusters.

基于上述步骤S101-步骤S104，获取预设时间用户终端的终端状态信息；基于终端状态信息确定停留点簇序列；基于停留点簇序列进行聚类，得到停留聚类点簇；基于停留聚类点簇识别用户的职住地。如此，解决了现有技术中职住地的识别对用户位置信息的依赖问题，提高了职住地的精确度。Based on the above steps S101 to S104, the terminal status information of the user terminal at the preset time is obtained; the stay point cluster sequence is determined based on the terminal status information; clustering is performed based on the stay point cluster sequence to obtain stay cluster point clusters; and the user's work and residence are identified based on the stay cluster point clusters. In this way, the problem of the prior art that the identification of the work and residence depends on the user's location information is solved, and the accuracy of the work and residence is improved.

下面分别对上述步骤S101至步骤S103作进一步说明。The above steps S101 to S103 are further explained below.

首先对步骤S101进行详细说明。First, step S101 will be described in detail.

手机可以作为所述用户终端的一个示例，但不限于此。A mobile phone can be used as an example of the user terminal, but is not limited thereto.

在一个具体实施例中，所述获取用户终端的终端状态信息，包括：在所述预设时间设置k个采样点，其中k为正整数；在每个所述采样点采集用户终端的终端状态信息。In a specific embodiment, the acquiring of the terminal status information of the user terminal includes: setting k sampling points at the preset time, where k is a positive integer; and collecting the terminal status information of the user terminal at each of the sampling points.

预设时间可以是待关注时间段的每一天。The preset time may be every day of the time period to be noted.

第一停留点簇序列是每一天对应的停留点簇序列。The first stay point cluster sequence is a stay point cluster sequence corresponding to each day.

具体来说，可以在每一天设置多个采样点，从而周期性地采集终端状态信息，并记录每个采样点的序号，其中采样点的序号表示为当天的第几个采样点。Specifically, multiple sampling points may be set every day to periodically collect terminal status information and record the serial number of each sampling point, wherein the serial number of the sampling point indicates the sampling point number of the day.

终端状态信息至少包括终端信令信息、终端连接上的WIFI信息、终端扫描到的WIFI列表。终端信令信息至少包括用户编号、用户年龄、用户性别和与该终端匹配的基站编号(基站id)。基于该基站编号，匹配基站位置，可获取用户连接基站的经度和纬度，将经纬度信息作为终端位置信息。The terminal status information includes at least the terminal signaling information, the WIFI information connected to the terminal, and the WIFI list scanned by the terminal. The terminal signaling information includes at least the user number, user age, user gender, and the base station number (base station ID) that matches the terminal. Based on the base station number, the base station location is matched, and the longitude and latitude of the base station to which the user is connected can be obtained, and the longitude and latitude information is used as the terminal location information.

如果当前的终端信令信息的基站id没有匹配的位置信息，则请求当前时刻的终端定位信息作为该基站匹配的位置。由于只需对没有匹配的基站id进行采样位置信息，所有减少了不必要的位置信息采样，减少了功耗。If the base station ID of the current terminal signaling information does not have matching location information, the terminal positioning information at the current moment is requested as the matching location of the base station. Since only the location information of the base station ID without a match needs to be sampled, unnecessary location information sampling is reduced, and power consumption is reduced.

以上是对步骤S101的进一步说明，下面继续对步骤S102作进一步说明。The above is a further description of step S101 , and the following is a further description of step S102 .

在一个实施例中，具体如图2所示，基于终端状态信息确定第一停留点簇序列的步骤可通过下述S1021至S1026实现。In one embodiment, as specifically shown in FIG. 2 , the step of determining the first stay point cluster sequence based on the terminal status information may be implemented through the following S1021 to S1026 .

S1021：基于所述预设时间的第一采样点构建第一停留点簇。S1021: Construct a first stay point cluster based on the first sampling point at the preset time.

在一个具体实施方式中，所述终端状态信息至少包括所述终端连接的基站编号信息、连接的WIFI信息、扫描到的WIFI列表和位置信息；所述基于所述预设时间的第一采样点构建第一停留点簇，包括：将所述第一采样点连接的基站编号信息添加至所述第一停留点簇的基站编号序列；将所述第一采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列；将所述第一采样点扫描到的WIFI列表添加至所述第一停留点簇的第二WIFI序列；将所述第一采样点位置信息作为所述第一停留点簇的位置信息；将所述第一采样点的序号添加至所述第一停留点簇的采样点序列。In a specific embodiment, the terminal status information includes at least the base station number information connected to the terminal, the connected WIFI information, the scanned WIFI list and the location information; the first sampling point based on the preset time is used to construct the first stay point cluster, including: adding the base station number information connected to the first sampling point to the base station number sequence of the first stay point cluster; adding the WIFI information connected to the first sampling point to the first WIFI sequence of the first stay point cluster; adding the WIFI list scanned by the first sampling point to the second WIFI sequence of the first stay point cluster; using the first sampling point location information as the location information of the first stay point cluster; adding the sequence number of the first sampling point to the sampling point sequence of the first stay point cluster.

停留点簇用于存储每个采样点采集的终端状态信息。停留点簇信息包括基站id序列、连接上的WIFI序列、扫描到的WIFI序列、位置信息(基站的经度和纬度信息)和采样点序列等。The stay point cluster is used to store the terminal status information collected at each sampling point. The stay point cluster information includes the base station ID sequence, the connected WIFI sequence, the scanned WIFI sequence, the location information (the longitude and latitude information of the base station) and the sampling point sequence.

具体来说，将首个采样点的信令信息的基站id加入到第一停留点簇的基站编号序列，将首个采样点的WIFI信息中连接上的WIFI信息加入到第一停留点簇的连接上的WIFI序列，将首个采样点的WIFI信息中扫描的WIFI列表加入到第一停留点簇的第二WIFI序列，也即扫描到的WIFI序列，将首个采样点的信令信息的基站id匹配的定位信息中的经度、维度作为第一停留点簇的位置信息，将首个采样点序号加入采样点序列。Specifically, the base station id of the signaling information of the first sampling point is added to the base station number sequence of the first stay point cluster, the connected WIFI information in the WIFI information of the first sampling point is added to the connected WIFI sequence of the first stay point cluster, the scanned WIFI list in the WIFI information of the first sampling point is added to the second WIFI sequence of the first stay point cluster, that is, the scanned WIFI sequence, the longitude and latitude in the positioning information matched with the base station id of the signaling information of the first sampling point are used as the location information of the first stay point cluster, and the first sampling point sequence number is added to the sampling point sequence.

S1022：判断第n采样点是否属于所述第一停留点簇，n为正整数，1＜n≤k。S1022: Determine whether the nth sampling point belongs to the first stay point cluster, where n is a positive integer, 1＜n≤k.

从第二个采样点开始，判断其是否属于第一停留点簇。Starting from the second sampling point, determine whether it belongs to the first stop point cluster.

在一个具体实施例中，所述判断第n采样点是否属于所述第一停留点簇，包括下述步骤：In a specific embodiment, the step of determining whether the nth sampling point belongs to the first stay point cluster comprises the following steps:

S11.判断所述第一停留点簇的基站编号序列是否包含所述第n采样点连接的基站编号信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S12；S11. Determine whether the base station number sequence of the first stay point cluster contains the base station number information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S12;

S12.判断所述第一停留点簇的第一WIFI序列是否包含所述第n采样点连接的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S13；S12. Determine whether the first WIFI sequence of the first stay point cluster contains the WIFI information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S13;

S13.判断所述第一停留点簇的第二WIFI序列与所述第n采样点扫描到的WIFI列表是否至少有一个相同的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S14；S13. Determine whether the second WIFI sequence of the first stay point cluster and the WIFI list scanned by the nth sampling point have at least one identical WIFI information; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S14;

S14.基于所述第一停留点簇的位置信息与所述第n采样点对应终端的位置信息确定第一距离，判断所述第一距离是否小于第一阈值，若是，则确定所述第n采样点属于所述第一停留点簇，若否，确定所述第n采样点不属于所述第一停留点簇。S14. Determine a first distance based on the location information of the first stay point cluster and the location information of the terminal corresponding to the nth sampling point, and determine whether the first distance is less than a first threshold; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, determine that the nth sampling point does not belong to the first stay point cluster.

对于S13，在一个优选实施方式中，可以是判断第一停留点簇的第二WIFI序列与第n采样点扫描到的WIFI列表是否有三个相同的WIFI信息，若是，则确定第n采样点属于第一停留点簇。For S13, in a preferred embodiment, it can be determined whether the second WIFI sequence of the first stay point cluster and the WIFI list scanned by the nth sampling point have three identical WIFI information, and if so, it is determined that the nth sampling point belongs to the first stay point cluster.

在S14中，以n＝2为例，可以是计算第一停留点簇的位置信息与第二采样点对应终端的位置信息之间的距离，判断该距离是否小于第一阈值，若是，则确定第二采样点属于第一停留点簇，若否，确定第二采样点不属于第一停留点簇。In S14, taking n=2 as an example, the distance between the location information of the first stay point cluster and the location information of the terminal corresponding to the second sampling point can be calculated to determine whether the distance is less than the first threshold. If so, it is determined that the second sampling point belongs to the first stay point cluster; if not, it is determined that the second sampling point does not belong to the first stay point cluster.

在上述步骤中，优先以基站id作为判断采样点是否属于第一停留点簇的依据，之后以WIFI信息为判断依据，最后才是位置信息作为判断依据，如此，在终端设备采样位置信息失败的情况下，将对最终结果的负面影响减到最小，从而降低了识别职住地过程中对位置信息的依赖。In the above steps, the base station ID is preferentially used as the basis for judging whether the sampling point belongs to the first stay point cluster, followed by the WIFI information, and finally the location information. In this way, when the terminal device fails to sample the location information, the negative impact on the final result will be minimized, thereby reducing the dependence on location information in the process of identifying the workplace and residence.

S1023：若是，基于所述第n采样点的终端状态信息更新所述第一停留点簇。S1023: If yes, update the first stay point cluster based on the terminal status information of the nth sampling point.

在一个具体实施方式中，所述基于所述第n采样点的终端状态信息更新所述第一停留点簇，包括：在所述第一停留点簇的基站编号序列不包含所述第n采样点的基站编号信息的情况下，将所述第n采样点的基站编号信息添加至所述第一停留点簇的基站编号序列中；在所述第一停留点簇的第一WIFI序列不包含所述第n采样点连接的WIFI信息的情况下，将所述第n采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列中；在所述第一停留点簇的第二WIFI序列不包含所述第n采样点扫描到的WIFI列表的至少一个WIFI信息的情况下，将所述第n采样点扫描到的WIFI列表的至少一个WIFI信息添加至所述第一停留点簇的第二WIFI序列中；基于所述第一停留点簇的位置信息与所述第n采样点的位置信息对所述第一停留点簇的位置信息进行更新；将所述第n采样点的序号添加至所述第一停留点簇的采样点序列。In a specific embodiment, the updating of the first stay point cluster based on the terminal status information of the nth sampling point includes: when the base station number sequence of the first stay point cluster does not include the base station number information of the nth sampling point, adding the base station number information of the nth sampling point to the base station number sequence of the first stay point cluster; when the first WIFI sequence of the first stay point cluster does not include the WIFI information connected to the nth sampling point, adding the WIFI information connected to the nth sampling point to the first WIFI sequence of the first stay point cluster; when the second WIFI sequence of the first stay point cluster does not include at least one WIFI information in the WIFI list scanned by the nth sampling point, adding at least one WIFI information in the WIFI list scanned by the nth sampling point to the second WIFI sequence of the first stay point cluster; updating the position information of the first stay point cluster based on the position information of the first stay point cluster and the position information of the nth sampling point; and adding the sequence number of the nth sampling point to the sampling point sequence of the first stay point cluster.

具体来说，以n＝2为例，如果第二采样点的信令信息的基站id没有在第一停留点簇的基站id序列中，则将第二采样点的信令信息的基站id加到第一停留点簇的基站编号序列中。Specifically, taking n=2 as an example, if the base station ID of the signaling information of the second sampling point is not in the base station ID sequence of the first stay point cluster, the base station ID of the signaling information of the second sampling point is added to the base station number sequence of the first stay point cluster.

如果采样点的WIFI信息中连接上的WIFI没有在第一停留点簇的连接上的WIFI序列中，则将采样点的WIFI信息中连接上的WIFI加入到第一停留点簇的连接上的WIFI序列中。If the connected WIFI in the WIFI information of the sampling point is not in the connected WIFI sequence of the first stay point cluster, the connected WIFI in the WIFI information of the sampling point is added to the connected WIFI sequence of the first stay point cluster.

将采样点的WIFI信息中扫描的WIFI列表中不在第一停留点簇的扫描到的WiFi序列的WIFI加到第一停留点簇的扫描到的WIFI序列。The WIFI in the WIFI list scanned in the WIFI information of the sampling point that is not in the scanned WIFI sequence of the first stay point cluster is added to the scanned WIFI sequence of the first stay point cluster.

将采样点的信令信息的基站id匹配的定位信息中的经度、纬度，与第一停留点簇的经度、纬度进行加权平均作为更新的第一停留点簇的经度、纬度。一个实施例中，采样点的权重和第一停留点簇的权重可以是预设数值。在另一个实施例中，采样点的权重为1，第一停留点簇的权重为采样点序列的长度。The longitude and latitude in the positioning information matched by the base station ID of the signaling information of the sampling point are weighted averaged with the longitude and latitude of the first stay point cluster as the updated longitude and latitude of the first stay point cluster. In one embodiment, the weight of the sampling point and the weight of the first stay point cluster can be preset values. In another embodiment, the weight of the sampling point is 1, and the weight of the first stay point cluster is the length of the sampling point sequence.

将当前的采样点序号加入第一停留点簇的采样点序列。Add the current sampling point sequence number to the sampling point sequence of the first stop point cluster.

S1024：若否，基于所述第n采样点构建第m停留点簇，判断第n+1采样点是否属于所述第m停留点簇，m为正整数，1＜m。S1024: If not, construct an mth stay point cluster based on the nth sampling point, and determine whether the (n+1)th sampling point belongs to the mth stay point cluster, where m is a positive integer and 1<m.

示例性地，例如第二采样点不属于第一停留点簇，基于第二采样点构建第二停留点簇，并继续判断第三个采样点是否属于第二停留点簇。Exemplarily, for example, if the second sampling point does not belong to the first stay point cluster, a second stay point cluster is constructed based on the second sampling point, and then it is determined whether the third sampling point belongs to the second stay point cluster.

S1025：循环上述步骤S1024，直至将所有采样点分配至对应的停留点簇。S1025: The above step S1024 is repeated until all sampling points are assigned to corresponding stay point clusters.

重复上述步骤S1024，直到找到第一个不属于第二停留点簇的采样点，继续构建第三停留点簇。如此，可以将所有的采样点分配至对应的停留点簇。Repeat the above step S1024 until the first sampling point that does not belong to the second stay point cluster is found, and continue to build the third stay point cluster. In this way, all sampling points can be assigned to corresponding stay point clusters.

S1026：基于所述停留点簇得到所述第一停留点簇序列。S1026: Obtain the first stay point cluster sequence based on the stay point cluster.

获得多个停留点簇后，判断每个停留点簇中的采样点序列长度是否大于等于预设长度，若是，则将停留点簇加入第一停留点簇序列，若否，将该停留点簇删除，从而得到第一停留点簇序列。After obtaining multiple stay point clusters, determine whether the sampling point sequence length in each stay point cluster is greater than or equal to a preset length. If so, add the stay point cluster to the first stay point cluster sequence. If not, delete the stay point cluster to obtain the first stay point cluster sequence.

以上是对步骤S102的进一步说明，下面继续对步骤S103作进一步说明。The above is a further description of step S102 , and the following is a further description of step S103 .

停留聚类点簇是聚类后的停留点簇的集合，具体是通过对第二停留点簇序列中的停留点簇进行聚类后得到。The stay point clustering cluster is a set of clustered stay point clusters, which is specifically obtained by clustering the stay point clusters in the second stay point cluster sequence.

第二停留点簇序列是待关注时间段的停留点簇序列，例如多天对应的停留点簇序列。由于每一天的停留点簇序列是第一停留点簇序列，故第二停留点簇序列包含多个第一停留点簇序列。The second stay point cluster sequence is a stay point cluster sequence of the time period to be concerned, such as a stay point cluster sequence corresponding to multiple days. Since the stay point cluster sequence of each day is the first stay point cluster sequence, the second stay point cluster sequence includes multiple first stay point cluster sequences.

在一个具体实施例中，具体如图3所示，基于所述第二停留点簇序列进行聚类得到停留聚类点簇，可通过下述S1031至S1034实现。In a specific embodiment, as shown in FIG3 , clustering is performed based on the second stay point cluster sequence to obtain stay point clusters, which can be achieved through the following S1031 to S1034.

S1031：确定所述第二停留点簇序列中任意两个停留点簇之间的距离。S1031: Determine the distance between any two stay point clusters in the second stay point cluster sequence.

在一个具体实施例中，所述确定所述第二停留点簇序列中任意两个停留点簇之间的距离，包括：In a specific embodiment, determining the distance between any two stay point clusters in the second stay point cluster sequence includes:

S21.判断所述任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述任意两个停留点簇之间的距离为第一预设距离；若否，执行S22；S21. Determine whether there is the same base station number in the base station number sequence of any two stay point clusters; if so, determine that the distance between the any two stay point clusters is a first preset distance; if not, execute S22;

S22.判断所述任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息，若是，则确定所述任意两个停留点簇之间的距离为第二预设距离；若否，基于所述任意两个停留点簇的位置信息确定所述任意两个停留点簇之间的距离。S22. Determine whether the first WIFI sequences of any two stay point clusters have the same WIFI information. If so, determine that the distance between the any two stay point clusters is a second preset distance; if not, determine the distance between the any two stay point clusters based on the location information of the any two stay point clusters.

第一预设距离和第二预设距离可以是预先通过实验获得的数值。The first preset distance and the second preset distance may be values obtained in advance through experiments.

在S22中，基于任意两个停留点簇的位置信息确定任意两个停留点簇之间的距离，可以是基于任意两个停留点簇的经纬度信息计算任意两个停留点簇之间的距离。In S22, the distance between any two stay point clusters is determined based on the position information of any two stay point clusters, and the distance between any two stay point clusters may be calculated based on the latitude and longitude information of any two stay point clusters.

S1032：基于所述任意两个停留点簇之间的距离得到距离矩阵。S1032: Obtain a distance matrix based on the distance between any two stay point clusters.

获得任意两个停留点簇之间的距离，能够获得第二停留点簇序列对应的距离矩阵。By obtaining the distance between any two stay point clusters, the distance matrix corresponding to the second stay point cluster sequence can be obtained.

S1033：基于所述距离矩阵对所述第二停留点簇序列中的停留点簇进行聚类，得到多个聚类簇。S1033: Clustering the stay point clusters in the second stay point cluster sequence based on the distance matrix to obtain a plurality of cluster clusters.

具体来说，基于距离矩阵、用最小预设距离、最小预设密度的DBSCAN密度聚类算法对第二停留点簇序列中的停留点簇进行聚类，得到多个聚类簇。Specifically, based on the distance matrix, the DBSCAN density clustering algorithm with the minimum preset distance and the minimum preset density is used to cluster the stay point clusters in the second stay point cluster sequence to obtain a plurality of cluster clusters.

DBSCAN聚类算法一种基于密度的聚类算法，这类密度聚类算法一般假定类别可以通过样本分布的紧密程度决定。同一类别的样本，他们之间的紧密相连的，也就是说，在该类别任意样本周围不远处一定有同类别的样本存在。通过将紧密相连的样本划为一类，这样就得到了一个聚类类别。通过将所有各组紧密相连的样本划为各个不同的类别，则我们就得到了最终的所有聚类类别结果。DBSCAN clustering algorithm is a density-based clustering algorithm. This type of density clustering algorithm generally assumes that the category can be determined by the density of sample distribution. Samples of the same category are closely connected, that is, there must be samples of the same category not far away from any sample of the category. By classifying closely connected samples into one category, we get a cluster category. By classifying all groups of closely connected samples into different categories, we get the final results of all cluster categories.

由于采用DBSCAN密度聚类算法进行聚类属于信息处理领域的常规操作，此处不赘述。Since clustering using the DBSCAN density clustering algorithm is a routine operation in the field of information processing, it will not be described here.

S1034：融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇。S1034: Merge the stay point clusters in each of the clusters to obtain the stay point clusters.

聚类后得到多个聚类簇，每个聚类簇中包括多个停留点簇。由于每个聚类簇中可能包括同一区域的停留点簇，因此需要对同一区域的停留点簇进行融合。After clustering, multiple clusters are obtained, each of which includes multiple stay point clusters. Since each cluster may include stay point clusters in the same area, it is necessary to merge the stay point clusters in the same area.

在一个具体实施例中，所述停留聚类点簇包括停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列、位置信息和采样点序列；所述融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇，包括：对每个所述聚类簇中所有停留点簇的基站编号序列、第一WIFI序列和第二WIFI序列分别取并集，得到所述停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列；对每个所述聚类簇中所有停留点簇的位置信息进行加权平均，得到所述停留聚类点簇的位置信息；对每个所述聚类簇中所有停留点簇的采样点序列进行合并，得到所述停留聚类点簇的采样点序列。In a specific embodiment, the stay cluster point cluster includes a base station numbering sequence, a first WIFI sequence and a second WIFI sequence, location information and a sampling point sequence of the stay cluster point cluster; the fusion of the stay point clusters in each of the clusters to obtain the stay cluster point cluster includes: taking the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of all the stay point clusters in each of the clusters to obtain the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of the stay cluster point cluster; performing weighted averaging on the location information of all the stay point clusters in each of the clusters to obtain the location information of the stay cluster point cluster; merging the sampling point sequences of all the stay point clusters in each of the clusters to obtain the sampling point sequence of the stay cluster point cluster.

具体来说，在融合过程中，对每个聚类簇中所有停留点簇的基站编号序列取并集，得到停留聚类点簇的基站编号序列。Specifically, during the fusion process, the base station number sequences of all stay point clusters in each cluster are combined to obtain the base station number sequence of the stay point cluster.

对每个聚类簇中所有停留点簇的第一WIFI序列取并集，得到停留聚类点簇的第一WIFI序列。The first WIFI sequence of all the stay point clusters in each cluster is taken as the union to obtain the first WIFI sequence of the stay point cluster.

对每个聚类簇中所有停留点簇的第二WIFI序列取并集，得到停留聚类点簇的第二WIFI序列。The second WIFI sequences of all the stay point clusters in each cluster are combined to obtain the second WIFI sequence of the stay point cluster.

对每个类簇中所有停留点簇的位置信息进行加权平均，得到停留聚类点簇的位置信息。其中每个停留点簇的权重可以是预设值，也可以是各自采样点序列的长度对应的权重。The location information of all the stay point clusters in each cluster is weighted averaged to obtain the location information of the stay point cluster, wherein the weight of each stay point cluster can be a preset value or a weight corresponding to the length of each sampling point sequence.

以上是对步骤S103的进一步说明，下面继续对步骤S104作进一步说明。The above is a further description of step S103 , and the following is a further description of step S104 .

在一个具体实施方式，具体如图4所示，基于所述停留聚类点簇识别所述用户的职住地可通过下述步骤S1041至S1043实现。In a specific implementation, as shown in FIG. 4 , identifying the user's workplace and residence based on the stay clustering point clusters can be achieved through the following steps S1041 to S1043 .

S1041：获取所述停留聚类点簇的采样点序列中每个采样点对应的第一权重和第二权重，其中所述第一权重为所述采样点对应用户居住地的权重，所述第二权重为所述采样点对应用户工作地的权重。S1041: Obtain a first weight and a second weight corresponding to each sampling point in the sampling point sequence of the stay cluster point cluster, wherein the first weight is the weight of the sampling point corresponding to the user's residence, and the second weight is the weight of the sampling point corresponding to the user's workplace.

具体来说，基于当地的平均作息时间，为每个采样点的采样点序号设置居住地的权重和工作地的权重。具体的，采样时间在上班时间的，设置采样点序号对应的居住地的权重为wh1，工作地的权重为ww1，wh1＜ww1；采样时间在休息时间的，设置采样点序号对应居住地的权重为wh2，工作地的权重为ww2，ww2＜wh2，其中wh1、ww1、wh2、ww2可以是根据实际场景给定的权重。Specifically, based on the local average work and rest time, the weight of the residence and the weight of the workplace are set for the sampling point number of each sampling point. Specifically, if the sampling time is during working hours, the weight of the residence corresponding to the sampling point number is set to wh1, and the weight of the workplace is set to ww1, wh1＜ww1; if the sampling time is during rest time, the weight of the residence corresponding to the sampling point number is set to wh2, and the weight of the workplace is set to ww2, ww2＜wh2, where wh1, ww1, wh2, and ww2 can be weights given according to actual scenarios.

S1042：基于所述第一权重和所述第二权重，分别确定所述停留聚类点簇作为用户居住地对应的第一置信度和作为用户工作地对应的第二置信度。S1042: Based on the first weight and the second weight, respectively determine a first confidence level corresponding to the stay cluster as the user's residence and a second confidence level corresponding to the user's workplace.

具体来说，将每个停留聚类点簇中采样点序列对应的采样点序号转换为居住地的权重，并求和作为居住地对应的第一置信度。将每个停留聚类点簇中采样点序列对应的采样点序号转换为工作地的权重，并求和作为工作地对应的第二置信度。Specifically, the sampling point numbers corresponding to the sampling point sequence in each stay cluster point cluster are converted into the weight of the residence, and the sum is used as the first confidence corresponding to the residence. The sampling point numbers corresponding to the sampling point sequence in each stay cluster point cluster are converted into the weight of the workplace, and the sum is used as the second confidence corresponding to the workplace.

S1043：基于所述第一置信度和所述第二置信度确定用户居住地和用户工作地。S1043: Determine the user's residence and the user's workplace based on the first confidence level and the second confidence level.

具体来说，如果第一置信度大于第二置信度，则将停留点簇识别为用户居住地，否则，将停留点簇识别为用户工作地。Specifically, if the first confidence is greater than the second confidence, the stay point cluster is identified as the user's residence; otherwise, the stay point cluster is identified as the user's workplace.

在一个具体实施方式中，所述方法还包括：从识别为用户居住地的所述停留聚类点簇中获取用户居住地信息；和/或从识别为用户工作地的所述停留聚类点簇中获取用户工作地信息。In a specific embodiment, the method further includes: obtaining user residence information from the stay clustering point cluster identified as the user's residence; and/or obtaining user workplace information from the stay clustering point cluster identified as the user's workplace.

具体来说，进一步还可以从识别为居住地或者工作地的停留点簇中提取处用户居住地或者工作地的信息。Specifically, information on the user's residence or workplace may be further extracted from the stay point cluster identified as the residence or workplace.

例如，对于识别为居住地的停留聚类点簇，将其基站id序列作为用户居住地的基站id序列，将停留聚类点簇的连接的WIFI序列作为居住地连接的WIFI序列，将停留聚类点簇的位置信息作为居住地的位置信息。For example, for the stay cluster point cluster identified as a residence, its base station ID sequence is used as the base station ID sequence of the user's residence, the WIFI sequence of the connection of the stay cluster point cluster is used as the WIFI sequence of the residence connection, and the location information of the stay cluster point cluster is used as the location information of the residence.

对于识别为工作地的停留聚类点簇，将停留聚类点簇的基站id序列作为工作地的基站id序列，将停留聚类点簇的连接的WIFI序列作为工作地连接的WIFI序列，将停留聚类点簇的位置信息作为工作地的位置信息。如此，不依赖于位置信息，也能够获得用户的职住地，提高了职住地的精确度。For the stay cluster point cluster identified as the workplace, the base station ID sequence of the stay cluster point cluster is used as the base station ID sequence of the workplace, the WIFI sequence of the connection of the stay cluster point cluster is used as the WIFI sequence of the workplace connection, and the location information of the stay cluster point cluster is used as the location information of the workplace. In this way, the user's workplace and residence can be obtained without relying on the location information, which improves the accuracy of the workplace and residence.

在一个具体实施方式中，在基于所述终端状态信息确定第一停留点簇序列之后，以及基于第二停留点簇序列进行聚类得到停留聚类点簇之前，所述方法还包括：判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇；若是，对所述第一停留点簇序列中包含同一区域的停留点簇进行融合；将融合后的所有停留点簇按照采样点序列的长度进行排序；将所述采样点序列的长度小于动态长度阈值的停留点簇从所述第一停留点簇序列中删除。In a specific embodiment, after determining the first stay point cluster sequence based on the terminal status information, and before clustering to obtain stay point clusters based on the second stay point cluster sequence, the method also includes: determining whether there are stay point clusters containing the same area in the first stay point cluster sequence; if so, merging the stay point clusters containing the same area in the first stay point cluster sequence; sorting all the fused stay point clusters according to the length of the sampling point sequence; and deleting the stay point clusters whose lengths of the sampling point sequences are less than a dynamic length threshold from the first stay point cluster sequence.

动态长度阈值指的是可调节的长度阈值，例如每天的第一停留点簇序列对应的动态长度阈值可以不同，具体根据实际应用场景设置动态长度阈值。The dynamic length threshold refers to an adjustable length threshold. For example, the dynamic length threshold corresponding to the first stay point cluster sequence of each day may be different. The dynamic length threshold is set according to the actual application scenario.

具体来说，在获得第一停留点簇序列后，需要对同一区域的停留点簇进行融合，并将融合后的所有停留点簇按照采样点序列的长度进行排序，对于采样点序列小于预设长度的停留点簇，说明用户在该位置的停留较短，无法作为识别用户职住地的依据，可以将其该停留点簇从第一停留点簇序列中删除。如此，减小了数据的复杂性，有利于提高对职住地的识别效率。其中，对于同一区域的停留点簇进行融合的具体手段可以参见S1034的详细步骤，此处不赘述。Specifically, after obtaining the first stay point cluster sequence, it is necessary to fuse the stay point clusters in the same area, and sort all the fused stay point clusters according to the length of the sampling point sequence. For the stay point clusters whose sampling point sequence is less than the preset length, it means that the user's stay at the location is short and cannot be used as a basis for identifying the user's work and residence. The stay point cluster can be deleted from the first stay point cluster sequence. In this way, the complexity of the data is reduced, which is conducive to improving the efficiency of identifying the work and residence. Among them, the specific means for fusing the stay point clusters in the same area can be referred to the detailed steps of S1034, which will not be repeated here.

在一个具体实施例中，所述判断所述第一停留点簇序列中是否存在包含同一区域的停留点簇，包括：In a specific embodiment, the determining whether there is a stay point cluster including the same area in the first stay point cluster sequence includes:

S31.判断所述第一停留点簇序列的任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S32。S31. Determine whether there are the same base station numbers in the base station number sequences of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there are stay point clusters covering the same area in the first stay point cluster sequence; if not, execute S32.

S32.判断所述第一停留点簇序列的任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息；若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，执行S33。S32. Determine whether there is the same WIFI information in the first WIFI sequences of any two stay point clusters in the first stay point cluster sequence; if so, determine whether there is a stay point cluster containing the same area in the first stay point cluster sequence; if not, execute S33.

S33.基于所述第一停留点簇序列中任意两个停留点簇的位置信息确定第二距离，判断所述第二距离是否小于第二阈值，若是，则确定所述第一停留点簇序列中存在包含同一区域的停留点簇，若否，则确定所述第一停留点簇序列中不存在包含同一区域的停留点簇。S33. Determine a second distance based on the position information of any two stay point clusters in the first stay point cluster sequence, and judge whether the second distance is less than a second threshold value. If so, determine that there are stay point clusters covering the same area in the first stay point cluster sequence; if not, determine that there are no stay point clusters covering the same area in the first stay point cluster sequence.

具体来说，第二距离可以是基于任意两个停留点簇的位置信息(经纬度)得到的。第二阈值可以是预先通过实验得到的数值。Specifically, the second distance may be obtained based on the location information (longitude and latitude) of any two stay point clusters. The second threshold may be a value obtained in advance through experiments.

通过上述步骤S31至S33即可判断第一停留点簇序列中是否存在包含同一区域的停留点簇，继而对同一区域的停留点簇进行融合。Through the above steps S31 to S33, it can be determined whether there is a stay point cluster including the same area in the first stay point cluster sequence, and then the stay point clusters in the same area are merged.

需要说明的是，本发明所提及的终端信令信息、终端连接上的WIFI信息、终端扫描到的WIFI列表等均是经过包括用户或各方充分授权后获得的。也就是说，本发明中的终端是授权终端。在一些实施方式中，可以通过终端或后台服务器来检测是否接收到授权信息，若接收到授权信息则表明当前终端是授权终端，否则当前终端是未授权终端。It should be noted that the terminal signaling information, the WIFI information connected to the terminal, the WIFI list scanned by the terminal, etc. mentioned in the present invention are all obtained after full authorization by the user or all parties. In other words, the terminal in the present invention is an authorized terminal. In some embodiments, the terminal or the backend server can detect whether the authorization information is received. If the authorization information is received, it indicates that the current terminal is an authorized terminal, otherwise the current terminal is an unauthorized terminal.

需要指出的是，尽管上述实施例中将各个步骤按照特定的先后顺序进行了描述，但是本领域技术人员可以理解，为了实现本发明的效果，不同的步骤之间并非必须按照这样的顺序执行，其可以同时(并行)执行或以其他顺序执行，这些变化都在本发明的保护范围之内。It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

本领域技术人员能够理解的是，本发明实现上述一实施例的方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读存储介质可以包括：能够携带所述计算机程序代码的任何实体或装置、介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器、随机存取存储器、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读存储介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读存储介质不包括电载波信号和电信信号。It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

进一步，本发明还提供了一种电子设备。在根据本发明的一个电子设备实施例中，具体如图5所示，电子设备包括至少一个处理器51和至少一个存储装置52，存储装置可以被配置成存储执行上述方法实施例的用户职住地识别方法的程序，处理器可以被配置成用于执行存储装置中的程序，该程序包括但不限于执行上述方法实施例的用户职住地识别方法的程序。为了便于说明，仅示出了与本发明实施例相关的部分，具体技术细节未揭示的，请参照本发明实施例方法部分。Furthermore, the present invention also provides an electronic device. In an electronic device embodiment according to the present invention, as specifically shown in FIG5 , the electronic device includes at least one processor 51 and at least one storage device 52, the storage device can be configured to store a program for executing the user's workplace identification method of the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to executing the user's workplace identification method of the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention.

在本发明实施例中电子设备可以是包括各种设备形成的控制装置设备。在一些可能的实施方式中，电子设备可以包括多个存储装置和多个处理器。而执行上述方法实施例的用户职住地识别方法的程序可以被分割成多段子程序，每段子程序分别可以由处理器加载并运行以执行上述方法实施例的用户职住地识别方法的不同步骤。具体地，每段子程序可以分别存储在不同的存储装置中，每个处理器可以被配置成用于执行一个或多个存储装置中的程序，以共同实现上述方法实施例的用户职住地识别方法，即每个处理器分别执行上述方法实施例的用户职住地识别方法的不同步骤，来共同实现上述方法实施例的用户职住地识别方法。In the embodiment of the present invention, the electronic device may be a control device device formed by various devices. In some possible implementations, the electronic device may include multiple storage devices and multiple processors. The program for executing the user's workplace and residence identification method of the above method embodiment can be divided into multiple subprograms, and each subprogram can be loaded and run by the processor to execute different steps of the user's workplace and residence identification method of the above method embodiment. Specifically, each subprogram can be stored in different storage devices, and each processor can be configured to execute the program in one or more storage devices to jointly implement the user's workplace and residence identification method of the above method embodiment, that is, each processor executes different steps of the user's workplace and residence identification method of the above method embodiment, to jointly implement the user's workplace and residence identification method of the above method embodiment.

上述多个处理器可以是部署于同一个设备上的处理器，例如上述电子设备可以是由多个处理器组成的高性能设备，上述多个处理器可以是该高性能设备上配置的处理器。此外，上述多个处理器也可以是部署于不同设备上的处理器，例如上述电子设备可以是服务器集群，上述多个处理器可以是服务器集群中不同服务器上的处理器。The above-mentioned multiple processors may be processors deployed on the same device. For example, the above-mentioned electronic device may be a high-performance device composed of multiple processors, and the above-mentioned multiple processors may be processors configured on the high-performance device. In addition, the above-mentioned multiple processors may also be processors deployed on different devices. For example, the above-mentioned electronic device may be a server cluster, and the above-mentioned multiple processors may be processors on different servers in the server cluster.

进一步，本发明还提供了一种计算机可读存储介质。在根据本发明的一个计算机可读存储介质实施例中，计算机可读存储介质可以被配置成存储执行上述方法实施例的用户职住地识别方法的程序，该程序可以由处理器加载并运行以实现上述用户职住地识别方法。为了便于说明，仅示出了与本发明实施例相关的部分，具体技术细节未揭示的，请参照本发明实施例方法部分。该计算机可读存储介质可以是包括各种电子设备形成的存储装置设备，可选的，本发明实施例中计算机可读存储介质是非暂时性的计算机可读存储介质。Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the user's workplace identification method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned user's workplace identification method. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

至此，已经结合附图所示的优选实施方式描述了本发明的技术方案，但是，本领域技术人员容易理解的是，本发明的保护范围显然不局限于这些具体实施方式。在不偏离本发明的原理的前提下，本领域技术人员可以对相关技术特征作出等同的更改或替换，这些更改或替换之后的技术方案都将落入本发明的保护范围之内。So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims (10)

Translated fromChinese

1.一种用户职住地识别方法，其特征在于，所述方法包括：1. A method for identifying a user's workplace and residence, characterized in that the method comprises:获取用户终端的终端状态信息；Obtain terminal status information of the user terminal;基于所述终端状态信息确定第一停留点簇序列；Determine a first stay point cluster sequence based on the terminal state information;基于第二停留点簇序列进行聚类，得到停留聚类点簇，所述第二停留点簇序列包括所述第一停留点簇序列；Perform clustering based on a second stay point cluster sequence to obtain a stay point cluster, wherein the second stay point cluster sequence includes the first stay point cluster sequence;基于所述停留聚类点簇识别所述用户职住地。The user's workplace and residence are identified based on the stay cluster point clusters.2.根据权利要求1所述的用户职住地识别方法，其特征在于，所述获取用户终端的终端状态信息，包括：2. The method for identifying a user's workplace and residence according to claim 1, wherein the step of obtaining the terminal status information of the user terminal comprises:在预设时间设置k个采样点，其中k为正整数；Set k sampling points at a preset time, where k is a positive integer;在每个所述采样点采集用户终端的终端状态信息。The terminal status information of the user terminal is collected at each sampling point.3.根据权利要求2所述的用户职住地识别方法，其特征在于，所述终端状态信息至少包括所述终端连接的基站编号信息、连接的WIFI信息、扫描到的WIFI列表和位置信息；所述基于所述终端状态信息确定第一停留点簇序列，包括：3. The user's workplace and residence identification method according to claim 2, characterized in that the terminal status information at least includes the base station number information connected to the terminal, the connected WIFI information, the scanned WIFI list and the location information; the determining the first stay point cluster sequence based on the terminal status information comprises:基于所述预设时间的第一采样点构建第一停留点簇；Constructing a first stay point cluster based on the first sampling point at the preset time;判断第n采样点是否属于所述第一停留点簇，n为正整数，1＜n≤k；Determine whether the nth sampling point belongs to the first stay point cluster, where n is a positive integer, 1＜n≤k;若是，基于所述第n采样点的终端状态信息更新所述第一停留点簇；If so, updating the first stay point cluster based on the terminal status information of the nth sampling point;若否，基于所述第n采样点构建第m停留点簇，判断第n+1采样点是否属于所述第m停留点簇，m为正整数，1＜m；If not, construct an mth stay point cluster based on the nth sampling point, and determine whether the n+1th sampling point belongs to the mth stay point cluster, where m is a positive integer and 1<m;直至将所有采样点分配至对应的停留点簇；Until all sampling points are assigned to the corresponding stay point clusters;基于所述停留点簇得到所述第一停留点簇序列。The first stay point cluster sequence is obtained based on the stay point cluster.4.根据权利要求3所述的用户职住地识别方法，其特征在于，所述基于所述预设时间的第一采样点构建第一停留点簇，包括：4. The method for identifying a user's workplace and residence according to claim 3, wherein the step of constructing a first stay point cluster based on the first sampling point at the preset time comprises:将所述第一采样点连接的基站编号信息添加至所述第一停留点簇的基站编号序列；Adding the base station number information connected to the first sampling point to the base station number sequence of the first stay point cluster;将所述第一采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列；Adding the WIFI information of the first sampling point connection to the first WIFI sequence of the first stay point cluster;将所述第一采样点扫描到的WIFI列表添加至所述第一停留点簇的第二WIFI序列；Add the WIFI list scanned by the first sampling point to the second WIFI sequence of the first stay point cluster;将所述第一采样点位置信息作为所述第一停留点簇的位置信息；Using the first sampling point location information as the location information of the first stay point cluster;将所述第一采样点的序号添加至所述第一停留点簇的采样点序列。The sequence number of the first sampling point is added to the sampling point sequence of the first stay point cluster.5.根据权利要求3所述的用户职住地识别方法，其特征在于，所述判断第n采样点是否属于所述第一停留点簇，包括：5. The method for identifying a user's workplace and residence according to claim 3, wherein the step of determining whether the nth sampling point belongs to the first stay point cluster comprises:S11.判断所述第一停留点簇的基站编号序列是否包含所述第n采样点连接的基站编号信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S12；S11. Determine whether the base station number sequence of the first stay point cluster contains the base station number information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S12;S12.判断所述第一停留点簇的第一WIFI序列是否包含所述第n采样点连接的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S13；S12. Determine whether the first WIFI sequence of the first stay point cluster contains the WIFI information connected to the nth sampling point; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S13;S13.判断所述第一停留点簇的第二WIFI序列与所述第n采样点扫描到的WIFI列表是否至少有一个相同的WIFI信息；若是，则确定所述第n采样点属于所述第一停留点簇，若否，执行S14；S13. Determine whether the second WIFI sequence of the first stay point cluster and the WIFI list scanned by the nth sampling point have at least one identical WIFI information; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, execute S14;S14.基于所述第一停留点簇的位置信息与所述第n采样点对应终端的位置信息确定第一距离，判断所述第一距离是否小于第一阈值，若是，则确定所述第n采样点属于所述第一停留点簇，若否，确定所述第n采样点不属于所述第一停留点簇。S14. Determine a first distance based on the location information of the first stay point cluster and the location information of the terminal corresponding to the nth sampling point, and determine whether the first distance is less than a first threshold; if so, determine that the nth sampling point belongs to the first stay point cluster; if not, determine that the nth sampling point does not belong to the first stay point cluster.6.根据权利要求3所述的用户职住地识别方法，其特征在于，所述基于所述第n采样点的终端状态信息更新所述第一停留点簇，包括：6. The method for identifying a user's workplace and residence according to claim 3, wherein updating the first stay point cluster based on the terminal status information of the nth sampling point comprises:在所述第一停留点簇的基站编号序列不包含所述第n采样点的基站编号信息的情况下，将所述第n采样点的基站编号信息添加至所述第一停留点簇的基站编号序列中；If the base station number sequence of the first stay point cluster does not include the base station number information of the nth sampling point, adding the base station number information of the nth sampling point to the base station number sequence of the first stay point cluster;在所述第一停留点簇的第一WIFI序列不包含所述第n采样点连接的WIFI信息的情况下，将所述第n采样点连接的WIFI信息添加至所述第一停留点簇的第一WIFI序列中；When the first WIFI sequence of the first stay point cluster does not include the WIFI information of the n-th sampling point connection, adding the WIFI information of the n-th sampling point connection to the first WIFI sequence of the first stay point cluster;在所述第一停留点簇的第二WIFI序列不包含所述第n采样点扫描到的WIFI列表的至少一个WIFI信息的情况下，将所述第n采样点扫描到的WIFI列表的至少一个WIFI信息添加至所述第一停留点簇的第二WIFI序列中；If the second WIFI sequence of the first stay point cluster does not include at least one WIFI information in the WIFI list scanned by the n-th sampling point, add at least one WIFI information in the WIFI list scanned by the n-th sampling point to the second WIFI sequence of the first stay point cluster;基于所述第一停留点簇的位置信息与所述第n采样点的位置信息对所述第一停留点簇的位置信息进行更新；updating the position information of the first stay point cluster based on the position information of the first stay point cluster and the position information of the nth sampling point;将所述第n采样点的序号添加至所述第一停留点簇的采样点序列。The sequence number of the nth sampling point is added to the sampling point sequence of the first stay point cluster.7.根据权利要求1所述的用户职住地识别方法，其特征在于，所述基于第二停留点簇序列进行聚类，得到停留聚类点簇，包括：7. The method for identifying a user's workplace and residence according to claim 1, wherein the step of clustering based on the second stay point cluster sequence to obtain the stay point clusters comprises:确定所述第二停留点簇序列中任意两个停留点簇之间的距离；Determining the distance between any two stay point clusters in the second stay point cluster sequence;基于所述任意两个停留点簇之间的距离得到距离矩阵；Obtaining a distance matrix based on the distance between any two stay point clusters;基于所述距离矩阵对所述第二停留点簇序列中的停留点簇进行聚类，得到多个聚类簇；Clustering the stay point clusters in the second stay point cluster sequence based on the distance matrix to obtain a plurality of cluster clusters;融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇。The stay point clusters in each of the clusters are fused to obtain the stay point clusters.8.根据权利要求7所述的用户职住地识别方法，其特征在于，所述确定所述第二停留点簇序列中任意两个停留点簇之间的距离，包括：8. The method for identifying a user's workplace and residence according to claim 7, wherein determining the distance between any two stay point clusters in the second stay point cluster sequence comprises:S21.判断所述任意两个停留点簇的基站编号序列中是否有相同的基站编号；若是，则确定所述任意两个停留点簇之间的距离为第一预设距离；若否，执行S22；S21. Determine whether there is the same base station number in the base station number sequence of any two stay point clusters; if so, determine that the distance between the any two stay point clusters is a first preset distance; if not, execute S22;S22.判断所述任意两个停留点簇的第一WIFI序列中是否有相同的WIFI信息，若是，则确定所述任意两个停留点簇之间的距离为第二预设距离；若否，基于所述任意两个停留点簇的位置信息确定所述任意两个停留点簇之间的距离。S22. Determine whether the first WIFI sequences of any two stay point clusters have the same WIFI information. If so, determine that the distance between the any two stay point clusters is a second preset distance; if not, determine the distance between the any two stay point clusters based on the location information of the any two stay point clusters.9.根据权利要求7所述的用户职住地识别方法，其特征在于，所述停留聚类点簇包括停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列、位置信息和采样点序列；所述融合每个所述聚类簇中的停留点簇，得到所述停留聚类点簇，包括：9. The user work and residence identification method according to claim 7, characterized in that the stay clustering point cluster includes a base station number sequence, a first WIFI sequence and a second WIFI sequence, location information and a sampling point sequence of the stay clustering point cluster; the fusion of the stay point clusters in each of the clusters to obtain the stay clustering point cluster comprises:对每个所述聚类簇中所有停留点簇的基站编号序列、第一WIFI序列和第二WIFI序列分别取并集，得到所述停留聚类点簇的基站编号序列、第一WIFI序列和第二WIFI序列；Taking the union of the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of all the stay point clusters in each of the clusters, respectively, to obtain the base station numbering sequence, the first WIFI sequence and the second WIFI sequence of the stay point cluster;对每个所述聚类簇中所有停留点簇的位置信息进行加权平均，得到所述停留聚类点簇的位置信息；Performing weighted averaging on the location information of all the stop point clusters in each of the clusters to obtain the location information of the stop point clusters;对每个所述聚类簇中所有停留点簇的采样点序列进行合并，得到所述停留聚类点簇的采样点序列。The sampling point sequences of all the stop point clusters in each of the clusters are merged to obtain the sampling point sequence of the stop point cluster.10.根据权利要求1所述的用户职住地识别方法，其特征在于，所述基于所述停留聚类点簇识别所述用户职住地，包括：10. The method for identifying a user's workplace and residence according to claim 1, wherein the identifying the user's workplace and residence based on the stay cluster point clusters comprises:获取所述停留聚类点簇的采样点序列中每个采样点对应的第一权重和第二权重，其中所述第一权重为所述采样点对应用户居住地的权重，所述第二权重为所述采样点对应用户工作地的权重；Obtaining a first weight and a second weight corresponding to each sampling point in the sampling point sequence of the stay cluster point cluster, wherein the first weight is the weight of the sampling point corresponding to the user's residence, and the second weight is the weight of the sampling point corresponding to the user's workplace;基于所述第一权重和所述第二权重，分别确定所述停留聚类点簇作为用户居住地对应的第一置信度和作为用户工作地对应的第二置信度；Based on the first weight and the second weight, respectively determining a first confidence level corresponding to the stay cluster as a user's residence and a second confidence level corresponding to the user's workplace;基于所述第一置信度和所述第二置信度确定用户居住地和用户工作地。The user's residence and the user's work place are determined based on the first confidence level and the second confidence level.