Address matching method, device, equipment, medium and product

Abstract

The embodiment of the invention discloses an address matching method and device, equipment and a medium, and the method comprises the steps: obtaining a to-be-matched address, and carrying out the word segmentation of the to-be-matched address, and obtaining an address word sequence; performing address node matching on each word in the address word sequence in a preset address node library to obtain an address node; determining an effective matching sequence matched with the address word sequence in the address node according to the position of the word in the address word sequence in the address word sequence and the position of the word in the corresponding address node; determining the node matching degree of the corresponding address node according to the importance score of the word in the effective matching sequence; constructing a candidate address node link according to the node matching degree and the corresponding node address hierarchy attribute; and determining a target address node link according to the link matching evaluation result, and taking an address formed by the target address node link as an address matching result. According to the technical scheme of the embodiment of the invention, the difference between address nodes can be identified, and the address matching accuracy is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to an address matching method, device, equipment, medium and product. Background Art

[0002] In the logistics business, the Chinese addresses filled in by users are often associated with specific cities, districts, streets and communities through address location algorithms to help logistics companies perform automated address verification and route planning.

[0003] However, in the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art: in the process of address resolution for the address to be queried, the accuracy of address segment division is not high enough, thereby affecting the accuracy of the address matching result. Summary of the invention

[0004] The embodiments of the present invention provide an address matching method, apparatus, device, medium and product, which can perform address matching based on word granularity, analyze and process address nodes in a more fine-grained manner, and improve the accuracy of address matching results.

[0005] In a first aspect, an embodiment of the present invention provides an address matching method, the method comprising:

[0006] In response to the address matching event, the to-be-matched address associated with the address matching event is obtained, and the to-be-matched address is segmented by word as a word segmentation unit to obtain a corresponding address word sequence;

[0007] Performing address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence;

[0008] Determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence in the address word sequence and a second position in a corresponding address node;

[0009] Determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library;

[0010] According to the node matching degree and the corresponding node address level attributes, the candidate address node link is constructed, and the link matching evaluation result is calculated;

[0011] The target address node link is determined according to the link matching evaluation result, and the address composed of the target address node link is used as the address matching result of the address to be matched.

[0012] In a second aspect, an embodiment of the present invention further provides an address matching device, the device comprising:

[0013] The to-be-matched address processing module is used to respond to the address matching event, obtain the to-be-matched address associated with the address matching event, and perform word segmentation processing on the to-be-matched address with words as word segmentation units to obtain a corresponding address word sequence;

[0014] An address node matching module is used to match address nodes in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence;

[0015] A first address node matching analysis module, used to determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence in the address word sequence and a second position in a corresponding address node;

[0016] A second address node matching analysis module is used to determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library;

[0017] The address node link analysis module is used to construct the candidate address node link according to the node matching degree and the corresponding node address level attributes, and calculate the link matching evaluation result;

[0018] The target address matching result determination module is used to determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0019] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0020] one or more processors;

[0021] A memory for storing one or more programs;

[0022] When one or more programs are executed by one or more processors, the one or more processors implement the address matching method provided by any embodiment of the present invention.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the address matching method provided by any embodiment of the present invention.

[0024] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, implements the address matching method provided in any embodiment of the present invention.

[0025] The embodiments of the above invention have the following advantages or beneficial effects:

[0026] According to an embodiment of the present invention, in response to an address matching event, an address to be matched associated with the address matching event is obtained, and the address to be matched is segmented with words as segmentation units to obtain a corresponding address word sequence; address node matching is performed in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence; a valid matching sequence in the address node that matches the address word sequence is determined based on the first position of the word in the address word sequence and the second position in the corresponding address node; a node matching degree of the address node corresponding to the valid matching sequence is determined based on the importance score of the word in the valid matching sequence; wherein the importance score is an importance analysis result of the word in the valid matching sequence determined based on the address corpus in the preset address node library; a candidate address node link is constructed based on the node matching degree and the corresponding node address hierarchical attribute, and a link matching evaluation result is calculated; a target address node link is determined based on the link matching evaluation result, and an address composed of the target address node link is used as the address matching result of the address to be matched. The technical solution of the present invention solves the problems that the correctness of address resolution is not high enough and the calculation of node matching degree is not accurate enough in the current address matching process. Address matching can be performed based on word granularity, and the analysis and processing of address nodes is more fine-grained. The link that best matches the address can be found, thereby improving the accuracy of the address matching result. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of an address matching method provided by an embodiment of the present invention;

[0028] Figure 2 is a flow chart of an address matching method provided by an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of a matching word list structure provided by an embodiment of the present invention;

[0030] Figure 4 1 is a schematic diagram of a sequence constraint of matching words provided by an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of an effective matching sequence provided by an embodiment of the present invention;

[0032] Figure 6 is a flow chart of an address matching method provided by an embodiment of the present invention;

[0033] Figure 7 is a flow chart of an address matching method provided by an embodiment of the present invention;

[0034] Figure 8 is a schematic diagram of an inverted index list of an address corpus provided by an embodiment of the present invention;

[0035] Fig. 9 This is a schematic diagram of address input abnormality correction provided by an embodiment of the present invention;

[0036] Fig.10 is a structural schematic diagram of an address matching device provided by an embodiment of the present invention;

[0037] Fig.11 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0039] Figure 1 This is a flowchart of an address matching method provided in an embodiment of the present invention. This embodiment can be applied to the scene of logistics address determination in the logistics field. The method can be executed by an address matching device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0040] like Figure 1 As shown, the address matching method of this embodiment includes the following steps:

[0041] S110 , in response to an address matching event, obtaining a to-be-matched address associated with the address matching event, and performing word segmentation processing on the to-be-matched address using characters as word segmentation units to obtain a corresponding address word sequence.

[0042] The address matching event can be any event that occurs in any business scenario that requires address matching analysis. For example, identifying the address after a logistics order generation event occurs, or confirming the address and navigating in an item delivery event. The address information contained in the address matching event is the address to be matched associated with the address matching event.

[0043] In this embodiment, the address to be matched is segmented with characters as the segmentation unit to obtain the corresponding address word sequence, and the address to be matched is processed by dividing the address fragments at the word granularity, without the need to perform the text parsing process of the address, which can avoid the accuracy of subsequent address matching affected by parsing errors. For example, if the address to be matched is "Xingfuli Community", the address word sequence corresponding to 5 characters "Xing", "Fu", "Li", "Xiao" and "Qu" can be obtained by segmentation.

[0044] Before address segmentation, the address to be matched may be formatted according to a preset address format requirement so that the format of the address to be matched is the same as the format of the address corpus in the address corpus, so as to improve the efficiency of address recognition and matching.

[0045] Specifically, the characters in the address text are divided into four categories, including Chinese characters, numbers represented by 0-9, English words represented by az and AZ, and connecting characters represented by various punctuation marks. The formatting process may include Chinese number formatting, converting the Chinese numbers in the address into Arabic numbers. For example, "Fifteen" is converted to "15" and "Thirty-four" is converted to "34". The formatting process may include English character formatting, which may be converting uppercase letters in English words into lowercase. For example, "Good" is converted to "good" and "Zoo" is converted to "zoo". The formatting process may include connecting character formatting, classifying all non-Chinese characters, non-numbers, and non-English characters as connecting characters, represented by "-".

[0046] S120 , performing address node matching in a preset address node library for each word in the address word sequence, and obtaining an address node containing any word in the address word sequence.

[0047] The preset address node library includes the address text and other address corpus currently available. The address corpus can be represented in the form of address nodes, and each address node can be an address fragment. In addition, each address node contains an address level attribute information, and the address level attribute corresponds to the geographical level of the address, such as province, city, district, street / township, community, point of interest, building, etc.

[0048] It is understandable that the serial number or identifier of the address node is used to distinguish different address nodes, and does not represent the address level to which it belongs.

[0049] For each word in the address word sequence, perform address node matching in the preset address node library, and address nodes containing any word in the address word sequence can be obtained. For example, for the words "lucky", "happy", "lane", "small", and "district" in the address word sequence, several address nodes containing the word "lucky", several address nodes containing the word "happy", several address nodes containing the word "lane", several address nodes containing the word "small", and several address nodes containing the word "district" can be matched. Different word sequences can match the same address nodes or different address nodes.

[0050] S130. Determine the effective matching sequence in the address node that matches the address word sequence according to the first position of the word in the address word sequence and the second position in the corresponding address node.

[0051] In this embodiment, the address nodes can be sorted with the address nodes as the objects, and the number of words in each address node that match the address word sequence of the address to be matched and the corresponding positions can be determined. Denote the sequence position of the word in the address word sequence as the first position, and denote the sequence position of the word in the address node as the second position. It can be understood that when a word appears in multiple address nodes, there can be multiple second positions corresponding to it. For a word in the address word sequence, its first position and second position are determined relative to a certain address node.

[0052] The more words in the address word sequence match the words in the address node, the higher the corresponding matching degree. When there are two or more words in an address node that are the same as the words in the address word sequence, the position order of the words in the address word sequence that match the address node can be analyzed to determine whether it is a valid match. If the relative position relationship of the second positions of the multiple identical words in the address word sequence is different from the relative position relationship of the first positions of these words, it indicates that the corresponding address node is an invalidly matched address node. If they are the same, it can be confirmed as a validly matched node. Therefore, some invalid matching results can be filtered out.

[0053] Furthermore, the sequence containing the matched words can be extracted from the validly matched nodes as the effective matching sequence.

[0054] S140. Determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the words in the effective matching sequence.

[0055] Among them, the importance score is the importance analysis result of the words in the effective matching sequence based on the address corpus in the preset address node library. For example, in the preset address node library constructed based on the inverted index, the inverse document frequency (IDF) of the "word" is used to express the importance of the word in the corpus.

[0056] The importance scores of all characters in the effective matching sequence are superimposed to form the node matching degree of the address node corresponding to the effective matching sequence.

[0057] S150: construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result.

[0058] The node address level attribute may indicate the geographical level such as province, city, district, street, community, and cell corresponding to the address node. The address node may be a geographical entity corresponding to the corresponding address level. The node address level attributes corresponding to each address node may be combined in the order of the address level to obtain multiple candidate address node links.

[0059] Then, the sum of the node matching degrees corresponding to each address node in the candidate address node link is taken as the link matching evaluation result.

[0060] S160: Determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0061] The links can be sorted based on the link matching evaluation results, and the target address node link can be determined based on the sorting results. For example, the link matching evaluation results indicate that the link with the highest matching degree, or the link composed of the address nodes included in the first N links with the highest link matching degree is the target address node link. Furthermore, the address composed of the target address node link can be used as the address matching result of the address to be matched.

[0062] The technical solution of this embodiment is to obtain a to-be-matched address associated with an address matching event in response to the address matching event, and perform word segmentation processing on the to-be-matched address with words as the word segmentation unit to obtain a corresponding address word sequence; perform address node matching for each word in the address word sequence in a preset address node library to obtain an address node containing any word in the address word sequence; determine a valid matching sequence in the address node that matches the address word sequence according to the first position of the word in the address word sequence and the second position in the corresponding address node; determine the node matching degree of the address node corresponding to the valid matching sequence according to the importance score of the word in the valid matching sequence; wherein, the importance score is the result of importance analysis of the word in the valid matching sequence based on the address corpus in the preset address node library; construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result; determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the to-be-matched address. The technical solution of the present invention solves the problems of low correctness of address parsing and inaccurate calculation of node matching degree in the current address matching process. It can perform address matching based on word granularity, analyze and process address nodes in a more fine-grained manner, find the link that best matches the address, and improve the accuracy of the address matching result.

[0063] Figure 2 FIG. is a flowchart of an address matching method provided by an embodiment of the present invention. This embodiment and the address matching method in the above embodiment belong to the same inventive concept, and further describes the process of determining the valid matching sequence. This method can be executed by an address matching device, and the device can be implemented in a software and / or hardware manner and integrated in a computer device with application development functions.

[0064] As Figure 2 shown, the address matching method of this embodiment includes the following steps:

[0065] S210. In response to an address matching event, obtain a to-be-matched address associated with the address matching event, and perform word segmentation processing on the to-be-matched address with words as the word segmentation unit to obtain a corresponding address word sequence.

[0066] Assume that the to-be-matched address is represented as cleanAddress. After word segmentation of the address cleanAddress, an address word sequence address.wordList composed of address.length (the number of words) words is obtained. The kth (0 ≤ k < address.length) word is represented as address.word k .

[0067] S220 , performing address node matching in a preset address node library for each word in the address word sequence, and obtaining an address node containing any word in the address word sequence.

[0068] That is, address.word k As keywords, address.word is searched in the inverted index of the preset address node library. k Address node.

[0069] S230 . For each address node, construct a matching word list, wherein the list elements in the matching word list are used to represent the first position and the second position of a word that exists in both the address word sequence and the address node.

[0070] Take each address node as the analysis object and build a matching word list, that is, find each word k After hitting the address node, the hit results are organized by address node as a unit to obtain all hit sequences node.hitLis on each node.

[0071] For a list of matching words, see Figure 3 The structure content is shown. Each node corresponds to a matching word list (hitList). Each list element (hit) in hitList is represented as<k,j> . That is, address.word k =node.word j , indicating that the kth word of the address hits the jth word of the node node, expressed as node.hit=<k,j> .

[0072] Among them, the serial number of k represents the matched word address.word k The first position in the address word sequence, and j represents the matched word address.word k The second position in the address node.

[0073] Figure 3 In the example, address.length=13, 12 of the words hit words at different positions on node1~node5, address.word7 did not hit any node, and address.word5 hit both node3 and node5.

[0074] S240: Verify the consistency between a first relative position relationship between first positions corresponding to any two list elements in the matching word list and a second relative position relationship between second positions corresponding to any two list elements in the matching word list.

[0075] The consistency of the first relative position relationship between the first positions and the second relative position relationship between the corresponding second positions indicates the consistency between the order of the words in the address word sequence and the order of the address text in the matching arrival address node. In the address matching process, the address hits on the node must meet the order constraint to be confirmed as a valid node matching result.

[0076] When judging, the position order may be judged based on the k and j values ​​of each list element (hit).

[0077] For example, for any two hits in node.hitList m and hit n , and hit m .k <hit n .k. If hit m .j <hit n .j, define hit m and hit n Comply with the order constraint, expressed as order(hit m ,hit n )=true; if hit m .j≥hit n .j, define hit m and hit n Does not meet the order constraint, expressed as order(hit m ,hit n )=false. Order constraint requirement, if hit in address m The location is hit n Before the position of , then hit in the node m The position should also be in hit n before the position.

[0078] S250: Take the words corresponding to the list elements corresponding to the first relative position relationship and the second relative position relationship that have undergone consistency verification as valid matching words, and determine a valid matching sequence that matches the address word sequence in the corresponding address node based on the valid matching words.

[0079] For example, if cleanAddress = "Xingfu Nanli Community", node1.cleanName = "Xingfu Nan Community", and node2.cleanName = "Xiaonan Street", then address.word2 = "South", address.word4 = "Xia", node1.word2 = "South", node1.word3 = "Xia", node2.word2 = "South", and node2.word1 = "Xia". So, in node1, order(South, Xia) = true, while in node2, order(South, Xia) = false, as Figure 4 shown. The "South" and "Xia" in node1 are valid matching words.

[0080] After determining the valid matching words, the longest matching sequence composed of the most matching words that satisfy the order constraint in the address node can be found as the valid matching sequence. Specifically, for an address node containing valid matching words, each valid matching word can be used as the first sequence element of a matching sequence; then, according to the order corresponding to the second position of each valid matching word, among the valid matching words other than the valid matching word corresponding to the first sequence element, the sequence elements after each first sequence element are determined to obtain at least one matching sequence and the corresponding sequence length; the matching sequence corresponding to the longest sequence length among the sequence lengths is used as the valid matching sequence.

[0081] Exemplarily, the valid matching sequence is denoted as node.matchHitList. The logic for finding node.matchHitList from node.hitList can be described as follows.

[0082] For each hit in node.hitList, all the hits that conform to the order constraint with hit are denoted as hit.followHitList = {followHit|followHit∈hitList,order(hit,followHit) = true}, and the length of the valid matching sequence starting with hit is denoted as hit.matchSize. Then, for each hit, 0 or 1 nextHit that satisfies the following three conditions can definitely be found in hitList, such that hit.matchSize = nextHit.matchSize + 1.

[0083] 1). nextHit∈hit.followHitList.

[0084] 2). nextHit.matchSize = max followHit∈hit.followHitList followHit.matchSize.

[0085] 3). For the case where otherHit∈hit.followHitList, otherHit≠nextHit, and otherHit.matchSize=nextHit.matchSize, it is required that otherHit.j>nextHit.j.

[0086] According to the above conditions, the hit.matchSize and hit.nextHit, matchHit0 of each hit can be calculated recursively. If there is more than one hit with the largest matchSize, the one with the largest hit.k is taken as matchHit0. The subsequent hits of node.matchHitList can be recursively constructed:

[0087] matchHit1=matchHit0.nextHit, matchHit2=matchHit1.nextHit, matchHit3=matchHit2.nextHit,…, matchHit t . Where matchHit t It is called Terminal Hit, which satisfies matchHit t .nextHit = null.

[0088] like Figure 5 As shown, the query address hits three levels of nodes, and each line represents a node i A hit in .hitList. A solid colored line represents a valid hit in node.matchHitList, and a dashed black line represents an invalid hit.

[0089] S260 . Determine the node matching degree of the address node corresponding to the valid matching sequence according to the importance scores of the words in the valid matching sequence.

[0090] The importance score is the result of importance analysis of the words in the effective matching sequence based on the address corpus in the preset address node library.

[0091] S270: Construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result.

[0092] S280: Determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0093] The technical solution of this embodiment is to obtain the to-be-matched address associated with the address matching event in response to the address matching event, and to perform word segmentation processing on the to-be-matched address with words as word segmentation units to obtain a corresponding address word sequence; to perform address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence; to construct a matching word list for each address node, wherein the list elements in the matching word list are used to represent the first position and the second position of the word that exist in both the address word sequence and the address node; to verify the consistency between the first relative position relationship between the first positions corresponding to any two list elements in the matching word list and the second relative position relationship between the corresponding second positions; The characters corresponding to the list elements corresponding to the first relative position relationship and the second relative position relationship of the verification are taken as valid matching characters, and the valid matching sequences matching the address character sequences in the corresponding address nodes are determined based on the valid matching characters; the node matching degree of the address nodes corresponding to the valid matching sequences is determined based on the importance scores of the characters in the valid matching sequences; wherein the importance scores are the importance analysis results of the characters in the valid matching sequences determined based on the address corpus in the preset address node library; according to the node matching degree and the corresponding node address hierarchical attributes, candidate address node links are constructed, and the link matching evaluation results are calculated; according to the link matching evaluation results, the target address node links are determined, and the address composed of the target address node links is used as the address matching result of the address to be matched. The technical solution of the present invention solves the problems that the correctness of address resolution is not high enough and the calculation of node matching degree is not accurate enough in the current address matching process, and address matching can be performed based on character granularity, and the analysis and processing of address nodes is more fine-grained, so that the link that best matches the address can be found, thereby improving the accuracy of the address matching results.

[0094] Figure 6 This is a flowchart of an address matching method provided in an embodiment of the present invention. This embodiment and the address matching method in the above embodiment belong to the same inventive concept, and further illustrates the process of calculating the node matching degree. The method can be executed by an address matching device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0095] like Figure 6 As shown, the address matching method of this embodiment includes the following steps:

[0096] S310 , in response to an address matching event, obtaining a to-be-matched address associated with the address matching event, and performing word segmentation processing on the to-be-matched address using characters as word segmentation units to obtain a corresponding address word sequence.

[0097] S320 , performing address node matching in a preset address node library for each word in the address word sequence, and obtaining an address node containing any word in the address word sequence.

[0098] S330. Determine a valid matching sequence that matches the address word sequence in the address node according to the first position of the word in the address word sequence and the second position in the corresponding address node.

[0099] S340. Calculate the sum of the first importance scores of each valid matching word in the valid matching sequence with respect to all address corpora in the preset address node library.

[0100] The first importance score of a valid matching word with respect to all address corpora in the preset address node library can be the inverse document frequency of the inverted index of each word in the preset address node library, expressed by the formula where T is the total number of nodes containing the corresponding word, and T_word is the word frequency.

[0101] The present invention takes the IDF value of the word as the score of the word, that is, word.score = word.idf.

[0102] The sum of the first importance scores is the result obtained by superimposing the inverse document frequencies of each word in the valid matching sequence.

[0103] S350. Calculate the sum of the second importance scores of each valid matching word in the valid matching sequence with respect to the corresponding address node.

[0104] To express the importance of a word in a single node, the concept of activation degree is proposed, that is, the second importance score of a valid matching word with respect to the corresponding address node.

[0105] The activation degree of the j-th word in the node node is expressed as word j .active = word j .score ÷ node.score. From the formula, it can be seen that the activation degree of the same word for different nodes is inversely proportional to node.score. Let node1.cleanName = "Happy Community" and node2.cleanName = "Xiaozhuang Village". The word "small" is node1.word2 and node2.word0 respectively. When node1.score > node2.score, there is node1.word2.active < node2.word0.active, that is, the importance of "small" in node2 is higher than that in node1.

[0106] The sum of the activation degrees of each valid matching word in the valid matching sequence with respect to the corresponding address node is the sum of the second importance scores.

[0107] S360: The product of the sum of the first importance scores and the sum of the second importance scores is used as the node matching degree of the address node corresponding to the valid matching sequence.

[0108] The product of the sum of activations and scores of all matching words in node.matchHitList is defined as the node's matching score node.matchScore, which can be formally expressed as follows:

[0109]

[0110] Because the word.score represents the importance of the word in the corpus, and the word.active represents the importance of the word in the node, the calculation mechanism of the matching score takes into account the global and local importance of the word, and more accurately expresses the difference in matching between nodes at different levels.

[0111] In a preferred embodiment, before determining the node matching degree of the address node corresponding to the effective matching sequence, the abnormality of the address input in the to-be-matched address can be determined according to the relative position relationship of two adjacent effective matching words in the effective matching sequence in the address word sequence and the relative position relationship in the corresponding address node; according to the abnormality of the address input, the effective matching sequence is sequence-corrected. Then, the node matching degree of the corresponding address node is calculated based on the corrected effective matching sequence.

[0112] The abnormalities of address input include wrong address, address abbreviation, address abbreviation, etc. Corrections are made for different abnormalities, such as correcting wrongly written words (not matched) in the address to matching words, and supplementing the words abbreviation or abbreviation of the address.

[0113] The identification of the abnormal address input situation can be performed based on the relative position relationship between two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node.

[0114] For example, if the relative position relationship of two adjacent valid matching words in the address word sequence is an adjacent position relationship, and the relative position relationship of two adjacent valid matching words in the corresponding address nodes is a position relationship with a gap, it is determined that the address input abnormality is an address abbreviation abnormality.

[0115] If the relative position relationship of two adjacent valid matching characters in the address word sequence is a gapped position relationship, and the relative position relationship of two adjacent valid matching characters in the corresponding address nodes is a gapped position relationship, identify the first pinyin of the character corresponding to the gapped position in the address word sequence and the second pinyin of the character corresponding to the gapped position in the address node; when the pinyin recognition result indicates that the first pinyin is the same as the second pinyin, determine that the address input exception is an address mistyped exception.

[0116] Furthermore, if the relative position relationship between two adjacent valid matching words in the valid matching sequence in the address word sequence and in the corresponding address node are both adjacent position relationships, determine whether an address omission exception occurs based on the relative position of the valid matching sequence in the address word sequence and the address node.

[0117] S370: Construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result.

[0118] S380: Determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0119] The technical solution of this embodiment is to obtain the address to be matched associated with the address matching event in response to the address matching event, and to perform word segmentation processing on the address to be matched with the word as the word segmentation unit to obtain the corresponding address word sequence; to perform address node matching in the preset address node library for each word in the address word sequence to obtain the address node containing any word in the address word sequence; to determine the effective matching sequence in the address node that matches the address word sequence according to the first position of the word in the address word sequence and the second position in the corresponding address node; to calculate the sum of the first importance score of each effective matching word in the effective matching sequence relative to all address corpora in the preset address node library; to calculate the sum of the second importance score of each effective matching word in the effective matching sequence relative to the corresponding address node; to use the product of the sum of the first importance score and the sum of the second importance score as the node matching degree of the address node corresponding to the effective matching sequence; to construct a candidate address node link according to the node matching degree and the corresponding node address hierarchical attribute, and to calculate the link matching evaluation result; to determine the target address node link according to the link matching evaluation result, and to use the address composed of the target address node link as the address matching result of the address to be matched. The technical solution of the present invention solves the problems that the correctness of address resolution is not high enough and the calculation of node matching degree is not accurate enough in the current address matching process. Address matching can be performed based on word granularity, and the analysis and processing of address nodes is more fine-grained. The link that best matches the address can be found, thereby improving the accuracy of the address matching result.

[0120] Figure 7 The flowchart of an address matching method provided by an embodiment of the present invention. This embodiment and the address matching method in the above embodiment belong to the same inventive concept, and further illustrate the process of determining an effective matching sequence. This method can be executed by an address matching device, which can be implemented in software and / or hardware and integrated in a computer device with application development functions.

[0121] As Figure 7 shown, the address matching method of this embodiment includes the following steps:

[0122] S410. Take each address segment in the address corpus of the preset address node library as an address node, and construct an inverted index for each word in the address node.

[0123] Specifically, each address segment can be expressed as node.cleanName. Divide node.cleanName into node.length words node.wordList, and the jth (0 ≤ j < node.length) word in node is expressed as node.word j = <node, j>, then the position of a word in different hierarchical nodes is expressed as word.nodeList = {<node i , j>|0 ≤ i < T, 0 ≤ j < node i .length}, where T is the total number of nodes.

[0124] For example, node1.cleanName = "Tuqiao pluss Community Phase 2", after word segmentation, it gets node1.wordList = {"Tu", "Qiao", "pluss", "Xiao", "Qu", "2", "Qi"}; node2.cleanName = "No. 2 Courtyard, Beidajie", after word segmentation, it gets node2.wordList = {"Bei", "Da", "Jie", "2", "Hao", "Yuan"}. "2" is the 5th word of node1 and the 3rd word of node2, then there is "2".nodeList = {<node1, 5>, <node2, 3>}.

[0125] In addition, the number of nodes containing word is called the word frequency of word, represented by T word For example, if 1000 node names contain "Xiao", then the word frequency of "Xiao" is equal to 1000.

[0126] Taking word as the key and word.nodeList as the value, and storing them in the Hash table, the inverted index of the hierarchical nodes is obtained, as Figure 8As shown in the figure. The inverted index can quickly find all nodes word.nodeList that contain the word according to the word.

[0127] S420. Calculate the inverse document frequency of each word according to the inverted index, and use the inverse document frequency as the first importance score of the corresponding word relative to the preset address node library.

[0128] In natural language processing, the inverse document frequency (IDF, Inverse Document Frequency) is used to express the importance of a word in a corpus, and the formula is used to represent it, where T is the total number of nodes, and T word is the word frequency. The present invention uses the IDF value of the word as the score of the word, that is, word.score = word.idf; the sum of the scores of all words in the node is used as the node score

[0129] S430. Calculate the sum of the first importance scores corresponding to all words in each address node to obtain the corresponding address node score, and use the ratio of the first importance score of each word to the address node score as the second importance score of each word in the address node relative to the address node.

[0130] In order to express the importance of a word in a single node, the present invention proposes the concept of activation degree. The activation degree of the j-th word in the node node is expressed as word j .active = word j .score ÷ node.score. It can be seen from the formula that the activation degree of the same word for different nodes is inversely proportional to node.score. Let node1.cleanName = "Happy Community" and node2.cleanName = "Xiaozhuang Village". The word "small" is node1.word2 and node2.word0 respectively. When node1.score > node2.score, there is node1.word2.active < node2.word0.active, that is, the importance of "small" in node2 is higher than that in node1.

[0131] Through the above scoring strategy, the importance of a word in the entire corpus and in a single node is defined respectively, which plays a key role in calculating the matching degree between the address cleanAddress and the node name node.cleanName in the subsequent process.

[0132] S440. In response to the address matching event, obtain the to-be-matched address associated with the address matching event, and perform word segmentation processing on the to-be-matched address with the word as the segmentation unit to obtain the corresponding address word sequence.

[0133] S450 , performing address node matching in a preset address node library for each word in the address word sequence, and obtaining an address node containing any word in the address word sequence.

[0134] Each word in the address word sequence is used as a search keyword, and the word.nodeList corresponding to the keyword is searched to determine the address node containing the search keyword.

[0135] S460: Determine a valid matching sequence in the address node that matches the address word sequence according to a first position of a word in the address word sequence in the address word sequence and a second position in a corresponding address node.

[0136] S470, determining an abnormality in the address input in the to-be-matched address according to the relative position relationship between two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node; and performing sequence correction on the valid matching sequence according to the abnormality in the address input.

[0137] Specifically, according to the relative position relationship between two adjacent valid matching characters in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node, if the relative position relationship between two adjacent valid matching characters in the address word sequence is a position relationship with a gap, and the relative position relationship between two adjacent valid matching characters in the corresponding address node is a position relationship with a gap, the first pinyin of the character corresponding to the gap position in the address word sequence and the second pinyin of the character corresponding to the gap position in the address node are identified; when the pinyin recognition result indicates that the first pinyin is the same as the second pinyin, it is determined that the address input exception is an address miswriting exception.

[0138] For the two hits in node.matchHitList m and hit m+1 , if hit m+1 .j-hit m .j>1, it means there is a gap (Gap) between the two hits on node.cleanName and no match is found; if hit m+1 .k-hit m .k>1, it means that there is a gap (Gap) between the two hits at the address cleanAddress and they do not match.

[0139] When hit m .k-hit m+1 .k = hit m .j-hit m+1.j>1, indicating that the gaps between the two hits in node.cleanName and cleanAddress are equal. This may be caused by homophones. k and node.word j Match according to pinyin, if address.word k .pinyin=node.word j .pinyin, it means that the kth word in the address and the jth word in the node are homophones. Because homophones are very common in the address placement scenario, the present invention uses hit=<k,j> Insert it into the corresponding position of node.matchHitList to enhance the hit rate of the address to the node. Fig. 9 (1) shows that the solid line represents the address.word k =node.word j The hits identified, while the dotted lines represent the hits based on address.word k .pinyin=node.word j .pinyin identifies the hit that occurs.

[0140] In addition, the word-granularity-based matching method can well support matching the correct hierarchical node when the address is abbreviated or shortened, such as Fig. 9 (2)(3) As shown. When the relative position relationship of two adjacent valid matching words in the address word sequence is an adjacent position relationship, and the relative position relationship of two adjacent valid matching words in the corresponding address node is a position relationship with a gap, the address input abnormality is determined to be an address abbreviation abnormality. Also, when the relative position relationship of two adjacent valid matching words in the address word sequence and the relative position relationship in the corresponding address node in the valid matching sequence are both adjacent position relationships, it can be determined whether an address abbreviation abnormality occurs based on the relative position of the valid matching sequence in the address word sequence and the address node, such as whether there are other words at the end or front of the sequence of the valid matching sequence.

[0141] S480: Determine the node matching degree of the address node corresponding to the valid matching sequence according to the importance scores of the characters in the corrected valid matching sequence.

[0142] The importance score is the result of importance analysis of the words in the effective matching sequence based on the address corpus in the preset address node library.

[0143] S490. Construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result; determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0144] After calculating the match score node.matchScore of each hit node, it is also necessary to build a link based on the ownership relationship of the hierarchical nodes in Definition 1. Figure 4 In the example, the address cleanAddress hits node1 (Xicheng District), node2 (Desheng Street), and node3 (6pukang North Street Community). In the geographical hierarchy tree, node2 is a node under node1, and node3 is a node under node2, so a matching link link=<node1,node2,node3> If nodeb is the ancestor node of nodea, it is represented by nodea.isAncestorOf(nodeb) = true. This ancestor relationship is transitive. For example, if node1.isAncestorOf(node2) = true and node2.isAncestorOf(node3) = true, then node1.isAncestorOf(node3) must be true.

[0145] This embodiment defines the link score of a node as node.linkScore, which is equal to the sum of the matching scores of the current node and all its ancestor nodes. Figure 8 In node1.linkScore=node1.matchScore, node2.linkScore=node1.matchScore+node2.matchScore, node3.linkScore=node1.matchScore+node2.matchScore+node3.matchScore.

[0146] The link score of a node not only considers the matching degree of the query address to the node, but also considers the matching degree to its ancestor node, so the link score of a node can better represent the matching degree of the node to the entire query address. The present invention sorts all hierarchical nodes from large to small according to their link score node.linkScore, and then takes the first k to obtain the k hierarchical nodes that best match the query address.

[0147] The technical solution of this embodiment is to take each address segment in the address corpus in the preset address node library as an address node and construct an inverted index for each word in the address node; calculate the inverse document frequency of each word according to the inverted index, and use the inverse document frequency as the first importance score of the corresponding word relative to the preset address node library; calculate the sum of the first importance scores corresponding to all words in each address node to obtain the corresponding address node score, and use the ratio of the first importance score of each word to the address node score as the second importance score of each word in the address node relative to the address node; in response to an address matching event, obtain the address to be matched associated with the address matching event, and perform word segmentation processing on the address to be matched with words as word segmentation units to obtain the corresponding address word sequence; perform address node matching in the preset address node library for each word in the address word sequence, and obtain a word containing any word in the address word sequence. The invention relates to an address node of a word; according to the first position of the word in the address word sequence and the second position in the corresponding address node, determine the effective matching sequence in the address node that matches the address word sequence; according to the relative position relationship of two adjacent effective matching words in the effective matching sequence in the address word sequence and the relative position relationship in the corresponding address node, determine the abnormality of the address input in the address to be matched; and according to the abnormality of the address input, perform sequence correction on the effective matching sequence; according to the importance score of the word in the corrected effective matching sequence, determine the node matching degree of the address node corresponding to the effective matching sequence; according to the node matching degree and the corresponding node address level attribute, construct the candidate address node link, and calculate the link matching evaluation result; according to the link matching evaluation result, determine the target address node link, and use the address composed of the target address node link as the address matching result of the address to be matched. The technical solution of the present invention solves the problem that the correctness of address resolution is not high enough and the calculation of node matching degree is not accurate enough in the current address matching process, can perform address matching based on word granularity, analyze and process address nodes more fine-grained, can find the link that best matches the address, and improve the accuracy of the address matching result.

[0148] Fig.10 A structural schematic diagram of an address matching device provided in an embodiment of the present invention. This embodiment can be applied to scenarios of logistics address determination or delivery route planning in the logistics field. The address matching device can be implemented by software and / or hardware and integrated into a computer terminal device with application development capabilities.

[0149] like Fig.10 The address matching device shown includes: a to-be-matched address processing module 510, an address node matching module 520, a first address node matching analysis module 530, a second address node matching analysis module 540, an address node link analysis module 550 and a target address matching result determination module 560.

[0150] The to-be-matched address processing module 510 is used to respond to an address matching event, obtain the to-be-matched address associated with the address matching event, and perform word segmentation processing on the to-be-matched address with words as word segmentation units to obtain a corresponding address word sequence; the address node matching module 520 is used to perform address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence; the first address node matching analysis module 530 is used to determine a valid matching sequence in the address node that matches the address word sequence based on the first position of the word in the address word sequence and the second position in the corresponding address node; the second address node matching analysis module 530 is used to determine a valid matching sequence in the address node that matches the address word sequence based on the first position of the word in the address word sequence and the second position in the corresponding address node; The point matching analysis module 540 is used to determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library; the address node link analysis module 550 is used to construct the candidate address node link according to the node matching degree and the corresponding node address hierarchical attributes, and calculate the link matching evaluation result; the target address matching result determination module 560 is used to determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

[0151] The technical solution of this embodiment is to obtain the address to be matched associated with the address matching event in response to the address matching event, and to perform word segmentation processing on the address to be matched with words as word segmentation units to obtain the corresponding address word sequence; to perform address node matching in a preset address node library for each word in the address word sequence, and to obtain an address node containing any word in the address word sequence; to determine the effective matching sequence in the address node that matches the address word sequence according to the first position of the word in the address word sequence and the second position in the corresponding address node; to determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the word in the effective matching sequence; wherein the importance score is the importance analysis result of the word in the effective matching sequence determined based on the address corpus in the preset address node library; to construct a candidate address node link according to the node matching degree and the corresponding node address hierarchical attribute, and to calculate the link matching evaluation result; to determine the target address node link according to the link matching evaluation result, and to use the address composed of the target address node link as the address matching result of the address to be matched. The technical solution of the present invention solves the problems that the correctness of address resolution is not high enough and the calculation of node matching degree is not accurate enough in the current address matching process. Address matching can be performed based on word granularity, and the analysis and processing of address nodes is more fine-grained. The link that best matches the address can be found, thereby improving the accuracy of the address matching result.

[0152] In an optional implementation manner, the first address node matching analysis module 530 is specifically used to:

[0153] For each address node, construct a matching word list, wherein the list elements in the matching word list are used to represent the first position and the second position of the word that exists in both the address word sequence and the address node;

[0154] Verify the consistency of a first relative position relationship between first positions corresponding to any two list elements in the matching word list and a second relative position relationship between second positions corresponding to any two list elements in the matching word list;

[0155] The words corresponding to the list elements corresponding to the first relative position relationship and the second relative position relationship that have undergone consistency check are taken as valid matching words, and a valid matching sequence matching the address word sequence in the corresponding address node is determined based on the valid matching words.

[0156] In an optional implementation manner, the first address node matching analysis module 530 is further specifically configured to:

[0157] Each valid matching word is regarded as the first sequence element of a matching sequence;

[0158] According to the order corresponding to the second position of each valid matching word, in the valid matching words other than the valid matching word corresponding to the first sequence element, determine the sequence elements after each first sequence element, and obtain at least one matching sequence and the corresponding sequence length;

[0159] The matching sequence corresponding to the longest sequence length among the sequence lengths is taken as the valid matching sequence.

[0160] In an optional implementation manner, the second address node matching analysis module 540 is specifically used to:

[0161] Calculate the sum of the first importance scores of each valid matching word in the valid matching sequence relative to all address corpora in the preset address node library;

[0162] Calculate the sum of the second importance scores of each valid matching word in the valid matching sequence relative to the corresponding address node;

[0163] The product of the sum of the first importance scores and the sum of the second importance scores is used as the node matching degree of the address node corresponding to the valid matching sequence.

[0164] In an optional implementation, the address matching device further includes an address anomaly identification and correction module, which is used to:

[0165] Before determining the node matching degree of the address node corresponding to the valid matching sequence, determining the abnormality of the address input in the to-be-matched address according to the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node;

[0166] According to the abnormal address input, the valid matching sequence is corrected.

[0167] In an optional implementation, the address anomaly identification and correction module may be used to:

[0168] If the relative position relationship of two adjacent valid matching words in the address word sequence is an adjacent position relationship, and the relative position relationship of two adjacent valid matching words in the corresponding address nodes is a position relationship with a gap, it is determined that the address input abnormality is an address abbreviation abnormality.

[0169] In an optional implementation, the address anomaly identification and correction module may be used to:

[0170] If the relative position relationship of two adjacent valid matching words in the address word sequence is a position relationship with a gap, and the relative position relationship of two adjacent valid matching words in the corresponding address nodes is a position relationship with a gap, identify the first pinyin of the word corresponding to the gap position in the address word sequence and the second pinyin of the word corresponding to the gap position in the address node;

[0171] When the pinyin recognition result indicates that the first pinyin is identical to the second pinyin, it is determined that the address input abnormality is an address miswriting abnormality.

[0172] In an optional implementation, the address anomaly identification and correction module may be used to:

[0173] If the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node are both adjacent position relationships, determine whether an address omission exception occurs based on the relative position of the valid matching sequence in the address word sequence and the address node.

[0174] In an optional implementation, the address node link analysis module 550 is specifically used to:

[0175] According to the node address level attribute of each address node, at least one candidate address node link is constructed;

[0176] The node matching degrees corresponding to each address node in the candidate address node link are superimposed to obtain the sum of the node matching degrees, and the sum of the node matching degrees is used as the link matching evaluation result of the corresponding candidate address node link.

[0177] In an optional implementation, the address corpus importance analysis module is used to:

[0178] Importance scores of characters in address nodes determined based on address corpus in a preset address node library;

[0179] The process of determining the importance score includes:

[0180] Take each address segment in the address corpus in the preset address node library as an address node, and construct an inverted index for each word in the address node;

[0181] Calculate the inverse document frequency of each word according to the inverted index, and use the inverse document frequency as the first importance score of the corresponding word relative to the preset address node library;

[0182] The sum of the first importance scores corresponding to all words in each address node is calculated to obtain the corresponding address node score, and the ratio of the first importance score of each word to the address node score is used as the second importance score of each word in the address node relative to the address node.

[0183] The address matching device provided in the embodiment of the present invention can execute the address matching method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0184] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Fig.11 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Fig.11 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller and server, a mobile phone and other terminal devices.

[0185] like Fig.11 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0186] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0187] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0188] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig.11 not shown, usually called a "hard drive"). Although Fig.11 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0189] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 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. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0190] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Fig.11 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0191] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the address matching method provided in the embodiment of the present invention, which includes:

[0192] In response to the address matching event, the to-be-matched address associated with the address matching event is obtained, and the to-be-matched address is segmented by word as a word segmentation unit to obtain a corresponding address word sequence;

[0193] Performing address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence;

[0194] Determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence in the address word sequence and a second position in a corresponding address node;

[0195] Determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library;

[0196] According to the node matching degree and the corresponding node address level attributes, the candidate address node link is constructed, and the link matching evaluation result is calculated;

[0197] The target address node link is determined according to the link matching evaluation result, and the address composed of the target address node link is used as the address matching result of the address to be matched.

[0198] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the address matching method provided in any embodiment of the present invention is implemented. The method includes:

[0199] In response to the address matching event, the to-be-matched address associated with the address matching event is obtained, and the to-be-matched address is segmented by word as a word segmentation unit to obtain a corresponding address word sequence;

[0200] Performing address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence;

[0201] Determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence in the address word sequence and a second position in a corresponding address node;

[0202] Determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library;

[0203] According to the node matching degree and the corresponding node address level attributes, the candidate address node link is constructed, and the link matching evaluation result is calculated;

[0204] The target address node link is determined according to the link matching evaluation result, and the address composed of the target address node link is used as the address matching result of the address to be matched.

[0205] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can 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 (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0206] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. 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. Computer-readable signal media may also be any computer-readable medium other than a computer-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.

[0207] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0208] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0209] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0210] An embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, implements the address matching method provided in any one of the embodiments of the present disclosure.

[0211] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0212] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An address matching method, characterized in that: include: In response to an address matching event, an address to be matched associated with the address matching event is acquired, and word segmentation processing is performed on the address to be matched using words as word segmentation units to obtain a corresponding address word sequence; Performing address node matching in a preset address node library for each word in the address word sequence to obtain an address node containing any word in the address word sequence; Determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence and a second position in the corresponding address node; Determining the node matching degree of the address node corresponding to the valid matching sequence according to the importance scores of the characters in the valid matching sequence; wherein the importance scores are the importance analysis results of the characters in the valid matching sequence determined based on the address corpus in the preset address node library; According to the node matching degree and the corresponding node address level attribute, a candidate address node link is constructed, and a link matching evaluation result is calculated; The target address node link is determined according to the link matching evaluation result, and the address composed of the target address node link is used as the address matching result of the address to be matched.

2. The method according to claim 1, characterized in that The determining, based on a first position of a word in the address word sequence in the address word sequence and a second position in the corresponding address node, a valid matching sequence in the address node that matches the address word sequence comprises: For each of the address nodes, construct a matching word list, wherein the list elements in the matching word list are used to represent the first position and the second position of the word that exist in both the address word sequence and the address node; Verifying consistency between a first relative position relationship between the first positions corresponding to any two list elements in the matching word list and a second relative position relationship between the corresponding second positions; The words corresponding to the list elements corresponding to the first relative position relationship and the second relative position relationship that have undergone consistency check are taken as valid matching words, and a valid matching sequence matching the address word sequence in the corresponding address node is determined based on the valid matching words.

3. The method according to claim 2, characterized in that The determining, based on the valid matching word, a valid matching sequence in the corresponding address node that matches the address word sequence comprises: Each of the valid matching words is respectively used as the first sequence element of a matching sequence; According to the order corresponding to the second position of each of the valid matching words, in the valid matching words other than the valid matching words corresponding to the first sequence element, determine the sequence elements after each of the first sequence elements, to obtain at least one matching sequence and a corresponding sequence length; The matching sequence corresponding to the longest sequence length among the sequence lengths is taken as a valid matching sequence.

4. The method according to claim 1, characterized in that Determining the node matching degree of the address node corresponding to the valid matching sequence according to the importance scores of the words in the valid matching sequence includes: Calculating the sum of the first importance scores of each valid matching word in the valid matching sequence relative to all address corpora in the preset address node library; Calculating the sum of the second importance scores of each valid matching word in the valid matching sequence relative to the corresponding address node; The product of the sum of the first importance scores and the sum of the second importance scores is used as the node matching degree of the address node corresponding to the valid matching sequence.

5. The method according to claim 4, characterized in that Before determining the node matching degree of the address node corresponding to the valid matching sequence, the method further includes: Determine the abnormality of the address input in the to-be-matched address according to the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node; According to the abnormality of the address input, the valid matching sequence is corrected.

6. The method according to claim 5, characterized in that Determining the abnormality of the address input in the to-be-matched address according to the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node includes: If the relative position relationship of the two adjacent valid matching words in the address word sequence is an adjacent position relationship, and the relative position relationship of the two adjacent valid matching words in the corresponding address nodes is a position relationship with a gap, it is determined that the address input abnormality is an address abbreviation abnormality.

7. The method according to claim 6, characterized in that The determining of the abnormality of the address input in the to-be-matched address according to the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node further includes: If the relative position relationship of the two adjacent valid matching words in the address word sequence is a position relationship with an interval, and the relative position relationship of the two adjacent valid matching words in the corresponding address nodes is a position relationship with an interval, identify the first pinyin of the word corresponding to the position of the interval in the address word sequence and the second pinyin of the word corresponding to the position of the interval in the address node; When the pinyin recognition result indicates that the first pinyin is the same as the second pinyin, it is determined that the address input exception is an address miswriting exception.

8. The method according to claim 6, characterized in that The process of determining the abnormality of the address input in the address to be matched also includes: If the relative position relationship of two adjacent valid matching words in the valid matching sequence in the address word sequence and the relative position relationship in the corresponding address node are both adjacent position relationships, determine whether an address abbreviation exception occurs based on the relative position of the valid matching sequence in the address word sequence and the address node.

9. The method according to claim 1, characterized in that: The node matching degree and the corresponding node address level attribute are used to construct a candidate address node link and calculate the link matching evaluation result, including: Constructing at least one candidate address node link according to the node address level attribute of each address node; The node matching degrees corresponding to each address node in the candidate address node link are superimposed to obtain a sum of the node matching degrees, and the sum of the node matching degrees is used as a link matching evaluation result of the corresponding candidate address node link.

10. The method according to any one of claims 1 to 9, characterized in that: The process of determining the importance score includes: Taking each address segment in the address corpus in the preset address node library as an address node, and constructing an inverted index of each word in the address node; Calculate the inverse document frequency of each word according to the inverted index, and use the inverse document frequency as the first importance score of the corresponding word relative to the preset address node library; The sum of the first importance scores corresponding to all the words in each of the address nodes is calculated to obtain the corresponding address node score, and the ratio of the first importance score of each word to the address node score is used as the second importance score of each word in the address node relative to the address node.

11. An address matching device, configured at a client, characterized in that: include: A to-be-matched address processing module is used to, in response to an address matching event, obtain an to-be-matched address associated with the address matching event, and perform word segmentation processing on the to-be-matched address with words as word segmentation units to obtain a corresponding address word sequence; An address node matching module, used for performing address node matching in a preset address node library for each word in the address word sequence, and obtaining an address node containing any word in the address word sequence; A first address node matching analysis module, configured to determine a valid matching sequence in the address node that matches the address word sequence based on a first position of a word in the address word sequence in the address word sequence and a second position in the corresponding address node; A second address node matching analysis module, configured to determine the node matching degree of the address node corresponding to the effective matching sequence according to the importance score of the characters in the effective matching sequence; wherein the importance score is the importance analysis result of the characters in the effective matching sequence determined based on the address corpus in the preset address node library; An address node link analysis module is used to construct a candidate address node link according to the node matching degree and the corresponding node address level attribute, and calculate the link matching evaluation result; The target address matching result determination module is used to determine the target address node link according to the link matching evaluation result, and use the address composed of the target address node link as the address matching result of the address to be matched.

12. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the address matching method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the address matching method as described in any one of claims 1 to 10 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the address matching method according to any one of claims 1 to 10.

Images