A method, apparatus, electronic device, and storage medium for detecting abnormal POI data.

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for detecting abnormal POI data, relating to the field of data processing, particularly the field of map data processing. The specific implementation scheme is as follows: For the POI to be detected in the map, the building information in the database and the building information in the map are segmented into words to obtain a first segmentation result and a second segmentation result. The first word in the first segmentation result is matched with the second word in the second segmentation result to obtain a binary matching result for each first word. If there exists a first word whose binary matching result is always a second preset value, then the building information in the map is determined to be abnormal. If there exists a first word whose binary matching result is always a second preset value, it indicates that the first segmentation result and the second segmentation result are different, meaning that the building information corresponding to the POI in the database is different from the building information corresponding to the POI in the map, thus determining that the POI data in the map is abnormal, thereby effectively detecting abnormal POI data.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the field of map data processing technology. Background Technology

[0002] Due to errors in map data linking, incorrect information may be displayed for Points of Interest (POIs) on the map. For example, multiple hotels may be displayed for the same POI, or the same hotel may be listed at multiple POI locations. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for detecting abnormal POI data.

[0004] According to one aspect of this disclosure, a method for detecting abnormal POI data is provided, comprising:

[0005] For each POI to be detected in the map, obtain the reference building information corresponding to the POI in the database and the attached building information corresponding to the POI in the map.

[0006] The reference building information and the attached building information are segmented into words respectively to obtain a first segmentation result and a second segmentation result; wherein, the first segmentation result is the segmentation result of one of the reference building information and the attached building information; and the second segmentation result is the segmentation result of the other of the reference building information and the attached building information.

[0007] For each first word in the first word segmentation result, the first word is matched with each second word in the second word segmentation result to obtain the binarized matching result of each first word. The binarized matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched.

[0008] If there is an abnormal first word in the first word segmentation result, then the attached building information is determined to be abnormal POI data, wherein the abnormal first word is the first word whose binary matching result is all the second preset value.

[0009] According to another aspect of this disclosure, an apparatus for detecting abnormal POI data is provided, comprising:

[0010] The acquisition module is used to acquire reference building information corresponding to the POI in the database and attached building information corresponding to the POI in the map for the POI to be detected in the map.

[0011] The word segmentation module is used to segment the reference building information and the attached building information into words respectively, to obtain a first word segmentation result and a second word segmentation result; wherein, the first word segmentation result is the word segmentation result of one of the reference building information and the attached building information; and the second word segmentation result is the word segmentation result of the other of the reference building information and the attached building information.

[0012] The matching module is used to match each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched.

[0013] The detection module is used to determine that the attached building information is abnormal POI data if there is an abnormal first word in the first word segmentation result, wherein the abnormal first word is a first word whose binary matching result is a second preset value.

[0014] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform any of the above-described methods for detecting abnormal POI data.

[0018] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute any of the above-described methods for detecting abnormal POI data.

[0019] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method for detecting abnormal POI data as described above.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0022] Figure 1 This is a schematic diagram of a first embodiment of the method for detecting abnormal POI data provided in this disclosure;

[0023] Figure 2 This is a schematic diagram of a second embodiment of the method for detecting abnormal POI data provided in this disclosure;

[0024] Figure 3 This is a flowchart illustrating the matching of the first word segmentation result and the second word segmentation result in the abnormal POI data detection method provided in this publication.

[0025] Figure 4 A schematic diagram of the third embodiment of the abnormal POI data detection method provided in this disclosure;

[0026] Figure 5 This is a schematic diagram of a device for detecting abnormal POI data provided in this disclosure;

[0027] Figure 6 This is a block diagram of an electronic device used to implement the abnormal POI data detection method provided in the embodiments of this disclosure. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and 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 this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] Currently, many types of apps (applications) use map data for route planning, information display, and more. For example, navigation apps use map data to plan routes from the starting point to the destination, while travel apps use map data to display hotel and attraction information.

[0030] Errors in map data linking can cause POI data on the map to differ from that in the database. The data in the database is typically collected by relevant personnel or uploaded by clients and reflects actual conditions. Therefore, if the POI data on the map differs from the information in the database, it indicates an anomaly in the map's POI data. For example, a POI in the database might correspond to hotel A, but due to a data linking error, the map might show that the POI as hotels A, B, and C.

[0031] Anomalies in POI data on maps can significantly impact related apps. For example, travel apps typically display information for only one hotel per POI. If multiple hotels correspond to the same POI, the app will display incomplete hotel information, narrowing the user's choices and degrading the user experience. Therefore, it is necessary to detect and correct abnormal POI data on maps to reduce the occurrence of such situations.

[0032] To detect abnormal POI data in maps, this disclosure provides a method, apparatus, electronic device, and storage medium for detecting abnormal POI data. The method for detecting abnormal POI data provided in this disclosure is first described by way of example:

[0033] The abnormal POI data detection method provided in this disclosure can be applied to any electronic device with abnormal POI data detection capabilities. Such electronic devices can be personal computers, mobile terminals, servers, etc.

[0034] like Figure 1 As shown, Figure 1 The flowchart of the first embodiment of the abnormal POI data detection method provided in this disclosure may specifically include the following steps:

[0035] Step S101: For the POI to be detected in the map, obtain the reference building information corresponding to the POI in the database and the attached building information corresponding to the POI in the map;

[0036] Step S102: Perform word segmentation on the reference building information and the attached building information respectively to obtain a first word segmentation result and a second word segmentation result; wherein, the first word segmentation result is the word segmentation result of one of the reference building information and the attached building information; the second word segmentation result is the word segmentation result of the other of the reference building information and the attached building information.

[0037] Step S103: For each first word in the first word segmentation result, match the first word with each second word in the second word segmentation result to obtain the binarized matching result of each first word. The binarized matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched.

[0038] Step S104: If there is an abnormal first word in the first word segmentation result, then the attached building information is determined to be abnormal POI data, wherein the abnormal first word is the first word whose binary matching result is all the second preset value.

[0039] By applying this embodiment, for a POI to be detected in a map, the building information corresponding to the POI in the database and the building information corresponding to the POI in the map are segmented into words to obtain a first segmentation result and a second segmentation result. Each first word in the first segmentation result is matched one by one with each second word in the second segmentation result to obtain a binary matching result for each first word. This binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word matched successfully, and the second preset value indicates that the first word and the second word did not match successfully. If there are first words whose binary matching results are all the second preset values, then the building information corresponding to the POI in the map is determined to be abnormal. If there are first words whose binary matching results are all the second preset values, it means that there is a first word in the first segmentation result that is different from all the second words. In other words, the first segmentation result is different from the second segmentation result, indicating that the building information corresponding to the POI in the database is different from the building information corresponding to the POI in the map. Therefore, it can be determined that the building information corresponding to the POI in the map is abnormal information. Therefore, by applying this embodiment, abnormal POI data can be effectively detected.

[0040] Furthermore, related technologies convert both the string of the location name or address corresponding to the POI to be detected in the map and the string of the name or address corresponding to the POI in the database into vectors, and calculate the similarity distance between the two vectors, such as cosine distance, Euclidean distance, etc. If the similarity distance is greater than a preset threshold, it is determined that the POI data in the map is abnormal. Compared with related technologies, the embodiments of this disclosure, when calculating the similarity between two sets of building information, can obtain the similarity value of the two sets of word segmentation results by performing simple word matching and binarization operations on the word segmentation results corresponding to the two sets of building information. It is not necessary to convert the two strings into vectors and then calculate the similarity through the similarity distance between the vectors, which improves the simplicity of similarity calculation and thus improves the efficiency of abnormal POI data detection.

[0041] The following provides an exemplary description of the above steps S101 - S104:

[0042] The above POI to be detected can be any POI in the map. In step S101, for the POI to be detected, building information corresponding to the POI in the database can be obtained, including the name and address of the building, etc. And call the map interface to obtain the attached basic information of the POI in the map. The above attached basic information is the basic information of the building attached to the above POI point in the map, which can include the name, address, phone number, and status (in business / not in business), etc. Then, the building name and address, etc. at the above POI point can be extracted from the above attached basic information. For the convenience of description, the building information corresponding to the POI in the database is hereinafter referred to as reference building information, and the building information corresponding to the above POI in the map is referred to as attached building information. The above building information can be the building name and / or the building address.

[0043] After that, it can be determined whether the above reference building information and attached building information point to the same building, such as whether they have the same name or the same address, etc. When comparing the reference building information and the attached building information, it is necessary to ensure that the types of the reference building information and the attached building information are consistent. For example, if the reference building information is the building name, then the attached building information is also the building name. If the reference building information is the building name and address, the attached building information is also the building name and address.

[0044] The following takes the calculation of the similarity between building names as an example to illustrate the above steps S102 - S104.

[0045] In step S102, when segmenting the above reference building information and attached building information, the above reference building information and attached building information can be segmented according to a fixed number of characters. For example, the reference building information and attached building information can be segmented into groups of two characters or three characters. For example, for the hotel name "AABC Hotel", if it is segmented into groups of two characters, the segmentation results of "AA", "AB", "BC", "C Hotel", and "Hotel" can be obtained. However, this is likely to result in meaningless segmentation results.

[0046] As another specific implementation, based on Figure 1 , as Figure 2 shown, the reference building information and attached building information can be segmented according to the following steps.

[0047] Step S201: Segment the reference building information and the attached building information respectively based on a preset basic vocabulary list to obtain the first candidate segmentation and the second candidate segmentation;

[0048] Step S202: Match the first candidate word segment and the second candidate word segment with words in the preset stop word list;

[0049] Step S203: Remove words from the first and second candidate word segments that successfully match words in the preset stop word list to obtain the first word segmentation result and the second word segmentation result.

[0050] In step S201, the aforementioned preset basic vocabulary list may include preset phrases for each building name or address. For example, it may include "special offer", "chain", "hotel", as well as hotel brand, city name, district / county name, etc., which can be preset according to the actual situation.

[0051] When segmenting the aforementioned reference building information and attached building information based on a preset basic vocabulary, each word in the preset basic vocabulary can be matched with the reference building information and attached building information to obtain a first candidate word and a second candidate word. The first candidate word is the result obtained after segmenting the reference building information or attached building information based on the preset basic vocabulary, while the second candidate word is another word segmentation result other than the first candidate word among the results obtained after segmenting the reference building information or attached building information based on the preset basic vocabulary.

[0052] The first and second candidate word segments mentioned above can include words from the preset basic word list that successfully match the reference building information and the attached building information, as well as words from the reference building information and the attached building information that do not successfully match in the preset basic word list. For example, if the reference building information is "AABC Hotel", and only "BC" and "hotel" are matched in the preset basic word list, then the resulting word segmentation results are "AA", "BC", and "hotel".

[0053] The first and second candidate word segments can then be filtered based on a preset stop word list. This preset stop word list can include conjunctions and symbols, etc., words without specific semantic meaning. For example, the preset stop word list can include "and", "with", "·", ",", "-", etc.

[0054] For example, each character in the preset stop word list can be matched one by one with the first candidate word segment and the second candidate word segment. The successfully matched words are then removed from the first candidate word segment and the second candidate word segment to obtain the first word segmentation result and the second word segmentation result.

[0055] It can be understood that hotel names and addresses usually contain fixed collocations of words, such as "express hotel", "preferential hotel", "City A", etc. The preset basic word list contains words preset for hotel names and / or addresses. Therefore, by performing word segmentation on the reference building information and the attached building information based on the preset basic word list and the preset stop word list, the possibility of meaningless words and symbols appearing in the word segmentation results can be reduced. For example, the possibility of obtaining a word segmentation result containing a meaningless word like "hui jiu" after segmenting "preferential hotel" can be reduced, thereby improving the subsequent similarity calculation efficiency.

[0056] After obtaining the above first word segmentation result and the second word segmentation result, the similarity between the above first word segmentation result and the second word segmentation result can be calculated. The similarity between the above first word segmentation result and the second word segmentation result is the similarity between the above reference building information and the attached building information.

[0057] When calculating the similarity between the above first word segmentation result and the second word segmentation result, for each first word in the first word segmentation result, the first word can be matched one by one with the second words in the second word segmentation result to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched. Exemplarily, the above first preset value can be 1, and the above second preset value can be 0. Of course, the above first preset value and the second preset value can also be other values, and the present disclosure does not make specific limitations thereto. The above "successful match" can mean that the first word and the second word are the same.

[0058] As a specific implementation manner, as Figure 3 shown, the following steps can be used to match each first word and the second words:

[0059] Step S301: Obtain the first word from the first word segmentation result.

[0060] In this step, the first words can be obtained in any order, or in the word order of each first word in the corresponding building information.

[0061] Step S302: For the first word, obtain the second word from the second word segmentation result.

[0062] In this step, the second words can be obtained in any order, or in the word order of each first word in the corresponding building information.

[0063] Step S303: Match the second word with the first word.

[0064] Step S304: Determine whether the second word matches the first word successfully; if the match is successful, proceed to step S305; if the match is unsuccessful, proceed to step S306.

[0065] Step S305: Determine the binarized matching result of the first word and the second word as the first preset value; execute step S309.

[0066] Step S306: Determine the binarized matching result of the first word and the second word as the second preset value.

[0067] Step S307: Determine whether all second words have been obtained; if not all second words have been obtained, proceed to step S308; if all second words have been obtained, proceed to step S309.

[0068] "All second words are retrieved" means that all second words in the second word segmentation result have been matched with the first word mentioned above.

[0069] Step S308: Obtain the new second word from the second word segmentation result, and return to step S303.

[0070] Step S309: Determine whether all first words have been obtained. If yes, end the process; otherwise, proceed to step S310.

[0071] Step S310: Obtain the new first word from the first word segmentation result and return to execute step 302.

[0072] As one specific implementation, the first word can be matched one by one with the second word in the second word segmentation result using a matrix to obtain the binary matching result of each first word, thereby calculating the similarity between the first word segmentation result and the second word segmentation result. For example, the first word segmentation result and the second word segmentation result can each be treated as a one-dimensional array, and the elements in the arrays can be matched one by one. The matching result of each element in the two arrays can be recorded using a matrix. For instance, after matching the i-th word in the array corresponding to the first word segmentation result with the j-th word in the array corresponding to the second word segmentation result, the matching result can be recorded at the i-th row and j-th column position or the j-th row and i-th column position of the matrix, where i is any positive integer from 1 to N, N is the number of words in the first word segmentation result, j is any positive integer from 1 to M, and M is the number of words in the second word segmentation result.

[0073] For example, if the first word segmentation result is word 1, word 2, word 3, and the second word segmentation result is word 4, word 5, word 3, then the array formed by the first word segmentation result is [word 1, word 2, word 3], and the array formed by the second word segmentation result is [word 4, word 5, word 3]. Matching the first and second word segmentation results yields the following result:

[0074]

[0075] The first word segmentation result mentioned above can be either the word segmentation result of the reference building information or the word segmentation result of the attached building information. The second word segmentation result mentioned above is another word segmentation result between the word segmentation result of the reference building information and the word segmentation result of the attached building information. During matching, words contained in the word segmentation result of the reference building information can be matched one by one with words contained in the word segmentation result of the attached building information, or words contained in the word segmentation result of the attached building information can be matched one by one with words contained in the word segmentation result of the reference building information.

[0076] Depending on the number of words contained in the first and second word segmentation results, the aforementioned one-to-one matching method can differ, as explained below:

[0077] Scenario 1: The number of words in the first word segmentation result is different from the number of words in the second word segmentation result.

[0078] In this scenario, if the segmentation result containing fewer words in both the reference building information segmentation result and the linked building information segmentation result is taken as the first segmentation result, and the segmentation result containing more words is taken as the second segmentation result, it will result in the second segmentation result containing second words that do not match any of the first words, even if each first word has a successfully matched second word. This does not mean that the first segmentation result and the second segmentation result are consistent. However, since there are no first words that do not match the second words, it may lead to the incorrect judgment that no abnormal POI data has appeared.

[0079] Therefore, in this situation, the segmentation result containing more words in both the reference building information segmentation result and the segmentation result containing fewer words can be used as the first segmentation result, and the segmentation result containing fewer words can be used as the second segmentation result. In this way, matching each first word in the first segmentation result with each second word in the second segmentation result is equivalent to simultaneously matching each second word in the second segmentation result with each first word. When there are no unmatched first words in the first segmentation result, there are also no unmatched second words in the second segmentation result, indicating that the first and second segmentation results are consistent.

[0080] Scenario 2: The number of words in the first segmentation result is equal to the number of words in the second segmentation result.

[0081] In this scenario, either the segmentation result referencing the building information or the segmentation result linking the building information is taken as the first segmentation result, and the other is taken as the second segmentation result. Matching each first word in the first segmentation result with each second word in the second segmentation result is equivalent to simultaneously matching each second word with each first word. If there are no first words in the first segmentation result that fail to match any of the second words in the second segmentation result, and there are also no second words in the second segmentation result that fail to match any of the first words, it can be concluded that the two segmentation results are consistent.

[0082] When matching each word in the first word segmentation result with each word in the second word segmentation result, the matching can be performed in any order, such as according to word order or not. This disclosure does not impose any specific restrictions on this.

[0083] If the binarized matching results of each first word in the first word segmentation result all contain the first preset value, it indicates that for each first word in the first word segmentation result, there exists a second word that successfully matches it, indicating that the first word segmentation result and the second word segmentation result are consistent. Therefore, it can be determined that the attached building information is normal POI data.

[0084] If the first word segmentation result contains a first word whose binary matching result is the second preset value, it indicates that the first and second word segmentation results are inconsistent, meaning the attached building information is abnormal. Therefore, the attachment can be removed, i.e., the attached building information corresponding to the above POI in the map can be deleted. Simultaneously, an unattachment change record can be recorded in the database to prevent incorrectly attached data from being repeatedly attached. This improves the accuracy of map POI data.

[0085] Regarding the aforementioned issue where abnormal POI data in maps leads to incomplete hotel information displayed by travel apps that utilize map data, thus narrowing the user's selection range, this embodiment can improve the accuracy of map POI data, thereby enhancing the comprehensiveness of hotel information displayed by travel apps, increasing the number of hotel quotes, and expanding the user's selection range.

[0086] If the number of words contained in the first segmentation result and the second segmentation result are different, it can also indicate that the two segmentation results are different and the information of the two buildings is different.

[0087] In real-world applications, hotel names may contain duplicate words. Using the method described above could lead to multiple matches for the same word, resulting in incorrectly identifying incorrect POI data as correct POI data.

[0088] Therefore, as a specific implementation, step S302 above, obtaining the second word from the second word segmentation result for the first word, may include:

[0089] For the first word, the second word is obtained from the words to be matched in the second word segmentation result. The words to be matched are initially all the second words in the second word segmentation result.

[0090] If the second word obtained matches the first word successfully, the second word can be deleted from the words to be matched in order to avoid the words in the second word segmentation result being matched repeatedly.

[0091] In step S307 above, determine whether all second words have been obtained. Specifically, determine whether all second words in the word to be matched have been obtained. If not all second words in the word to be matched have been obtained, proceed to step S308. If all second words in the word to be matched have been obtained, proceed to step S309.

[0092] Step S308 above: Obtain a new second word from the second word segmentation result. Specifically, this can be to obtain a new second word from the words to be matched in the second word segmentation result.

[0093] For example, the first word segmentation result includes words A, B, and C, and the second word segmentation result includes words A, B, and C. The first word segmentation result is matched with each of the second words in the order of words A, B, and C. Word A in the first word segmentation result matches successfully with word A in the second word segmentation result. Therefore, word A can be removed from the second word segmentation result, and the remaining words are used as the words to be matched in subsequent matching. For instance, when matching word B in the first word segmentation result with words in the second word segmentation result, only words B in the first word segmentation result will be matched with words B and C in the second word segmentation result.

[0094] In one specific implementation, a first word segmentation result array and a second word segmentation result array can be maintained separately. Initially, the first word segmentation result array contains all first words, and the second word segmentation result array contains all second words. If, during the matching process, a second word that successfully matches a first word is found, it can be deleted from the second word segmentation result array.

[0095] This reduces the likelihood of matching errors caused by repeated words in the word segmentation results, improves the accuracy of similarity calculation, and thus improves the detection accuracy of abnormal POI data.

[0096] Because building information comes from various sources, including data uploaded by businesses and collected by relevant personnel, the descriptions of building information from different sources may differ. This could lead to different, similar-sounding hotel names being uploaded for the same hotel. For example, the same hotel might have two names: "Special Offer Hotel" and "Discount Hotel." In such cases, using the matching method described above could result in correct POI data being identified as abnormal POI data.

[0097] Therefore, as a specific implementation method, based on Figure 1 ,like Figure 2 As shown, the first and second word segmentation results can be matched using the following steps:

[0098] Step S204: Based on the preset thesaurus, obtain the synonyms of each second word in the second word segmentation result;

[0099] Step S205: For each first word in the first word segmentation result, match the first word with each second word and each synonym of the second word to obtain the binary matching result of each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word is the same as the second word or the synonym of the second word. The second preset value indicates that the first word is not the same as the second word and the synonym of the second word.

[0100] In step S204, the aforementioned thesaurus can be pre-set according to actual circumstances. For example, "special offer" and "special price" can be set as synonyms.

[0101] By combining the thesaurus to match the first and second word segmentation results, misjudgments that may be caused by different building names due to different data sources can be avoided to some extent, thus improving the accuracy of detecting abnormal POI data.

[0102] like Figure 4 As shown, Figure 4 A flowchart illustrating a specific embodiment of the abnormal POI data detection method provided in this disclosure may include the following steps:

[0103] Step S401: Obtain the hotel name corresponding to the target POI from the database, and call the map interface to obtain the basic information of the target POI in the map, and extract the hotel name corresponding to the target POI from it.

[0104] For example, the hotel name corresponding to the target POI obtained from the database is "AABC Hotel", and the hotel name corresponding to the target POI obtained from the map is "DEBC Hotel".

[0105] Step S402: Perform word processing on the two hotel names mentioned above.

[0106] For example, “AABC hotel” and “DEBC hotel” are segmented into words based on a preset basic vocabulary, and the stop words in the segmented results are filtered based on a preset stop word list to obtain two segmentation results. The segmentation results of “AABC hotel” are: “AA”, “BC” and “hotel”, and the segmentation results of “DEBC hotel” are: “DE”, “BC” and “hotel”.

[0107] Step S403: Calculate the similarity of the two-word segmentation results. If a synonym is found, return 1.

[0108] For example, by combining a thesaurus, synonyms for "DE", "BC", and "hotel" are obtained. Then, the words "AA", "BC", and "hotel" in the word segmentation results of "AABC hotel" are matched one by one with "DE", "BC", "hotel", and their synonyms. If a match is successful, the similarity between the corresponding words is recorded as 1. The overall similarity is then calculated based on the matching results of each word. Specifically, if all words are matched successfully, the overall similarity between the first and second word segmentation results is 1.

[0109] Each of the above steps S401-S403 targets a hotel name in a database and a hotel name on a map. If a target POI on the map corresponds to multiple hotel names, steps S401-S403 can be executed multiple times.

[0110] Step S404: Filter out hotels with a similarity score of not 1.

[0111] Step S405: Send an unattachment event to the database, which means unlinking "DEBC Hotel" from the target POI in the database, or deleting the "DEBC Hotel" information from the target POI on the map. Record the unattachment change in the database to prevent incorrectly attached data from being reattached, such as reattaching the "DEBC Hotel" information to the target POI.

[0112] By applying the embodiments of this disclosure, abnormal POI data in the map is detected and deleted, which effectively reduces the probability of multiple hotels being attached to the same POI, improves the accuracy of hotel attachment, avoids redundancy of hotels attached to POIs, increases the diversity of hotel price information displayed on the map, improves user choice, and enhances user experience.

[0113] like Figure 5 As shown, Figure 5 This is a schematic diagram of a structural device for detecting abnormal POI data provided in this disclosure. The device may include:

[0114] The acquisition module 501 is used to acquire, for example, reference building information corresponding to the POI in the database and attached building information corresponding to the POI in the map for the POI to be detected in the map.

[0115] The word segmentation module 502 is used to segment the reference building information and the attached building information into words respectively, to obtain a first word segmentation result and a second word segmentation result; wherein, the first word segmentation result is the word segmentation result of one of the reference building information and the attached building information; and the second word segmentation result is the word segmentation result of the other of the reference building information and the attached building information.

[0116] The matching module 503 is used to match each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched.

[0117] The detection module 504 is used to determine that the attached building information is abnormal POI data if there is an abnormal first word in the first word segmentation result, wherein the abnormal first word is a first word whose binary matching result is a second preset value.

[0118] In one possible embodiment, the step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binarized matching result for each first word includes:

[0119] Based on a preset thesaurus, obtain the synonyms of each second word in the second word segmentation result;

[0120] For each first word in the first word segmentation result, the first word is matched with each second word and each synonym of the second word to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word is the same as the second word or the synonym of the second word, and the second preset value indicates that the first word is not the same as the second word and the synonym of the second word.

[0121] In one possible embodiment, the step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binarized matching result for each first word includes:

[0122] Obtain the first word from the first word segmentation result;

[0123] For the first word, obtain the second word from the second word segmentation result;

[0124] Match the second word with the first word;

[0125] If the second word matches the first word successfully, the binarized matching result of the first word and the second word is determined as the first preset value; if the second word does not match the first word successfully, the binarized matching result of the first word and the second word is determined as the second preset value.

[0126] Obtain a new second word from the second word segmentation result, and return to the step of matching the second word with the first word until the second word matches the first word successfully, or, all second words in the second word segmentation result for the first word are obtained;

[0127] Obtain a new first word from the first word segmentation result, and return to execute the step of obtaining a second word from the second word segmentation result for the first word, until all first words in the first word segmentation result have been obtained.

[0128] In one possible embodiment, obtaining the second word from the second word segmentation result for the first word includes:

[0129] For the first word, a second word is obtained from the words to be matched in the second word segmentation result, wherein the words to be matched are initially all the second words in the second word segmentation result;

[0130] The matching module is configured to delete the second word from the words to be matched if the second word matches the first word successfully;

[0131] The step of obtaining a new second word from the second word segmentation result and returning to perform the step of matching the second word with the first word, until all second words in the second word segmentation result for the first word have been obtained, includes:

[0132] Obtain new second words from the words to be matched in the second word segmentation result, and return to the step of matching the second words with the first words, until all second words in the words to be matched in the second word segmentation result for the first words have been obtained.

[0133] In one possible embodiment, the step of segmenting the reference building information and the attached building information into words to obtain a first segmentation result and a second segmentation result includes:

[0134] Based on a preset basic vocabulary, the information of the reference building and the information of the attached building are segmented into words to obtain a first candidate word and a second candidate word.

[0135] Match the first candidate word segment and the second candidate word segment with words in the preset stop word list;

[0136] Remove words from the first and second candidate word segments that successfully match words in the preset stop word list to obtain the first word segmentation result and the second word segmentation result.

[0137] In one possible embodiment, the detection module is configured to determine that the attached building information is normal POI data if the binarized matching results of each first word in the first word segmentation result all contain the first preset value.

[0138] The collection, storage, use, processing, transmission, provision, and disclosure 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.

[0139] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0140] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0141] like Figure 6As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0142] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0143] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for detecting abnormal POI data. For example, in some embodiments, the method for detecting abnormal POI data may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method for detecting abnormal POI data described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method for detecting abnormal POI data by any other suitable means (e.g., by means of firmware).

[0144] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0146] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0149] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0150] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0151] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting abnormal POI data, comprising: For a POI to be detected in the map, obtain the reference building information corresponding to the POI in the database and the attached building information corresponding to the POI in the map; Building information includes the building name and / or building address; Each word in the preset basic vocabulary is matched with the reference building information and the attached building information to obtain a first candidate word segment and a second candidate word segment; the preset basic vocabulary includes word groups preset for each building name or address; the first candidate word segment and the second candidate word segment respectively include words in the preset basic vocabulary that successfully match the reference building information and the attached building information, as well as words in the reference building information and the attached building information that do not successfully match the preset basic vocabulary. Match the first candidate word segment and the second candidate word segment with words in the preset stop word list; Words that successfully match words in the preset stop word list are removed from the first and second candidate word segments to obtain the first word segmentation result and the second word segmentation result; wherein, the first word segmentation result is the word segmentation result containing a large number of words in the word segmentation results of the reference building information and the attached building information; the second word segmentation result is the word segmentation result containing a small number of words in the word segmentation results of the reference building information and the attached building information; For each first word in the first word segmentation result, the first word is matched with each second word in the second word segmentation result to obtain the binarized matching result of each first word. The binarized matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched. If an abnormal first word exists in the first word segmentation result, the attached building information is determined to be abnormal POI data, the attached building information corresponding to the POI in the map is deleted, and the unattachment change record table is recorded in the database; wherein, the abnormal first word is the first word whose binary matching result is all the second preset value.

2. The method according to claim 1, wherein, The step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word includes: Based on a preset thesaurus, obtain the synonyms of each second word in the second word segmentation result; For each first word in the first word segmentation result, the first word is matched with each second word and each synonym of the second word to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word is the same as the second word or the synonym of the second word, and the second preset value indicates that the first word is not the same as the second word and the synonym of the second word.

3. The method according to claim 1, wherein, The step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word includes: Obtain the first word from the first word segmentation result; For the first word, obtain the second word from the second word segmentation result; Match the second word with the first word; If the second word matches the first word successfully, the binarized matching result of the first word and the second word is determined as the first preset value; if the second word does not match the first word successfully, the binarized matching result of the first word and the second word is determined as the second preset value. Obtain a new second word from the second word segmentation result, and return to the step of matching the second word with the first word until the second word matches the first word successfully, or, all second words in the second word segmentation result for the first word are obtained; Obtain a new first word from the first word segmentation result, and return to execute the step of obtaining a second word from the second word segmentation result for the first word, until all first words in the first word segmentation result have been obtained.

4. The method according to claim 3, wherein, The step of obtaining the second word from the second word segmentation result for the first word includes: For the first word, a second word is obtained from the words to be matched in the second word segmentation result, wherein the words to be matched are initially all the second words in the second word segmentation result; The method further includes: If the second word matches the first word, then the second word is deleted from the list of words to be matched. The step of obtaining a new second word from the second word segmentation result and returning to perform the step of matching the second word with the first word, until all second words in the second word segmentation result for the first word have been obtained, includes: Obtain new second words from the words to be matched in the second word segmentation result, and return to the step of matching the second words with the first words, until all second words in the words to be matched in the second word segmentation result for the first words have been obtained.

5. The method according to claim 1, further comprising: If the binarized matching results of each first word in the first word segmentation result all contain the first preset value, then the attached building information is determined to be normal POI data.

6. A device for detecting abnormal POI data, comprising: The acquisition module is used to acquire reference building information corresponding to the POI in the database and attached building information corresponding to the POI in the map for the POI to be detected in the map. Building information includes the building name and / or building address; The word segmentation module is used to match each word in a preset basic word list with the reference building information and the attached building information to obtain a first candidate word and a second candidate word; match the first candidate word and the second candidate word with words in a preset stop word list; and remove words in the first candidate word and the second candidate word that successfully match words in the preset stop word list to obtain a first word segmentation result and a second word segmentation result; wherein, the first word segmentation result is the word segmentation result containing a large number of words in the word segmentation results of the reference building information and the attached building information; the second word segmentation result is the word segmentation result containing a small number of words in the word segmentation results of the reference building information and the attached building information; the preset basic word list includes preset word groups for each building name or address; the first candidate word and the second candidate word respectively include words in the preset basic word list that successfully match the reference building information and the attached building information, and words in the reference building information and the attached building information that do not successfully match in the preset basic word list; The matching module is used to match each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word and the second word are successfully matched, and the second preset value indicates that the first word and the second word are not successfully matched. The detection module is used to determine that the attached building information is abnormal POI data if there is an abnormal first word in the first word segmentation result, delete the attached building information corresponding to the POI in the map, and record the unattachment change record table in the database; wherein, the abnormal first word is the first word whose binary matching result is all the second preset value.

7. The apparatus according to claim 6, wherein, The step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word includes: Based on a preset thesaurus, obtain the synonyms of each second word in the second word segmentation result; For each first word in the first word segmentation result, the first word is matched with each second word and each synonym of the second word to obtain a binary matching result for each first word. The binary matching result includes a first preset value and a second preset value. The first preset value indicates that the first word is the same as the second word or the synonym of the second word, and the second preset value indicates that the first word is not the same as the second word and the synonym of the second word.

8. The apparatus according to claim 6, wherein, The step of matching each first word in the first word segmentation result with each second word in the second word segmentation result to obtain a binary matching result for each first word includes: Obtain the first word from the first word segmentation result; For the first word, obtain the second word from the second word segmentation result; Match the second word with the first word; If the second word matches the first word successfully, the binarized matching result of the first word and the second word is determined as the first preset value; if the second word does not match the first word successfully, the binarized matching result of the first word and the second word is determined as the second preset value. Obtain a new second word from the second word segmentation result, and return to the step of matching the second word with the first word until the second word matches the first word successfully, or, all second words in the second word segmentation result for the first word are obtained; Obtain a new first word from the first word segmentation result, and return to execute the step of obtaining a second word from the second word segmentation result for the first word, until all first words in the first word segmentation result have been obtained.

9. The apparatus according to claim 8, wherein, The step of obtaining the second word from the second word segmentation result for the first word includes: For the first word, a second word is obtained from the words to be matched in the second word segmentation result, wherein the words to be matched are initially all the second words in the second word segmentation result; The matching module is configured to delete the second word from the words to be matched if the second word matches the first word successfully; The step of obtaining a new second word from the second word segmentation result and returning to perform the step of matching the second word with the first word, until all second words in the second word segmentation result for the first word have been obtained, includes: Obtain new second words from the words to be matched in the second word segmentation result, and return to the step of matching the second words with the first words, until all second words in the words to be matched in the second word segmentation result for the first words have been obtained.

10. The apparatus according to claim 6, wherein the detection module is configured to determine that the attached building information is normal POI data if the binarized matching result of each first word in the first word segmentation result contains the first preset value.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images