Address standardization method, device and equipment based on AC automaton

Abstract

The invention discloses an address standardization method, device and equipment based on an AC automaton, and the method comprises the steps: taking a Chinese character type address in an address standard library as a tree node in the construction process of the AC automaton, determining the level relation between the tree nodes of Chinese characters, and constructing a Chinese character tree structure; taking the pinyin-form addresses in the address standard library as tree nodes, determining a level relationship among the pinyin tree nodes, and constructing a pinyin tree structure; in response to the address standardization instruction, obtaining a to-be-standardized address input into the AC automaton; and performing address matching on a to-be-standardized address by using an AC automaton based on the Chinese character tree structure and the pinyin tree structure and adopting a multi-modal matching algorithm, and obtaining a standardized address according to a matching result. Therefore, the problems that a traditional deep learning algorithm is limited by resources, a traditional matching algorithm carries out searching according to character string matching, however, the algorithms cannot be used for well processing addresses with the same sound and different characters and the like are solved.

Description

Background Art

[0002] With the acceleration of the process of social informatization, address information has become an indispensable data element for individuals and enterprises, playing a key role in many fields such as logistics distribution, travel navigation, and financial services. However, in real life, address information is generally non-standard and non-uniform, such as multiple names for one place, missing information, incorrect spelling, and vague expressions, which have brought many troubles to people's lives and also posed challenges to the operational efficiency and service quality of related industries.

[0003] Address standardization technology is a very important technology. Existing technologies are divided into traditional algorithms and deep learning-related algorithms. Deep learning algorithms have better effects due to their large model-related implementation solutions, but are limited by resources and cannot be used well without good hardware resources. Traditional matching algorithms mainly include maximum fuzzy matching and prefix tree search algorithms. The basic idea is to search based on string matching. However, these algorithms cannot handle problems such as homophonic but different characters in addresses. Summary of the invention

[0004] The purpose of this application is to provide an address standardization method, device and equipment method based on AC automaton, which is used to solve the problem that traditional deep learning algorithms are limited by resources and traditional matching algorithms are all searched based on string matching. However, these algorithms cannot handle the problem of homophonic but different characters in addresses.

[0005] In a first aspect, an embodiment of the present application provides an address standardization method based on an AC automaton, the method comprising:

[0006] In the construction process of AC automaton, the addresses in Chinese character form in the address standard library are used as tree nodes, and the level relationship between the tree nodes of Chinese characters is determined according to the level relationship between the addresses to construct the Chinese character tree structure;

[0007] In the construction process of AC automaton, the addresses in the pinyin form in the address standard library are used as tree nodes, and the level relationship between the pinyin tree nodes is determined according to the level relationship between the addresses to construct the pinyin tree structure;

[0008] In response to an address standardization instruction, obtaining an address to be standardized input to the AC automaton;

[0009] The AC automaton is used to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and a standardized address is obtained according to the matching result.

[0010] The AC automaton-based address standardization method, device and equipment provided in the embodiments of the present application, during the AC automaton construction process, not only constructs a Chinese character tree structure, but also simultaneously constructs a pinyin tree structure, so that for address matching of homophonic but different input characters, the pinyin tree structure can be used to solve the standardization of addresses with homophonic but different input characters, and addresses can be standardized in a timely and effective manner using very few resources, thereby reducing errors caused by non-standard data; and problems related to address input typos, homophonic but different input characters, etc. can be solved very well.

[0011] In some possible embodiments, the process of constructing the Chinese character tree structure / pinyin tree structure further includes:

[0012] According to the complete address with abbreviation in the address standard library, determine the abbreviation to be omitted when the complete address in the address standard library is abstracted into the abbreviation;

[0013] Using the abbreviation as a newly added tree node, and adding the newly added tree node between the tree node of the complete address and the tree node of the previous level of the complete address;

[0014] When it is determined that there are multiple identical newly added nodes, the multiple identical newly added nodes are merged into one newly added node.

[0015] In the process of constructing the Chinese character tree structure / pinyin tree structure, the embodiment of the present application adds a new node for the address with abbreviations, so that when the abbreviation matching algorithm matches, the address search is directly performed within the tree node range of the newly added node, which can quickly achieve address matching of the abbreviation address.

[0016] In some possible embodiments, the multimodal matching algorithm includes any of the following:

[0017] An accurate matching algorithm for matching the complete address to be standardized based on the Chinese character tree structure and the pinyin tree structure;

[0018] For some of the addresses to be standardized, a fuzzy matching algorithm is used to match the addresses based on the Chinese character tree structure and the pinyin tree structure;

[0019] When it is determined that there is an abbreviated address in the standardized address, an abbreviated matching algorithm for address matching is performed in the tree node range of the newly added node in the Chinese character tree structure and the pinyin tree structure.

[0020] The multimodal matching algorithm provided in the embodiment of the present application includes exact matching, fuzzy matching and abbreviated matching. The use of a combination of multimodal algorithms for address matching can improve the success rate of address standardization.

[0021] In some possible embodiments, when a multi-modal matching algorithm is used for address matching, any modal matching algorithm uses the following method to perform address matching:

[0022] For the address to be standardized in Chinese characters, when a new starting address is determined, the following address traversal is triggered:

[0023] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Chinese character tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0024] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. The search is triggered again. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0025] The new starting address is initially the first Chinese character of the address to be standardized.

[0026] In the embodiment of the present application, for a tree structure in the form of Chinese characters, Chinese characters are moved from left to right from the address to be standardized for matching, and the search range is screened secondary after matching. If the matching identification redetermines the starting address and matches from left to right until the match is successful, the matching success rate in the tree structure in the form of Chinese characters can be improved.

[0027] In some possible embodiments, when a multi-modal matching algorithm is used for address matching, any modal matching algorithm uses the following method to perform address matching:

[0028] For the address to be standardized in pinyin format, when a new starting address is determined, the following address traversal is triggered:

[0029] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Pinyin tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Pinyin letter of the current address, otherwise the next Pinyin letter of the current address is determined as the new starting address to trigger the address traversal again;

[0030] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next pinyin letter of the current address. The search is triggered again. Otherwise, the next pinyin letter of the current address is determined as the new starting address to trigger the address traversal again.

[0031] The new starting address is initially the first pinyin letter of the address to be standardized.

[0032] In the embodiment of the present application, for a tree structure in the form of pinyin, letters are moved from left to right from the address to be standardized for matching, and the search range is screened for a second time after matching. If the matching identification redetermines the starting address and matches from left to right until the match is successful, the matching success rate in the tree structure in the form of Chinese characters can be improved.

[0033] In some possible embodiments, based on the Chinese character tree structure and the pinyin tree structure, a multimodal matching algorithm is used to perform address matching, including any of the following steps:

[0034] When it is determined according to the search mode setting information that the simultaneous search is set, a multi-modal matching algorithm is simultaneously used to perform address matching in the Chinese character tree structure and the pinyin tree structure;

[0035] According to the search mode setting information, when it is determined that the search is set to be performed according to the priority, based on the priority in the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used in the tree structure with a high priority to perform address matching. If the match is successful, the process ends; otherwise, a multi-modal matching algorithm is used in the tree structure with a low priority to perform address matching;

[0036] According to the search method setting information, when it is determined that the setting is to search the specified tree structure first, the tree structure is specified in the Chinese character tree structure and the pinyin tree structure, and a multimodal matching algorithm is used for address matching. If the match is successful, the process ends, otherwise a multimodal matching algorithm is used in another tree structure for address matching.

[0037] Through the above method, users can modify the setting information as needed, thereby supporting a combination of address matching based on the Chinese character tree structure and the pinyin tree structure, and improving the success rate of address standardization.

[0038] In some possible embodiments, the method further includes at least one of the following steps:

[0039] Before using the address in Chinese character form in the address standard library as a tree node, removing redundant information from the address in Chinese character form;

[0040] Before using the pinyin address in the address standard library as a tree node, redundant information is removed from the pinyin address.

[0041] In the process of constructing the Chinese character tree structure and the Pinyin tree structure, the embodiment of the present application removes redundant information in the address in the form of Chinese characters / Pinyin, which can reduce unnecessary matching information.

[0042] In a second aspect, an embodiment of the present application provides an address standardization device based on an AC automaton, the device comprising:

[0043] A Chinese character tree construction module is used to use the addresses in Chinese character form in the address standard library as tree nodes during the construction process of the AC automaton, determine the level relationship between the tree nodes of Chinese characters according to the level relationship between the addresses, and construct a Chinese character tree structure;

[0044] The pinyin tree construction module is used to use the pinyin addresses in the address standard library as tree nodes in the construction process of the AC automaton, determine the level relationship between the pinyin tree nodes according to the level relationship between the addresses, and construct the pinyin tree structure;

[0045] A module for acquiring an address to be standardized, for acquiring an address to be standardized input to the AC automaton in response to an address standardization instruction;

[0046] The address standardization module is used to use the AC automaton to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and obtain a standardized address according to the matching result.

[0047] In some possible embodiments, the Chinese character tree construction module / Pinyin tree construction module is further used in the process of constructing the Chinese character tree structure / Pinyin tree structure:

[0048] According to the complete address with abbreviation in the address standard library, determine the abbreviation to be omitted when the complete address in the address standard library is abstracted into the abbreviation;

[0049] Using the abbreviation as a newly added tree node, and adding the newly added tree node between the tree node of the complete address and the tree node of the previous level of the complete address;

[0050] When it is determined that there are multiple identical newly added nodes, the multiple identical newly added nodes are merged into one newly added node.

[0051] In some possible embodiments, the multimodal matching algorithm includes any of the following:

[0052] An accurate matching algorithm for matching the complete address to be standardized based on the Chinese character tree structure and the pinyin tree structure;

[0053] For some of the addresses to be standardized, a fuzzy matching algorithm is used to match the addresses based on the Chinese character tree structure and the pinyin tree structure;

[0054] When it is determined that there is an abbreviated address in the standardized address, an abbreviated matching algorithm for address matching is performed in the tree node range of the newly added node in the Chinese character tree structure and the pinyin tree structure.

[0055] In some possible embodiments, when the address standardization module uses a multi-modal matching algorithm to perform address matching, any modal matching algorithm uses the following method to perform address matching:

[0056] For the address to be standardized in Chinese characters, when a new starting address is determined, the following address traversal is triggered:

[0057] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Chinese character tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0058] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. The search is triggered again. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0059] The new starting address is initially the first Chinese character of the address to be standardized.

[0060] In some possible embodiments, when the address standardization module uses a multi-modal matching algorithm to perform address matching, any modal matching algorithm uses the following method to perform address matching:

[0061] For the address to be standardized in pinyin format, when a new starting address is determined, the following address traversal is triggered:

[0062] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Pinyin tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Pinyin letter of the current address, otherwise the next Pinyin letter of the current address is determined as the new starting address to trigger the address traversal again;

[0063] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next pinyin letter of the current address. The search is triggered again. Otherwise, the next pinyin letter of the current address is determined as the new starting address to trigger the address traversal again.

[0064] The new starting address is initially the first pinyin letter of the address to be standardized.

[0065] In some possible embodiments, the address standardization module uses a multimodal matching algorithm to perform address matching based on the Chinese character tree structure and the pinyin tree structure, including any of the following steps:

[0066] When it is determined according to the search mode setting information that the simultaneous search is set, a multi-modal matching algorithm is simultaneously used to perform address matching in the Chinese character tree structure and the pinyin tree structure;

[0067] According to the search mode setting information, when it is determined that the search is set to be performed according to the priority, based on the priority in the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used in the tree structure with a high priority to perform address matching. If the match is successful, the process ends; otherwise, a multi-modal matching algorithm is used in the tree structure with a low priority to perform address matching;

[0068] According to the search method setting information, when it is determined that the setting is to search the specified tree structure first, the tree structure is specified in the Chinese character tree structure and the pinyin tree structure, and a multimodal matching algorithm is used for address matching. If the match is successful, the process ends, otherwise a multimodal matching algorithm is used in another tree structure for address matching.

[0069] In some possible embodiments, the Chinese character tree construction module / Pinyin tree construction module is further used to perform at least one of the following steps:

[0070] Before using the address in Chinese character form in the address standard library as a tree node, removing redundant information from the address in Chinese character form;

[0071] Before using the pinyin address in the address standard library as a tree node, redundant information is removed from the pinyin address.

[0072] In the third aspect, another embodiment of the present application also provides an address standardization device based on AC automaton, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any address standardization method based on AC automaton provided in the embodiment of the present application.

[0073] In a fourth aspect, another embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to enable a computer to execute any address standardization method based on an AC automaton provided in an embodiment of the present application.

[0074] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1 is a flow chart of an address standardization method based on AC automaton according to an embodiment of the present application;

[0077] Figure 2 A detailed flow chart of an address standardization method based on an AC automaton according to an embodiment of the present application;

[0078] Figure 3 The structure diagram of an address standardization device based on AC automaton according to one embodiment of the present application;

[0079] Figure 4 The structure diagram of an address standardization device based on AC automaton according to one embodiment of the present application. DETAILED DESCRIPTION

[0080] To further illustrate the technical solution provided by the embodiment of the present application, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiment of the present application provides the method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiment of the present application. The method can be executed in the order of the method shown in the embodiment or drawings or in parallel during the actual processing process or when the control device is executed.

[0081] Address standardization technology is a very important technology. Taking the express delivery industry as an example, unclear delivery addresses may lead to delivery errors and duplicate deliveries. With the growth of business volume, if this situation is not improved, it will have a serious impact on the operating costs and customer satisfaction of express delivery companies. In the field of intelligent navigation, non-standard addresses may lead to navigation deviations or even misleading, wasting users' valuable time and reducing user experience. As for banking business, customers may make administrative division errors, incomplete information or false reporting when filling in address information. These problems make it difficult for financial institutions to effectively warn of potential risks and increase business risks.

[0082] In view of the fact that traditional deep learning algorithms in related technologies are limited by resource constraints and traditional matching algorithms are all based on string matching for searching, these algorithms cannot well handle the problem of homophonic but different characters in addresses. This application proposes an address standardization method, device and equipment based on AC automaton.

[0083] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings.

[0084] The following describes in detail the address standardization method based on AC automaton in the embodiment of the present application in conjunction with the accompanying drawings.

[0085] like Figure 1 The figure shows a flow chart of the address standardization method based on AC automaton provided by the present application, which mainly includes:

[0086] Step 101, in the process of constructing the AC automaton, the addresses in Chinese character form in the address standard library are used as tree nodes, and the level relationship between the tree nodes of Chinese characters is determined according to the level relationship between the addresses, so as to construct a Chinese character tree structure;

[0087] AC automaton is mainly used to solve the matching problem of multi-mode strings. It is a variant of the dictionary tree (trie tree). In the construction process of the AC automaton in the embodiment of the present application, the standard address library data set is first sorted out. Specifically, according to the published standard address data set, the data is sorted according to five levels: province, city, district (county), street (township), and community (village). The address of each level has a corresponding area code, which is saved as a csv file according to the given area code and address name.

[0088] The embodiment of the present application can organize the above five levels of addresses into an Excel table, which has 10 fields, namely the address name and area code of each level.

[0089] In the above, the addresses in Chinese characters are used as tree nodes, and the hierarchical relationship between the tree nodes of Chinese characters is determined according to the hierarchical relationship between the addresses. In the process of constructing the Chinese character tree structure, the provincial-level addresses are first used as the top-level tree nodes, and the address name and the corresponding area code are stored in the tree node information. Then, the city-level address under the provincial-level address is used as the next-level tree node, and the tree structure is obtained by analogy. In the process of constructing the Chinese character tree structure, the tree node is equivalent to the key, and the tree node information is equivalent to the value.

[0090] In some possible embodiments, in order to reduce unnecessary matching information, before using the Chinese character address in the address standard library as a tree node, redundant information is removed from the Chinese character address; illustratively, some suffix information in the address name is removed, such as removing Chinese characters such as province, city, and district.

[0091] Step 102, in the construction process of the AC automaton, the addresses in the pinyin form in the address standard library are used as tree nodes, and the level relationship between the pinyin tree nodes is determined according to the level relationship between the addresses to construct a pinyin tree structure;

[0092] During the construction of the AC automaton in the embodiment of the present application, a pinyin tree structure is also constructed simultaneously, so that addresses to be standardized with the same pronunciation but different characters can be matched. The construction method of the pinyin tree structure is similar to the construction method of the Chinese character tree structure, except that the tree node information in the pinyin tree structure is the address name in pinyin form and the corresponding area code.

[0093] In some possible embodiments, in order to reduce unnecessary matching information, before using the phonetic address in the address standard library as a tree node, the phonetic address is subjected to redundant information removal. For example, some suffix information in the address name is removed, such as removing the phonetic address of the province, city, district, etc.

[0094] Step 103, in response to the address standardization instruction, obtaining the address to be standardized input to the AC automaton;

[0095] After the initialization of the AC automaton is completed through the above process, the address to be standardized is input by the user, and in response to the address standardization instruction, the address to be standardized input to the AC automaton is obtained.

[0096] In some possible embodiments, the address to be standardized input by the user is in Chinese characters, and the embodiment of the present application will automatically convert the address to be standardized in Chinese characters into the address to be standardized in Pinyin.

[0097] Step 104, using the AC automaton to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and obtaining a standardized address according to the matching result.

[0098] The AC automaton-based address standardization method, device and equipment provided in the embodiments of the present application, during the AC automaton construction process, not only constructs a Chinese character tree structure, but also simultaneously constructs a pinyin tree structure, so that for address matching of homophonic but different input characters, the pinyin tree structure can be used to solve the standardization of addresses with homophonic but different input characters, and addresses can be standardized in a timely and effective manner using very few resources, thereby reducing errors caused by non-standard data; and problems related to address input typos, homophonic but different input characters, etc. can be solved very well.

[0099] This application combines the Chinese character tree structure and the pinyin tree structure for address matching. Based on the Chinese character tree structure and the pinyin tree structure, a multimodal matching algorithm is used for address matching. Any of the following methods can be used:

[0100] 1) When it is determined according to the search mode setting information that the search is set to be performed simultaneously, a multi-modal matching algorithm is simultaneously used to perform address matching in the Chinese character tree structure and the pinyin tree structure;

[0101] The user can set the search method through the UI interface, using multiple options, including simultaneous search, search by priority, or search a specified tree structure first.

[0102] If it is set to search simultaneously, a multi-modal matching algorithm is used to perform address matching in both the Chinese character tree structure and the pinyin tree structure. When a match is successful in either tree structure, the search in the other tree structure is terminated.

[0103] 2) According to the search mode setting information, when it is determined that the search is set to be performed according to the priority, based on the priority in the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used in the tree structure with a high priority to perform address matching. If the match is successful, the search ends; otherwise, a multi-modal matching algorithm is used in the tree structure with a low priority to perform address matching;

[0104] The user sets the priority of the Chinese character tree structure and the Pinyin tree structure through the UI interface, such as setting the Chinese character tree structure to high priority and the Pinyin tree structure to low priority, and of course, it can also be set in reverse. In the address matching process, according to the set priority, the tree structure with high priority is searched first, and if the match is successful, the tree structure with high priority is searched again.

[0105] 3) According to the search method setting information, when it is determined that the setting is to search the specified tree structure first, the tree structure is specified in the Chinese character tree structure and the pinyin tree structure, and the multimodal matching algorithm is used for address matching. If the match is successful, the process ends. Otherwise, the multimodal matching algorithm is used for address matching in another tree structure.

[0106] In the embodiment of the present application, the Chinese character tree structure can be set as the specified tree structure. When performing address matching, address matching is performed preferentially in the Chinese character tree structure. If the match is successful, the process ends. Otherwise, address matching is performed in the pinyin tree structure.

[0107] In order to process the to-be-standardized address with the abbreviated address into the corresponding standardized address, the embodiment of the present application further includes:

[0108] According to the complete address with abbreviation in the address standard library, determine the abbreviation to be omitted when the complete address in the address standard library is abstracted into the abbreviation;

[0109] Using the abbreviation as a newly added tree node, and adding the newly added tree node between the tree node of the complete address and the tree node of the previous level of the complete address;

[0110] When it is determined that there are multiple identical new nodes, the multiple identical new nodes are merged into one new node. The embodiment of the present application merges the nodes with the new node names, so that the upper-level nodes share the new nodes, and the lower-level nodes include more tree nodes. In this way, when encountering nodes with the same name, the original address information can be returned as much as possible.

[0111] For complete addresses with abbreviated addresses, the corresponding abbreviations need to be determined first. For example, addresses below a certain city level A include XX1 Development Zone, XX2 Development Zone, XX3 Development Zone, etc., and addresses below another city level B include YY1 Development Zone, YY2 Development Zone, etc. In actual use, they are generally abbreviated as XX1, XX2, XX3, YY1, YY2, so the corresponding omitted abbreviation is the development zone. Then city level A and city level B share a new tree node, which is the name of the development zone, and the subordinate nodes of the new tree node are XX1 Development Zone, XX2 Development Zone, XX3 Development Zone, YY1 Development Zone, and YY2 Development Zone. For example, for example, the addresses below a certain city level A include XX1 High-tech Zone, XX2 High-tech Zone, XX3 High-tech Zone, etc., and the addresses below another city level B include YY1 High-tech Zone, YY2 High-tech Zone, etc., which are generally abbreviated as XX1, XX2, XX3, YY1, YY2 in actual use, so the corresponding abbreviation is High-tech Zone. Then city level A and city level B share the newly added tree node, which is the name of the high-tech zone, and the subordinate nodes of the newly added tree node are XX1 High-tech Zone, XX2 High-tech Zone, XX3 High-tech Zone, YY1 High-tech Zone and YY2 High-tech Zone.

[0112] The above-mentioned method of adding tree nodes is applicable to the Chinese character tree structure and the pinyin tree structure.

[0113] In some possible embodiments, the multimodal matching algorithm in the embodiments of the present application includes any of the following:

[0114] 1) An accurate matching algorithm for matching the complete address to be standardized based on the Chinese character tree structure and the pinyin tree structure;

[0115] That is, the address to be standardized input by the user is a detailed address, and a multi-modal matching algorithm is used to perform address matching on the detailed address based on the Chinese character tree structure and the pinyin tree structure, and a standardized address is obtained according to the matching result.

[0116] 2) For some of the addresses to be standardized, a fuzzy matching algorithm is used to match the addresses based on the Chinese character tree structure and the pinyin tree structure;

[0117] In the fuzzy matching algorithm, only part of the address to be standardized is matched, which can be done by intercepting part of the address from back to front, or extracting keywords for fuzzy matching.

[0118] 3) When it is determined that there is an abbreviated address in the standardized address, an abbreviated matching algorithm for address matching is performed in the tree node range of the newly added node in the Chinese character tree structure and the pinyin tree structure.

[0119] If the standardized address contains an abbreviated address, the newly added node is directly located, and the abbreviated matching algorithm for address matching is performed in the tree node range below the newly added node. Specifically, it can be determined that the standardized address contains an abbreviated address according to the user's instructions.

[0120] The embodiment of the present application provides an address matching algorithm based on AC automaton, which uses AC automaton to match standard addresses, and combines Chinese character form with pinyin to quickly and accurately parse addresses into five-level standard address formats, and can effectively match problems such as different characters with the same pronunciation and address abbreviations. The multi-mode matching algorithm in the present application includes steps such as accurate address matching, fuzzy matching, pinyin matching, and abbreviation matching. Different matching methods are used to obtain candidate standard addresses. The address matching process applies the search for small addresses under the upper-level address range, and the standardized address is obtained according to the matching results to realize accurate small address derivation of upper-level addresses, etc., and can correct the lower-level erroneous address according to the large address, and infer the upper-level address with the small address. The method provided in the embodiment of the present application can be quickly deployed, and through k8s deployment, it can quickly expand applications to meet different service resources.

[0121] In some possible embodiments, when a multi-modal matching algorithm is used for address matching, any modal matching algorithm uses the following method to perform address matching:

[0122] For the address to be standardized in Chinese characters, when a new starting address is determined, the following address traversal is triggered:

[0123] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Chinese character tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0124] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. The search is triggered again. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0125] The new starting address is initially the first Chinese character of the address to be standardized.

[0126] In some possible embodiments, when a multi-modal matching algorithm is used for address matching, any modal matching algorithm uses the following method to perform address matching:

[0127] For the address to be standardized in pinyin format, when a new starting address is determined, the following address traversal is triggered:

[0128] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Pinyin tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Pinyin letter of the current address, otherwise the next Pinyin letter of the current address is determined as the new starting address to trigger the address traversal again;

[0129] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next pinyin letter of the current address. The search is triggered again. Otherwise, the next pinyin letter of the current address is determined as the new starting address to trigger the address traversal again.

[0130] The new starting address is initially the first pinyin letter of the address to be standardized.

[0131] In the embodiment of the present application, when searching in the Chinese character tree structure / pinyin tree structure, the AC vector machine is searched in order from left to right. When a valid result is matched, a list storing relevant address information will be returned. A secondary screening will be performed based on this list. For example, for the input address to be standardized, xin yang (Xinyang), when xin is searched, the returned pinyin has a node such as xing tai (Xingtai), but when the search continues, the next letter is yang, and it is obvious that tai is wrong and can be filtered out, which increases the accuracy and improves the matching speed. Then, the first-level return address information can be screened out according to the matched data, which can be temporarily recorded; then the matching position is moved, and according to the returned data, the length of the return result node can be easily pushed back to the string to be matched. When the returned result node is greater than 1, it means that there is a duplicate address in the address match, and the address can be repeated. Repeat the above steps until the address data matching is completed, or when there is only one address matching result, it is considered that the most detailed address is matched, and this result is recorded. Then continue the above steps until the string traversal is completed or the smallest village-level administrative level unit is matched.

[0132] In the process of address standardization, according to the above results, the matching addresses at all levels will be returned, and then relevant logical checks will be performed according to the codes of the matching addresses. For example, the first two digits of the code are the province, the first four digits are the city, the first six digits are the district (county), the first nine digits are the street (township), and the first 12 digits are the community (village). For example, the address to be inferred is Jinshuiyuan, Zhengzhou, and the street (township) code such as 410103016000 is finally obtained. It can be accurately inferred that it is Henan Province, Zhengzhou City, Erqi District, and Jinshuiyuan Street. In this way, the address can be accurately completed as Jinshuiyuan Street, Erqi District, Zhengzhou City, Henan Province.

[0133] The following is a detailed flow chart of the address standardization method based on AC automaton provided in the embodiment of the present application. Figure 2 As shown, it mainly includes:

[0134] Step 201, sorting standard addresses according to five levels: province, city, district (county), street (township), community (village), and obtaining a standard address database;

[0135] Step 202, remove redundant information from the addresses in the standard address library, use the addresses in Chinese characters as tree nodes, store the address name and area code in the tree node information, establish a hierarchical relationship between different tree nodes, add new nodes corresponding to the omitted abbreviations at the next level for complete addresses with abbreviations, and merge the new nodes with the same name to obtain a Chinese character tree structure;

[0136] Step 203, remove redundant information from the addresses in the standard address library, use the addresses in pinyin form as tree nodes, store the address name and area code in the tree node information, establish a hierarchical relationship between different tree nodes, and for complete addresses with abbreviations, add new nodes corresponding to the omitted abbreviations at the next level, and merge the new nodes with the same name to obtain a pinyin tree structure;

[0137] Step 204, in response to the address standardization instruction, obtaining the address to be standardized input to the AC automaton;

[0138] Step 205, performing address matching using a multi-modal algorithm of address exact matching, fuzzy matching, and abbreviation matching;

[0139] Step 206, in the process of address matching using any modal algorithm, determining to first search in the Chinese character tree structure according to the setting information;

[0140] Step 207, when the address is successfully matched in the Chinese character tree structure, the standardized address is output and the search ends, otherwise the search is performed in the pinyin tree structure;

[0141] Step 208, output the standardized address when the address is successfully matched in the pinyin tree structure, otherwise output a prompt message indicating that the address standardization recognition fails.

[0142] Based on the same inventive concept, the present application also provides an address standardization device 300 based on AC automaton, such as Figure 3 As shown, the device comprises:

[0143] A Chinese character tree construction module 301 is used to use the addresses in Chinese character form in the address standard library as tree nodes during the construction process of the AC automaton, determine the level relationship between the tree nodes of the Chinese characters according to the level relationship between the addresses, and construct a Chinese character tree structure;

[0144] The pinyin tree construction module 302 is used to use the pinyin addresses in the address standard library as tree nodes in the construction process of the AC automaton, determine the level relationship between the pinyin tree nodes according to the level relationship between the addresses, and construct the pinyin tree structure;

[0145] The to-be-standardized address acquisition module 303 is used to acquire the to-be-standardized address input to the AC automaton in response to the address standardization instruction;

[0146] The address standardization module 304 is used to use the AC automaton to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and obtain a standardized address according to the matching result.

[0147] In some possible embodiments, the Chinese character tree construction module / Pinyin tree construction module is further used in the process of constructing the Chinese character tree structure / Pinyin tree structure:

[0148] According to the complete address with abbreviation in the address standard library, determine the abbreviation to be omitted when the complete address in the address standard library is abstracted into the abbreviation;

[0149] Using the abbreviation as a newly added tree node, and adding the newly added tree node between the tree node of the complete address and the tree node of the previous level of the complete address;

[0150] When it is determined that there are multiple identical newly added nodes, the multiple identical newly added nodes are merged into one newly added node.

[0151] In some possible embodiments, the multimodal matching algorithm includes any of the following:

[0152] An accurate matching algorithm for matching the complete address to be standardized based on the Chinese character tree structure and the pinyin tree structure;

[0153] For some of the addresses to be standardized, a fuzzy matching algorithm is used to match the addresses based on the Chinese character tree structure and the pinyin tree structure;

[0154] When it is determined that there is an abbreviated address in the standardized address, an abbreviated matching algorithm for address matching is performed in the tree node range of the newly added node in the Chinese character tree structure and the pinyin tree structure.

[0155] In some possible embodiments, when the address standardization module uses a multi-modal matching algorithm to perform address matching, any modal matching algorithm uses the following method to perform address matching:

[0156] For the address to be standardized in Chinese characters, when a new starting address is determined, the following address traversal is triggered:

[0157] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Chinese character tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0158] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. The search is triggered again. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again.

[0159] The new starting address is initially the first Chinese character of the address to be standardized.

[0160] In some possible embodiments, when the address standardization module uses a multi-modal matching algorithm to perform address matching, any modal matching algorithm uses the following method to perform address matching:

[0161] For the address to be standardized in pinyin format, when a new starting address is determined, the following address traversal is triggered:

[0162] The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Pinyin tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Pinyin letter of the current address, otherwise the next Pinyin letter of the current address is determined as the new starting address to trigger the address traversal again;

[0163] When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next pinyin letter of the current address. The search is triggered again. Otherwise, the next pinyin letter of the current address is determined as the new starting address to trigger the address traversal again.

[0164] The new starting address is initially the first pinyin letter of the address to be standardized.

[0165] In some possible embodiments, the address standardization module uses a multimodal matching algorithm to perform address matching based on the Chinese character tree structure and the pinyin tree structure, including any of the following steps:

[0166] When it is determined according to the search mode setting information that the simultaneous search is set, a multi-modal matching algorithm is simultaneously used to perform address matching in the Chinese character tree structure and the pinyin tree structure;

[0167] According to the search mode setting information, when it is determined that the search is set to be performed according to the priority, based on the priority in the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used in the tree structure with a high priority to perform address matching. If the match is successful, the process ends; otherwise, a multi-modal matching algorithm is used in the tree structure with a low priority to perform address matching;

[0168] According to the search method setting information, when it is determined that the setting is to search the specified tree structure first, the tree structure is specified in the Chinese character tree structure and the pinyin tree structure, and a multimodal matching algorithm is used for address matching. If the match is successful, the process ends, otherwise a multimodal matching algorithm is used in another tree structure for address matching.

[0169] In some possible embodiments, the Chinese character tree construction module / Pinyin tree construction module is further used to perform at least one of the following steps:

[0170] Before using the address in Chinese character form in the address standard library as a tree node, removing redundant information from the address in Chinese character form;

[0171] Before using the pinyin address in the address standard library as a tree node, redundant information is removed from the pinyin address.

[0172] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0173] In some possible implementations, the electronic device according to the present application may include at least one processor and at least one memory. The memory stores program code, and when the program code is executed by the processor, the processor executes the steps in the search method for monitoring nodes according to various exemplary implementations of the present application described above in this specification. For example, the processor may execute the steps in the search method for monitoring nodes.

[0174] Refer to the following Figure 4 The AC automaton-based address standardization device 140 according to this embodiment of the present application is described. Figure 4 The displayed AC automaton-based address standardization device 140 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0175] like Figure 4 As shown, the AC automaton-based address standardization device 140 is presented in the form of a general electronic device. The components of the AC automaton-based address standardization device 140 may include but are not limited to: at least one processor 141, at least one memory 142, and a bus 143 connecting different system components (including the memory 142 and the processor 141).

[0176] Bus 143 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0177] The memory 142 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 1421 and / or a cache memory 1422 , and may further include a read-only memory (ROM) 1423 .

[0178] Memory 142 may also include a program / utility 1425 having a set (at least one) of program modules 1424, such program modules 1424 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.

[0179] The AC automaton-based address standardization device 140 may also communicate with one or more external devices 144 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the AC automaton-based address standardization device 140, and / or may communicate with any device that enables the AC automaton-based address standardization device 140 to communicate with one or more other electronic devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 145. Furthermore, the AC automaton-based address standardization device 140 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 146. As shown, the network adapter 146 communicates with other modules of the AC automaton-based address standardization device 140 via a bus 143. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the AC automaton-based address standardization device 140, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0180] In some possible implementations, various aspects of an AC automaton-based address standardization method provided by the present application may also be implemented in the form of a program product, which includes program code. When the program product is run on a computer device, the program code is used to enable the computer device to execute the steps of an AC automaton-based address standardization method according to various exemplary implementations of the present application described above in this specification.

[0181] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access 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.

[0182] The program product for monitoring of the embodiment of the present application can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on an electronic device. However, the program product of the present application is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, an apparatus or a device or used in combination with it.

[0183] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0184] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0185] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user electronic device, partially on the user device, as an independent software package, partially on the user electronic device and partially on the remote electronic device, or entirely on the remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, using an Internet service provider to connect through the Internet).

[0186] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0187] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0188] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0189] The present application is described with reference to the flowcharts and block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and block diagram, as well as the combination of the processes and boxes in the flowchart and block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and block diagram. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0190] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 Process or multiple processes and boxes Figure 1 A function specified in one or more boxes.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 Process or multiple processes and boxes Figure 1 The steps for the functions specified in one or more boxes.

[0192] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0193] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An address standardization method based on AC automaton, characterized in that: The method comprises: In the construction process of AC automaton, the addresses in Chinese character form in the address standard library are used as tree nodes, and the level relationship between the tree nodes of Chinese characters is determined according to the level relationship between the addresses to construct the Chinese character tree structure; In the construction process of AC automaton, the addresses in the pinyin form in the address standard library are used as tree nodes, and the level relationship between the pinyin tree nodes is determined according to the level relationship between the addresses to construct the pinyin tree structure; In response to an address standardization instruction, obtaining an address to be standardized input to the AC automaton; The AC automaton is used to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and a standardized address is obtained according to the matching result.

2. The method according to claim 1, characterized in that The process of constructing the Chinese character tree structure / pinyin tree structure also includes: According to the complete address with abbreviation in the address standard library, determine the abbreviation to be omitted when the complete address in the address standard library is abstracted into the abbreviation; Using the abbreviation as a newly added tree node, and adding the newly added tree node between the tree node of the complete address and the tree node of the previous level of the complete address; When it is determined that there are multiple identical newly added nodes, the multiple identical newly added nodes are merged into one newly added node.

3. The method according to claim 1 or 2, characterized in that: The multimodal matching algorithm includes any of the following: An accurate matching algorithm for matching the complete address to be standardized based on the Chinese character tree structure and the pinyin tree structure; For some of the addresses to be standardized, a fuzzy matching algorithm is used to match the addresses based on the Chinese character tree structure and the pinyin tree structure; When it is determined that there is an abbreviated address in the standardized address, an abbreviated matching algorithm for address matching is performed in the tree node range of the newly added node in the Chinese character tree structure and the pinyin tree structure.

4. The method according to claim 1 or 2, characterized in that: When a multi-modal matching algorithm is used for address matching, any of the matching algorithms of the mode uses the following method to match the address: For the address to be standardized in Chinese characters, when a new starting address is determined, the following address traversal is triggered: The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Chinese character tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again. When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next Chinese character at the current address. The search is triggered again. Otherwise, the next Chinese character at the current address is determined as the new starting address to trigger the address traversal again. The new starting address is initially the first Chinese character of the address to be standardized.

5. The method according to claim 1 or 2, characterized in that: When a multi-modal matching algorithm is used for address matching, any of the matching algorithms of the mode uses the following method to match the address: For the address to be standardized in pinyin format, when a new starting address is determined, the following address traversal is triggered: The new starting address is used as the current address, and the search is traversed from the upper level to the lower level in the Pinyin tree structure. When a matching target tree node is found, the current search range is updated using all the tree nodes below the target tree node, and the current address is updated using the next Pinyin letter of the current address, otherwise the next Pinyin letter of the current address is determined as the new starting address to trigger the address traversal again; When it is determined that the current address is updated, the search is triggered: the search is traversed within the current search range. When a matching target tree node is found, the current search range is updated using all tree nodes below the target tree node, and the current address is updated using the next pinyin letter of the current address. The search is triggered again. Otherwise, the next pinyin letter of the current address is determined as the new starting address to trigger the address traversal again. The new starting address is initially the first pinyin letter of the address to be standardized.

6. The method according to claim 1 or 2, characterized in that: Based on the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used to perform address matching, including any of the following steps: When it is determined according to the search mode setting information that the simultaneous search is set, a multi-modal matching algorithm is simultaneously used to perform address matching in the Chinese character tree structure and the pinyin tree structure; According to the search mode setting information, when it is determined that the search is set to be performed according to the priority, based on the priority in the Chinese character tree structure and the pinyin tree structure, a multi-modal matching algorithm is used in the tree structure with a high priority to perform address matching. If the match is successful, the process ends; otherwise, a multi-modal matching algorithm is used in the tree structure with a low priority to perform address matching; According to the search method setting information, when it is determined that the setting is to search the specified tree structure first, the tree structure is specified in the Chinese character tree structure and the pinyin tree structure, and a multimodal matching algorithm is used for address matching. If the match is successful, the process ends, otherwise a multimodal matching algorithm is used in another tree structure for address matching.

7. The method according to claim 1, characterized in that It also includes at least one of the following steps: Before using the address in Chinese character form in the address standard library as a tree node, removing redundant information from the address in Chinese character form; Before using the pinyin address in the address standard library as a tree node, redundant information is removed from the pinyin address.

8. An address standardization device based on AC automaton, characterized in that: The device comprises: A Chinese character tree construction module is used to use the addresses in Chinese character form in the address standard library as tree nodes during the construction process of the AC automaton, determine the level relationship between the tree nodes of Chinese characters according to the level relationship between the addresses, and construct a Chinese character tree structure; The pinyin tree construction module is used to use the pinyin addresses in the address standard library as tree nodes in the construction process of the AC automaton, determine the level relationship between the pinyin tree nodes according to the level relationship between the addresses, and construct the pinyin tree structure; A module for acquiring an address to be standardized, for acquiring an address to be standardized input to the AC automaton in response to an address standardization instruction; The address standardization module is used to use the AC automaton to perform address matching on the address to be standardized based on the Chinese character tree structure and the pinyin tree structure using a multi-modal matching algorithm, and obtain a standardized address according to the matching result.

9. An address standardization device based on AC automaton, characterized in that: It comprises at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and the computer program is used to enable a computer to execute the method according to any one of claims 1 to 7.

Images