Method and device for querying user duplicate addresses

Abstract

The present disclosure provides a method and device for querying a user's duplicate address, which is used to improve the query efficiency of duplicate addresses. The method includes: in response to a duplicate address query request sent by a user, based on the address information corresponding to the duplicate address query request, determining a first address vector corresponding to the address information; using the first address vector and the center vector of each address category, obtaining a first similarity between the first address vector and the center vector of each address category; determining a target address category corresponding to the first address vector according to the first similarity; obtaining at least one target address vector through a second similarity between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to the pre-stored address information; determining a target address corresponding to the target address vector as a duplicate address corresponding to the address information.

Description

Background Art

[0002] Since the same user address may have different address names in the system, it is necessary to query the duplicate addresses with different names but the same actual address, and replace and update each duplicate address.

[0003] In the prior art, similarity is calculated between the vector of the address information input by the user and the vectors of all other address information in the database to determine other addresses that are duplicated with the input address information. However, this method results in low query efficiency for duplicate addresses. Summary of the invention

[0004] In an exemplary embodiment of the present disclosure, a method and device for querying a user's duplicate address are provided to improve the query efficiency of the duplicate address.

[0005] A first aspect of the present disclosure provides a method for querying a user's duplicate address, the method comprising:

[0006] In response to a duplicate address query request sent by a user, based on address information corresponding to the duplicate address query request, determining a first address vector corresponding to the address information;

[0007] Using the first address vector and the center vector of each address category, obtaining first similarities between the first address vector and the center vector of each address category;

[0008] Determining a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of each address category;

[0009] Obtaining at least one target address vector by determining the second similarities between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to pre-stored address information;

[0010] The target address corresponding to the target address vector is determined as a repeated address corresponding to the address information.

[0011] In this embodiment, the target address category corresponding to the first address vector is determined by the first similarity between the first address vector and the central vector of each address category, and at least one target address vector is obtained by the second similarity between the first address vector and each second address vector corresponding to the target address category, and then the target address corresponding to the target address vector is determined as a duplicate address corresponding to the address information. Therefore, in this embodiment, the first address vector only needs to determine the second similarity between each second address vector corresponding to the target address category to determine the duplicate address, thereby improving the query efficiency of the duplicate address.

[0012] In one embodiment, obtaining at least one target address vector by using the second similarities between the first address vector and each second address vector corresponding to the target address category includes:

[0013] Sorting the second similarities to obtain an arrangement order of the second similarities;

[0014] Determining each second target similarity that meets a specified condition from the arrangement order of each second similarity;

[0015] For any second target similarity, input the second address vector corresponding to the second target similarity and the first address vector into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector;

[0016] If the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector.

[0017] In this embodiment, the second similarities are sorted to obtain the arrangement order of the second similarities, and the second target similarities that meet the specified conditions are determined from the arrangement order of the second similarities. Then, for any second target similarity, the second address vector corresponding to the second target similarity and the first address vector are input into a pre-trained neural network to obtain the third similarity between the second address vector and the first address vector; if the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector. Therefore, in this embodiment, the target address vector is determined by calculating the similarity twice, so that the target address vector is determined more accurately.

[0018] In one embodiment, determining the target address category corresponding to the first address vector according to the first similarities between the first address vector and the center vectors of each address category includes:

[0019] From each of the first similarities, determine the center vector corresponding to the highest similarity; and,

[0020] The address category corresponding to the central vector is determined as the target address category.

[0021] In this embodiment, the center vector corresponding to the highest similarity is determined from each of the first similarities, and the address category corresponding to the center vector is determined as the target address category, thereby improving the accuracy of the target address category.

[0022] In one embodiment, each address category is determined in the following manner:

[0023] Clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set;

[0024] Allocating a category identifier to each address set in turn, and determining each category identifier as each address category;

[0025] For any address category, the second address vectors corresponding to the target address set are determined as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

[0026] This implementation clusters the second address vectors corresponding to each pre-stored address information through a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set, and then assigns a category identifier to each address set in turn, and determines each category identifier as each address category, and for any address category, determines each second address vector corresponding to the target address set as each second address vector corresponding to the address category. Thus, the query efficiency is further improved.

[0027] In one embodiment, using the first address vector and the center vector of each address category to obtain a first similarity between the first address vector and the center vector of each address category includes:

[0028] For a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category.

[0029] In this embodiment, for a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category, thereby making it more accurate to determine the first similarity.

[0030] A second aspect of the present disclosure provides a device for querying a user's duplicate address, the device comprising:

[0031] A first address vector determining module, configured to respond to a duplicate address query request sent by a user and determine a first address vector corresponding to the address information based on the address information corresponding to the duplicate address query request;

[0032] A first similarity determination module, configured to obtain first similarities between the first address vector and the center vectors of each address category by using the first address vector and the center vectors of each address category;

[0033] a target address category determination module, configured to determine a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of the respective address categories;

[0034] a target address vector determination module, configured to obtain at least one target address vector by determining a second similarity between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to pre-stored address information;

[0035] The repeated address determining module is used to determine the target address corresponding to the target address vector as a repeated address corresponding to the address information.

[0036] In one embodiment, the target address vector determination module is specifically configured to:

[0037] Sorting the second similarities to obtain an arrangement order of the second similarities;

[0038] Determining each second target similarity that meets a specified condition from the arrangement order of each second similarity;

[0039] For any second target similarity, input the second address vector corresponding to the second target similarity and the first address vector into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector;

[0040] If the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector.

[0041] In one embodiment, the target address category determination module is specifically configured to:

[0042] From each of the first similarities, determine the center vector corresponding to the highest similarity; and,

[0043] The address category corresponding to the central vector is determined as the target address category.

[0044] In one embodiment, the apparatus further comprises:

[0045] The address category determination module is used to determine each address category in the following way:

[0046] Clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set;

[0047] Allocating a category identifier to each address set in turn, and determining each category identifier as each address category;

[0048] For any address category, the second address vectors corresponding to the target address set are determined as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

[0049] In one embodiment, the first similarity determination module is specifically configured to:

[0050] For a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category.

[0051] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0052] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executed by the at least one processor; the instructions are executed by the at least one processor so that the at least one processor can execute the method as described in the first aspect.

[0053] According to a fourth aspect provided by an embodiment of the present disclosure, a computer storage medium is provided, wherein the computer storage medium stores a computer program, and the computer program is used to execute the method as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0055] Figure 1 A schematic diagram of an applicable scenario in an embodiment of the present disclosure;

[0056] Figure 2 This is a flowchart of a method for querying duplicate addresses of a user according to an embodiment of the present disclosure;

[0057] Figure 3 A schematic diagram of a process for determining each address category according to an embodiment of the present disclosure;

[0058] Figure 4 The second flowchart of the method for querying duplicate addresses of a user according to an embodiment of the present disclosure;

[0059] Figure 5 A device for querying a user's repeated address according to an embodiment of the present disclosure;

[0060] Figure 6 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0062] In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0063] The application scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems. In the description of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more.

[0064] In the prior art, similarity is calculated between the vector of the address information input by the user and the vectors of all other address information in the database to determine other addresses that are duplicated with the input address information. However, this method results in low query efficiency for duplicate addresses.

[0065] Therefore, the present disclosure provides a method for querying duplicate addresses of users, which determines the target address category corresponding to the first address vector through the first similarity between the first address vector and the center vector of each address category, and obtains at least one target address vector through the second similarity between the first address vector and each second address vector corresponding to the target address category, and then determines the target address corresponding to the target address vector as a duplicate address corresponding to the address information. Therefore, in this embodiment, the first address vector only needs to determine the second similarity between each second address vector corresponding to the target address category to determine the duplicate address, thereby improving the query efficiency of the duplicate address. Below, the scheme of the present disclosure is described in detail in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, an application scenario of a method for querying a user's duplicate address includes multiple terminal devices 110 and a server 120. Figure 1 In the example, three terminal devices 110 are used, but the number of terminal devices 110 is not limited. The terminal devices 110 may be mobile phones, tablet computers, personal computers, etc. The server 120 may be implemented by a single server or multiple servers. The server 120 may be implemented by a physical server or a virtual server.

[0067] In a possible application scenario, the server 120 responds to a duplicate address query request sent by a user, and based on the address information corresponding to the duplicate address query request, determines a first address vector corresponding to the address information; and uses the first address vector and the center vector of each address category to obtain a first similarity between the first address vector and the center vector of each address category; then the server 120 determines the target address category corresponding to the first address vector based on the first similarity between the first address vector and the center vector of each address category, and obtains at least one target address vector through the second similarity between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to the pre-stored address information; finally, the server 120 determines the target address corresponding to the target address vector as a duplicate address corresponding to the address information, and sends the duplicate address corresponding to the address information to the terminal device 110 for display.

[0068] like Figure 2 FIG. 1 is a flow chart of a method for querying duplicate user addresses disclosed in the present invention, which may include the following steps:

[0069] Step 201: In response to a duplicate address query request sent by a user, based on address information corresponding to the duplicate address query request, determining a first address vector corresponding to the address information;

[0070] Wherein, the duplicate address query request includes the address information.

[0071] The ALBERT model in this embodiment is used to obtain the result, and the ALBERT model in this embodiment adds a dropout layer after the last fully connected layer, and adds a fully connected layer after the dropout layer, so as to prevent the ALBERT model from overfitting.

[0072] It should be noted that: the above-mentioned determination of the first address vector by the ALBERT model in this embodiment is only for illustrative purposes, and the specific model for determining the first vector can be set according to actual conditions, and this embodiment does not limit this.

[0073] Step 202: using the first address vector and the center vector of each address category, obtaining a first similarity between the first address vector and the center vector of each address category;

[0074] In one embodiment, the first similarities between the first vectors and the center vectors of the address categories are determined in the following manner:

[0075] For the center vector of any address category, the first address vector is multiplied by the center vector of the address category to obtain a first similarity between the first address vector and the center vector of the address category. The first similarity can be determined by formula (1):

[0076]

[0077] Among them, S1 is the first similarity, is the first address vector, is the center vector of the address category.

[0078] Step 203: determining a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of the address categories;

[0079] In one embodiment, the target address category corresponding to the first address vector is determined in the following manner: from each of the first similarities, a central vector corresponding to the highest similarity is determined; and the address category corresponding to the central vector is determined as the target address category.

[0080] For example, the address categories include: address category 1, address category 2, address category 3, address category 4 and address category 5. If the first address vector has the highest first similarity with the center vector of address category 3, address category 3 is determined as the target address category of the first address vector.

[0081] The central vector of any address category is obtained based on the second address vector in the address category.

[0082] Step 204: Obtain at least one target address vector through second similarities between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to pre-stored address information;

[0083] In one embodiment, the at least one target address vector is determined by:

[0084] The second similarities are sorted to obtain an arrangement order of the second similarities; the second target similarities that meet the specified conditions are determined from the arrangement order of the second similarities; for any second target similarity, the second address vector corresponding to the second target similarity and the first address vector are input into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector; if the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector.

[0085] If the second similarities are sorted from large to small, the specified condition is the first specified number of second similarities in the order of arrangement. If the second similarities are sorted from small to large, the specified condition is the last specified number of second similarities in the order of arrangement.

[0086] For example, the second address vectors corresponding to the second target similarity are: address vector 1, address vector 2, address vector 3, address vector 4 and address vector 5. If the similarity between address vector 1 and the first address vector is 50%, the similarity between address vector 2 and the first address vector is 45%, the similarity between address vector 3 and the first address vector is 90%, and the similarity between address vector 4 and the first address vector is 88% obtained through the pre-trained neural network. The similarity between address 5 and the first address vector is 40%. Taking the specified threshold of 80% as an example, the target address vectors are determined to be address vector 3 and address vector 4.

[0087] It should be noted that the specified threshold in this embodiment can be set according to actual conditions, and this embodiment does not limit the specific value of the specified threshold. In addition, the pre-trained neural network in this embodiment is the ALBERT model described above.

[0088] Step 205: Determine the target address corresponding to the target address vector as a repeated address corresponding to the address information.

[0089] For example, address vector 3 and address vector 4 are target address vectors, if the target address corresponding to address vector 3 is address 3, and the target address corresponding to address vector 3 is address 4, it is determined that address 3 and address 4 are duplicate addresses corresponding to the address information.

[0090] In order to determine each address category more accurately, in one embodiment, Figure 3 As shown, a flow chart for determining each address category may include the following steps:

[0091] Step 301: clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set;

[0092] Among them, the preset clustering algorithm in this embodiment can be set according to actual conditions, and this embodiment does not limit it here.

[0093] Step 302: assigning a category identifier to each address set in turn, and determining each category identifier as each address category;

[0094] For example, if the address sets obtained by clustering are: address set A, address set B, address set C and address set D, then after assigning classification identifiers to each address set in turn, the address sets are: address set 1, address set 2, address set 3 and address set 4. Then, address set 1 is determined to be address category 1, address set 2 is determined to be address category 2, address set 3 is determined to be address category 3, and address set 4 is determined to be address category 4.

[0095] Step 303: For any address category, determine the second address vectors corresponding to the target address set as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

[0096] For example, the second address vectors corresponding to address set 1 are respectively: vector 1 and vector 2. Then, it is determined that the second address vectors corresponding to address category 1 include: vector 1 and vector 2.

[0097] In order to further understand the technical solution of the present disclosure, Figure 4 A detailed description may include the following steps:

[0098] Step 401: In response to a duplicate address query request sent by a user, based on address information corresponding to the duplicate address query request, determining a first address vector corresponding to the address information;

[0099] Step 402: using the first address vector and the center vector of each address category, obtaining a first similarity between the first address vector and the center vector of each address category;

[0100] Step 403: Determine the center vector corresponding to the highest similarity from each of the first similarities; Step 404: Determine the address category corresponding to the center vector as the target address category;

[0101] Step 405: sorting the second similarities to obtain an arrangement order of the second similarities;

[0102] Step 406: determining each second target similarity satisfying a specified condition from the arrangement order of each second similarity;

[0103] Step 407: for any second target similarity, input the second address vector corresponding to the second target similarity and the first address vector into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector; if the third similarity is greater than a specified threshold, determine the second address vector as the target address vector;

[0104] Step 408: Determine the target address corresponding to the target address vector as a repeated address corresponding to the address information.

[0105] Based on the same disclosure concept, the above-mentioned method for querying duplicate user addresses can also be implemented by a device for querying duplicate user addresses. The effect of the device for querying duplicate user addresses is similar to that of the above-mentioned method, and will not be described in detail here.

[0106] Figure 5 The present invention is a schematic diagram of the structure of a device for querying a user's duplicate address according to an embodiment of the present disclosure.

[0107] like Figure 5 As shown, the user duplicate address query device 500 disclosed in the present invention may include a first address vector determination module 510 , a first similarity determination module 520 , a target address category determination module 530 , a target address vector determination module 540 and a duplicate address determination module 550 .

[0108] A first address vector determining module 510, configured to respond to a duplicate address query request sent by a user and determine a first address vector corresponding to the address information based on the address information corresponding to the duplicate address query request;

[0109] A first similarity determination module 520, configured to obtain first similarities between the first address vector and the center vectors of each address category by using the first address vector and the center vectors of each address category;

[0110] a target address category determination module 530, configured to determine a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of the respective address categories;

[0111] a target address vector determination module 540, configured to obtain at least one target address vector by determining a second similarity between the first address vector and each second address vector corresponding to the target address category, wherein any second address vector is a vector corresponding to pre-stored address information;

[0112] The duplicate address determining module 550 is used to determine the target address corresponding to the target address vector as a duplicate address corresponding to the address information.

[0113] In one embodiment, the target address vector determination module 540 is specifically configured to:

[0114] Sorting the second similarities to obtain an arrangement order of the second similarities;

[0115] Determining each second target similarity that meets a specified condition from the arrangement order of each second similarity;

[0116] For any second target similarity, input the second address vector corresponding to the second target similarity and the first address vector into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector;

[0117] If the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector.

[0118] In one embodiment, the target address category determination module 530 is specifically configured to:

[0119] From each of the first similarities, determine the center vector corresponding to the highest similarity; and,

[0120] The address category corresponding to the central vector is determined as the target address category.

[0121] In one embodiment, the apparatus further comprises:

[0122] The address category determination module 560 is used to determine each address category in the following manner:

[0123] Clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set;

[0124] Allocating a category identifier to each address set in turn, and determining each category identifier as each address category;

[0125] For any address category, the second address vectors corresponding to the target address set are determined as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

[0126] In one embodiment, the first similarity determination module 520 is specifically configured to:

[0127] For a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category.

[0128] After introducing a method and device for querying a user's duplicate address according to an exemplary embodiment of the present disclosure, next, an electronic device according to another exemplary embodiment of the present disclosure is introduced.

[0129] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0130] In some possible implementations, the electronic device according to the present disclosure may include at least one processor and at least one computer storage medium. The computer storage medium stores program code, and when the program code is executed by the processor, the processor executes the steps of the method for querying duplicate addresses of users according to various exemplary implementations of the present disclosure described above in this specification. For example, the processor may execute the following steps: Figure 2 Steps 201-205 shown in .

[0131] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0132] like Figure 6 As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include but are not limited to: at least one processor 601, at least one computer storage medium 602, and a bus 603 connecting different system components (including the computer storage medium 602 and the processor 601).

[0133] Bus 603 represents one or more of several types of bus structures, including a computer storage media bus or computer storage media controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0134] The computer storage media 602 may include readable media in the form of volatile computer storage media, such as random access computer storage media (RAM) 621 and / or cache storage media 622 , and may further include read-only computer storage media (ROM) 623 .

[0135] The computer storage medium 602 may also include a program / utility 625 having a set (at least one) of program modules 624, such program modules 624 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0136] The electronic device 600 may also communicate with one or more external devices 604 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or may communicate with any device that enables the electronic device 600 to communicate with one or more other electronic devices (e.g., routers, modems, etc.). This communication may be performed via an input / output (I / O) interface 605. In addition, the electronic device 600 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 606. As shown, the network adapter 606 communicates with other modules for the electronic device 600 via a bus 603. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0137] In some possible implementations, various aspects of a method for querying duplicate user addresses provided by the present disclosure may also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to enable the computer device to execute the steps of the method for querying duplicate user addresses according to various exemplary embodiments of the present disclosure described above in this specification.

[0138] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access computer storage medium (RAM), a read-only computer storage medium (ROM), an erasable programmable read-only computer storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only computer storage medium (CD-ROM), an optical computer storage medium, a magnetic computer storage medium, or any suitable combination of the above.

[0139] The program product of the user's duplicate address query of the embodiment of the present disclosure can adopt a portable compact disk read-only computer storage medium (CD-ROM) and include program code, and can be run on an electronic device. However, the program product of the present disclosure is not limited to this. In this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0140] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0141] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0142] Program code for performing the disclosed operations may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user electronic device, partially on the user device, as a separate software package, partially on the user electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In the case of a remote electronic device, the remote electronic device may be connected to the user electronic device via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external electronic device (e.g., via the Internet using an Internet service provider).

[0143] It should be noted that although several modules of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be embodied.

[0144] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0145] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk computer storage media, CD-ROM, optical computer storage media, etc.) containing computer-usable program codes.

[0146] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable computer storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable computer storage medium produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A method for querying duplicate addresses of users, characterized in that: The method comprises: In response to a duplicate address query request sent by a user, based on address information corresponding to the duplicate address query request, determining a first address vector corresponding to the address information; Using the first address vector and the center vector of each address category, obtaining first similarities between the first address vector and the center vector of each address category; Determining a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of each address category; Sorting the second similarities corresponding to the target address type to obtain an arrangement order of the second similarities, wherein any second address vector is a vector corresponding to pre-stored address information; Determining each second target similarity that meets a specified condition from the arrangement order of each second similarity; For any second target similarity, the second address vector corresponding to the second target similarity and the first address vector are input into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector, wherein the neural network is an ALBERT model with a dropout layer added after it, and a fully connected layer is added after the dropout layer; If the third similarity is greater than a specified threshold, determining the second address vector as the target address vector; The target address corresponding to the target address vector is determined as a repeated address corresponding to the address information.

2. The method according to claim 1, characterized in that The determining, according to the first similarities between the first address vector and the central vectors of the respective address categories, a target address category corresponding to the first address vector comprises: From each of the first similarities, determine the center vector corresponding to the highest similarity; and, The address category corresponding to the central vector is determined as the target address category.

3. The method according to claim 1, characterized in that Each address class is determined as follows: Clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set; Allocating a category identifier to each address set in turn, and determining each category identifier as each address category; For any address category, the second address vectors corresponding to the target address set are determined as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

4. The method according to claim 1, characterized in that: The obtaining, using the first address vector and the central vector of each address category, a first similarity between the first address vector and the central vector of each address category, comprises: For a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category.

5. A device for querying a user's duplicate address, characterized in that: The device comprises: A first address vector determining module, configured to respond to a duplicate address query request sent by a user and determine a first address vector corresponding to the address information based on the address information corresponding to the duplicate address query request; A first similarity determination module, configured to obtain first similarities between the first address vector and the center vectors of each address category by using the first address vector and the center vectors of each address category; a target address category determination module, configured to determine a target address category corresponding to the first address vector according to first similarities between the first address vector and the central vectors of the respective address categories; A target address vector determination module is used to sort the second similarities corresponding to the target address type to obtain an arrangement order of the second similarities, wherein any second address vector is a vector corresponding to the pre-stored address information; determine the second target similarities that meet the specified conditions from the arrangement order of the second similarities; for any second target similarity, input the second address vector corresponding to the second target similarity and the first address vector into a pre-trained neural network to obtain a third similarity between the second address vector and the first address vector, wherein the neural network is an ALBERT model with a dropout layer added after the dropout layer, and a fully connected layer is added after the dropout layer; if the third similarity is greater than a specified threshold, the second address vector is determined as the target address vector; The repeated address determining module is used to determine the target address corresponding to the target address vector as a repeated address corresponding to the address information.

6. The device according to claim 5, characterized in that The target address category determination module is specifically used to: From each of the first similarities, determine the center vector corresponding to the highest similarity; and, The address category corresponding to the central vector is determined as the target address category.

7. The device according to claim 5, characterized in that The device also includes: The address category determination module is used to determine each address category in the following way: Clustering the second address vectors corresponding to each pre-stored address information using a preset clustering algorithm to obtain each address set and the second address vectors corresponding to each address set; Allocating a category identifier to each address set in turn, and determining each category identifier as each address category; For any address category, the second address vectors corresponding to the target address set are determined as the second address vectors corresponding to the address category, wherein the target address set is the address set corresponding to the address category.

8. The device according to claim 5, characterized in that The first similarity determination module is specifically used to: For a central vector of any address category, the first address vector is multiplied by the central vector of the address category to obtain a first similarity between the first address vector and the central vector of the address category.

9. An electronic device, characterized in that: It comprises at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executed by the at least one processor; and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-4.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1-4.

Images