A method and apparatus for address latitude and longitude correction

Abstract

This invention discloses an address latitude and longitude correction method and apparatus, relating to the field of big data technology. One specific implementation of the method includes: in response to receiving an address latitude and longitude correction request, performing natural language processing on the user-submitted address number information to obtain address entity information corresponding to the address number information; performing inverse address parsing based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching address keywords input by the user; determining the credibility of the new address latitude and longitude information, and determining the target address latitude and longitude information based on the credibility. This embodiment can correct the location of the searched and matched address latitude and longitude based on the user-submitted address number information. The corrected address latitude and longitude is generally closer to the address latitude and longitude that the user expects to need, thereby improving delivery efficiency and enhancing the user experience.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a method and apparatus for address latitude and longitude correction. Background Technology

[0002] In same-city instant delivery scenarios, users need to fill in relevant information such as the origin and destination of the delivery service. A certain percentage of users enter overly general address search keywords when searching for detailed addresses, such as only specifying the district or neighborhood name. This results in a large discrepancy between the latitude and longitude of the search results and the address the user expects to receive the service from, leading to low delivery efficiency and a poor user experience. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide an address latitude and longitude correction method and apparatus, which can correct the location of the searched and matched address latitude and longitude based on the address number information submitted by the user. The corrected address latitude and longitude is closer to the address latitude and longitude that the user expects to need, thereby improving delivery efficiency and enhancing the user experience.

[0004] To achieve the above objectives, according to one aspect of the present invention, an address latitude and longitude correction method is provided, comprising:

[0005] In response to receiving an address latitude and longitude correction request, the user-submitted house number information is processed by natural language recognition to obtain the address entity information corresponding to the house number information;

[0006] Reverse address parsing is performed based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user.

[0007] Determine the credibility of the new address latitude and longitude information, and determine the target address latitude and longitude information based on the credibility.

[0008] Optionally, reverse address resolution is performed based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information, including:

[0009] The user's initial address latitude and longitude information is concatenated with the address entity information to obtain search keywords;

[0010] The map search interface is invoked based on the search keywords to perform a query, and the new address latitude and longitude information is determined based on the query results returned by the map search interface.

[0011] Optionally, the reliability of the new address latitude and longitude information is determined, including:

[0012] The new address latitude and longitude information is converted into a first numerical vector and a second numerical vector along with the user's initial address latitude and longitude information;

[0013] Calculate the cosine similarity between the first and second numerical vectors, and determine the reliability of the new address latitude and longitude information based on the calculation results.

[0014] Optionally, the latitude and longitude information of the target address is determined based on the degree of confidence, including:

[0015] If the reliability level exceeds the preset range, the new address latitude and longitude information will be used as the target address latitude and longitude information.

[0016] If the credibility level is within the preset range, the new address latitude and longitude information and the initial address latitude and longitude information will be sent to the user, and the target address latitude and longitude information will be determined based on the user's selection results.

[0017] If the reliability level is lower than the preset range, the user's initial address latitude and longitude information will be used as the target address latitude and longitude information.

[0018] Optionally, the user-submitted house number information is processed using natural language processing to obtain the address entity information corresponding to the house number information, including:

[0019] Named entity recognition technology is used to extract the address entity information corresponding to the door number information submitted by the user.

[0020] Optionally, the method further includes:

[0021] In response to a failure of reverse address resolution, the user's initial address latitude and longitude information is used as the target address latitude and longitude information.

[0022] Optionally, after determining the latitude and longitude information of the target address based on the degree of confidence, the method further includes:

[0023] Orders are published based on the latitude and longitude of the target address, and delivery services are provided to users according to the orders.

[0024] According to a second aspect of the present invention, an address latitude and longitude correction device is provided, comprising:

[0025] The identification module is used to respond to the received address latitude and longitude correction request, perform natural language recognition on the door number information submitted by the user, and obtain the address entity information corresponding to the door number information;

[0026] The parsing module is used to perform reverse address parsing based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user;

[0027] The determination module is used to determine the credibility of new address latitude and longitude information, and to determine the target address latitude and longitude information based on the credibility.

[0028] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0029] One or more processors;

[0030] Memory, used to store one or more programs.

[0031] When one or more programs are executed by one or more processors, the one or more processors implement the methods of any of the above embodiments.

[0032] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0033] According to a fifth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0034] One embodiment of the above invention has the following advantages or beneficial effects: In response to receiving an address latitude and longitude correction request, the user-submitted house number information is processed by natural language recognition to obtain the address entity information corresponding to the house number information; inverse address parsing is performed based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user; the credibility of the new address latitude and longitude information is determined, and the target address latitude and longitude information is determined based on the credibility; thereby, the location correction of the searched and matched address latitude and longitude can be performed based on the user-submitted house number information, and the corrected address latitude and longitude is closer to the address latitude and longitude that the user expects to need, thereby improving delivery efficiency and enhancing the user experience.

[0035] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0036] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0037] Figure 1 This is a schematic diagram of the main process of the address latitude and longitude correction method according to an embodiment of the present invention;

[0038] Figure 2 This is a schematic diagram of the main process of the address latitude and longitude correction method according to a preferred embodiment of the present invention;

[0039] Figure 3 This is a schematic diagram of the main modules of the address latitude and longitude correction device according to an embodiment of the present invention;

[0040] Figure 4 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied;

[0041] Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0042] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0043] It should be noted that the acquisition, storage, and application of personal information involved in the embodiments of the present invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0044] In same-city instant delivery scenarios, users need to fill in relevant information such as the origin and destination of the delivery service. A certain percentage of users enter overly general address search keywords when searching for detailed addresses, such as only specifying the district or neighborhood name. This results in a large discrepancy between the latitude and longitude of the search results and the address the user expects to receive the service from, leading to low delivery efficiency and a poor user experience.

[0045] In view of this, according to one aspect of the present invention, an address latitude and longitude correction method is provided.

[0046] Figure 1 This is a schematic diagram of the main process of the address latitude and longitude correction method according to an embodiment of the present invention. Figure 1 As shown, the address latitude and longitude correction method according to an embodiment of the present invention includes the following steps S101 to S103.

[0047] Step S101: In response to receiving the address latitude and longitude correction request, the address number information submitted by the user is processed by natural language recognition to obtain the address entity information corresponding to the address number information.

[0048] Address latitude and longitude correction requests refer to requests made after a user has filled in or confirmed their address information, to determine the latitude and longitude that need to be corrected by comparing and processing this information. These requests include a detailed description of the user's current geographic location (such as the name of the residential area, street, etc.) and the corresponding latitude and longitude coordinates. The address number information submitted by the user is the specific location information provided when filling in the address, including building number, unit number, and door number. The address entity information corresponding to the door number information refers to the key geographic location information extracted from the user-submitted door number information, such as building number, floor, room number, street name, and POI (Point of Interest).

[0049] Upon receiving an address latitude and longitude correction request, the user-submitted address information can be processed using natural language recognition based on traditional machine learning methods such as Named Entity Recognition (NER). Specifically, a Conditional Random Field (CRF) model can be used. CRF models learn to identify and classify different types of address entities by labeling large amounts of address data containing address information. By recognizing contextual information in the text, CRF models can accurately extract geographical location information such as building numbers and room numbers from the address information. Alternatively, deep learning models, such as the BERT (Bidirectional Encoder Representation) model, can be used for natural language understanding on pre-trained large-scale text data. BERT models, through bidirectional context modeling, can more accurately understand the context of address information, identify address entities, and perform efficient recognition in complex, unstructured text, handling diverse and ambiguous expressions. Another approach is rule-based matching, which defines a set of rules to identify address entities in address information. Using techniques such as regular expressions, dictionary matching, and pattern matching, address information such as address number, street name, and city name can be extracted from the address information. The above methods can be used individually or in combination to achieve higher recognition accuracy and adaptability.

[0050] Step S102: Perform reverse address parsing based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user.

[0051] The initial address latitude and longitude information of a user refers to the geographic coordinates obtained by matching the address keywords (such as street name, neighborhood name, etc.) entered by the user. This information is a preliminary location based on the geographic description provided by the user and may not cover specific details such as buildings or units, thus having a certain degree of accuracy deviation. Reverse address resolution refers to the process of querying and obtaining the corresponding detailed address information using given geographic coordinates. The new address latitude and longitude information is more accurate latitude and longitude data corresponding to the initial address latitude and longitude obtained through reverse address resolution. By further analyzing and correcting the user's initial address latitude and longitude, and combining it with address entity information, reverse address resolution can provide more accurate positioning results. For example, the latitude and longitude obtained by keyword query may be located in a large area, but after reverse address resolution, the system can obtain a more specific location, such as the precise coordinates of a building.

[0052] Specifically, reverse address parsing, based on the user's initial address latitude and longitude information and address entity information, can combine the user's initial address latitude and longitude information with address entity information. Through a reverse query interface (such as an application programming interface provided by a map provider), this detailed entity information (such as building numbers, street signs, etc.) can be used for more accurate positioning. Alternatively, the initial address latitude and longitude information and address entity information can be directly combined, and address inference and correction can be performed using machine learning or deep learning models. These models, by learning a large number of address-latitude and longitude correspondences, can infer more accurate geographic coordinates from the initial address latitude and longitude information, thus providing more accurate results than simple reverse address parsing.

[0053] Step S103: Determine the credibility of the new address latitude and longitude information, and determine the target address latitude and longitude information based on the credibility.

[0054] Reliability refers to the evaluation standard of the accuracy of address latitude and longitude information. It reflects the degree to which the new address latitude and longitude information obtained in the reverse addressing process matches the actual location. It involves the reliability of the data source, the accuracy of the parsing algorithm, and the consistency with the user's initial address latitude and longitude. In practical applications, a higher reliability means that the new address latitude and longitude information better meets the user's expectations, and the accuracy and usability are also higher. Target address latitude and longitude information refers to the latitude and longitude data ultimately used for target location positioning. This latitude and longitude information undergoes further confirmation and verification to ensure that it accurately points to the target location, such as the precise coordinates of shops, residential areas, or other landmark buildings.

[0055] In practical applications, the credibility of new address latitude and longitude information can be divided into three levels: high, medium, and low, and these levels can be quantified based on different factors. For example, the quantification standard for credibility can be set based on factors such as matching degree, information completeness, and contextual support. For instance, addresses with a matching degree of over 90% are rated as "high credibility," those between 60% and 90% are rated as "medium credibility," and those below 60% are rated as "low credibility." Specifically, the credibility of new address latitude and longitude information can be determined by comparing it with the user's initial address latitude and longitude information and assessing the differences between the two. If the new address latitude and longitude is close to the user's initial address latitude and longitude and has a high degree of matching with the geographical environment or address entity, then the new address latitude and longitude information can be considered to have a high degree of credibility. In addition, the credibility of new address latitude and longitude information can be verified using external map services or third-party data sources. If the new address latitude and longitude information is verified to be correct by multiple trusted data sources and is highly consistent with real geographical information, then it can be considered to have a high degree of credibility.

[0056] The target address's latitude and longitude information is determined based on its level of trustworthiness. If the trustworthiness of the new address's latitude and longitude information is assessed as high, it can directly replace the user's initial address's latitude and longitude information, using the new information as the target address's latitude and longitude. This method simplifies the processing flow and ensures that the user obtains high-precision address location. Furthermore, if the trustworthiness of the new address's latitude and longitude information is considered moderate, a pop-up window or other interactive method can prompt the user to verify the new information. In this case, the user can choose whether to accept the new address's latitude and longitude information or maintain the initial information, thus ensuring that the final target address's latitude and longitude information matches the user's actual needs and intentions.

[0057] This invention, in response to a received address latitude and longitude correction request, performs natural language processing on the user-submitted house number information to obtain the address entity information corresponding to the house number; performs inverse address parsing based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching address keywords entered by the user; determines the credibility of the new address latitude and longitude information, and determines the target address latitude and longitude information based on the credibility; thus, it can perform location correction on the searched and matched address latitude and longitude information based on the user-submitted house number information, and the corrected address latitude and longitude is closer to the address latitude and longitude of the address the user expects to need, thereby improving delivery efficiency and enhancing user experience.

[0058] Optionally, reverse address parsing is performed based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information, including: concatenating the user's initial address latitude and longitude information and address entity information to obtain search keywords; calling the map search interface to perform a query based on the search keywords; and determining the new address latitude and longitude information based on the query results returned by the map search interface.

[0059] During reverse address resolution, the user's initial address latitude and longitude information can be concatenated with address entity information to generate more accurate search keywords. Based on these search keywords, the map search interface provided by the map service is invoked to perform the query. These map search interfaces match the search keywords with a large amount of geographic location information in their database, and then directly extract the most matching address latitude and longitude information from the data returned by the search interface, using it as the new address latitude and longitude information. Alternatively, a local search optimization strategy can be employed. A set of candidate results is retrieved based on the search keywords, and then compared with the user's initial address latitude and longitude to filter out the most suitable query results. This method not only relies on precise keyword matching but also further narrows the query range and improves query accuracy by combining the user's initial latitude and longitude information. This embodiment transforms the originally vague or coarse address information into precise and reliable geographic coordinates through reverse address resolution, resulting in more accurate address positioning.

[0060] Optionally, determining the credibility of the new address latitude and longitude information includes: converting the new address latitude and longitude information and the user's initial address latitude and longitude information into a first numerical vector and a second numerical vector; calculating the cosine similarity between the first numerical vector and the second numerical vector; and determining the credibility of the new address latitude and longitude information based on the calculation result.

[0061] The new address latitude and longitude information is input into the BERT model along with the user's initial address latitude and longitude information. The model generates a low-dimensional numerical vector for the text through a deep network, namely a first numerical vector and a second numerical vector. The cosine similarity between the first and second numerical vectors is calculated, which measures the angle between the two vectors in high-dimensional space to determine their similarity. Specifically, the inner product of the two vectors can be directly calculated and divided by the norm of the vectors to obtain the cosine similarity. The higher the cosine similarity, the more similar the two address latitude and longitude information is, and the higher the credibility. Alternatively, the vectors can be weighted, assigning different weights to different geographical features. By calculating the cosine similarity after weighting, the model's sensitivity to specific features can be improved, thus making the credibility judgment more accurate. The credibility of the new address latitude and longitude information is determined based on the calculation results. A threshold can be directly set based on the cosine similarity value. For example, when the similarity exceeds 0.9, the new address latitude and longitude information is considered to be very consistent with the user's initial address latitude and longitude information, and the credibility is high; when the similarity is below 0.5, the credibility is considered low. Alternatively, by analyzing historical data and sample experience, and combining more contextual information, such as the completeness, accuracy, and source of address data, the credibility can be comprehensively judged. This approach takes into account more external factors and can provide a more stable credibility assessment in practical applications.

[0062] Optionally, determining the target address latitude and longitude information based on the level of trust includes: in response to the level of trust exceeding a preset range, using the new address latitude and longitude information as the target address latitude and longitude information; in response to the level of trust being within a preset range, sending the new address latitude and longitude information and the initial address latitude and longitude information to the user, and determining the target address latitude and longitude information based on the user's selection result; in response to the level of trust being lower than a preset range, using the user's initial address latitude and longitude information as the target address latitude and longitude information.

[0063] In this embodiment, the first step is to determine whether the credibility value exceeds a preset range. When the calculated credibility exceeds the preset range, the new address latitude and longitude information can be directly used as the target address latitude and longitude information. Since the new address latitude and longitude information is highly consistent with the initial address latitude and longitude information, its credibility is considered high and meets the user's actual needs. Therefore, no further operation is required, and the new address latitude and longitude information is directly applied for subsequent operations. When the credibility is within the preset range, the target address latitude and longitude information cannot be directly determined. In this case, the new address latitude and longitude information can be sent to the user along with the user's initial address latitude and longitude information. The user can choose to use the new address latitude and longitude information or keep the initial address latitude and longitude information according to their understanding and needs. This method provides space for user participation in decision-making and ensures that the accuracy of the address information matches the user's intentions. If the calculated credibility is lower than the preset range, it is determined that the new address latitude and longitude information is not accurate enough or has a large deviation. Therefore, the user's initial address latitude and longitude information is used as the target address latitude and longitude information. This method avoids the uncertainty caused by erroneous data correction and ensures that the final address latitude and longitude information used remains within a relatively reliable range.

[0064] Optionally, the address number information submitted by the user is subjected to natural language processing to obtain the address entity information corresponding to the address number information, including: extracting the address entity information corresponding to the address number information from the address number information submitted by the user based on named entity recognition technology.

[0065] During implementation, Named Entity Recognition (NER) technology can automatically identify and extract relevant address entities from user-submitted address text. NER is a technology that identifies specific information units (such as building numbers, room numbers, etc.) in text using a model. In this implementation, the user-input address number is first segmented, and NER technology is used to identify various geographically relevant entities within the address number, such as the community name, street name, building number, and floor. NER recognition accurately extracts core address information related to the address number, which can be used for further address correction or querying. This not only improves the accuracy of address latitude and longitude but also reduces manual intervention and increases the efficiency of automated processing.

[0066] Optionally, the method further includes: in response to a failure of reverse address resolution, using the user's initial address latitude and longitude information as the target address latitude and longitude information.

[0067] In some cases, reverse address resolution may fail, failing to provide valid latitude and longitude or address data. In such situations, in response to reverse address resolution failure, the user's initial address latitude and longitude information can be automatically selected as the target address latitude and longitude information. Although reverse address resolution may not successfully improve address accuracy, it preserves the initial address latitude and longitude data, preventing user information loss or incorrect geographical location due to resolution failure. This approach ensures that the initial latitude and longitude information is maintained even when data is abnormal or more accurate information is unavailable, thereby improving the validity and stability of address data and reducing the risk of data processing errors.

[0068] Optionally, after determining the latitude and longitude information of the target address based on the degree of trust, the method further includes: issuing an order based on the latitude and longitude information of the target address, so as to provide delivery services to users according to the order.

[0069] Once the target address's latitude and longitude are determined, an order can be placed based on this information, providing users with precise delivery services. First, the target address's latitude and longitude are used to generate the order's delivery address data, including a detailed address description and geographic location information. This information is integrated into the order and sent to relevant delivery personnel or logistics systems through the order management system. The delivery system can plan the optimal delivery route based on the target address's latitude and longitude, for example, using a map navigation system to determine the shortest or fastest delivery path, ensuring delivery efficiency. Delivery personnel accurately deliver the goods to the target address according to navigation guidance, completing the service loop. If any abnormalities occur during delivery, such as an unknown address or location deviation, the order address information can be retrieved to assist in resolving the issue, further improving the delivery experience and service quality.

[0070] Figure 2 This is a schematic diagram of the main flow of an address latitude and longitude correction method according to a preferred embodiment of the present invention. This embodiment of the invention can be used in two scenarios to improve the map accuracy of addresses entered by users: for example, when a user manually enters an address on a platform, or when a user authorizes the entry of an address already entered from another platform. The following describes the interaction steps of this embodiment in the scenario where the user manually enters an address on a platform.

[0071] like Figure 2 As shown, users enter the order placement platform to fill in the order placement location information.

[0072] Users enter detailed address keywords, and the system searches for a set of addresses associated with those keywords. The search results may include less precise administrative districts, roads, residential areas, and commercial areas, or more precise building numbers, street signs, landmarks in residential areas, and landmarks in commercial areas. Users select one search result as the delivery location based on their delivery intentions and understanding of the address. The selected search result includes a detailed address description and its corresponding latitude and longitude.

[0073] The user fills in the house number. Next, the user submits the order address. At this stage, the address latitude and longitude correction function is triggered. The client submits the detailed address selected by the user, the corresponding latitude and longitude, and the house number entered by the user to the server. The server then determines whether the latitude and longitude can be further identified as more accurate.

[0074] After receiving the address latitude and longitude correction request, the server performs NER (Nearest Entity Recognition) on the address content to identify address entities contained in the natural language, such as POI, building number, floor, and room number. NER recognition involves segmenting the address text into words and labeling it with entity categories. In the Chinese address domain, common entity categories after segmentation include administrative district names, road names, street signs, business districts, residential areas, building names, building numbers, and room numbers. For address-related NER recognition, since the text is generally short and has significant regular features, traditional machine learning algorithms, such as CRF (Conditional Random Field), can achieve good results. CRF is a probabilistic graphical model used for sequence labeling tasks. It predicts by defining conditional probability distributions on the observation and label sequences. The core idea of ​​CRF is to find the optimal label by searching for the solution that maximizes the conditional probability of the label sequence among all labeled sequences. Through the above NER recognition, words with geographical location information, such as POI and building number, can be extracted from the address number entered by the user.

[0075] The system combines the user-selected address with the POI and building number identified by NER (Non-Electronic Address Recognition), and performs reverse address parsing again to obtain a new latitude and longitude, POI, and detailed address of the POI. The system judges the credibility of the result based on the data source of the reverse address parsing. If the credibility is high, the latitude and longitude of the user-selected address are directly replaced; if the reverse address parsing fails or the credibility is low, the correction is abandoned; if the credibility is moderate, a pop-up window allows the user to confirm whether the new location's latitude and longitude matches their intention, and the user can choose whether to use the new location or keep the original location. After reverse address parsing, the credibility of the corrected address is judged using a text similarity algorithm from natural language processing. Specifically, the text to be compared is first input into the BERT (Bidirectional Encoder Representations from Transformers) model. The model generates a low-dimensional numerical vector for the text through a deep network; then, cosine similarity is used to calculate the similarity between the two vectors. Cosine similarity is a value between -1 and 1, with a larger number indicating higher similarity. Based on sample experience, similarity is divided into three levels, from low to high: dissimilar, uncertain, and textually consistent. The cosine similarity between two vectors is calculated as follows:

[0076]

[0077] Where A · B is the inner product of two vectors. ||A|| is the first norm of the vector, which is equal to the square root of the sum of the squares of all its components. The formula is: .

[0078] After the correction, the latitude and longitude of the order address are more accurate. When the user submits an order, the system publishes the order using the corrected latitude and longitude. The rider accepts the order and fulfills the service based on the new latitude and longitude.

[0079] In this embodiment of the invention, after the user fills in the house number, the latitude and longitude matched by the user based on the detailed address keywords are corrected a second time to obtain a more accurate latitude and longitude. The correction process utilizes the content filled in by the user in the house number. The system performs natural language semantic recognition on the house number content to extract more detailed address information such as POI and building number. Combined with the latitude and longitude matched by the user's keywords, reverse address parsing is performed. When the system uses the new latitude and longitude to issue an order, the address latitude and longitude of the order is more accurate.

[0080] According to a second aspect of the present invention, an address latitude and longitude correction device is provided.

[0081] Figure 3 This is a schematic diagram of the main modules of the address latitude and longitude correction device according to an embodiment of the present invention. Figure 3As shown, the address latitude and longitude correction device 300 includes:

[0082] The identification module 301 is used to respond to the received address latitude and longitude correction request by performing natural language recognition on the door number information submitted by the user to obtain the address entity information corresponding to the door number information;

[0083] The parsing module 302 is used to perform reverse address parsing based on the user's initial address latitude and longitude information and address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user;

[0084] The determination module 303 is used to determine the credibility of the new address latitude and longitude information, and to determine the target address latitude and longitude information based on the credibility.

[0085] Optionally, the parsing module 302 is also used for:

[0086] The user's initial address latitude and longitude information is concatenated with the address entity information to obtain search keywords;

[0087] The map search interface is invoked based on the search keywords to perform a query, and the new address latitude and longitude information is determined based on the query results returned by the map search interface.

[0088] Optionally, the determining module 303 is also used for:

[0089] The new address latitude and longitude information is converted into a first numerical vector and a second numerical vector along with the user's initial address latitude and longitude information;

[0090] Calculate the cosine similarity between the first and second numerical vectors, and determine the reliability of the new address latitude and longitude information based on the calculation results.

[0091] Optionally, the determining module 303 is also used for:

[0092] If the reliability level exceeds the preset range, the new address latitude and longitude information will be used as the target address latitude and longitude information.

[0093] If the credibility level is within the preset range, the new address latitude and longitude information and the initial address latitude and longitude information will be sent to the user, and the target address latitude and longitude information will be determined based on the user's selection results.

[0094] If the reliability level is lower than the preset range, the user's initial address latitude and longitude information will be used as the target address latitude and longitude information.

[0095] Optionally, the identification module 301 is also used for:

[0096] Named entity recognition technology is used to extract the address entity information corresponding to the door number information submitted by the user.

[0097] Optionally, the correction device 300 further includes a confirmation module, which is used for:

[0098] In response to a failure of reverse address resolution, the user's initial address latitude and longitude information is used as the target address latitude and longitude information.

[0099] Optionally, the correction device 300 also includes a publishing module, which is used for:

[0100] Orders are published based on the latitude and longitude of the target address, and delivery services are provided to users according to the orders.

[0101] It should be noted that the specific implementation details of the address latitude and longitude correction device of the present invention have been described in detail in the address latitude and longitude correction method above, so the details will not be repeated here.

[0102] According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the present invention.

[0103] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0104] According to a fifth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0105] Figure 4 An exemplary system architecture 400 is shown that can be applied to the address latitude and longitude correction method or address latitude and longitude correction device of the present invention.

[0106] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, and 403, a network 404, and a server 405. Network 404 serves as the medium for providing communication links between terminal devices 401, 402, and 403 and server 405. Network 404 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0107] Users can use terminal devices 401, 402, and 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, and 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0108] Terminal devices 401, 402, and 403 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0109] Server 405 can be a server that provides various services, such as a backend management server that supports shopping websites browsed by users using terminal devices 401, 402, and 403 (for example only). The backend management server can analyze and process data such as received address latitude and longitude correction requests, and feed back the processing results (such as target address latitude and longitude information - for example only) to the terminal device.

[0110] It should be noted that the address latitude and longitude correction method provided in the embodiments of the present invention is generally run by server 405, and correspondingly, the address latitude and longitude correction device is generally set in server 405.

[0111] It should be understood that Figure 4 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0112] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing a terminal device of the present invention. Figure 5 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0113] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0114] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. Drive 510 is also connected to I / O interface 505 as needed. Removable media 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 510 as needed so that computer programs read from them can be installed into storage section 508 as needed.

[0115] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is run by the central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0116] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more operable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually operate substantially in parallel, and they may sometimes operate in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0118] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor can be described as including an identification module, a parsing module, and a determination module. The names of these modules do not necessarily limit the module itself; for example, the identification module can also be described as "a module used to, in response to receiving an address latitude and longitude correction request, perform natural language recognition on the address number information submitted by the user to obtain the address entity information corresponding to the address number information."

[0119] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to: in response to receiving an address latitude and longitude correction request, perform natural language recognition on the address number information submitted by the user to obtain address entity information corresponding to the address number information; perform inverse address parsing based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching address keywords input by the user; determine the credibility of the new address latitude and longitude information, and determine target address latitude and longitude information based on the credibility.

[0120] The computer program product provided in this embodiment of the invention includes a computer program that, when executed by a processor, implements the address latitude and longitude correction method in this embodiment of the invention.

[0121] According to the technical solution of the present invention, the following advantages or beneficial effects are achieved: In response to receiving an address latitude and longitude correction request, the user-submitted house number information is processed using natural language recognition to obtain the address entity information corresponding to the house number information; inverse address parsing is performed based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching address keywords entered by the user; the credibility of the new address latitude and longitude information is determined, and the target address latitude and longitude information is determined based on the credibility; thereby, the location of the searched and matched address latitude and longitude can be corrected based on the user-submitted house number information, and the corrected address latitude and longitude is generally closer to the address latitude and longitude that the user expects to need service for, thus improving delivery efficiency and enhancing the user experience.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0123] It should be noted that the acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

Claims

1. A method for correcting address latitude and longitude, characterized in that, include: In response to receiving an address latitude and longitude correction request, the user-submitted house number information is processed by natural language recognition to obtain the address entity information corresponding to the house number information; Reverse address parsing is performed based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching the address keywords entered by the user; Determine the credibility of the new address latitude and longitude information, and determine the target address latitude and longitude information based on the credibility.

2. The method according to claim 1, characterized in that, Based on the user's initial address latitude and longitude information and the address entity information, inverse address parsing is performed to obtain new address latitude and longitude information, including: The user's initial address latitude and longitude information is concatenated with the address entity information to obtain search keywords; The map search interface is invoked based on the search keywords to perform a query, and the new address latitude and longitude information is determined based on the query results returned by the map search interface.

3. The method according to claim 1, characterized in that, Determining the reliability of the new address latitude and longitude information includes: The new address latitude and longitude information and the user's initial address latitude and longitude information are converted into a first numerical vector and a second numerical vector; Calculate the cosine similarity between the first and second numerical vectors, and determine the reliability of the new address latitude and longitude information based on the calculation result.

4. The method according to claim 1, characterized in that, Determining the latitude and longitude information of the target address based on the aforementioned level of confidence includes: If the confidence level exceeds a preset range, the new address latitude and longitude information is used as the target address latitude and longitude information. If the credibility level is within a preset range, the new address latitude and longitude information and the initial address latitude and longitude information are sent to the user, and the target address latitude and longitude information is determined based on the user's selection result. If the credibility level is lower than a preset range, the user's initial address latitude and longitude information will be used as the target address latitude and longitude information.

5. The method according to claim 1, characterized in that, The user-submitted house number information is processed using natural language processing to obtain the address entity information corresponding to the house number information, including: Named entity recognition technology is used to extract the address entity information corresponding to the address number information submitted by the user.

6. The method according to claim 1, characterized in that, The method further includes: In response to the failure of the reverse address resolution, the user's initial address latitude and longitude information is used as the target address latitude and longitude information.

7. The method according to claim 1, characterized in that, After determining the target address's latitude and longitude information based on the aforementioned level of confidence, the process also includes: Orders are published based on the latitude and longitude information of the target address, so as to provide delivery services to users according to the orders.

8. An address latitude and longitude correction device, characterized in that, include: The identification module is used to respond to the received address latitude and longitude correction request by performing natural language recognition on the door number information submitted by the user to obtain the address entity information corresponding to the door number information; The parsing module is used to perform reverse address parsing based on the user's initial address latitude and longitude information and the address entity information to obtain new address latitude and longitude information; the user's initial address latitude and longitude information is obtained by matching address keywords input by the user; The determination module is used to determine the credibility of the new address latitude and longitude information, and determine the target address latitude and longitude information based on the credibility.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images