Address correction method, device, apparatus and storage medium

Abstract

The present disclosure provides an address correction method and device, equipment and a storage medium, and relates to the technical field of communication networks. In some embodiments of the present disclosure, a mobile communication identifier, a complaint time period and a complaint user address are obtained. According to the mobile communication identifier, the position information of a target base station in which the user resides in the complaint time period is determined. According to the position information of the target base station, the target base station is clustered to obtain a position clustering label of the target base station. The base station geographic grid coverage range of the target base stations with the same position clustering label is merged to obtain a complaint address coverage range. The complaint user address is automatically corrected according to the point of interest address in the complaint address coverage range, the complaint user address is automatically corrected, the correction efficiency of the complaint user address is improved, and the labor cost is reduced.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication network, and particularly relates to an address correction method and device, equipment and storage medium. BACKGROUND

[0002] In the processing flow of user complaints, the importance of user address is very high, which plays a crucial role in user complaint processing. The user address can help the analyst accurately locate the geographical location of the user, so as to better analyze the network situation of the location where the user is located, and accurately locate the problem. At the same time, the user address is converted into longitude and latitude through the GIS interface, which is important basic information to realize automatic association of network data. However, the user complaint address registered by the customer service system at present is generally obtained by user oral description and manual recording by customer service personnel, which often leads to inaccuracy of Chinese description address due to language difference, recording error, understanding error and other human factors, greatly affecting the accuracy and efficiency of complaint processing analysis.

[0003] At present, the complaint user address mainly relies on manual inspection, which is low in efficiency and high in labor cost. SUMMARY

[0004] The present disclosure provides an interface display control method to at least solve the problem that the existing complaint user address relies on manual inspection, which is low in efficiency and high in labor cost.

[0005] The technical solution of the present disclosure is as follows:

[0006] The present disclosure provides an address correction method, comprising:

[0007] obtaining a mobile communication identifier, a complaint time period and a complaint user address;

[0008] determining location information of a target base station in which a user resides in the complaint time period according to the mobile communication identifier;

[0009] clustering the target base station according to the location information of the target base station to obtain a location clustering label of the target base station;

[0010] merging base station geographic grid coverage ranges of the target base stations with the same location clustering label to obtain a complaint address coverage range;

[0011] correcting the complaint user address according to a point of interest address in the complaint address coverage range.

[0012] Optionally, the clustering the target base station according to the location information of the target base station to obtain a location clustering label of the target base station comprises:

[0013] marking all latitude and longitude points as unvisited state, and selecting a neighborhood radius ε and a minimum number of neighborhood points, wherein each of the latitude and longitude points corresponds to a target base station;

[0014] randomly selecting an unvisited latitude and longitude point P, and marking the latitude and longitude point P as visited state;

[0015] if the number of points in the neighborhood of the latitude and longitude point P is greater than or equal to the minimum number of neighborhood points, then expanding a new cluster as the current cluster with the latitude and longitude point P as the center;

[0016] adding the latitude and longitude point P to the current cluster;

[0017] finding all unvisited points within the neighborhood radius ε of the latitude and longitude point P, and adding all unvisited points to the current cluster and marking all unvisited points as visited state;

[0018] for each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to the minimum number of neighborhood points, then adding it to the current cluster;

[0019] if the number of points in the neighborhood of the latitude and longitude point P is less than the minimum number of neighborhood points, then marking the latitude and longitude point P as a noise point, until all the latitude and longitude points are visited, obtaining the position clustering label of the target base station.

[0020] Optionally, before the interest point address within the complaint address coverage range is used to correct the complaint user address, the method further comprises:

[0021] extending a set length outward from the outermost grid around the complaint address coverage range to obtain a quadrilateral area as a user complaint geographic frame;

[0022] obtaining the interest point address within the user complaint geographic frame.

[0023] Optionally, the interest point address within the complaint address coverage range is used to correct the complaint user address, comprising:

[0024] performing word segmentation on each of the interest point address and the complaint user address respectively to obtain first word segmentation of each of the interest point address and second word segmentation of the complaint user address;

[0025] calculating word segmentation similarity between each of the second word segmentation and each of the first word segmentation of each of the interest point address;

[0026] selecting a target interest point address from the interest point address according to the word segmentation similarity;

[0027] replace the target point of interest address with the complaint user address.

[0028] Optionally, the computing the segmentation similarity of each of the second segmentation and each of the first segmentation of each of the point of interest address comprises:

[0029] According to the edit distance algorithm, the similarity of the pinyin of each of the second segmentation and the pinyin of each of the first segmentation of each of the point of interest address is calculated as the segmentation similarity.

[0030] Optionally, the selecting the target point of interest address from the point of interest address according to the segmentation similarity comprises:

[0031] According to the segmentation similarity, the information entropy sum of the complaint user address and each of the point of interest address is calculated.

[0032] The target point of interest address with the minimum information entropy sum is selected from the point of interest address.

[0033] The embodiment of the present disclosure further provides an address correction device, comprising:

[0034] An acquisition module is configured to acquire a mobile communication identifier, a complaint time period and a complaint user address.

[0035] A determination module is configured to determine location information of a target base station in which a user resides in the complaint time period according to the mobile communication identifier.

[0036] A clustering module is configured to cluster the target base station according to the location information of the target base station to obtain a location clustering label of the target base station.

[0037] A merging module is configured to merge base station geographic grid coverage ranges of the target base stations with the same location clustering label to obtain a complaint address coverage range.

[0038] A correction module is configured to correct the complaint user address according to a point of interest address in the complaint address coverage range.

[0039] The embodiment of the present disclosure further provides an electronic device, comprising:

[0040] A processor;

[0041] A memory for storing instructions executable by the processor;

[0042] The processor is configured to execute the instructions to implement each step in the above method.

[0043] The embodiment of the present disclosure further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize each step in the method.

[0044] The embodiment of the present disclosure further provides a computer program product, which comprises computer programs / instructions, and the computer programs / instructions are executed by a processor to realize each step in the method.

[0045] The embodiment of the present disclosure provides at least the following beneficial effects:

[0046] In some embodiments of the present disclosure, a mobile communication identifier, a complaint time period and a complaint user address are acquired; location information of a target base station in which a user stays in the complaint time period is determined according to the mobile communication identifier; the target base station is clustered according to the location information of the target base station, and a location clustering label of the target base station is obtained; base station geographic grid coverage ranges of target base stations with the same location clustering label are merged, and a complaint address coverage range is obtained; and the complaint user address is automatically corrected according to a point of interest address in the complaint address coverage range, so that the complaint user address is automatically corrected, the correction efficiency of the complaint user address is improved, and the labor cost is reduced.

[0047] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings incorporated in the specification and forming a part thereof illustrate embodiments consistent with the present disclosure and together with the description are used to explain the principles of the present disclosure, and do not limit the present disclosure.

[0049] Figure 1 A flowchart of an address correction method provided by an exemplary embodiment of the present disclosure is shown in the figure;

[0050] Figure 2 A structure diagram of an address correction device provided by an exemplary embodiment of the present disclosure is shown in the figure;

[0051] Figure 3 A structure diagram of an electronic device provided by an exemplary embodiment of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0052] In order to make ordinary people in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Instead, they are only examples of devices and methods consistent with some aspects of the present disclosure.

[0054] It should be noted that the user information involved in the present disclosure includes but is not limited to: user equipment information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in the present disclosure comply with the provisions of relevant laws and regulations, and do not violate public order and good customs.

[0055] In order to solve the above technical problems, in some embodiments of the present disclosure, a mobile communication identifier, a complaint time period and a complaint user address are obtained; according to the mobile communication identifier, the location information of the target base station in which the user resides in the complaint time period is determined; according to the location information of the target base station, the target base station is clustered to obtain a location clustering label of the target base station; the base station geographic grid coverage range of the target base stations with the same location clustering label is merged to obtain a complaint address coverage range; the complaint user address is automatically corrected according to the point of interest address in the complaint address coverage range, and the complaint user address is automatically corrected, thereby improving the correction efficiency of the complaint user address and reducing the labor cost.

[0056] The technical solutions provided by the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0057] Figure 1 A flowchart of an address correction method provided by an exemplary embodiment of the present disclosure is shown in FIG. Figure 1 As shown in the figure, the method comprises:

[0058] S101: obtaining a mobile communication identifier, a complaint time period and a complaint user address;

[0059] S102: according to the mobile communication identifier, determining the location information of the target base station in which the user resides in the complaint time period;

[0060] S103: according to the location information of the target base station, clustering the target base station to obtain a location clustering label of the target base station;

[0061] S104: merging the base station geographic grid coverage range of the target base stations with the same location clustering label to obtain a complaint address coverage range;

[0062] S105: Correct the complaint user address according to the point of interest address within the complaint address coverage range.

[0063] In the embodiment, the execution subject of the method can be a terminal device or a server.

[0064] The terminal device includes, but is not limited to, a mobile station (MS), a mobile terminal, a mobile telephone, a handset, a portable equipment, and the like. The terminal device can communicate with one or more core networks through a radio access network (RAN). For example, the terminal device can be a mobile phone (also referred to as a "cellular" phone), a computer with wireless communication functions, and the like. The terminal device can also be a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an AR terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical treatment, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, and the like. An operating system installed on the terminal device includes, but is not limited to, an IOS, an Android, a windows, a linux, a Mac OS, and the like. The terminal device can be referred to by different names in different networks. For example, the terminal device can be referred to as a user equipment, a mobile station, a subscriber unit, a station, a cellular phone, a personal digital assistant, a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop station, a television, and the like. For the sake of convenience, the terminal device is referred to as a terminal device in the embodiment.

[0065] In the embodiment, the implementation form of the server is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, and the like. The server mainly includes a processor, a hard disk, a memory, a system bus, and the like, and has a general computer architecture type.

[0066] It should be noted that the mobile communication identifier can be a phone number.

[0067] In the embodiment, the disclosure obtains the complaint number and the complaint time period, associates the base station list in which the user stays in the complaint time period in the signaling control plane interface of the communication network, and obtains the corresponding base station latitude and longitude information, the poor quality base station label, and the permanent base station label from the communication system. The DBSCAN clustering algorithm is used to cluster the latitude and longitude of the permanent poor quality base station, and multiple geographical coverage faces are formed. The base station geographical grid coverage range is obtained based on the MDT data. The same clustering label is merged into one geographical face, 1-N complaint address coverage ranges are obtained, and the POI address in the coverage range is associated as a reference address set based on the complaint address coverage range. The user complaint is used as a to-be-calibrated address. A complaint address calibration model based on address information entropy is constructed, and the calibrated address is output, so as to realize automatic evaluation and calibration of the complaint address.

[0068] In some embodiments of the disclosure, a mobile communication identifier, a complaint time period, and a complaint user address are obtained. According to the mobile communication identifier, the position information of a target base station in which the user stays in the complaint time period is determined. One realizable way is that, based on a customer service system, a complaint number and a complaint time are obtained, and a base station list in which the user stays in the complaint time is associated in the signaling control plane interface between the base station and the core network of the communication network. It should be noted that the position information of the target base station can be the latitude and longitude of the base station. In addition, a poor quality base station label and a permanent base station label can also be obtained from the communication system.

[0069] In the embodiment, the disclosure obtains the complaint number and the complaint time period, associates the base station list in which the user stays in the complaint time period in the signaling control plane interface of the communication network, and obtains the corresponding base station latitude and longitude information, the poor quality base station label, and the permanent base station label from the communication system. The DBSCAN clustering algorithm is used to cluster the latitude and longitude of the permanent poor quality base station, and multiple geographical coverage faces are formed. The base station geographical grid coverage range is obtained based on the MDT data. The same clustering label is merged into one geographical face, 1-N complaint address coverage ranges are obtained, and the POI address in the coverage range is associated as a reference address set based on the complaint address coverage range. The user complaint is used as a to-be-calibrated address. A complaint address calibration model based on address information entropy is constructed, and the calibrated address is output, so as to realize automatic evaluation and calibration of the complaint address.

[0070]

[0071] Table 1

[0072] In some embodiments of the present disclosure, the target base stations are clustered according to the location information of the target base stations to obtain location clustering labels of the target base stations. One implementable way is to mark all longitude and latitude points as unvisited states, and select a neighborhood radius ε and a minimum number of neighborhood points, wherein each longitude and latitude point corresponds to a target base station; randomly select an unvisited longitude and latitude point P and mark the longitude and latitude point P as a visited state; in the case that the number of points in the neighborhood of the longitude and latitude point P is greater than or equal to the number of neighborhood points, then expand a new cluster with the longitude and latitude point P as the center as a current cluster; add the longitude and latitude point P to the current cluster; find all unvisited points within the neighborhood radius ε of the longitude and latitude point P, and add all the unvisited points to the current cluster and mark all the unvisited points as visited states; for each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to the number of neighborhood points, then add the newly added point to the current cluster; in the case that the number of points in the neighborhood of the longitude and latitude point P is less than the number of neighborhood points, then mark the longitude and latitude point P as a noise point, until all longitude and latitude points are visited to obtain the location clustering labels of the target base stations.

[0073] wherein the longitude and latitude of the resident base stations and the poor-quality base stations are clustered by using the DBSCAN clustering algorithm to obtain the location clustering labels of each base station. The DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm, and the algorithm steps are as follows:

[0074] Initialization: mark all longitude and latitude points as unvisited states, and select a neighborhood radius ε and a minimum number of neighborhood points MinPts.

[0075] Randomly select an unvisited longitude and latitude point P and mark it as visited.

[0076] If the number of points in the neighborhood of the point P is greater than or equal to MinPts, then expand a new cluster with P as the center.

[0077] Add the point P to the current cluster.

[0078] Find all unvisited points within the ε-neighborhood of P and add them to the current cluster and mark them as visited.

[0079] For each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to MinPts, then add the newly added point to the current cluster.

[0080] If the number of points in the neighborhood of the point P is less than MinPts, then mark P as a noise point.

[0081] Repeat the above steps until all data points are visited.

[0082] According to the above DBSCAN clustering algorithm, the neighborhood radius ε is set to 1000 meters, the number of neighborhood points MinPts is set to 3, and clustering operations are performed on all base station longitude and latitude points to label each base station with a position cluster label. The data example is shown in Table 2 below:

[0083] Base station ID Base station longitude Base station latitude Longitude and latitude cluster label 189921 114.1667999 22.75324488 10001 322112 114.1667667 22.69061258 10001 231112 114.1667617 22.72335698 10001 ... ... ... ... 433121 114.1266598 22.74231704 10004

[0084] Table 2

[0085] In some embodiments of the present disclosure, the base station geographic grid coverage ranges of target base stations with the same position cluster label are merged to obtain a complaint address coverage range. Among them, the base station geographic grid coverage range is obtained based on MDT (Minimization Drive Test, Minimization Drive Test) data, and the same cluster label is merged into a geographic surface information to obtain 1-N cluster complaint address coverage range, as shown in Table 3 below.

[0086]

[0087] Table 3

[0088] In some embodiments of the present disclosure, a square area is obtained by extending the outermost grid around the complaint address coverage range outward by a set length, as a user complaint geographic frame; and the point of interest address within the user complaint geographic frame is obtained. For example, a square surface is generated by extending the outermost grid in the southeast, southwest and northwest of the complaint address coverage range outward by 100 meters, forming an expanded user complaint geographic frame; and all POI (Point of Interest) address data within the user complaint geographic frame is obtained based on the expanded complaint geographic frame.

[0089] The obtained point of interest address is shown in Table 4 below:

[0090]

[0091] Table 4

[0092] In some embodiments of the present disclosure, the complaint user address is corrected according to the point of interest address within the complaint address coverage range. One realizable way is to perform word segmentation processing on each point of interest address and complaint user address respectively to obtain first word segmentation of each point of interest address and second word segmentation of the complaint user address; calculate the word segmentation similarity between each second word segmentation and each first word segmentation of each point of interest address; select a target point of interest address from the point of interest address according to the word segmentation similarity; and replace the target point of interest address with the complaint user address.

[0093] Among them, the complaint user address is obtained based on the customer service system as a to-be-calibrated address, as shown in Table 5 below.

[0094]

[0095] Table 5

[0096] The obtained point of interest address is taken as a correction reference address. The address to be calibrated and each reference address string are cut into phrases, and the edit distance algorithm is used to calculate the phrase pinyin similarity of the address to be calibrated and each reference address respectively. Then, the address information entropy algorithm is used to calculate the information entropy sum of the address to be calibrated and each reference address. The information entropy sum is used to represent the difference between the two strings. The smaller the entropy value is, the more similar the two addresses are. The reference address with the smallest information entropy is selected as the calibration address output.

[0097] For example, the address to be calibrated and the reference address are subjected to phrase segmentation respectively to obtain phrase segmentation results. The data examples are as follows:

[0098] The address to be calibrated is: Guangdong Province, Guangzhou City, Tianhe District, Huacheng Avenue, Jiantao Plaza, 10th floor.

[0099] Reference address 1: Guangdong Province, Guangzhou City, Tianhe District, Tianhe North Road, 28-32 Times Plaza, 2nd floor atrium.

[0100] Reference address 2: Guangdong Province, Guangzhou City, Tianhe District, Huacheng Avenue, Jiantao Plaza, 10th floor.

[0101] Reference address 3: Guangdong Province, Guangzhou City, Tianhe District, Tianhe East Road, No. 18, Tianhui Pavilion.

[0102] Phrase segmentation results:

[0103] The address to be calibrated is: Guangdong Province, Guangzhou City, Tianhe District, Huacheng Avenue, Jiantao Plaza, 10th floor.

[0104] Reference address 1: Guangdong Province, Guangzhou City, Tianhe District, Tianhe North Road, 28-32 Times Plaza, 2nd floor atrium.

[0105] Reference address 2: Guangdong Province, Guangzhou City, Tianhe District, Huacheng Avenue, Jiantao Plaza, 10th floor.

[0106] Reference address 3: Guangdong Province, Guangzhou City, Tianhe District, Tianhe East Road, No. 18, Tianhui Pavilion.

[0107] In an exemplary embodiment of the present disclosure, for each phrase of the address to be calibrated, the edit distance algorithm is used to match with the phrases of the reference addresses one by one to calculate the phrase similarity of each second phrase and each first phrase of each point of interest address. One implementable way is to calculate the similarity of the pinyin of each second phrase and the pinyin of each first phrase of each point of interest address according to the edit distance algorithm as the phrase similarity.

[0108] The specific steps of the edit distance algorithm are as follows: for each word in the address to be calibrated, the words of the reference address are matched and compared one by one. The edit distance between the two words is calculated, that is, the minimum number of operations required to convert the word of the address to be calibrated into the word of the reference address. The similarity is calculated according to the edit distance, and the similarity of each word is calculated using the following formula: similarity = 1-edit distance / max(len(word of address to be calibrated), len(word of reference address)). Each word of the address to be calibrated is matched with the word of the reference address and the similarity is calculated. The similarity results of all words are returned.

[0109] For example, for the address in the above example, the word similarity calculation is as follows:

[0110] The similarity of the pinyin of each word of the address to be calibrated and the reference address 1 is calculated as follows:

[0111] Guangdong Province: similarity = 1-edit distance("guang dong sheng", "guang dong sheng") / max(3, 3) = 1-0 / 3 = 1.

[0112] Guangzhou City: similarity = 1-edit distance("guang zhou shi", "guang zhou shi") / max(3, 3) = 1-0 / 3 = 1.

[0113] According to the above formula, the similarity of the words of the address to be calibrated and each reference address is calculated as follows:

[0114] The similarity of the word results of the address to be calibrated and the word of the reference address 1 is as follows: Guangdong Province / Guangdong Province similarity is 1; Guangzhou City / Guangzhou City similarity is 1; Tianhe District / Tianhe District similarity is 1; Huacheng Avenue / Tianhe North Road similarity is 0; Jiantao Plaza / 28-32 Times Plaza similarity is 0.5; 10th floor / 2nd floor atrium similarity is 0.

[0115] The similarity of the word results of the address to be calibrated and the word of the reference address 2 is as follows: Guangdong Province / Guangdong Province similarity is 1; Guangzhou City / Guangzhou City similarity is 1; Tianhe District / Tianhe District similarity is 1; Huacheng Avenue / Huacheng Avenue similarity is 1; Jiantao Plaza / Jiantao Plaza similarity is 1; 10th floor / 10th floor similarity is 1.

[0116] The similarity of the word results of the address to be calibrated and the word of the reference address 3 is as follows: Guangdong Province / Guangdong Province similarity is 1; Guangzhou City / Guangzhou City similarity is 1; Tianhe District / Tianhe District similarity is 1; Huacheng Avenue / Tianhe East Road similarity is 0; Jiantao Plaza / No. 18 similarity is 0; 10th floor / Tianhui Court similarity is 0.

[0117] In some embodiments of the present disclosure, a target POI address is selected from the POI addresses according to the word similarity. One implementable way is to calculate the sum of information entropy of the complaint user address and each POI address according to the word similarity, and select the target POI address with the minimum sum of information entropy from the POI addresses.

[0118] wherein for each pair of words in the matching result, the sum of information entropy of the pair of words is calculated using the address information entropy algorithm, the sum of information entropy is used to represent the difference between the two strings, and the smaller the entropy value is, the more similar the two address strings are.

[0119] The formula for calculating the sum of information entropy is:

[0120] H(X) = -∑(p(x)log2p(x))

[0121] wherein H(X) represents the sum of information entropy; p(x) represents the probability of the random variable X taking the value x, and x is the word similarity; log2p(x) represents the calculation of the logarithm with base 2, i.e. log2(p(x)).

[0122] For example, the sum of information entropy of the address to be calibrated and the reference address 1 is H(X) = -(1*log21 + 1*log21 + 1*log21 + 0*log20 + 0.5*log20.5 + 0*log20) = -(3 + 3 + 3 + 0 + 0.693 + 0) = -9.693.

[0123] The sum of information entropy of the address to be calibrated and the reference address 2 is H(X) = -(1*log21 + 1*log21 + 1*log21 + 1*log21 + 1*log21 + 1*log21) = -(3 + 3 + 3 + 3 + 3 + 3) = -18.

[0124] The sum of information entropy of the address to be calibrated and the reference address 3 is H(X) = -(1*log21 + 1*log21 + 1*log21 + 0*log20 + 0*log20 + 0*log20) = -(3 + 3 + 3 + 0 + 0 + 0) = -9.

[0125] According to the calculated sum of information entropy of the address to be calibrated and each reference address, the matching result corresponding to the smallest entropy value is selected as the final calibrated address. As shown in the above calculation example, the minimum information entropy of the reference address is -18, and the final calibrated address output is: Guangdong Province, Guangzhou City, Tianhe District, Huacheng Avenue, Jianta Square, 10th Floor.

[0126] In some embodiments of the present disclosure, the address quality is evaluated before and after calibration. Optionally, the addresses before and after calibration are matched with the complaint addresses obtained by field testing, 20 addresses before calibration are inconsistent with the measured addresses, and 20 addresses after calibration are matched with the measured addresses, with an accuracy of 100 %; it can be seen that the model has good effect. The example data is shown in Table 6.

[0127]

[0128]

[0129] Table 6

[0130] In the above method embodiments of the present disclosure, the mobile communication identifier, the complaint time period and the complaint user address are obtained; the location information of the target base station in which the user resides in the complaint time period is determined according to the mobile communication identifier; the target base station is clustered according to the location information of the target base station, and the location clustering label of the target base station is obtained; the base station geographic grid coverage range of the target base stations with the same location clustering label is merged, and the complaint address coverage range is obtained; the complaint user address is automatically corrected according to the point of interest address in the complaint address coverage range, the complaint user address is automatically corrected, the correction efficiency of the complaint user address is improved, and the labor cost is reduced.

[0131] Figure 2 A structural schematic diagram of an address correction device 20 provided for an exemplary embodiment of the present disclosure is shown in FIG. 2. As shown in FIG. 2, the address correction device 20 includes an acquisition module 21, a determination module 22, a clustering module 23, a merging module 24 and a correction module 25. Figure 2

[0132] The acquisition module 21 is configured to acquire a mobile communication identifier, a complaint time period and a complaint user address.

[0133] The determination module 22 is configured to determine the location information of a target base station in which a user resides in a complaint time period according to the mobile communication identifier.

[0134] The clustering module 23 is configured to cluster the target base station according to the location information of the target base station, and obtain a location clustering label of the target base station.

[0135] The merging module 24 is configured to merge the base station geographic grid coverage range of the target base stations with the same location clustering label, and obtain a complaint address coverage range.

[0136] The correction module 25 is configured to correct the complaint user address according to the point of interest address in the complaint address coverage range.

[0137] ​Optionally, the clustering module 23, when clustering target base stations according to location information of the target base stations to obtain location clustering labels of the target base stations, is configured to:

[0138] mark all latitude and longitude points as unvisited, and select a neighborhood radius ε and a minimum number of neighborhood points, wherein each latitude and longitude point corresponds to a target base station;

[0139] randomly select an unvisited latitude and longitude point P, and mark the latitude and longitude point P as visited;

[0140] if the number of points in the neighborhood of the latitude and longitude point P is greater than or equal to the minimum number of neighborhood points, then expand a new cluster with the latitude and longitude point P as the center as a current cluster;

[0141] add the latitude and longitude point P to the current cluster;

[0142] find all unvisited points within the neighborhood radius ε of the latitude and longitude point P, and add all the unvisited points to the current cluster and mark all the unvisited points as visited;

[0143] for each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to the minimum number of neighborhood points, then add the newly added point to the current cluster;

[0144] if the number of points in the neighborhood of the latitude and longitude point P is less than the minimum number of neighborhood points, then mark the latitude and longitude point P as a noise point, until all latitude and longitude points are visited to obtain the location clustering labels of the target base stations.

[0145] Optionally, the correction module 25, before correcting the complaint user address according to the interest point addresses within the complaint address coverage range, is further configured to:

[0146] expand the outermost grid around the complaint address coverage range outward by a set length to obtain a quadrilateral area as a user complaint geographic frame;

[0147] obtain the interest point addresses within the user complaint geographic frame.

[0148] Optionally, the correction module 25, when correcting the complaint user address according to the interest point addresses within the complaint address coverage range, is configured to:

[0149] perform word segmentation on each interest point address and the complaint user address respectively to obtain first word segmentation of each interest point address and second word segmentation of the complaint user address;

[0150] calculate the word segmentation similarity between each second word segmentation and each first word segmentation of each interest point address;

[0151] select a target interest point address from the interest point addresses according to the word segmentation similarity;

[0152] Replace the complainant's address with the target point of interest address.

[0153] Optionally, the correction module 25, when calculating the segmentation similarity between each second segment and each first segment of each interest point address, is used to:

[0154] Based on the edit distance algorithm, the similarity between the pinyin of each second word and the pinyin of each first word at each point of interest is calculated as the word similarity.

[0155] Optionally, when selecting the target interest point address from the interest point addresses based on word segmentation similarity, the correction module 25 is used to:

[0156] Based on word segmentation similarity, calculate the sum of information entropy between the complainant's address and each point of interest address;

[0157] Select the target point of interest address with the smallest sum of information entropy from the point of interest addresses.

[0158] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0159] Figure 3 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this disclosure. For example... Figure 3 As shown, the electronic device includes a memory 31 and a processor 32. Additionally, the electronic device also includes a power supply component 33 and a communication component 34.

[0160] Memory 31 is used to store computer programs and can be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device.

[0161] The memory 31 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0162] Communication component 34 is used for data transmission with other devices.

[0163] The processor 32 can execute computer instructions stored in the executable memory 31 to obtain a mobile communication identifier, a complaint time period and a complaint user address, determine location information of a target base station in which the user resides in the complaint time period according to the mobile communication identifier, cluster the target base station according to the location information of the target base station to obtain a location clustering label of the target base station, merge base station geographic grid coverage ranges of target base stations with the same location clustering label to obtain a complaint address coverage range, and correct the complaint user address according to a point of interest address in the complaint address coverage range.

[0164] Correspondingly, the embodiments of the present disclosure further provide a computer readable storage medium storing a computer program. When the computer readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors are caused to execute the steps of the method embodiments. Figure 1 The steps of the method embodiments.

[0165] Correspondingly, the embodiments of the present disclosure further provide a computer program product, which comprises a computer program / instruction executed by a processor Figure 1 The steps of the method embodiments.

[0166] The communication component in the above Figure 3 The communication component in the above The communication component in the above

[0167] The power supply component in the above Figure 3 The power supply component in the above

[0168] The electronic device in the above

[0169] The display screen includes a screen, which can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touch or a slide action, but also detect a duration and a pressure associated with a touch or a slide operation.

[0170] An audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device in which the audio component is located is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory or transmitted via the communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0171] In the above-mentioned device, apparatus, storage medium and computer program product embodiments of the present disclosure, the mobile communication identifier, the complaint time period and the complaint user address are acquired; the location information of a target base station in which the user resides in the complaint time period is determined according to the mobile communication identifier; the target base station is clustered according to the location information of the target base station, and a location clustering label of the target base station is obtained; the base station geographic grid coverage range of the target base stations with the same location clustering label is merged, and a complaint address coverage range is obtained; and the complaint user address is automatically corrected according to the point of interest address in the complaint address coverage range, so that the complaint user address is automatically corrected, the correction efficiency of the complaint user address is improved, and the labor cost is reduced.

[0172] Those skilled in the art will appreciate that embodiments of the present disclosure can be provided as methods, systems, or computer program products. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) having computer-usable program code embodied in the medium.

[0173] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions described in the flowcharts and / or block diagrams.Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0174] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow or flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow or flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0176] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0177] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or a combination of non-volatile memories. The memory is an example of computer-readable media.

[0178] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0179] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0180] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An address correction method characterized by, The method comprises the following steps: acquiring a mobile communication identifier, a complaint time period and a complaint user address; determining location information of a target base station in which a user stays in the complaint time period according to the mobile communication identifier; marking all latitude and longitude points as unvisited states, and selecting a neighborhood radius ε and a minimum number of neighborhood points, wherein each of the latitude and longitude points corresponds to a target base station; randomly selecting an unvisited latitude and longitude point P and marking the latitude and longitude point P as a visited state; if the number of points in the neighborhood of the latitude and longitude point P is greater than or equal to the number of neighborhood points, then expanding a new cluster as a current cluster with the latitude and longitude point P as the center; adding the latitude and longitude point P to the current cluster; finding all unvisited points in the neighborhood radius ε of the latitude and longitude point P, and adding all the unvisited points to the current cluster and marking all the unvisited points as visited states; for each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to the number of neighborhood points, then adding the newly added point to the current cluster; if the number of points in the neighborhood of the latitude and longitude point P is less than the number of neighborhood points, then marking the latitude and longitude point P as a noise point, until all the latitude and longitude points are visited, to obtain a location clustering label of the target base station; merging base station geographic grid coverage ranges of the target base stations with the same location clustering label to obtain a complaint address coverage range; correcting the complaint user address according to a point of interest address in the complaint address coverage range.

2. The method of claim 1, wherein, Before the step of correcting the complaint user address according to the point of interest address in the complaint address coverage range, the method further comprises: expanding a square area as a user complaint geographic frame by expanding a set length outward from the outermost grid around the complaint address coverage range; acquiring the point of interest address in the user complaint geographic frame.

3. The method of claim 1, wherein, The step of correcting the complaint user address according to the point of interest address in the complaint address coverage range comprises: performing word segmentation on each of the point of interest addresses and the complaint user address respectively to obtain first word segmentation of each of the point of interest addresses and second word segmentation of the complaint user address; calculating word segmentation similarity between each of the second word segmentation and each of the first word segmentation of each of the point of interest addresses; selecting a target point of interest address from the point of interest addresses according to the word segmentation similarity; replacing the complaint user address with the target point of interest address.

4. The method of claim 3, wherein, The step of calculating word segmentation similarity between each of the second word segmentation and each of the first word segmentation of each of the point of interest addresses comprises: calculating similarity between pinyin of each of the second word segmentation and pinyin of each of the first word segmentation of each of the point of interest addresses according to an edit distance algorithm as word segmentation similarity.

5. The method of claim 3, wherein, The step of selecting a target point of interest address from the point of interest addresses according to the word segmentation similarity comprises: calculating information entropy sum of the complaint user address and each of the point of interest addresses according to the word segmentation similarity; selecting a target point of interest address with minimum information entropy sum from the point of interest addresses.

6. An address correction device, characterized by The method comprises the following steps: An acquisition module is configured to acquire a mobile communication identifier, a complaint time period, and a complaint user address; A determination module is configured to determine location information of a target base station in which a user resides in the complaint time period according to the mobile communication identifier; A clustering module is configured to cluster the target base station according to the location information of the target base station, and obtain a location clustering label of the target base station; A merging module is configured to merge a base station geographic grid coverage range of the target base station with the same location clustering label, and obtain a complaint address coverage range; A correction module is configured to correct the complaint user address according to a point of interest address in the complaint address coverage range; The clustering module is specifically configured to: mark all latitude and longitude points as unvisited states, and select a neighborhood radius ε and a minimum number of neighborhood points, wherein each latitude and longitude point corresponds to a target base station; randomly select an unvisited latitude and longitude point P, and mark the latitude and longitude point P as a visited state; if the number of points in the neighborhood of the latitude and longitude point P is greater than or equal to the number of neighborhood points, then expand a new cluster as a current cluster with the latitude and longitude point P as the center; add the latitude and longitude point P to the current cluster; find all unvisited points in the neighborhood radius ε of the latitude and longitude point P, and add all unvisited points to the current cluster, and mark all unvisited points as visited states; for each newly added point, if the number of points in the neighborhood of the newly added point is greater than or equal to the number of neighborhood points, then add the newly added point to the current cluster; if the number of points in the neighborhood of the latitude and longitude point P is less than the number of neighborhood points, then mark the latitude and longitude point P as a noise point, until all latitude and longitude points are visited, and obtain the location clustering label of the target base station.

7. An electronic device, comprising: comprise: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement each step in the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement each step in the method of any one of claims 1-5.

9. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to implement each step in the method of any one of claims 1-5.

Images