Geographical Name and Address Translation System and Matching Method Based on Artificial Intelligence and Specialized and General Name Databases

Abstract

This application relates to the technical field of place name and address translation. Specifically, it discloses a place name and address translation system and matching method based on artificial intelligence and a special and common name database. It extracts multiple candidate geographical entity information descriptions from a geographical entity information database based on the place name and address text to be translated input by the user, and uses natural language processing technology to perform in-depth context semantic interaction matching analysis between the place name and address text to be translated and each candidate geographical entity information description. Based on the standard place name and address description of the matched candidate geographical entity, combined with the translation knowledge in the special and common name database, it performs target language translation matching and normalization processing on the standard place name and address description to generate the final target language translated place name and address. By using the geographical entity information database to assist in identifying fuzzy or non-standard place names and addresses input by the user, this application helps to provide reliable geographical entity anchoring for the translation process and improve the accuracy and consistency of translation.

Description

Technical Field

[0001] The present application relates to the technical field of place name and address translation, and more specifically, to a place name and address translation system and matching method based on artificial intelligence and a dedicated name database. Background Art

[0002] With the acceleration of globalization and the increasing frequency of international communication, the demand for accurate and efficient cross-language information communication has increased significantly. In the field of geographic information, place names and addresses, as key carriers for describing specific geographic locations, play a vital role in cross-border trade, international logistics, tourist navigation, multilingual map services, and geographic information system (GIS) applications.

[0003] Traditional translation methods often rely on general dictionaries or simple transliteration rules, making them difficult to cope with the complex structures and cultural differences unique to place names and addresses, and easily leading to semantic deviations or information loss. For example, the place names and addresses to be translated that users input often come in a variety of forms, including abbreviations, aliases, colloquial names, historical names, and even spelling errors or non-standard expressions. Consequently, literal translation based directly on general translation models or dictionary matching often fails to capture the uniqueness of place names and addresses as specific geographic entities and their standardized expression in the target language. This can easily lead to translation errors, ambiguities, and even loss of geographic reference meaning, seriously affecting the accurate transmission and efficient application of cross-language geographic information.

[0004] Therefore, it is necessary to provide an optimized place name and address translation system and matching method based on artificial intelligence and a dedicated name database to solve the above technical problems. Summary of the Invention

[0005] In order to solve the above technical problems, this application is proposed.

[0006] According to one aspect of the present application, a place name and address translation and matching method based on artificial intelligence and a dedicated name database is provided, which includes:

[0007] Get the place name and address text to be translated and the specified target translation language entered by the user;

[0008] Building a geographic entity information database, and extracting a plurality of candidate geographic entity information descriptions from the geographic entity information database based on the place name and address text to be translated;

[0009] Matching and analyzing the multiple candidate geographic entity information descriptions with the place name and address text to be translated to obtain multiple candidate geographic entity confidence scores;

[0010] Extracting the standard place name and address description in the candidate geographic entity information description corresponding to the maximum value from the plurality of candidate geographic entity confidence scores as the best matching standard place name and address description;

[0011] Perform word segmentation and named entity recognition annotation on the optimal matching standard place name and address description to obtain a sequence of component-annotated place name and address word segments to be translated;

[0012] Based on the target translation language, use the proper noun library and common noun library to perform translation matching on the sequence of component-annotated place name and address word segments to be translated to obtain the target language translated place name and address.

[0013] According to another aspect of the present application, a place name and address translation system based on artificial intelligence and proper / common noun libraries is provided, which includes:

[0014] A user input module for obtaining the place name and address text to be translated input by the user and the specified target translation language;

[0015] A geographical entity information extraction module for constructing a geographical entity information library and extracting multiple candidate geographical entity information descriptions from the geographical entity information library based on the place name and address text to be translated;

[0016] A matching analysis module for respectively performing matching analysis on the multiple candidate geographical entity information descriptions and the place name and address text to be translated to obtain multiple candidate geographical entity confidence scores;

[0017] An optimal matching selection module for extracting the standard place name and address description in the candidate geographical entity information description corresponding to the maximum value from the multiple candidate geographical entity confidence scores as the optimal matching standard place name and address description;

[0018] A place name and address annotation module for performing word segmentation and named entity recognition annotation on the optimal matching standard place name and address description to obtain a sequence of component-annotated place name and address word segments to be translated;

[0019] A place name and address translation matching module for performing translation matching on the sequence of component-annotated place name and address word segments to be translated based on the target translation language, using the proper noun library and common noun library to obtain the target language translated place name and address.

[0020] Beneficial effects: Compared with the prior art, the place name and address translation system and matching method based on artificial intelligence and a specialized and common name library provided by this application extracts multiple candidate geographical entity information descriptions from a geographical entity information library based on the place name and address text to be translated input by the user, and uses natural language processing technology to perform in-depth context semantic interaction matching analysis between the place name and address text to be translated and each candidate geographical entity information description to determine the candidate geographical entity that best matches the user's input intention. Furthermore, based on the standard place name and address description of the matched candidate geographical entity, combined with the translation knowledge in the specialized and common name library, target language translation matching and normalization processing are performed on the standard place name and address description to generate the final target language translated place name and address. This method helps to provide a reliable geographical entity anchor for the translation process by using the geographical entity information library to assist in identifying fuzzy or non-standard place names and addresses input by the user, improving the accuracy and consistency of translation. Brief Description of the Drawings

[0021] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0022] Figure 1 It is a flowchart of the place name and address translation matching method based on artificial intelligence and a specialized and common name library according to an embodiment of the present application.

[0023] Figure 2 It is a data flow diagram of the place name and address translation matching method based on artificial intelligence and a specialized and common name library according to an embodiment of the present application.

[0024] Figure 3 It is a flowchart of sub-step S3 of the place name and address translation matching method based on artificial intelligence and a specialized and common name library according to an embodiment of the present application.

[0025] Figure 4 It is a flowchart of sub-step S32 of the place name and address translation matching method based on artificial intelligence and a specialized and common name library according to an embodiment of the present application.

[0026] Figure 5 It is a block diagram of the place name and address translation system based on artificial intelligence and a specialized and common name library according to an embodiment of the present application. Detailed Description of the Embodiments

[0027] As shown in this application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] Although this application makes various references to certain modules in the system according to the embodiments of this application, however, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0029] Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the previous or following operations are not necessarily executed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0030] Next, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the exemplary embodiments described here.

[0031] It should be noted in advance that all relevant processing of the data in this application is carried out on the premise of complying with the corresponding data protection regulations and policies of the place where it is located and obtaining authorization from the corresponding authority manager.

[0032] Figure 1 It is a flowchart of a method for translating and matching geographical names and addresses based on artificial intelligence and a specialized common name library according to an embodiment of this application. Figure 2 It is a data flow diagram of a method for translating and matching geographical names and addresses based on artificial intelligence and a specialized common name library according to an embodiment of this application. As Figure 1 and Figure 2As shown in the figure, the above-mentioned method for translating and matching place names and addresses based on artificial intelligence and a specialized and common name library includes the following steps: S1, obtaining the text of the place name and address to be translated input by the user and the specified target translation language; S2, constructing a geographical entity information library, and based on the text of the place name and address to be translated, extracting multiple candidate geographical entity information descriptions from the geographical entity information library; S3, respectively matching and analyzing the multiple candidate geographical entity information descriptions with the text of the place name and address to be translated to obtain multiple candidate geographical entity confidence scores; S4, extracting the standard place name and address description in the candidate geographical entity information description corresponding to the maximum value from the multiple candidate geographical entity confidence scores as the optimal matching standard place name and address description; S5, performing word segmentation and named entity recognition and annotation on the optimal matching standard place name and address description to obtain a sequence of word segments of the place name and address to be translated with component annotations; S6, based on the target translation language, using the specialized name library and the common name library to perform translation matching on the sequence of word segments of the place name and address to be translated with component annotations to obtain the target language translated place name and address.

[0033] In the above-mentioned method for translating and matching place names and addresses based on artificial intelligence and a specialized and common name library, in step S1, the text of the place name and address to be translated input by the user and the specified target translation language are obtained. It should be understood that the core goal of place name and address translation is to meet the cross-language expression needs of users for specific geographical entities, and there are significant differences in the naming rules of geographical entities in different language systems. Therefore, in order to ensure the directivity and controllability of the translation process, based on the design of the user interaction interface, this application receives the text to be translated and the target language parameters submitted by the user through the front-end input module or API interface, and uses them as the initial input for subsequent processing. Specifically, the user can provide the original place name and address through form input or file upload, and select the target language (such as English), so as to provide clear boundary conditions for subsequent semantic parsing and translation processing.

[0034] In the specific implementation process, the user usually submits the text of the place name and address to be translated to the system through a graphical interface or a program interface. For example, in application scenarios such as map services, logistics scheduling, or multilingual GIS systems, the user may manually enter the name of a specific location, such as "No. 1, Zhongguancun Street, Haidian District, Beijing", or upload a file containing multiple address entries in batches for centralized cross-language conversion. At the same time, the user also needs to clearly specify the target translation language, such as English, French, Spanish, etc., so that the system can perform differential processing according to the selected language rules. In order to meet the requirements in different usage scenarios, the system needs to support multiple input forms, including but not limited to single-line text box input, multi-line text editor, file upload control, etc., and at the same time be compatible with the import methods of multiple data formats such as JSON, CSV, XML, etc. This flexibility not only improves the applicability of the system but also provides a good foundation for subsequent automated processing.

[0035] At the interface level, the system usually exposes the place name and address translation service externally in the form of an API (Application Programming Interface), allowing third-party platforms or internal modules to call. For example, an international logistics company may integrate this translation module into its order processing system. When a user fills in the shipping or receiving address, the system automatically converts the Chinese address into the target language version for generating international shipping labels or customer notification emails. In this case, the user input does not directly come from the keyboard operation of the end user, but is transmitted by other system modules through standard protocols. Therefore, the system must have reliable parameter parsing capabilities to identify and extract the address fields and language identifiers therein. Specifically, the API interface should support GET or POST request methods, accept a request body containing the original address text and the target language code, and return a structured response result, reserving a unified data interface for subsequent processing.

[0036] In addition to the traditional text input method, modern place name and address translation systems are gradually introducing emerging technologies such as speech recognition and image OCR (Optical Character Recognition) as supplementary input means. For example, users can take pictures of envelopes, signs or map screenshots containing foreign addresses with a mobile device. The system uses OCR technology to extract the text content in the image and processes it as the text to be translated. In addition, for some special groups or specific usage environments, the system also supports voice input functions. Users can quickly enter address information through natural language instructions, and the system converts the audio stream into text form through a speech recognition engine. Although these diverse input channels increase the complexity of system implementation, they also significantly improve the user experience and usage efficiency, enabling the place name and address translation service to cover more diverse usage scenarios.

[0037] In terms of specifying language parameters, the ways for the system to support users to select the target translation language are also diverse. A common way is to let users select from a preset language list through a drop-down menu or tab, and each language corresponds to a standardized language code (such as en for English, es for Spanish, ja for Japanese, etc.). Another way is through an intelligent recommendation mechanism that automatically infers the target language based on the user's geographical location, browser settings or historical preferences, thereby reducing the user's operation burden. For example, if the user is currently located in Germany and the browser language setting is German, the system can default the translation target to German unless the user actively changes this setting. This intelligent language selection strategy helps to improve the friendliness and adaptability of the system, especially suitable for map services or travel navigation applications open to the public.

[0038] It should be noted that due to the fact that place names often carry specific cultural backgrounds and naming conventions, there are significant differences in the ways of expressing place names between different language systems. For example, Chinese place names are usually arranged in a hierarchical structure of "Province - City - District - Street", while English place names tend to follow the order of "Street, City, State, Country", and commas are often used to separate the components. In addition, in the composition of place names in some regions, directional words (such as North, South), administrative division types (such as County, Province), or official naming signs (such as Saint, Mount) are incorporated, and these details need to be preserved or appropriately adjusted during the translation process. Therefore, when the system receives user input, it not only needs to identify the semantic content of the address itself but also record its original language attribute for reference to the corresponding grammar rules and naming norms in the subsequent translation process.

[0039] To ensure the integrity and accuracy of the input information, the system also needs to have a certain fault tolerance mechanism and data verification ability. For example, when the content entered by the user contains spelling mistakes, abbreviated forms, or non-standard expressions, the system should be able to identify potential problems through the built-in error correction module or fuzzy matching algorithm and prompt the user for confirmation or correction. In addition, for situations where the address text is too long, the format is not standardized, or it contains illegal characters, the system should also provide a corresponding feedback mechanism to prevent subsequent processing failures due to abnormal input. Although this data preprocessing ability does not fall within the core scope of this step, it is an important support for ensuring the stability of the overall system.

[0040] In the above-mentioned method for translating and matching place names and addresses based on artificial intelligence and a specialized common name database, in step S2, a geographic entity information database is constructed, and based on the text of the place name and address to be translated, multiple candidate geographic entity information descriptions are extracted from the geographic entity information database. It should be understood that in this application, it is considered that the text of the place name and address to be translated input by the user may adopt a non-standard format, contain abbreviations, aliases, common names, or even be incorrect, and there are differences from the standard geographic entity descriptions, resulting in easy translation errors, ambiguities, or even loss of geographical reference meaning when directly performing literal translation. Therefore, in order to accurately identify the potential standard geographic entities that the user input text may point to, this application constructs a geographic entity information database containing a large amount of standardized data of geographic entities, and based on the search and matching technology of the text of the place name and address to be translated, retrieves and extracts multiple candidate geographic entity information descriptions related to the input text from this geographic entity information database, providing an initial candidate set for subsequent geographic entity anchoring. Specifically, the geographic entity information database pre-stores detailed data of geographic entities in a specific area, including their standard place name and address descriptions, entity types (such as provinces, cities, districts, streets, buildings, scenic spots, etc.), administrative division information (such as subordination relationships), geographic coordinates, various aliases, common names, former names, and associated entity descriptions (information of surrounding or superior associated entities); after receiving the text of the place name and address to be translated input by the user, using a retrieval algorithm based on word vector similarity, perform retrieval and matching based on partial keywords on the text of the place name and address to be translated and each candidate geographic entity information description in the geographic entity information database, and retrieve multiple candidate geographic entity information descriptions potentially related to the text of the place name and address to be translated as the candidate set. Through this method, it is possible to effectively handle the ambiguity and non-standard expressions of the user input. Even if the user inputs a non-standard or fuzzy place name and address, the closest standard place name and address description can be found through matching with the geographic entity information database, providing an accurate geographic entity basis for subsequent translation.

[0041] In the above-mentioned method for matching and translating geographical names and addresses based on artificial intelligence and a specialized common name database, in step S3, the multiple candidate geographical entity information descriptions are respectively matched and analyzed with the geographical name and address text to be translated to obtain multiple candidate geographical entity confidence scores. Specifically, since the traditional literal matching method cannot distinguish the semantic differences between "Chaoyangmen" as a geographical name and "Chaoyang District" as an administrative region in "South Street of Chaoyangmen", and it is difficult to handle spelling mistakes (such as "Hu" misspelled as "Hu"). Therefore, in order to more accurately determine the specific geographical entity pointed to by the geographical name and address to be translated entered by the user, the present application further introduces the ability of deep semantic understanding. By respectively performing in-depth semantic understanding and interactive analysis of the context of each candidate geographical entity information description and the geographical name and address text to be translated, the semantic association strength between each candidate entity and the geographical name and address text to be translated is quantified, thereby breaking through the limitation of surface character similarity and achieving accurate matching based on deep semantics. Among them, Figure 3 is a flowchart of sub-step S3 of the method for matching and translating geographical names and addresses based on artificial intelligence and a specialized common name database according to an embodiment of the present application. As Figure 3 shown, step S3 includes the steps: S31, respectively extracting the context semantic features of the candidate geographical entity information description and the geographical name and address text to be translated to obtain a candidate geographical entity information description context semantic coding vector and a geographical name and address context semantic coding vector to be translated; S32, performing semantic transfer inference interactive coding on the geographical name and address context semantic coding vector to be translated and the candidate geographical entity information description context semantic coding vector to obtain a geographical name and address - candidate geographical entity semantic interaction response inference coding vector; S33, performing feature decoding on the geographical name and address - candidate geographical entity semantic interaction response inference coding vector to obtain the candidate geographical entity confidence score.

[0042] Specifically, in a specific example of the present application, the step S31 includes: performing context semantic encoding based on the BERT model on the candidate geographical entity information description and the to-be-translated place name address text respectively to obtain the candidate geographical entity information description context semantic encoding vector and the to-be-translated place name address context semantic encoding vector. Specifically, in order to effectively identify the semantic equivalence between non-standard expressions input by the user (such as the semantic equivalence between "Jingshi Nine Gates" and the standard name "Nine Gates of the Inner City of Beijing") and implicit context associations (such as "bridge" may refer to a bridge entity or a regional name in different contexts), the present application, based on the context awareness ability of the pre-trained language model, through the bidirectional Transformer architecture of the BERT model, performs context semantic encoding on the candidate geographical entity information description and the to-be-translated place name address text respectively. By using the deep semantic understanding ability obtained by the BERT model through pre-training on a large-scale corpus, after performing word segmentation and word embedding processing on the candidate geographical entity information description and the to-be-translated place name address text respectively, the context semantic features at the word level and sentence level in the text are extracted through a multi-layer self-attention mechanism, and the deep semantic information and context relevance of the text are mined, so as to generate a high-dimensional context semantic vector representation, and obtain the candidate geographical entity information description context semantic encoding vector and the to-be-translated place name address context semantic encoding vector. In this way, the candidate geographical entity information description and the to-be-translated place name address text can be mapped to a unified semantic space, laying a foundation for subsequent fine-grained semantic interaction matching.

[0043] Specifically, in step S32, semantic transfer inference interaction encoding is performed on the context semantic encoding vector of the to-be-translated place name and address text and the context semantic encoding vector of the candidate geographical entity information description to obtain a to-be-translated place name and address - candidate geographical entity semantic interaction response inference encoding vector. It should be understood that this application takes into account that simple vector cosine similarity calculation can only capture the similarity between the candidate geographical entity information description and the to-be-translated place name and address text at the global macro semantic level, and it is difficult to reveal the deep interaction relationship between the two in terms of micro semantic details and context association (for example, it is difficult to handle the high similarity between "Huangpu River" and "Huangpu District" in some feature dimensions). Therefore, in order to more accurately measure the semantic fit between the candidate geographical entity and the to-be-translated place name and address, this application introduces a neural network model to perform semantic transfer inference interaction modeling on the context semantic encoding vector of the to-be-translated place name and address text and the context semantic encoding vector of the candidate geographical entity information description, so as to deeply explore the deep interaction relationship between the candidate geographical entity and the to-be-translated place name and address in terms of micro semantic details and context association. By continuously aggregating and updating the feature responses of the two in terms of micro semantic details, a more accurate to-be-translated place name and address - candidate geographical entity semantic interaction response inference encoding vector is generated, providing a more accurate semantic basis for the subsequent calculation of the candidate geographical entity confidence score. Among them, Figure 4 is a flowchart of sub-step S32 of the place name and address translation matching method based on artificial intelligence and the specialized and common name library according to an embodiment of the present application. As Figure 4 shown, step S32 includes the steps of: S321, performing local fine-grained semantic interaction response encoding on the context semantic encoding vector of the to-be-translated place name and address text and the context semantic encoding vector of the candidate geographical entity information description to obtain a sequence of to-be-translated place name and address - candidate geographical entity local semantic interaction response encoding matrices; S322, performing local semantic interaction feature inference transfer encoding on the sequence of to-be-translated place name and address - candidate geographical entity local semantic interaction response encoding matrices to obtain the to-be-translated place name and address - candidate geographical entity semantic interaction response inference encoding vector.

[0044] More specifically, step S321 includes: First, performing an ordered arrangement based on the eigenvalue size on the context semantic encoding vector of the to-be-translated place name and address text and the context semantic encoding vector of the candidate geographical entity information description to obtain an ordered encoding vector of the to-be-translated place name semantic features and an ordered encoding vector of the candidate geographical entity semantic features, which is represented by the formula:

[0045] ;

[0046] ;

[0047] Among them, Represents the context semantic encoding vector of the text of the place name and address to be translated, Represents the context semantic encoding vector of the description of the candidate geographical entity information, Represents the operation of sorting the vector elements, Represents the ordered arrangement encoding vector of the semantic features of the place name and address to be translated, Represents the ordered arrangement encoding vector of the semantic features of the candidate geographical entity.

[0048] Through the ordered arrangement, the attention is focused on the distribution pattern and relative intensity of the feature values, rather than the initial position of the features, so that the model obtains invariance or equivariance to the input arrangement, making the context semantic encoding vectors of the place name and address text to be translated from different sources and the context semantic encoding vectors of the candidate geographical entity information description have a more consistent representation form in the feature space, generating the ordered arrangement encoding vectors of the semantic features of the place name and address to be translated and the ordered arrangement encoding vectors of the semantic features of the candidate geographical entity, thereby significantly improving the stability of semantic matching, highlighting the importance of key semantic features, suppressing the interference of noise features, and further improving the calculation accuracy of the confidence score of the candidate geographical entity.

[0049] Then, perform equal-grained feature segmentation on the ordered arrangement encoding vector of the semantic features of the place name and address to be translated and the ordered arrangement encoding vector of the semantic features of the candidate geographical entity to obtain a sequence of ordered encoding vectors of the local semantic features of the place name and address to be translated and a sequence of ordered encoding vectors of the local semantic features of the candidate geographical entity, which is expressed by the formula:

[0050] ;

[0051] ;

[0052] Among them, , , and respectively represent the first, second, and th, and th ordered encoding vectors of the local semantic features of the place name and address to be translated in the sequence of ordered encoding vectors of the local semantic features of the place name and address to be translated, is the number of ordered encoding vectors of the local semantic features of the place name and address to be translated, , , and respectively represent the first, second, and th, and th ordered encoding vectors of the local semantic features of the candidate geographical entity in the sequence of ordered encoding vectors of the local semantic features of the candidate geographical entity, Represents a feature segmentation function.

[0053] It should be understood that there may be differences in the detailed expressions of the ordered encoding vectors of the semantic features of the to-be-translated place names and addresses from different sources and the ordered encoding vectors of the semantic features of the candidate geographical entities. Directly performing an overall match is likely to overlook local semantic details, while equal-grained segmentation can decompose complex semantics into comparable basic units to facilitate capturing more detailed semantic correspondence relationships. Therefore, in this application, the ordered encoding vectors of the semantic features of the to-be-translated place names and addresses and the ordered encoding vectors of the semantic features of the candidate geographical entities are decomposed into sequences of ordered encoding vectors of local semantic features of the to-be-translated place names and addresses with equal grains and sequences of ordered encoding vectors of local semantic features of the candidate geographical entities, so as to more accurately locate the semantic association points between the to-be-translated text and the candidate geographical entities. Even in the case of abbreviations, aliases, or spelling mistakes, potential correct correspondence relationships can be identified through local matching, thereby significantly improving the accuracy of semantic matching and optimizing the usage efficiency of computing resources while ensuring the accuracy of semantic analysis.

[0054] Finally, each pair of corresponding ordered encoding vectors of local semantic features of the to-be-translated place names and addresses and ordered encoding vectors of local semantic features of the candidate geographical entities in the sequences of ordered encoding vectors of local semantic features of the to-be-translated place names and addresses and the sequences of ordered encoding vectors of local semantic features of the candidate geographical entities are input into the semantic interaction response inference unit to obtain a sequence of to-be-translated place name - candidate geographical entity local semantic interaction response encoding matrices, which is represented by the formula:

[0055] ;

[0056] Where, Represents a linear transformation matrix, Represents the ReLU activation function, Represents matrix multiplication, Represents And The to-be-translated place name - candidate geographical entity local semantic interaction response encoding matrix between.

[0057] Since the semantic matching between the to-be-translated place name address and the candidate geographical entity involves various complex semantic relationships, such as similarity, difference, alignment relationship, etc., therefore, in this application, the local semantic feature ordered encoding vectors of the to-be-translated place name address and the local semantic feature ordered encoding vectors of the candidate geographical entity are input into the semantic interaction response inference unit to quantify and encode the semantic interaction patterns between the local semantic feature ordered encoding vectors of the to-be-translated place name address and the local semantic feature ordered encoding vectors of the candidate geographical entity within a specific feature value range, and generate a sequence of to-be-translated place name address - candidate geographical entity local semantic interaction response encoding matrices, so as to more accurately describe the semantic association therebetween and provide a more reliable semantic basis for the subsequent calculation of the matching confidence score.

[0058] More specifically, in a specific example of this application, the step S322 includes: inputting the sequence of the to-be-translated place name address - candidate geographical entity local semantic interaction response encoding matrices into the LSTM transfer encoding module with an attention mechanism to obtain the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector, which is represented by the formula:

[0059] ;

[0060] ;

[0061] ;

[0062] Where represents the matrix flattening operation, represents the to-be-translated place name address - candidate geographical entity local semantic interaction response encoding vector obtained by expanding represents the exponential function operation with base e, is the feature modulation function based on the attention mechanism, represents and the to-be-translated place name address - candidate geographical entity local semantic interaction response encoding matrix between represents and the to-be-translated place name address - candidate geographical entity local semantic interaction response encoding matrix between LSTM model, represents the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector.

[0063] Specifically, an LSTM transfer encoding module with an attention mechanism is used to deeply explore the cross-interval dependencies and global context between the local semantic interaction response encoding matrices of each place name to be translated and the candidate geographic entity. This allows for more accurate capture of the overall semantic interaction relationships between them. This enables the model to better handle ambiguous or non-standard representations when faced with complex place name and address translation tasks, significantly improving the accuracy and consistency of place name and address translation. The resulting semantic interaction response inference encoding vector for the place name to be translated and the candidate geographic entity has greater expressiveness and robustness, providing a more reliable semantic foundation for subsequent translation matching and normalization, thereby improving the performance of the entire translation system.

[0064] In particular, considering that the segmentation granularity of equal-granularity feature segmentation affects the regional granularity size of the to-be-translated place name address-candidate geographic entity local semantic interaction response encoding matrix, it will also directly affect the interaction structure representation between the corresponding sequence of to-be-translated place name address local semantic feature ordered encoding vectors and the candidate geographic entity local semantic feature ordered encoding vectors. Based on this, in a preferred example of the present application, the step S322 includes: first, based on the semantic interaction response connection density between each group of corresponding to-be-translated place name address local semantic feature ordered encoding vectors and the candidate geographic entity local semantic feature ordered encoding vectors, each to-be-translated place name address-candidate geographic entity local semantic interaction response encoding matrix in the sequence of the to-be-translated place name address-candidate geographic entity local semantic interaction response encoding matrix is subjected to feature sparsification constraints to obtain a sequence of optimized to-be-translated place name address-candidate geographic entity local semantic interaction response encoding matrices; then, the sequence of optimized to-be-translated place name address-candidate geographic entity local semantic interaction response encoding matrices is input into an LSTM transfer encoding module with an attention mechanism to obtain the to-be-translated place name address-candidate geographic entity semantic interaction response inference encoding vector.

[0065] Specifically, since the local semantic interaction response encoding matrix of the place name address to be translated - candidate geographic entity is a cross-regional interaction response between two local areas, it actually uses its row vector as a benchmark to express the interaction space metric, and the row vector length is also an expression of the regional constraint strength. If the regional constraint strength, that is, the row vector length If it is introduced as the regional constraint strength, then the low-dimensional space metric representation of the local semantic interaction response encoding matrix of the place name address to be translated-candidate geographical entity, that is, the F norm It should follow the Poisson distribution relationship:

[0066] ;

[0067] in, represents factorial, denotes the Frobenius norm, denotes the length of the row vector of denotes the exponential function with the natural constant as the base, denotes the Poisson distribution parameter, which characterizes the expected frequency of the local semantic interaction of the to-be-translated place name address - candidate geographical entity. Thus, the Poisson distribution parameter can be solved .

[0068] In this way, when introducing the case of generating a Poisson distribution process with the local interaction constraint strength of and the mean expectation of , with [[ID=We use to describe the edge association representation of the interaction space metric, then further determine the semantic interaction response connection density between two local to-be-translated place name addresses and candidate geographical entities as:

[0069] ;

[0070] where denotes and the semantic interaction response connection density between denotes taking the absolute value, denotes calculating the two-norm.

[0071] Then, use the semantic interaction response connection density to perform parameter iterative optimization on the local interaction constraint strength :

[0072] ;

[0073] where [[ID=5The .

[0074] Finally, use the optimized to re-constrain the sparsity of the to-be-translated place name address - candidate geographical entity local semantic interaction response coding matrix :

[0075] ;

[0076] where denotes the corresponding optimized to-be-translated place name address - candidate geographical entity local semantic interaction response coding matrix.

[0077] That is, while strictly ensuring that the expected degree is In this case, the regularization of the overall interaction space metric is determined by the regularization constraint of the mean expectation connection probability fluctuation of each line, so that the semantic interaction information within the regional interaction structure can avoid the risk of regional overfitting, improve the overall expression efficiency of the sequence of the local semantic interaction response encoding matrix of the to-be-translated place name address - candidate geographical entity, and further improve the accuracy and robustness of the subsequent global semantic interaction transfer aggregation based on the LSTN model.

[0078] Specifically, in step S33, the feature decoding is performed on the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector to obtain the confidence score of the candidate geographical entity. In a specific example of the present application, step S33 includes: inputting the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector into a feature decoder based on a multi-layer perceptron to obtain the confidence score of the candidate geographical entity. That is, in order to convert the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector into a comparable scalar score, based on the non-linear fitting ability of the multi-layer perceptron (MLP) in the present application, a feature decoder is constructed by stacking fully connected layers and activation functions (such as ReLU, Sigmoid). Specifically, by inputting the to-be-translated place name address - candidate geographical entity semantic interaction response inference encoding vector into an MLP model with two hidden layers, the non-linear transformation ability of the MLP is used to perform non-linear transformation on it to extract implicit information such as the strong correlation between the candidate geographical entity and the to-be-translated place name address, and the consistency of the administrative division context, and after Dropout regularization, a normalized confidence score s∈[0,1] is output as a quantitative index for the matching degree between the candidate geographical entity and the to-be-translated place name address. In this way, the semantic matching degree between the candidate entity and the user input address can be quantified, providing a differentiable decision basis for the optimal entity selection, and solving the problem of mis-matching caused by the traditional similarity calculation method ignoring the semantic level.

[0079] In the above-mentioned method for translating and matching place names and addresses based on artificial intelligence and a specialized common name library, in step S4, the standard place name and address description in the candidate geographical entity information description corresponding to the maximum value is extracted from the confidence scores of the multiple candidate geographical entities. That is, in order to select the only standard geographical entity that best represents the user's intention from potential candidate entities, based on the principle of maximum confidence selection, this application traverses all candidate geographical entities and their associated confidence score lists, extracts the maximum confidence score of the candidate geographical entities, and locates the candidate geographical entity information description corresponding to the highest candidate geographical entity confidence score, and extracts the content of the "standard place name and address description" field therefrom as the benchmark for this translation task. In this way, from the possibly ambiguous or non-standard user input, the geographical entity with a standardized representation behind it is determined, and its standard address description is used as the only input for subsequent translation processing, avoiding ambiguity and uncertainty.

[0080] In the above-mentioned method for translating and matching place names and addresses based on artificial intelligence and a specialized common name library, in step S5, the optimal matching standard place name and address description is segmented and named entity recognition is performed to obtain a sequence of segmented and labeled place name and address word segments to be translated. Specifically, since geographical addresses have a certain internal structure, including different types of geographical components such as administrative divisions, street names, house numbers, building names, etc., and the translation methods and rules for different components may be different (for example, administrative divisions may have established translations, street names may need to be transliterated plus common names, and building names may need to query a specific word library). Therefore, in order to structurally analyze the optimal matching standard place name and address description and generate a sequence of translatable word segments, this application is based on the component analysis method in linguistics, and hierarchically annotates the optimal matching standard place name and address description through a pre-trained named entity recognition (NER) model to identify each component in the place name and address. In the embodiment of this application, a BiLSTM-CRF model is used to identify components such as administrative divisions (such as "Beijing City"), common names (such as "Street"), and proper names (such as "Zhongguancun") in the optimal matching standard place name and address description, and outputs an annotation sequence (such as "[Administrative Division] Beijing City / [Administrative Division] Haidian District / [Proper Name] Zhongguancun / [Common Name] Street"), so as to provide a structured input with clear semantic roles for subsequent address translation and avoid component misalignment caused by overall translation.

[0081] In the above method for translating and matching place names and addresses based on artificial intelligence and specialized and common name libraries, in step S6, based on the target translation language, the specialized name library and the common name library are used to perform translation matching on the sequence of the component-labeled place name and address word segments to obtain the target language translated place name and address. It should be understood that since specialized names (such as "Yangtze River") need to follow transliteration or historical customary translations ("Yangtze River"), and common names (such as "river") need to be translated according to the target language norms ("River"), traditional unified translation strategies will result in the loss of cultural attributes or grammar errors. Therefore, in order to balance translation norms and cultural preservation, this application is based on the "separate treatment of specialized and common names" principle in translation studies. By constructing a bilingual-aligned specialized name library and common name library, each word segment in the sequence of the component-labeled place name and address word segments is respectively matched with the target language expression. Specifically, first, the sequence of the component-labeled place name and address word segments is traversed. According to the semantic roles (such as administrative division, specialized name, common name, etc.) labeled for each place name and address word segment to be translated, the specialized name library is called to match proper nouns (such as "Zhongguancun → Zhongguancun"), or the common name library is called to match general terms (such as "Street → Avenue"). Finally, the target language translation results of each place name and address word segment to be translated found are combined and formatted according to the writing habits and order of the place name and address in the target language to form the final target language translated place name and address string. In this way, the professional translation knowledge in the field is fully utilized, ensuring the accuracy, standardization, and practicality of the translation results, and effectively solving the deficiencies of the general translation method in place name and address translation.

[0082] In summary, the method for translating and matching place names and addresses based on artificial intelligence and specialized and common name libraries according to the embodiments of this application is elucidated. It extracts multiple candidate geographical entity information descriptions from the geographical entity information library based on the user-input place name and address text to be translated, and uses natural language processing technology to perform in-depth context semantic interaction matching analysis between the place name and address text to be translated and each candidate geographical entity information description to determine the candidate geographical entity that best matches the user input intention. Furthermore, based on the standard place name and address description of the matched candidate geographical entity, combined with the translation knowledge in the specialized and common name libraries, target language translation matching and normalization processing are performed on the standard place name and address description to generate the final target language translated place name and address. This method helps to provide a reliable geographical entity anchor for the translation process by using the geographical entity information library to assist in identifying fuzzy or non-standard place names and addresses input by the user, improving the accuracy and consistency of the translation.

[0083] Furthermore, a place name and address translation system based on artificial intelligence and specialized and common name libraries is also provided.

[0084] Figure 5The block diagram of a place name and address translation system based on artificial intelligence and a specialized and common name database according to an embodiment of the present application. As Figure 5 shown, the place name and address translation system 100 based on artificial intelligence and a specialized and common name database according to an embodiment of the present application includes: a user input module 110, configured to obtain a place name and address text to be translated input by a user and a specified target translation language; a geographical entity information extraction module 120, configured to construct a geographical entity information database, and based on the place name and address text to be translated, extract multiple candidate geographical entity information descriptions from the geographical entity information database; a matching analysis module 130, configured to perform matching analysis on the multiple candidate geographical entity information descriptions and the place name and address text to be translated respectively to obtain multiple candidate geographical entity confidence scores; an optimal matching selection module 140, configured to extract the standard place name and address description in the candidate geographical entity information description corresponding to the maximum value from the multiple candidate geographical entity confidence scores as the optimal matching standard place name and address description; a place name and address annotation module 150, configured to perform word segmentation and named entity recognition annotation on the optimal matching standard place name and address description to obtain a sequence of segmented and annotated place name and address word segments to be translated; a place name and address translation matching module 160, configured to perform translation matching on the sequence of segmented and annotated place name and address word segments to be translated by using a specialized name database and a common name database based on the target translation language to obtain a target language translated place name and address.

[0085] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations. It cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details to implement.

[0086] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, in any aspect, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0088] In addition, it is obvious that the term "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0089] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the technical solutions are modified or equivalently replaced with reference to the preferred embodiments, they do not depart from the spirit and scope of the technical solutions of the present invention.

Claims

1. A place name and address translation and matching method based on artificial intelligence and a dedicated name database is characterized by: include: Get the place name and address text to be translated and the specified target translation language entered by the user; Building a geographic entity information database, and extracting a plurality of candidate geographic entity information descriptions from the geographic entity information database based on the place name and address text to be translated; Matching and analyzing the plurality of candidate geographic entity information descriptions with the place name and address text to be translated to obtain a plurality of candidate geographic entity confidence scores; Extracting the standard place name and address description in the candidate geographic entity information description corresponding to the maximum value from the plurality of candidate geographic entity confidence scores as the best matching standard place name and address description; Performing word segmentation and named entity recognition annotation on the best matching standard place name and address description to obtain a sequence of component-annotated place name and address word segments to be translated; Based on the target translation language, the sequences of the place name and address word fragments to be translated marked with the components are translated and matched using the proper name library and the common name library to obtain the target language translated place name and address.

2. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 1 is characterized in that: The geographic entity information description includes a standard place name address description, entity type, administrative division information, geographic coordinates, alias, common name, former name, and associated entity description.

3. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 2 is characterized in that: Matching and analyzing the multiple candidate geographic entity information descriptions with the place name and address text to be translated to obtain multiple candidate geographic entity confidence scores includes: Extracting contextual semantic features of the candidate geographic entity information description and the to-be-translated place name and address text respectively to obtain a candidate geographic entity information description contextual semantic coding vector and a to-be-translated place name and address contextual semantic coding vector; Performing semantic transfer reasoning interaction coding on the to-be-translated place name address text context semantic coding vector and the candidate geographic entity information description context semantic coding vector to obtain a to-be-translated place name address-candidate geographic entity semantic interaction response reasoning coding vector; Feature decoding is performed on the to-be-translated place name address-candidate geographic entity semantic interaction response reasoning encoding vector to obtain the candidate geographic entity confidence score.

4. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 3 is characterized in that: Extracting contextual semantic features of the candidate geographic entity information description and the to-be-translated place name and address text respectively to obtain a candidate geographic entity information description contextual semantic encoding vector and a to-be-translated place name and address contextual semantic encoding vector, including: The candidate geographic entity information description and the place name and address text to be translated are respectively subjected to contextual semantic encoding based on the BERT model to obtain the candidate geographic entity information description contextual semantic encoding vector and the place name and address text to be translated contextual semantic encoding vector.

5. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 4 is characterized in that: Performing semantic transfer reasoning interaction coding on the to-be-translated place name and address text context semantic coding vector and the candidate geographic entity information description context semantic coding vector to obtain a to-be-translated place name and address-candidate geographic entity semantic interaction response reasoning coding vector, including: Performing local fine-grained semantic interaction response encoding on the to-be-translated place name and address text context semantic encoding vector and the candidate geographic entity information description context semantic encoding vector to obtain a sequence of to-be-translated place name and address-candidate geographic entity local semantic interaction response encoding matrices; The sequence of the local semantic interaction response coding matrix of the place name address to be translated and the candidate geographical entity is subjected to local semantic interaction feature reasoning transfer coding to obtain the semantic interaction response reasoning coding vector of the place name address to be translated and the candidate geographical entity.

6. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 5 is characterized in that: Performing local fine-grained semantic interaction response encoding on the to-be-translated place name and address text context semantic encoding vector and the candidate geographic entity information description context semantic encoding vector to obtain a sequence of to-be-translated place name and address-candidate geographic entity local semantic interaction response encoding matrices, including: The context semantic coding vector of the place name and address to be translated and the context semantic coding vector of the candidate geographic entity information description are arranged in an ordered manner based on the size of the feature values to obtain an ordered arrangement coding vector of semantic features of the place name and address to be translated and an ordered arrangement coding vector of semantic features of the candidate geographic entity; Performing equal-granularity feature segmentation on the ordered arrangement coding vectors of semantic features of the place names and addresses to be translated and the ordered arrangement coding vectors of semantic features of the candidate geographic entities to obtain a sequence of ordered coding vectors of local semantic features of the place names and addresses to be translated and a sequence of ordered coding vectors of local semantic features of the candidate geographic entities; Each corresponding group of ordered coding vectors of local semantic features of place names and addresses to be translated and ordered coding vectors of local semantic features of candidate geographic entities in the sequence of ordered coding vectors of local semantic features of place names and addresses to be translated and the sequence of ordered coding vectors of local semantic features of candidate geographic entities are input into the semantic interaction response reasoning unit to obtain a sequence of local semantic interaction response coding matrices of place names and addresses to be translated-candidate geographic entities.

7. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 6 is characterized in that: Performing local semantic interaction feature reasoning and transfer coding on the sequence of the to-be-translated place name address-candidate geographical entity local semantic interaction response coding matrices to obtain the to-be-translated place name address-candidate geographical entity semantic interaction response reasoning coding vector, including: The sequence of the local semantic interaction response encoding matrix of the place name address to be translated-candidate geographic entity is input into the LSTM transfer encoding module with an attention mechanism to obtain the semantic interaction response inference encoding vector of the place name address to be translated-candidate geographic entity.

8. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 6 is characterized in that: Performing local semantic interaction feature reasoning and transfer coding on the sequence of the to-be-translated place name address-candidate geographical entity local semantic interaction response coding matrices to obtain the to-be-translated place name address-candidate geographical entity semantic interaction response reasoning coding vector, including: Based on the semantic interaction response connection density between each group of corresponding ordered encoding vectors of local semantic features of place names and addresses to be translated and ordered encoding vectors of local semantic features of candidate geographical entities, feature sparsification constraints are performed on each of the local semantic interaction response encoding matrices of place names and addresses to be translated and candidate geographical entities in the sequence of local semantic interaction response encoding matrices of place names and addresses to be translated and candidate geographical entities to obtain an optimized sequence of local semantic interaction response encoding matrices of place names and addresses to be translated and candidate geographical entities; The sequence of the optimized local semantic interaction response encoding matrix of the place name address to be translated and the candidate geographic entity is input into the LSTM transfer encoding module with an attention mechanism to obtain the semantic interaction response inference encoding vector of the place name address to be translated and the candidate geographic entity.

9. The place name and address translation and matching method based on artificial intelligence and a dedicated name database according to claim 3 is characterized in that: Performing feature decoding on the semantic interaction response reasoning encoding vector of the place name address to be translated and the candidate geographic entity to obtain a confidence score of the candidate geographic entity includes: The place name address to be translated-candidate geographic entity semantic interaction response inference encoding vector is input into a feature decoder based on a multi-layer perceptron to obtain the candidate geographic entity confidence score.

10. A place name and address translation system based on artificial intelligence and a dedicated name database, characterized in that: include: A user input module is used to obtain the place name and address text to be translated and the specified target translation language input by the user; A geographic entity information extraction module is used to construct a geographic entity information database and extract multiple candidate geographic entity information descriptions from the geographic entity information database based on the place name and address text to be translated; A matching analysis module, configured to perform matching analysis on the plurality of candidate geographic entity information descriptions and the place name and address text to be translated to obtain confidence scores of the plurality of candidate geographic entity information descriptions; An optimal matching selection module is configured to extract the standard place name and address description in the candidate geographic entity information description corresponding to the maximum value from among the plurality of candidate geographic entity confidence scores as the optimal matching standard place name and address description; A place name and address tagging module is used to perform word segmentation and named entity recognition tagging on the best matching standard place name and address description to obtain a sequence of component-annotated place name and address word segments to be translated; The place name and address translation and matching module is used to translate and match the sequence of the place name and address word fragments to be translated with the component annotations based on the target translation language using the proper name library and the common name library to obtain the target language translated place name and address.

Images