Method and device for identifying POI name change and program product

Abstract

The embodiment of the invention provides a method and device for recognizing POI name change and a program product. The method comprises the following steps: acquiring waybill addresses of a plurality of waybills; performing hierarchical segmentation on the waybill address to obtain geographical location information corresponding to each waybill and a POI name corresponding to the geographical location information; according to the geographical location information, POI names corresponding to the geographical location information are divided into at least one cluster; and based on the processing time corresponding to the waybill and the POI name in each cluster, determining whether the POI name corresponding to the geographical location information is changed or not. The method is used for increasing the POI name change judgment speed.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method, device, and program product for identifying changes in POI names. Background Art

[0002] Commonly, map providers usually use Geographic Information System (GIS) and database technologies to manage and update map data. However, with the acceleration of urbanization and the rapid changes in human geographical landscapes, the update of POI names has become increasingly complex and frequent.

[0003] In related technologies, a method based on real-scene image comparison is adopted to automatically identify changes in POI names, but it faces many problems in practical applications. For example, the determination of whether different pictures correspond to the same location; moreover, the automatic recognition process is extremely vulnerable to various factors, including but not limited to image quality, shooting clarity, perspective changes, and the presence of occlusions. These factors not only increase the difficulty of recognition but also significantly reduce the recognition accuracy. Summary of the Invention

[0004] Embodiments of this application provide a method, device, and program product for identifying changes in POI names, so as to achieve the effect of improving the speed and accuracy of identifying changes in POI names.

[0005] In a first aspect, embodiments of this application provide a method for identifying changes in POI names, including:

[0006] Obtaining the waybill addresses of multiple waybills;

[0007] Performing hierarchical segmentation on the waybill addresses to obtain the geographical location information corresponding to each waybill and the POI name corresponding to the geographical location information;

[0008] Dividing the POI names corresponding to each geographical location information into at least one cluster according to the geographical location information;

[0009] Based on the processing time corresponding to the waybill and the POI names within each cluster, determining whether the POI name corresponding to the geographical location information has changed.

[0010] In a second aspect, embodiments of this application provide a device for identifying changes in POI names, including:

[0011] An obtaining module, configured to obtain the waybill addresses of multiple waybills;

[0012] A segmentation module, configured to perform hierarchical segmentation on the waybill addresses to obtain the geographical location information corresponding to each waybill and the POI name corresponding to the geographical location information;

[0013] A partitioning module, configured to partition the POI names corresponding to the geographical location information into at least one cluster according to the geographical location information;

[0014] A determining module, configured to determine whether the POI name corresponding to the geographical location information has changed based on the processing time corresponding to the waybill and the POI names within each cluster.

[0015] In a third aspect, an embodiment of the present application provides a computer program product, including a computer program, which when executed by a processor implements the above first aspect and / or various possible implementations of the first aspect or the above second aspect and / or various possible implementations of the second aspect.

[0016] The method, device and program product for identifying POI name change provided by the embodiments of the present application can extract the waybill address from the actually generated waybills, thereby ensuring the validity of the geographical location information and POI names included in the waybill address. Further, all existing POI names corresponding to different geographical location information are clustered, and finally, the processing time of the waybill can be used to determine whether the POI name corresponding to the geographical location information has changed. The method for identifying POI name change depends on the generated waybill data and has no additional acquisition cost. It can not only ensure the validity of the POI name, but also cover all areas where users gather in the geographical scope of POI name change judgment, and at the same time speed up the speed of POI name change judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0018] Figure 1 It is a schematic diagram of the scenario of the method for identifying POI name change provided by the present application;

[0019] Figure 2 It is a schematic flowchart of the method for identifying POI name change provided by the present application;

[0020] Figure 3 It is a schematic structural diagram of the device for identifying POI name change provided by the present application;

[0021] Figure 4 It is a schematic structural diagram of the computer device provided by the present application.

[0022] Through the above drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0023] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0024] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards, and corresponding operation entrances are provided for the user to choose to authorize or refuse.

[0025] The method for identifying POI name changes provided in the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network.

[0026] For example, when the method for identifying POI name changes is applied to the terminal 102, the terminal 102 can obtain the waybill addresses of multiple waybills from the data storage system of the server 104; then perform hierarchical segmentation on the waybill addresses to obtain the geographical location information corresponding to each waybill and the POI name corresponding to the geographical location information; and divide the POI names corresponding to each geographical location information into at least one cluster according to the geographical location information; finally, the terminal 102 determines whether the POI name corresponding to the geographical location information has changed based on the processing time corresponding to the waybill and the POI names within each cluster. Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers. The terminal 102 and the server 104 can be directly or indirectly connected through wired or wireless communication means, such as through a network connection.

[0027] For another example, the method for identifying a change in a POI name is applied to the server 104. After being triggered by the terminal 102, the server 104 can obtain the waybill addresses of multiple waybills from the data storage system. Subsequently, the waybill addresses are hierarchically segmented to obtain the geographical location information corresponding to each waybill and the POI name corresponding to the geographical location information. Then, based on the geographical location information, the POI names corresponding to the geographical location information are divided into at least one cluster. Finally, the server 104 determines whether the POI name corresponding to the geographical location information has changed based on the processing time corresponding to the waybill and the POI names within each cluster. It can be understood that the data storage system can be an independent storage device, or the data storage system is located on the server 104, or the data storage system is located on another terminal.

[0028] In one embodiment, a method for identifying a change in a POI name is provided. In this embodiment, an example is given where the method for identifying a change in a POI name is applied to a terminal. It can be understood that the method for identifying a change in a POI name can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. As Figure 2 shown, the method for identifying a change in a POI name includes:

[0029] Step 202: Obtain the waybill addresses of multiple waybills.

[0030] Specifically, a waybill refers to business-related information generated after a user pre-registers, logs in on a platform designated by a specific service provider, and uses the services or functions provided by the platform. The services or functions provided by the platform may include, but are not limited to, item delivery, address navigation, etc.

[0031] When the business is item delivery, the waybill may specifically include the original address where the item is located and the POI name corresponding to the original address, the delivery address to which the item needs to be delivered and the POI name corresponding to the delivery address, the path planning content between the original address and the delivery address, item information, etc. At this time, the waybill address of the waybill may include the original address, the POI name corresponding to the original address, the delivery address, and the POI name corresponding to the delivery address. When the business is address navigation, the waybill may specifically include the starting address where the target object is located and the POI name corresponding to the starting address, the target address to which the target object needs to go and the POI name corresponding to the target address, the path planning between the starting address and the target address, etc. At this time, the waybill address of the waybill may include the starting address, the POI name corresponding to the starting address, the target address, and the POI name corresponding to the target address.

[0032] Specifically, in the address navigation scenario, the waybill address of a waybill may include the starting address "No. D, Street C, District B, City A" where the target object is located and the corresponding POI name "E Restaurant" of the starting address, the target address to be traveled to "No. G, Street F, District B, City A" and the corresponding POI name "H Coffee Shop" of the target address.

[0033] As an example, the terminal may obtain the waybill addresses of multiple waybills in response to a received detection instruction. Specifically, the terminal may also obtain the waybill addresses of multiple waybills generated within a preset duration in the past in response to a received detection instruction.

[0034] Among them, the detection instruction may be issued by a staff member through the human-computer interaction interface of the terminal. The human-computer interaction interface of the terminal may specifically display a platform interface pre-specified by the service provider for maintaining the POI names of points of interest (POIs). The staff member issues a detection instruction carrying the identity tag of the corresponding virtual object by clicking on the area representing different virtual objects in the specified platform interface. It should be noted that the user can create the corresponding virtual object by registering in advance on the above platform interface. When the user calls a specific service on the service platform specified by the service provider, the terminal can collect the service-related information generated, fill the service-related information into a preset waybill, and store it corresponding to the identity tag of the user's virtual object in the data storage system of the server. Or, the detection instruction may be automatically generated by the terminal according to a preset detection frequency; specifically, the terminal may automatically generate a detection instruction according to a preset detection frequency, and the virtual object corresponding to the detection instruction may be randomly determined. It can be understood that the identity tag of the virtual object carried by the detection instruction may be randomly selected. The above identity tag may be composed of at least one of letters, characters, or numbers. The identity tag is used to uniquely represent the virtual object. In the server of this embodiment, a mapping relationship between the identity tag and the virtual object is pre-stored.

[0035] As an example, the terminal may cluster and divide virtual objects according to multiple criteria. When the terminal automatically generates a detection instruction according to a preset detection frequency, the detection instruction may successively carry the identity tags of virtual objects in different clusters. For example, the terminal may divide a preset number of virtual objects into a cluster according to the chronological order of the registration time of each virtual object; or, according to the user address filled in when each virtual object is registered and multiple pre-divided geographical regions, divide the virtual objects with the user addresses belonging to the same geographical region into a cluster.

[0036] Specifically, the terminal can determine a target object in response to a received detection instruction, based on the identity tag carried by the detection instruction, match a corresponding waybill from the data storage system of the server according to the identity tag, and extract the waybill address from the waybill.

[0037] Step 204: Perform hierarchical segmentation on the waybill address to obtain the geographical location information corresponding to each waybill and the POI name corresponding to the geographical location information.

[0038] As an example, after the terminal obtains the waybill addresses included in multiple waybills, it can input the multiple waybill addresses into a pre-trained text tokenization model, which is used to split the waybill address into text to obtain the geographical location information and POI name included in the waybill address.

[0039] Among them, the text tokenization model can be trained using multiple sample waybill addresses, and the sample waybill addresses can be randomly combined using multiple sample addresses and sample POI names. Each word in the sample waybill address carries a corresponding category label, which is used to distinguish the above sample addresses and sample POI names. The image segmentation model can adopt a deep neural network, a long short-term memory network, etc. The present application does not limit the model structure adopted by the text tokenization model, as long as it can be trained based on the sample waybill address and split the waybill address into geographical location information and POI name.

[0040] The geographical location information is used to indicate a specific physical location, and the POI name is used to indicate the name of an entity located at a specific physical location.

[0041] Step 206: Divide the POI names corresponding to the geographical location information into at least one cluster according to the geographical location information.

[0042] In this embodiment, the terminal obtains n sets of "geographical location information - POI name" corresponding to n waybill addresses in step 204. The terminal can further set clusters for different geographical location information. It can be understood that one cluster corresponds to one geographical location information. The terminal can first establish the first cluster for the first set of "geographical location information - POI name" and store the POI names in the first set of "geographical location information - POI name" into the first cluster. Subsequently, for the second set of "geographical location information - POI name", first determine whether the geographical location information is the same as the geographical location information in the first set of "geographical location information - POI name". If it is the same, store the POI names in the second set of "geographical location information - POI name" into the first cluster. If it is not the same, establish the second cluster for the second set of "geographical location information - POI name" and store the POI names in the second set of "geographical location information - POI name" into the second cluster. Further, for the third set of "geographical location information - POI name", first determine whether the geographical location information is the same as the geographical location information in the first set of "geographical location information - POI name". If it is the same, store the POI names in the third set of "geographical location information - POI name" into the first cluster. If it is not the same, continue to determine whether the geographical location information is the same as the geographical location information in the second set of "geographical location information - POI name". If it is the same, store the POI names in the third set of "geographical location information - POI name" into the second cluster. If it is not the same, establish the third cluster for the third set of "geographical location information - POI name", and so on, until the POI names in the nth set of "geographical location information - POI name" are stored in the cluster corresponding to the geographical location information.

[0043] A cluster contains at least one POI name corresponding to one geographical location information, and the POI names in the same cluster may be repeated or different.

[0044] As an example, when extracting four waybill addresses from multiple waybills: ① "E Hotel, No. D, Street C, District B, City A", ② "H Coffee Shop, No. G, Street F, District B, City A", ③ "I Coffee Shop, No. D, Street C, District B, City A", and ④ "E Hotel, No. D, Street C, District B, City A", the first cluster can be established based on the geographical location information of "No. D, Street C, District B, City A" in ①, and the "E Hotel" in ① can be stored in the first cluster. Subsequently, for ②, since "No. D, Street C, District B, City A" is different from "No. G, Street F, District B, City A", the terminal can establish a second cluster based on the geographical location information of "No. G, Street F, District B, City A" in ② and store the "H Coffee Shop" in ② in the second cluster. For ③, since "No. D, Street C, District B, City A" in ① is the same as "No. D, Street C, District B, City A" in ③, the "I Coffee Shop" in ③ can be stored in the first cluster. For ④, since "No. D, Street C, District B, City A" in ① is the same as "No. D, Street C, District B, City A" in ④, the "E Hotel" in ④ can be stored in the first cluster. Finally, two clusters are obtained. The first cluster corresponds to the geographical location information of "No. D, Street C, District B, City A" and contains three POI names: "E Hotel", "I Coffee Shop", and "E Hotel"; the second cluster corresponds to the geographical location information of "No. G, Street F, District B, City A" and contains one POI name: "H Coffee Shop".

[0045] Step 208: Based on the processing time corresponding to the waybill and the POI names in each cluster, determine whether the POI name corresponding to the geographical location information has changed.

[0046] The processing time corresponding to the waybill is used to indicate the specific time when the user invokes the service. For example, when the service is item delivery, the processing time corresponding to the waybill can refer to the moment when the item is delivered to the delivery address; when the service is address navigation, the processing time corresponding to the waybill can refer to the moment when the destination address is reached.

[0047] Specifically, the terminal can, for example, use the processing time corresponding to each waybill as the processing time corresponding to the corresponding POI name. For each cluster, first determine the POI name with the latest processing time. Subsequently, the terminal can obtain the mapping relationship between at least one actual geographical location and at least one POI name from the POI name address library of the data storage system, and for each cluster, determine whether the POI name with the latest processing time in the cluster conforms to the POI name corresponding to the geographical location information stored in the POI name address library. If it conforms, it is confirmed that the POI name corresponding to the geographical location information of the current cluster has changed; otherwise, it is confirmed that the POI name corresponding to the geographical location information of the current cluster has not changed.

[0048] As an example, the processing time corresponding to the above three waybill addresses ① is t 1 and the processing time corresponding to ③ is t 3, the processing time corresponding to ④ is t 4 , and t 1 , t 3 , t 4 among which t 3 is the latest. Moreover, the POI name corresponding to the actual geographical location of "No. D, Street C, District B, City A" stored in the POI name and address library is "E Restaurant". Then, for the geographical location information corresponding to the first cluster, which is "No. D, Street C, District B, City A", it can be determined that the processing times of the three POI names included in the first cluster, namely "E Restaurant", "I Coffee Shop", and "E Restaurant", are t 1 , t 3 , t 4 . Further, based on t 3 , the corresponding POI name "I Coffee Shop" is the POI name with the latest processing time. Further, the POI name "I Coffee Shop" with the latest processing time is compared with the POI name "E Restaurant" corresponding to "No. D, Street C, District B, City A" stored in the POI name and address library. At this time, it can be determined that the POI name corresponding to the geographical location information of "No. D, Street C, District B, City A" has changed.

[0049] The method for identifying POI name change provided by the embodiments of the present application can extract the waybill address from the waybills actually generated by users, thereby ensuring the validity of the geographical location information and POI names included in the waybill address. Further, taking the geographical location information as the clustering criterion, all existing POI names corresponding to different geographical location information are clustered. Finally, the processing time of the waybill can be used to determine whether the POI name corresponding to the geographical location information has changed. This method relies on the generated waybill data and has no additional acquisition cost. It can not only ensure the validity of the POI name, but also cover all regions where users gather for the geographical scope of POI name change judgment, and at the same time speed up the speed of POI name change judgment.

[0050] In some optional embodiments, before step 206, it further includes:

[0051] Based on at least one pre-stored standard location information, address correction is performed on the geographical location information;

[0052] Based on the mapping relationship between at least one pre-stored standard POI name and at least one same-name POI name, name correction is performed on the POI name corresponding to the geographical location information.

[0053] At least one standard location information can be stored in a standard address information database, for example. The process of correcting the address of geographical location information may include: comparing and matching the geographical location information with multiple standard geographical locations, finding the standard geographical location that is most similar to the geographical location information, and correcting the corresponding geographical location information based on the most similar standard geographical location to obtain the corrected geographical location information.

[0054] As an example, the standard address information database may include standard geographical locations such as "No. J, Huayuan South Road, B District, A City" and "No. D, Huayuan North Road, B District, A City". The terminal can match the most similar standard geographical location "No. D, Huayuan North Road, B District, A City" based on the geographical location information "No. D, Huayuan North Road, B District, A City", and correct the address based on the standard geographical location "No. D, Huayuan North Road, B District, A City", changing "No. D, Huayuan North Road, B District, A City" to "No. D, Huayuan North Road, B District, A City"; or match the most similar standard geographical location "No. D, Huayuan North Road, B District, A City" based on the geographical location information "No. d, Huayuan North Road, B District, A City", and standardize the address based on the standard geographical location "No. D, Huayuan North Road, B District, A City", changing "No. d, Huayuan North Road, B District, A City" to "No. D, Huayuan North Road, B District, A City"; or alternatively, the terminal can match the most similar standard geographical location "No. D, Huayuan North Road, B District, A City" based on the geographical location information "No. d, Huayuan North Road, A City", and complete the address based on the standard geographical location "No. D, Huayuan North Road, B District, A City", changing "No. d, Huayuan North Road, A City" to "No. D, Huayuan North Road, B District, A City".

[0055] The mapping relationship between at least one standard POI name and at least one POI name with the same name can be stored in a same-name mapping information database, for example. The process of correcting the name of the POI may include: comparing and matching the POI name with the POI names with the same name in the mapping relationship. If a POI name with the same name that matches the POI name is found, the name of the POI is corrected based on the standard POI name corresponding to the matched POI name with the same name to obtain the corrected POI name.

[0056] As an example, the same-name mapping information database contains the mapping relationship between the standard POI name "Apple Coffee Shop" and the two POI names with the same name "APPLE Coffee Shop" and "APPLE COFFEE". The terminal can match the corresponding POI name with the same name from the above mapping relationship based on the POI name "APPLE Coffee Shop", and then further be able to correct the POI name "APPLE Coffee Shop" based on the standard POI name "Apple Coffee Shop" corresponding to the POI name with the same name "APPLE Coffee Shop" to obtain the corrected POI name "Apple Coffee Shop".

[0057] In this embodiment, the terminal can standardize and integrate the waybill address filled in by the actual user by using at least one standard location information and at least one standard POI name, so as to prevent conflicts or duplications of address information due to different naming methods of the same POI name or the same geographical location by different users; perform address correction and name correction on the waybill address, so that the corrected geographical location information and POI name are more standardized and unified, facilitating subsequent data comparison and analysis, and improving the judgment accuracy of whether the POI name has changed.

[0058] In some alternative embodiments, step 208 includes:

[0059] Sort the POI names in each cluster based on the processing time corresponding to the waybill to obtain a sorting result;

[0060] Calculate the similarity between any two POI names within each cluster;

[0061] Based on the similarity and the sorting result, determine whether the POI name corresponding to the geographical location information of each cluster has changed.

[0062] The sorting result is used to indicate the order of appearance time of the POI names within each cluster. For example, the terminal can obtain the processing time of the waybills corresponding to each POI name within each cluster, and sort the POI names within the cluster according to the order of the processing time to obtain the sorting result.

[0063] Specifically, the step of calculating the similarity between any two POI names within each cluster may include: dividing the POI name into multiple sequentially arranged information segments based on a preset step size and a sliding window length; calculating the matching probability between the information segments corresponding to any two POI names according to the arrangement order of the information segments; and calculating the similarity based on the matching probability.

[0064] Among them, the process of obtaining the matching probability between the information segments corresponding to any two POI names may be, for example, calculating the matching probability between the first information segment of the first POI name and the first information segment of the second POI name, the matching probability between the second information segment of the first POI name and the second information segment of the second POI name... and so on, until the matching probability between the last information segment of the first POI name and the last information segment of the second POI name is calculated, and further calculating the sum of all matching probabilities. Finally, dividing the sum of the matching probabilities by the total number of information segments in the first POI name or the total number of information segments in the second POI name to obtain the similarity.

[0065] As an example, when the texts in two information segments are exactly the same, the matching probability is 1. When there are different texts between two information segments, the matching probability is 0. In the current cluster, there are two POI names, namely "Zhang San's First Green Food Store" and "Zhang San's First Green Source Food Store". Given that the preset step length is 1 byte and the preset sliding window length is 4 bytes, the terminal can, based on the preset step length and preset sliding window length, split the POI name "Zhang San's First Green Food Store" into six information segments: "Zhang San's First", "San's First Green", "First Green Food", "Green Food Store", "Food Store", and "Store". The POI name "Zhang San's First Green Source Food Store" is split into six information segments: "Zhang San's First", "San's First Green", "First Green Source", "Green Source Food", "Source Food Store", and "Food Store". Among them, the first information segment "Zhang San's First" of the POI name "Zhang San's First Green Food Store" is compared with the corresponding first information segment "Zhang San's First" of the POI name "Zhang San's First Green Source Food Store", and the matching probability is 1. The second information segment "San's First Green" of the POI name "Zhang San's First Green Food Store" is compared with the corresponding second information segment "San's First Green" of the POI name "Zhang San's First Green Source Food Store", and the matching probability is 1... and so on. The matching probabilities corresponding to the six information segments in the POI name "Zhang San's First Green Food Store" are 1, 1, 0, 0, 0, 0 respectively. Then, the similarity between the two POI names "Zhang San's First Green Food Store" and "Zhang San's First Green Source Food Store" is the quotient of the sum of the matching probabilities of each information segment and the total number of information segments, that is

[0066] Alternatively, to improve the accuracy of the matching probability, the matching probability can be calculated based on the number of matching characters between information segments corresponding to any two POI names. As an example, the total number of identical characters between two information segments is divided by the total number of characters in one information segment to obtain the matching probability. In the current cluster, there are two POI names, "Zhang San's First Green Food Store" and "Zhang San's First Lvyuan Food Store", and the preset step size is 1 byte and the preset sliding window length is 4 bytes. Then, based on the preset step size and preset sliding window length, the terminal can divide the POI name "Zhang San's First Green Food Store" into six information segments: "Zhang San's First", "San's First Green", "First Green Food", "Green Food Store", "Food Store", and "Store"; divide the POI name "Zhang San's First Lvyuan Food Store" into six information segments: "Zhang San's First", "San's First Green", "First Lvyuan", "Lvyuan Food", "Food Store", and "Store". Among them, the first information segment "Zhang San's First" of the POI name "Zhang San's First Green Food Store" is compared with the first information segment "Zhang San's First" corresponding to the POI name "Zhang San's First Lvyuan Food Store", and its matching probability is the quotient of the total number of identical characters 4 between the two information segments and the total number of characters 4 in one information segment, which is 1. The second information segment "San's First Green" of the POI name "Zhang San's First Green Food Store" is compared with the second information segment "San's First Green" corresponding to the POI name "Zhang San's First Lvyuan Food Store", and its matching probability is the quotient of the total number of identical characters 4 between the two information segments and the total number of characters 4 in one information segment, which is 1... And so on. The matching probabilities corresponding to the six information segments in the POI name "Zhang San's First Green Food Store" are 1, 1, 3 / 4, 3 / 4, 3 / 4, 3 / 4 respectively. Then, the similarity between the two POI names "Zhang San's First Green Food Store" and "Zhang San's First Lvyuan Food Store" is the quotient of the sum of the matching probabilities of each information segment and the total number of information segments of one POI name, that is

[0067] In this embodiment, the terminal can decompose the POI name into smaller information segments according to the preset step size and preset sliding window length, so as to perform a finer-grained comparison of each part of the POI name, which helps to capture the local similarity between two POI names, rather than just the global similarity; and, through text segmentation, the text length of the comparison object is reduced, the comparison complexity is reduced, and the comparison speed is improved.

[0068] In some alternative embodiments, based on the similarity and sorting results, determining whether a POI name change has occurred in the geographical location information corresponding to each cluster includes:

[0069] Dividing the POI names in each cluster into at least one object set according to the similarity;

[0070] For each cluster, based on the sorting result of the POI names, determine the cross status between the POI names in each object set;

[0071] Based on the cross status, determine whether the POI name corresponding to the geographical location information of the cluster has changed.

[0072] The cross status is used to indicate the cross status of the processing times corresponding to the POI names in different object sets within the same cluster. As an example, for two object sets included in a cluster, there are three POI names, namely "Apple Café, Apple Café, Apple Café" in the first object set, corresponding to processing times t1, t3, and t4 respectively, and there is one POI name, namely "Banana Café" in the second object set, and the processing time corresponding to "Banana Café" is t2. Among them, after arranging the occurrence times of the four POI names in this cluster from earliest to latest, the sorting result is t1, t2, t3, t4. This indicates that there is a situation where the two POI names, Apple Café and Banana Café, cross-occur. At this time, the cross status of the two object sets of this cluster is that the processing times of the three POI names in the first object set are not continuous, and it can be directly considered that the POI name has not changed.

[0073] If there are three POI names, namely "Apple Café, Apple Café, Apple Café" in the first object set, corresponding to processing times t1, t2, and t3 respectively, and there are two POI names, namely "Banana Café, Banana Café" in the second object set, and the processing times corresponding to "Banana Café" are t4 and t5. Among them, after arranging the occurrence times of the five POI names in this cluster from earliest to latest, the sorting result is t1, t2, t3, t4, t5. This indicates that there is no cross-occurrence situation between the two POI names, Apple Café and Banana Café. At this time, the cross status of the two object sets of this cluster is that the processing times of the three POI names in the first object set and the two POI names in the second object set are both continuous, and it can be directly considered that the POI name has not changed.

[0074] Among them, the step of determining whether the POI name corresponding to the geographical location information of the cluster has changed based on the cross status includes: when the cross status indicates that the processing times corresponding to the POI names in each object set are continuous, based on the POI name address library and the sorting result, determine whether the POI name corresponding to the geographical location information of each cluster has changed;

[0075] When there is only one object set in the cluster, or when the cross status indicates that the processing times corresponding to the POI names in any one object set are discontinuous, it is determined that the POI name corresponding to the geographical location information of the cluster has not changed. As an example, in the step of dividing the POI names in each cluster into at least one object set according to similarity, for the m POI names in a cluster, the terminal first divides the first POI name into the first object set, and then determines whether the similarity between the second POI name and the first POI name reaches a preset threshold. If it reaches, the second POI name is also divided into the first object set; otherwise, the second POI name is divided into the second object set. Further, it is determined whether the similarity between the third POI name and the first POI name reaches the preset threshold. If it reaches, the third POI name is also divided into the first object set; otherwise, it continues to determine whether the similarity between the third POI name and the second POI name reaches the preset threshold. If it reaches, the third POI name is also divided into the second object set; otherwise, the third POI name is divided into the third object set, and so on, until the mth group of POI names is divided into the corresponding object sets.

[0076] In the step of determining the cross status between the POI names in each object set based on the sorting result of the POI names for each cluster, the terminal can determine whether the appearance times of the POI names in each object set within the current cluster are continuous based on the chronological relationship of the appearance times of all POI names. If they are not continuous, it can be determined that the cross status is that the POI names in each object set appear crosswise. If the appearance times of the POI names in each object set are continuous, it is determined that the cross status is that the POI names in each object set do not appear crosswise.

[0077] In this embodiment, the terminal can calculate the similarity between all POI names corresponding to the same geographical location information to confirm whether there are different POI names for the same geographical location information. If so, it further determines whether the appearance times of the different POI names overlap based on the chronological relationship of the appearance times of all POI names. If there are no different POI names for the same geographical location information, or if there are different POI names and the appearance times of the different POI names overlap, it can be considered that the POI name of this geographical location information has not changed. Through this setting, it is possible to quickly confirm whether the POI name of the geographical location information has changed and ensure the accuracy of the judgment result.

[0078] In some alternative embodiments, determining whether the POI name corresponding to the geographical location information of each cluster has changed based on the POI name address library and the sorting result includes:

[0079] Obtain the POI names corresponding to the geographical locations of the clusters from the POI name and address library; the POI name and address library includes the mapping relationship between at least one actual geographical location and at least one POI name;

[0080] Based on the sorting result, determine the POI name with the latest processing time corresponding to the cluster from the POI names within the cluster;

[0081] When the POI name stored in the POI name and address library is the same as the POI name with the latest processing time, it is determined that the POI name corresponding to the geographical location of the cluster has not changed, otherwise, it is determined that the POI name corresponding to the geographical location of the cluster has changed.

[0082] The POI name and address library can be used to indicate the POI names corresponding to at least one geographical location currently stored.

[0083] When the terminal determines that there are different POI names for the same geographical location information and the occurrence times of the different POI names do not overlap, it can be considered that the POI name corresponding to the current geographical location information has changed. At this time, it is necessary to confirm whether the change has been completed in the data storage system. Then the terminal obtains the POI names corresponding to multiple geographical locations currently stored in the POI name and address library from the data storage system; subsequently, it matches the actual geographical location corresponding to the geographical location information from the POI name and address library, and determines the POI name corresponding to the geographical location information based on the mapping relationship in the POI name and address library. Further, based on the sorting result of the POI names within the cluster corresponding to the geographical location information, determine the POI name with the latest processing time, that is, the newly appeared POI name, as the changed POI name; and determine whether the POI name with the latest processing time corresponds to the POI name of the geographical location information stored in the POI name and address library. If they correspond, it can be determined that the POI name of the current geographical location information has not changed, otherwise, it is determined that the POI name of the geographical location information has changed.

[0084] In this embodiment, when the terminal determines that there are different POI names for a geographical location information and the occurrence times of the different POI names do not overlap, it compares the POI name with the latest processing time with the POI name corresponding to the geographical location information stored in the POI name and address library. If they match, it is considered that the POI name change has been previously made, and there is no need to change the POI name again at this time. If they do not match, it can be considered that the POI name corresponding to the geographical location information stored in the POI name and address library no longer conforms to the actual situation, and it is determined that the POI name of the geographical location information has changed; through this setting, the judgment result of whether the POI name of the geographical location information has changed is more accurate.

[0085] In some alternative embodiments, the method for identifying a change in the POI name further includes:

[0086] When a POI name change occurs in the geographical location information corresponding to the cluster, update the POI name corresponding to the geographical location information in the POI name address library to the POI name with the latest processing time.

[0087] The POI name address library refers to a database pre-established by the service provider of the electronic map for storing the POI names currently corresponding to at least one actual geographical location, so as to meet the navigation or positioning needs of users.

[0088] In this embodiment, when the POI name with the latest processing time in the cluster corresponding to the geographical location information is different from the POI name corresponding to the geographical location information stored in the POI name address library, the terminal can determine that the POI name of the geographical location information has changed, and store the POI name with the latest processing time in the cluster as the newly changed POI name into the POI name address library to replace the originally stored POI name corresponding to the geographical location information, so as to realize the timely update of the POI name corresponding to the geographical location information.

[0089] It should be understood that although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0090] Based on the same inventive concept, the embodiments of the present application also provide a device for identifying a change in the POI name for implementing the method for identifying a change in the POI name involved above. The solution provided by the device for identifying a change in the POI name to solve the problem is similar to the solution described in the method for identifying a change in the POI name above. Therefore, the specific limitations in one or more of the following device embodiments can be referred to the limitations on the method for identifying a change in the POI name above, and will not be repeated here.

[0091] In one embodiment, as Figure 3 shown, a device 300 for identifying a change in the POI name is provided, including:

[0092] An obtaining module 302, configured to obtain the waybill addresses of multiple waybills;

[0093] A splitting module 304, configured to hierarchically split the waybill addresses to obtain the geographical location information corresponding to each waybill and the POI names corresponding to the geographical location information;

[0094] A partitioning module 306, configured to partition the POI names corresponding to each geographical location information into at least one cluster according to the geographical location information;

[0095] A determining module 308, configured to determine whether the POI names corresponding to the geographical location information have changed based on the processing time corresponding to the waybill and the POI names within each cluster.

[0096] In some alternative embodiments, the splitting module 304 is further configured to:

[0097] Perform address correction on the geographical location information based on at least one pre-stored standard location information;

[0098] Perform name correction on the POI names corresponding to the geographical location information based on the mapping relationship between at least one pre-stored standard POI name and at least one POI name with the same name. The partitioning module 306 is further configured to:

[0099] Partition the corrected POI names into at least one cluster according to the corrected geographical location information.

[0100] In some alternative embodiments, the determining module 308 is further configured to:

[0101] Sort the POI names within each cluster based on the processing time corresponding to the waybill to obtain a sorting result;

[0102] Calculate the similarity between any two POI names within each cluster;

[0103] Determine whether the geographical location information corresponding to each cluster has a POI name change based on the similarity and the sorting result.

[0104] In some alternative embodiments, the determining module 308 is further configured to:

[0105] Split the POI names into multiple sequentially arranged information segments based on a preset step size and a sliding window length;

[0106] Calculate the matching probability between the information segments corresponding to any two POI names in the order of arrangement of the information segments, and calculate the similarity based on the matching probability.

[0107] In some alternative embodiments, the determining module 308 is further configured to:

[0108] Divide the POI names within each cluster into at least one set of objects according to the similarity.

[0109] For each cluster, determine the intersection status of the sets of objects based on the sorting result of the POI names.

[0110] Based on the intersection status, determine whether a POI name change has occurred in the geographical location information corresponding to the cluster. In some alternative embodiments, the determining module 308 is further configured to:

[0111] When the intersection status indicates that the processing times corresponding to the POI names in each set of objects are continuous, determine whether a POI name change has occurred in the geographical location information corresponding to the cluster based on the POI name address library and the sorting result.

[0112] When there is only one set of objects in the cluster, or the intersection status indicates that the processing times corresponding to the POI names in any one set of objects are not continuous, determine that no POI name change has occurred in the geographical location information corresponding to the cluster.

[0113] In some alternative embodiments, the determining module 308 is further configured to:

[0114] Obtain the POI name of the geographical location information corresponding to the cluster from the POI name address library; the POI name address library stores the corresponding relationship between at least one actual geographical location and at least one POI name.

[0115] Based on the sorting result, determine the POI name with the latest processing time from the POI names within the cluster.

[0116] When the POI name stored in the POI name address library is the same as the POI name with the latest processing time, determine that no POI name change has occurred in the geographical location information corresponding to the cluster; otherwise, determine that a POI name change has occurred in the geographical location information corresponding to the cluster.

[0117] In some alternative embodiments, the determining module 308 is further configured to:

[0118] When a POI name change has occurred in the geographical location information corresponding to the cluster, update the POI name corresponding to the geographical location information in the POI name address library to the POI name with the latest processing time.

[0119] Each module in the above device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0120] The (device subject) provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effects are similar. Details are not described herein in this embodiment.

[0121] Figure 4 It is a schematic structural diagram of a computer provided in this application. As Figure 4 shown, the computer device 40 provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. Among them, the processor 401, the memory 402, and the communication component 403 are connected through a bus 404.

[0122] In a specific implementation process, at least one processor 401 executes computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0123] For the specific implementation process of the processor 401, reference can be made to the above method embodiment, and its implementation principle and technical effects are similar. Details are not described herein in this embodiment.

[0124] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application-specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0125] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0126] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the attached drawings of this application are not limited to only one bus or one type of bus.

[0127] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0128] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the above method is implemented.

[0129] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0130] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0131] The division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in an electrical, mechanical, or other forms.

[0132] The unit described as a separating component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across 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.

[0133] In addition, in each embodiment of the present invention, each functional unit may be integrated into a processing unit, may exist separately physically for each unit, or two or more units may be integrated into one unit.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0135] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0136] Finally, it should be noted that: after considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation schemes of the present invention. The present invention aims to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the precise structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for identifying POI name changes, characterized in that: include: Get the waybill addresses of multiple waybills; The waybill addresses are hierarchically segmented to obtain geographical location information corresponding to each waybill and a POI name corresponding to the geographical location information; According to the geographic location information, the POI names corresponding to the geographic location information are divided into at least one cluster; Based on the processing time corresponding to the waybill and the POI names in each of the clusters, it is determined whether the POI name corresponding to the geographic location information is changed.

2. The method according to claim 1, characterized in that Before dividing the POI names corresponding to the geographical location information into at least one cluster according to the geographical location information, the method further includes: Based on at least one pre-stored standard location information, performing address correction on the geographical location information; Based on a pre-stored mapping relationship between at least one standard POI name and at least one POI name with the same name, modifying the POI name corresponding to the geographic location information; The step of dividing the POI names corresponding to the geographical location information into at least one cluster according to the geographical location information includes: According to the corrected geographical location information, the corrected POI names are divided into at least one cluster.

3. The method according to claim 1, characterized in that The determining, based on the processing time corresponding to the waybill and the POI names in each of the clusters, whether the POI name corresponding to the geographic location information has changed includes: Based on the processing time corresponding to the waybill, the POI name in each cluster is sorted to obtain a sorting result; Calculating the similarity between any two POI names in each cluster; Based on the similarity and the sorting result, it is determined whether the geographical location information corresponding to each cluster has a POI name change.

4. The method according to claim 3, characterized in that The calculating the similarity between any two POI names in each cluster comprises: Based on a preset step size and a sliding window length, the POI name is divided into a plurality of sequentially arranged information segments; According to the arrangement order of the information segments, the matching probabilities between any two of the information segments corresponding to the POI names are calculated, and based on the matching probabilities, the similarity is calculated.

5. The method according to claim 3 or 4, characterized in that: The determining, based on the similarity and the sorting result, whether the geographical location information corresponding to each cluster has a POI name change includes: According to the similarity, the POI name in each cluster is divided into at least one object set; For each of the clusters, based on the sorting results of the POI names, determining the intersection status between the POI names in each of the object sets; Based on the intersection state, it is determined whether a POI name change occurs in the geographical location information corresponding to the cluster.

6. The method according to claim 5, characterized in that The determining, based on the intersection state, whether a POI name change occurs in the geographical location information corresponding to the cluster, includes: When the intersection state indicates that the processing times corresponding to the POI names in each of the object sets are continuous, determining whether the geographical location information corresponding to the cluster has a POI name change based on the POI name address library and the sorting result; When the cluster has only one object set, or the intersection state indicates that the processing time corresponding to the POI name in any one of the object sets is discontinuous, it is determined that no POI name change occurs in the geographical location information corresponding to the cluster.

7. The method according to claim 6, characterized in that The determining, based on the POI name address database and the sorting result, whether the geographical location information corresponding to each cluster has a POI name change includes: Obtaining the POI name corresponding to the geographical location information of the cluster from the POI name and address database; the POI name and address database stores a corresponding relationship between at least one actual geographical location and at least one POI name; Based on the sorting result, determining the POI name with the latest processing time from the POI names in the cluster; When the POI name stored in the POI name address library is consistent with the POI name with the latest processing time, it is determined that the geographical location information corresponding to the cluster has not been changed; otherwise, it is determined that the geographical location information corresponding to the cluster has been changed.

8. The method according to claim 7, characterized in that The method further comprises: When the POI name corresponding to the geographical location information of the cluster is changed, the POI name corresponding to the geographical location information in the POI name address database is updated to the POI name with the latest processing time.

9. A device for identifying POI name changes, characterized in that: include: The acquisition module is used to obtain the waybill addresses of multiple waybills; A segmentation module, used to perform hierarchical segmentation on the waybill address to obtain geographical location information corresponding to each waybill and a POI name corresponding to the geographical location information; A division module, used for dividing the POI names corresponding to the geographical location information into at least one cluster according to the geographical location information; The determination module is used to determine whether the POI name corresponding to the geographic location information is changed based on the processing time corresponding to the waybill and the POI name in each cluster.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images