A position recommendation information obtaining method and device, electronic equipment and storage medium

Abstract

The application provides a position recommendation information obtaining method, comprising: obtaining a plurality of position element texts in a position query text, the plurality of position element texts being texts used for describing positions in the position query text; obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; and sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of times of occurrence of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to a sorting result. The position recommendation information obtaining method can ensure that the candidate position information in the position recommendation information for the position query text corresponds to the plurality of position element texts, and improves the accuracy of the position recommendation information when there are a plurality of position element texts in the position query text.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a position recommendation information obtaining method. The present application also relates to a position recommendation information obtaining device, an electronic device and a storage medium. BACKGROUND

[0002] With the wide application of wireless communication technology and intelligent terminals, the fusion of geographic location and text data is becoming more and more common. Specifically, there are more and more Web objects with location attributes, such as the web pages of scenic spots and restaurants containing geographic locations. In addition, many points of interest (POI) have text descriptions. Due to the increasing fusion of geographic location and text data, the development of spatial keyword search (SKS) is promoted. Spatial keyword search mainly includes spatial query and keyword query. The main purpose is to find a number of candidate location information containing address keywords in the location query text and closest to the query location. For example, through map query, the location information of several fast food stores or gas stations closest to the current location is obtained.

[0003] In the existing technical solution of spatial keyword search, in the process of finding a number of candidate location information containing keywords and closest to the query location, the candidate location information is sorted based on the text similarity between the candidate location information and the address keywords and the distance between the candidate location information and the query location. According to the sorting result, the position recommendation information output for the location query text is obtained to ensure the accuracy of the position recommendation information. However, in the case where the query location cannot be positioned or the positioning accuracy of the query location is low, the candidate location information can only be sorted based on the text similarity between the candidate location information and the address keywords. However, if there are multiple address keywords in the query text, the distribution range of the candidate location information will be very wide. At this time, the accuracy of the position recommendation information is low based on the sorting of the candidate location information based on the text similarity between the candidate location information and the address keywords. SUMMARY

[0004] The present application provides a position recommendation information obtaining method, device, electronic device and storage medium to improve the accuracy of position recommendation information when there are multiple location element texts in the location query text.

[0005] The present application provides a position recommendation information obtaining method, comprising:

[0006] obtaining a plurality of location element texts in a location query text, the plurality of location element texts being texts in the location query text for describing locations;

[0007] obtain candidate location information corresponding to the plurality of location element texts;

[0008] sort the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtain location recommendation information for the location query text according to a sorting result.

[0009] Optionally, the method further comprises:

[0010] cluster the candidate location information corresponding to different location element texts in the plurality of location element texts to obtain a first clustering cluster of the candidate location information corresponding to the different location element texts;

[0011] obtain a clustering cluster center of the first clustering cluster according to the first clustering cluster;

[0012] cluster the clustering cluster center of the first clustering cluster to obtain a second clustering cluster of the clustering cluster center of the first clustering cluster;

[0013] obtain a cluster containing the most location element text types in the second clustering cluster as a clustering cluster center of the second clustering cluster according to the second clustering cluster;

[0014] obtain a clustering score of the candidate location information corresponding to the plurality of location element texts according to distances between the candidate location information corresponding to the different location element texts and the clustering cluster center of the second clustering cluster.

[0015] Optionally, the method further comprises:

[0016] obtain the number of occurrences of different location element texts in the plurality of location element texts in the location query text;

[0017] obtain the number of occurrences of the plurality of location element texts in the location query text according to the number of occurrences of the different location element texts in the location query text.

[0018] Optionally, the sorting of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to the sorting result, comprises: sorting the candidate location information corresponding to the plurality of location element texts according to the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to the sorting result.

[0019] Optionally, the sorting of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to the sorting result, comprises:

[0020] Obtaining the text similarity between the plurality of location element texts and the candidate location information corresponding to the plurality of location element texts, and / or the text similarity between the location query text and the candidate location information corresponding to the plurality of location element texts as the target text similarity corresponding to the plurality of location element texts;

[0021] According to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarity corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to the sorting result.

[0022] Optionally, the sorting of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to the sorting result, comprises: according to the number of occurrences of the plurality of location element texts in the location query text, the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarity corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to the sorting result.

[0023] Optionally, the position recommendation information is obtained according to the sorting result, and the sorting of the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and the target text similarity of the candidate position information corresponding to the plurality of position element texts.

[0024] The user current position information is obtained, and the user current position information is position information when a user device corresponding to a user sends a position query text;

[0025] The distance between the candidate position information corresponding to the plurality of position element texts and the user current position information is obtained according to the user current position information and the candidate position information corresponding to the plurality of position element texts.

[0026] The candidate position information corresponding to the plurality of position element texts is sorted according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, the target text similarity of the candidate position information corresponding to the plurality of position element texts, and the distance between the candidate position information corresponding to the plurality of position element texts and the user current position information, and the position recommendation information is obtained according to a sorting result.

[0027] Optionally, the position recommendation information is obtained according to the sorting result, and the sorting of the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and the target text similarity of the candidate position information corresponding to the plurality of position element texts, and the distance between the candidate position information corresponding to the plurality of position element texts and the user current position information, and the position recommendation information is obtained according to a sorting result.

[0028] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to the occurrence times of the plurality of location element texts in the location query text, the clustering scores of the candidate position information corresponding to the plurality of location element texts, the target text similarities of the candidate position information corresponding to the plurality of location element texts, and the distances between the candidate position information corresponding to the plurality of location element texts and the current position information of the user.

[0029] The occurrence times of the plurality of location element texts in the location query text are normalized to obtain a first sorting weight for sorting the candidate position information corresponding to the plurality of location element texts.

[0030] The clustering scores of the candidate position information corresponding to the plurality of location element texts are normalized to obtain a second sorting weight for sorting the candidate position information corresponding to the plurality of location element texts.

[0031] The target text similarities of the candidate position information corresponding to the plurality of location element texts are taken as a third sorting weight for sorting the candidate position information corresponding to the plurality of location element texts.

[0032] The distances between the candidate position information corresponding to the plurality of location element texts and the current position information of the user are normalized to obtain a fourth sorting weight for sorting the candidate position information corresponding to the plurality of location element texts.

[0033] The candidate position information corresponding to the plurality of location element texts is sorted according to the first sorting weight, the second sorting weight, the third sorting weight, and the fourth sorting weight, and the position recommendation information is obtained according to the sorting result.

[0034] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to the occurrence times of the plurality of location element texts in the location query text, the clustering scores of the candidate position information corresponding to the plurality of location element texts, the target text similarities of the candidate position information corresponding to the plurality of location element texts, and the distances between the candidate position information corresponding to the plurality of location element texts and the current position information of the user.

[0035] The candidate position information corresponding to the plurality of location element texts is sorted according to the sorting result of the candidate position information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the sorting result.

[0036] Optionally, the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information for the location query text is obtained according to a sorting result.

[0037] The sorting scores of the candidate location information corresponding to the plurality of location element texts are obtained according to the number of occurrences of the plurality of location element texts in the location query text.

[0038] The candidate location information corresponding to the plurality of location element texts is sorted according to the sorting scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to a sorting result.

[0039] Optionally, the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information for the location query text is obtained according to a sorting result.

[0040] The sorting scores of the candidate location information corresponding to the plurality of location element texts are obtained according to the clustering scores of the candidate location information corresponding to the plurality of location element texts.

[0041] The candidate location information corresponding to the plurality of location element texts is sorted according to the sorting scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to a sorting result.

[0042] Optionally, the candidate location information corresponding to the plurality of location element texts is sorted according to the sorting scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to a sorting result, including that the candidate location information corresponding to the plurality of location element texts is sorted in a descending order of the sorting scores according to the sorting scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to a sorting result.

[0043] Optionally, the position recommendation information is obtained according to a result of the sorting.

[0044] Optionally, the candidate position information corresponding to the plurality of location element texts is obtained by:

[0045] a preset number of candidate position information corresponding to different location element texts in the plurality of location element texts is obtained;

[0046] the candidate position information corresponding to the plurality of location element texts is obtained according to the preset number of candidate position information corresponding to the different location element texts.

[0047] Optionally, the position recommendation information is provided to a user device.

[0048] Optionally, the plurality of location element texts in the location query text is obtained by:

[0049] the position recommendation information is provided to the user device according to the location query instruction.

[0050] Optionally, the position recommendation information is displayed.

[0051] Another aspect of the present application also provides a position recommendation information obtaining device, comprising:

[0052] a location element text obtaining unit, configured to obtain a plurality of location element texts in a location query text, the plurality of location element texts being texts in the location query text for describing a location;

[0053] a candidate position obtaining unit, configured to obtain candidate position information corresponding to the plurality of location element texts according to the plurality of location element texts;

[0054] The position recommendation information obtaining unit is configured to sort the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to a sorting result.

[0055] In another aspect, the present application provides an electronic device, comprising:

[0056] a processor; and

[0057] a memory configured to store a program of a position recommendation information obtaining method, and the electronic device is configured to execute the following steps after being powered on and running the program of the position recommendation information obtaining method by the processor:

[0058] obtaining a plurality of position element texts in a position query text, the plurality of position element texts being texts in the position query text for describing positions;

[0059] obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts;

[0060] sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to a sorting result.

[0061] In another aspect, the present application provides a storage medium storing a program of a position recommendation information obtaining method, and the program is configured to be run by a processor to execute the following steps:

[0062] obtaining a plurality of position element texts in a position query text, the plurality of position element texts being texts in the position query text for describing positions;

[0063] obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts;

[0064] sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to a sorting result.

[0065] In another aspect, the present application provides a position recommendation information obtaining method applied to an electronic map application, comprising:

[0066] obtaining position query text from the position query audio data;

[0067] obtaining a plurality of position element texts in the position query text, the plurality of position element texts being texts in the position query text for describing positions;

[0068] obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts;

[0069] ranking the candidate position information corresponding to the plurality of position element texts according to at least one of a number of occurrences of the plurality of position element texts in the position query text and a clustering score of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to a ranking result;

[0070] displaying the position recommendation information through a man-machine interaction interface of the user equipment.

[0071] Another aspect of the present application also provides a vehicle-mounted device, comprising: an audio collection module, an audio recognition module, and a position recommendation information obtaining module.

[0072] The audio collection module is configured to collect position query audio data.

[0073] The audio recognition module is configured to perform audio recognition on the position query audio data to obtain position query text corresponding to the position query audio data.

[0074] The position recommendation information obtaining module is configured to obtain a plurality of position element texts in the position query text, the plurality of position element texts being texts in the position query text for describing positions; obtain candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; rank the candidate position information corresponding to the plurality of position element texts according to at least one of a number of occurrences of the plurality of position element texts in the position query text and a clustering score of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to a ranking result; and display the position recommendation information.

[0075] Compared with the prior art, the present application has the following advantages:

[0076] This application provides a method for obtaining location recommendation information. The method involves obtaining multiple location element texts from a location query text, where the multiple location element texts are texts describing locations within the query text. For each of the multiple location element texts, candidate location information corresponding to the multiple location element texts is obtained. Based on at least one of the frequency of occurrence of each location element text in the location query text and the clustering score of the candidate location information corresponding to the multiple location element texts, the candidate location information is sorted. Based on the sorting result, location recommendation information for the location query text is obtained. The location recommendation information obtaining method provided by this application, by sorting the candidate location information corresponding to multiple location element texts, ensures that the candidate location information in the location recommendation information for the location query text corresponds to multiple location element texts, thereby improving the accuracy of the location recommendation information when multiple location element texts exist in the location query text. Attached Figure Description

[0077] Figure 1 This is a schematic diagram of a first scenario for the location recommendation information acquisition method provided in the first embodiment of this application.

[0078] Figure 2 This is a flowchart of a method for obtaining location recommendation information provided in the first embodiment of this application.

[0079] Figure 3 This is a schematic diagram of a location recommendation information acquisition device provided in the second embodiment of this application.

[0080] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this application.

[0081] Figure 5 This is a flowchart of a method for obtaining location recommendation information provided in the fifth embodiment of this application.

[0082] Figure 6 This is a schematic diagram of a vehicle-mounted device provided in the sixth embodiment of this application. Detailed Implementation

[0083] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0084] First Embodiment

[0085] In order to more clearly show the position recommendation information obtaining method provided in the first embodiment of the present application, first, the application scenario of the position recommendation information obtaining method provided in the first embodiment of the present application is introduced. The position recommendation information obtaining method provided in the first embodiment of the present application can be executed by a server, or a client with a related text recognition application installed, or both the server and the client, that is, through the interaction between the server and the client to complete the position recommendation information obtaining method. The client is an application program or software with a position recommendation information obtaining function installed on a user device, the user device is generally a mobile phone, a PC (Personal Computer), a tablet computer and the like in the specific implementation mode, and the application program (APP, Application) or software with the position recommendation information obtaining function can be an electronic map application program, a web-based online electronic map software, or a take-out service platform APP, a car-hailing service platform APP and a tourism service platform APP and the like. The server is a computing device for providing data processing and the like for the above-mentioned client, and the server is generally a server or a server cluster in the specific implementation mode.

[0086] In the first embodiment of the present application, the application scenario of the position recommendation information obtaining method completed through the interaction between the server and the client, and the client being an electronic map APP with a position recommendation information obtaining function installed on a mobile phone is taken as an example to explain the position recommendation information obtaining method provided in the first embodiment of the present application in detail. Please refer to Figure 1 , which is the first scenario diagram of the position recommendation information obtaining method provided in the first embodiment of the present application.

[0087] First, the client 101 obtains the position query audio data of the user through the user device after the audio collection trigger operation triggered by the client 101.

[0088] Then, the client 101 performs audio recognition on the collected location query audio data, obtains the location query text corresponding to the location query audio data, and sends the location query text to the server 102. In the specific implementation process, the location query audio data is input into a neural network-based speech recognition model to obtain the location query text, so as to realize the conversion of the location query audio data into the location query text. Specifically, the neural network-based speech recognition model is a pre-trained model used to obtain the text corresponding to the audio data to be recognized according to the audio data to be recognized. Common neural network-based speech recognition models include FSMN (Feed-Forward Sequential Memory Network, feed-forward sequential memory network) model, DFCNN (Deep Fully Convolutional Neural Network, deep fully convolutional neural network) model, etc. It should be noted that the conversion of the location query audio data into the location query text can be performed after noise reduction processing of the location query audio data, and the location query text can also be subjected to noise reduction processing after the location query text is obtained. After the client 101 obtains the location query text, a location query instruction is issued for the location query text, and the location query instruction carries the location query text. In the specific implementation process, the client 101 sends the location query instruction carrying the location query text to the server 102.

[0089] In addition, in the first embodiment of the present application, the client 101 can also send the location query instruction carrying the location query audio data to the server 102, and the server 102 can realize the conversion of the location query audio data into the location query text.

[0090] In addition, the process of obtaining the location query text can also be to directly obtain the location query text input by the user through the human-computer interaction interface corresponding to the client 101. After the client 101 obtains the location query text, it further sends the location query instruction carrying the location query text to the server 102. That is, the user device sends the location query instruction to the server 102 for the location query text, and the location query instruction carries the location query text. It should be noted that the location query text can also be subjected to noise reduction processing after the location query text is obtained.

[0091] In the first embodiment of the present application, the noise reduction processing of the location query audio data and / or the noise reduction processing of the location query audio data are both to ensure the accuracy of the location query text, so as to improve the accuracy of the final location recommendation information for the location query text.

[0092] In the first embodiment of the present application, the position query audio data is audio information used for position query, and the position query text is text used for position query. The position query audio data can be specifically a position query instruction issued by a user in a voice manner to the client 101, such as "I am near a certain street in Chaoyang District, Beijing, please find a gas station near the certain street in Chaoyang District, Beijing", "search for a food shop near a certain street in Chaoyang District, Beijing", and the like. At this time, the position query text can be specifically "I am near a certain street in Chaoyang District, Beijing, please find a gas station near the certain street in Chaoyang District, Beijing", "search for a food shop near a certain street in Chaoyang District, Beijing", and the like. In addition, the position query audio data can also be user dialogue audio data or communication dialogue audio data, such as the communication dialogue audio data "A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou, please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes; B: OK". At this time, the position query text can be specifically communication dialogue text, such as "A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou, please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes; B: OK".

[0093] In the first embodiment of the present application, the specific manner in which the client 101 sends the position query text to the server 102 is not specifically limited.

[0094] After the server 102 obtains the position query text, the following steps are sequentially performed to obtain the position recommendation information for the position query text. For details, please refer to Figure 2 which is a flowchart of a position recommendation information obtaining method provided in the first embodiment of the present application.

[0095] In step S201, a plurality of position element texts in the position query text are obtained, and the plurality of position element texts are texts used for describing positions in the position query text.

[0096] The text used for describing positions is generally a position keyword in the position query text, such as "Beijing", "Chaoyang District", "a certain street", and "gas station" in "I am near a certain street in Chaoyang District, Beijing, please find a gas station near the certain street in Chaoyang District, Beijing". For another example, "Hangzhou", "Yuhang District", "a certain street", and "a certain hotel" in "A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou, please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes; B: OK".

[0097] In the first embodiment of the present application, the process of obtaining the plurality of location element texts in the location query text can be based on a preset word segmentation strategy for the location query text to obtain the plurality of location element texts.

[0098] In step S202, for the plurality of location element texts, candidate location information corresponding to the plurality of location element texts is obtained.

[0099] In the specific implementation process, in order to prevent the existence of wrong texts such as wrong characters and / or homophonic characters in the plurality of location element texts, in the process of obtaining the candidate location information corresponding to the plurality of location element texts, a substring matching, a fuzzy search and other retrieval methods are used to retrieve the candidate location information corresponding to the plurality of location element texts. In this way, the accuracy of retrieving the candidate location information can be ensured. Specifically, a preset number of candidate location information corresponding to different location element texts in the plurality of location element texts is obtained; and then the candidate location information corresponding to the plurality of location element texts is obtained according to the candidate location information corresponding to the preset number of different location element texts. For example, the different location element texts in the plurality of location element texts are sorted according to the text similarity between the location element texts and the searched candidate address information, and a preset number of candidate location information corresponding to different location element texts is obtained; and then the candidate location information corresponding to the plurality of location element texts is obtained according to the candidate location information corresponding to the preset number of different location element texts.

[0100] Taking the communication dialogue text "A: Hello, I am now in a certain hotel near a certain street in Yuhang District, Hangzhou City, please wait for me downstairs; B: Are you waiting for me downstairs in a certain hotel? A: Yes, yes; B: OK" as an example, the different location element texts are "Hangzhou City", "Yuhang District", "a certain street" and "a certain hotel". When obtaining the candidate location information corresponding to the plurality of location element texts, 10 corresponding candidate location information can be obtained for "Hangzhou City", "Yuhang District", "a certain street" and "a certain hotel" respectively; and then the 10 candidate location information corresponding to the different location element texts "Hangzhou City", "Yuhang District", "a certain street", "hotel" and "a certain hotel" are superimposed to obtain 50 candidate location information corresponding to the plurality of location element texts "Hangzhou City", "Yuhang District", "a certain street", "hotel" and "a certain hotel".

[0101] In step S203, the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the location recommendation information for the location query text is obtained according to the sorting result.

[0102] In the implementation process, before the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the number of occurrences of the plurality of location element texts in the location query text needs to be obtained. Specifically, first, the number of occurrences of different location element texts in the plurality of location element texts in the location query text is obtained; then, the number of occurrences of the plurality of location element texts in the location query text is obtained according to the number of occurrences of different location element texts in the location query text. For example, in the communication dialogue text "A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou City, please wait for me at the hotel downstairs; B: Are you waiting at the hotel downstairs? A: Yes, yes; B: OK", the different location element texts are "Hangzhou City", "Yuhang District", "a certain street", "hotel" and "a certain hotel", among which the number of occurrences of "Hangzhou City", "Yuhang District", "a certain street" and "hotel" is 1, and the number of occurrences of "a certain hotel" is 2.

[0103] In the implementation process, first, the sorting score of the candidate location information corresponding to the plurality of location element texts can be obtained according to the number of occurrences of the plurality of location element texts in the location query text. Second, the candidate location information corresponding to the plurality of location element texts is sorted according to the sorting score of the candidate location information corresponding to the plurality of location element texts, and the location recommendation information is obtained according to the sorting result. Third, the candidate location information corresponding to the plurality of location element texts is sequentially sorted in descending order of the sorting score according to the sorting score of the candidate location information corresponding to the plurality of location element texts, and the location recommendation information is obtained according to the sorting result. Specifically, a preset number of candidate location information corresponding to the plurality of location element texts is sequentially sorted in descending order of the sorting score, and the preset number of candidate location information is obtained from the candidate location information corresponding to the plurality of location element texts as the location recommendation information. For example, 10 candidate location information is obtained from the candidate location information corresponding to the plurality of location element texts as the location recommendation information by sequentially sorting a preset number of candidate location information corresponding to the plurality of location element texts in descending order of the sorting score.

[0104] In the implementation process, before the sorting of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the clustering score of the candidate location information corresponding to the plurality of location element texts needs to be obtained. Specifically, first, the candidate location information corresponding to different location element texts in the plurality of location element texts is clustered to obtain a first clustering cluster of the candidate location information corresponding to different location element texts; second, the clustering cluster center of the first clustering cluster is obtained according to the first clustering cluster; third, the clustering cluster center of the first clustering cluster is clustered to obtain a second clustering cluster of the clustering cluster center of the first clustering cluster; fourth, the cluster containing the most location element text types in the second clustering cluster is obtained as the clustering cluster center of the second clustering cluster according to the second clustering cluster; and fifth, the clustering score of the candidate location information corresponding to the plurality of location element texts is obtained according to the distance between the candidate location information corresponding to different location element texts and the clustering cluster center of the second clustering cluster.

[0105] The specific implementation of obtaining the clustering cluster center of the second clustering cluster is to perform twice clustering on the candidate location information corresponding to the plurality of location element texts by using a DBSCAN (Density-Based Spatial Clustering Of Applications With Noise) clustering algorithm to obtain the clustering cluster center of the second clustering cluster. Specifically, first, the first clustering, that is, the candidate location information corresponding to different location element texts in the plurality of location element texts is clustered to obtain a first clustering cluster of the candidate location information corresponding to different location element texts. At this time, the ε-neighborhood and MinPts (Minimum Points) of the first clustering need to be determined. Based on the ε-neighborhood, MinPts, and the longitude and latitude of the candidate location information corresponding to different location element texts, the candidate location information corresponding to different location element texts is clustered respectively to obtain the first clustering cluster of the candidate location information corresponding to different location element texts. Second, the clustering cluster center of the first clustering cluster is obtained according to the first clustering cluster. Third, the ε-neighborhood and MinPts of the second clustering are determined. Based on the ε-neighborhood, MinPts, and the longitude and latitude of the clustering cluster center of the first clustering cluster of different location element texts, the clustering cluster center of the first clustering cluster of different location element texts is clustered respectively to obtain a second clustering cluster of the clustering cluster center of the first clustering cluster. Finally, the cluster containing the most location element text types in the second clustering cluster is obtained as the clustering cluster center of the second clustering cluster according to the second clustering cluster.

[0106] In the implementation process, firstly, the ranking scores of the candidate location information corresponding to the plurality of location element texts can be obtained according to the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the closer the distance, the higher the ranking score. Secondly, the candidate location information corresponding to the plurality of location element texts is sorted according to the ranking scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the sorting result. Thirdly, the candidate location information corresponding to the plurality of location element texts is sorted in turn according to the ranking scores from high to low, and the position recommendation information is obtained according to the sorting result. Specifically, the preset number of candidate location information corresponding to the plurality of location element texts is sorted in turn according to the ranking scores from high to low, and the preset number of candidate location information is obtained from the candidate location information corresponding to the plurality of location element texts as the position recommendation information. For example, the preset number of candidate location information corresponding to the plurality of location element texts is sorted in turn according to the ranking scores from high to low, and 5 candidate location information is obtained from the candidate location information corresponding to the plurality of location element texts as the position recommendation information.

[0107] In the first embodiment of the present application, the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information for the location query text is obtained according to the sorting result. It can be further provided that the candidate location information corresponding to the plurality of location element texts is sorted according to the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information for the location query text is obtained according to the sorting result.

[0108] Specifically, first, the number of occurrences of the plurality of location element texts in the location query text is normalized to obtain a first sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; second, the clustering scores of the candidate location information corresponding to the plurality of location element texts are normalized to obtain a second sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; third, the candidate location information corresponding to the plurality of location element texts is sorted according to the first sorting weight and the second sorting weight, and the position recommendation information is obtained according to the sorting result. Fourth, the first sorting weight and the second sorting weight are summed to obtain the ranking scores of the candidate location information corresponding to the plurality of location element texts; fifth, the candidate location information corresponding to the plurality of location element texts is sorted according to the ranking scores of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the sorting result.

[0109] To further improve the accuracy of the position recommendation information when multiple location element texts exist in the position query text, in the first embodiment of the present application, when sorting the candidate position information corresponding to the multiple location element texts, the text similarity between the multiple location element texts and the candidate position information corresponding to the multiple location element texts, and / or the text similarity between the position query text and the candidate position information corresponding to the multiple location element texts can be further introduced as the target text similarity of the multiple location element texts as the sorting index. At this time, the text similarity between the multiple location element texts and the candidate position information corresponding to the multiple location element texts, and / or the text similarity between the position query text and the candidate position information corresponding to the multiple location element texts as the target text similarity of the multiple location element texts need to be obtained first; then the candidate position information corresponding to the multiple location element texts is sorted according to at least one of the number of occurrences of the multiple location element texts in the position query text and the clustering score of the candidate position information corresponding to the multiple location element texts, and the target text similarity of the multiple location element texts, and the position recommendation information is obtained according to the sorting result.

[0110] In the specific implementation process, the process of sorting the candidate position information corresponding to the multiple location element texts according to at least one of the number of occurrences of the multiple location element texts in the position query text and the clustering score of the candidate position information corresponding to the multiple location element texts, and the target text similarity of the multiple location element texts, and obtaining the position recommendation information according to the sorting result is: sorting the candidate position information corresponding to the multiple location element texts according to the number of occurrences of the multiple location element texts in the position query text, the clustering score of the candidate position information corresponding to the multiple location element texts, and the target text similarity of the multiple location element texts, and obtaining the position recommendation information according to the sorting result.

[0111] Specifically, first, the number of occurrences of the plurality of location element texts in the location query text is normalized to obtain a first sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; second, the clustering score of the candidate location information corresponding to the plurality of location element texts is normalized to obtain a second sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; third, the target text similarity of the plurality of location element texts is taken as a third sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; fourth, the candidate location information corresponding to the plurality of location element texts is sorted according to the first sorting weight, the second sorting weight, and the third sorting weight, and the location recommendation information is obtained according to the sorting result; fifth, the first sorting weight, the second sorting weight, and the third sorting weight are summed to obtain a sorting score of the candidate location information corresponding to the plurality of location element texts; sixth, the candidate location information corresponding to the plurality of location element texts is sorted according to the sorting score of the candidate location information corresponding to the plurality of location element texts, and the location recommendation information is obtained according to the sorting result.

[0112] In the first embodiment of the present application, the text similarity between the plurality of location element texts and the candidate location information corresponding to the plurality of location element texts, and / or the text similarity between the location query text and the candidate location information corresponding to the plurality of location element texts is introduced as the target text similarity of the plurality of location element texts as a sorting index, which can further increase the accuracy of the candidate location information corresponding to the plurality of location element texts, thereby further improving the accuracy of the location recommendation information when the location query text contains multiple location element texts.

[0113] In addition, in order to further improve the accuracy of the location recommendation information when the location query text contains multiple location element texts, in the first embodiment of the present application, the user's current location information can be further introduced as a sorting index when sorting the candidate location information corresponding to the plurality of location element texts. The so-called user's current location information is the location information when the user corresponding to the user equipment sends the location query text. At this time, the user's current location information needs to be obtained first; then the distance between the candidate location information corresponding to the plurality of location element texts and the user's current location information is obtained according to the user's current location information and the candidate location information corresponding to the plurality of location element texts; finally, the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity of the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the user's current location information, and the location recommendation information is obtained according to the sorting result.

[0114] In the implementation process, according to at least one of the number of times of the plurality of location element texts appearing in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity corresponding to the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user, the candidate location information corresponding to the plurality of location element texts is sorted, and the process of obtaining the location recommendation information according to the sorting result is: according to the number of times of the plurality of location element texts appearing in the location query text, the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity corresponding to the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to the sorting result.

[0115] Specifically, first, the number of times of the plurality of location element texts appearing in the location query text is normalized to obtain a first sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; second, the clustering score of the candidate location information corresponding to the plurality of location element texts is normalized to obtain a second sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; third, the target text similarity corresponding to the plurality of location element texts is taken as a third sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; fourth, the candidate location information corresponding to the plurality of location element texts is sorted according to the first sorting weight, the second sorting weight, and the third sorting weight, and the location recommendation information is obtained according to the sorting result; fifth, the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user is normalized to obtain a fourth sorting weight for sorting the candidate location information corresponding to the plurality of location element texts; sixth, the candidate location information corresponding to the plurality of location element texts is sorted according to the first sorting weight, the second sorting weight, the third sorting weight, and the fourth sorting weight, and the location recommendation information is obtained according to the sorting result.

[0116] In the first embodiment of the present application, the specific implementation manner of obtaining the position recommendation information according to the first sorting weight, the second sorting weight, the third sorting weight and the fourth sorting weight is as follows: first, sum the first sorting weight, the second sorting weight, the third sorting weight and the fourth sorting weight to obtain the sorting score of the candidate position information corresponding to the plurality of location element texts; second, sort the candidate position information corresponding to the plurality of location element texts according to the sorting score of the candidate position information corresponding to the plurality of location element texts, and obtain the position recommendation information according to the sorting result; third, obtain the sorting score of the candidate position information corresponding to the plurality of location element texts according to the clustering score of the candidate position information corresponding to the plurality of location element texts; and finally, sort the candidate position information corresponding to the plurality of location element texts according to the sorting score of the candidate position information corresponding to the plurality of location element texts, and obtain the position recommendation information according to the sorting result.

[0117] In the first embodiment of the present application, the introduction of the current position information of the user can limit the distribution range of the candidate position information corresponding to the plurality of location element texts, so that the distribution range of the candidate position information corresponding to the plurality of location element texts is not too wide, thereby increasing the accuracy of the candidate position information corresponding to the plurality of location element texts, and further improving the accuracy of the position recommendation information when there are a plurality of location element texts in the position query text.

[0118] It should be noted that in the first embodiment of the present application, the specific implementation manner of normalizing the distance between the candidate position information corresponding to the plurality of location element texts and the current position information of the user is to normalize the distance between the candidate position information corresponding to the plurality of location element texts and the current position information of the user to 0-1 by using function 2-2 Sigmoid(x) (Sigmoid Function, S-shaped growth curve).

[0119] Please refer to Figure 1In the first embodiment of the present application, the position query text is "A: Hello, I am now near a certain hotel in a certain street of Yuhang District, Hangzhou City. Please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes, yes; B: OK", and the ranking result of the five candidate address with the highest score is sequentially ranked according to the score, which is taken as an example of the position recommendation information obtained by the server 102 for the position query text. The server 102 will provide the position recommendation information to the client 101 according to the position query instruction issued by the client 101. After the client 101 obtains the position recommendation information, it will display the position recommendation information. The position recommendation information obtaining method provided in the first embodiment of the present application can also be applied to the application scenario in which the client is the execution subject. At this time, the client can be a take-out service platform APP, a taxi service platform APP, and a tourism service platform APP, etc.

[0120] In the specific implementation process, after the client obtains the position query audio data obtained by the user equipment, it will sequentially perform the following steps: recognizing the position query audio data obtained by the user equipment, obtaining the position query text;

[0121] Obtaining a plurality of location element texts in the position query text, the plurality of location element texts being texts in the position query text for describing a position; obtaining candidate position information corresponding to the plurality of location element texts for the plurality of location element texts; sorting the candidate position information corresponding to the plurality of location element texts according to at least one of the number of times of occurrence of the plurality of location element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of location element texts; obtaining the position recommendation information for the position query text according to the ranking result; and displaying the position recommendation information through the man-machine interaction interface of the user equipment.

[0122] The position recommendation information obtaining method provided in the first embodiment of the present application can also be applied to the application scenario in which the server is the execution subject. At this time, it can be the server of a take-out service platform APP, a taxi service platform APP, and a tourism service platform APP, etc.

[0123] In the specific implementation process, after the server obtains the position query audio data obtained by the user equipment, it will sequentially perform the following steps: recognizing the position query audio data obtained by the user equipment, obtaining the position query text;

[0124] A plurality of location element texts in the location query text are obtained, the plurality of location element texts being texts in the location query text for describing a location; candidate location information corresponding to the plurality of location element texts is obtained; the candidate location information corresponding to the plurality of location element texts is sorted according to at least one of a number of times that the plurality of location element texts appear in the location query text and a clustering score of the candidate location information corresponding to the plurality of location element texts; location recommendation information for the location query text is obtained according to a sorting result; and the location recommendation information is displayed through a human-computer interaction interface of a user device.

[0125] In the first embodiment, the application of the location recommendation information obtaining method provided in the first embodiment is not specifically limited, for example, the location recommendation information obtaining method provided in the first embodiment can also be applied to other scenarios, which will not be described one by one. The above application scenarios are provided to facilitate understanding of the location recommendation information obtaining method provided in the first embodiment, and are not intended to limit the location recommendation information obtaining method provided in the first embodiment.

[0126] The first embodiment provides a location recommendation information obtaining method, which obtains a plurality of location element texts in a location query text, the plurality of location element texts being texts in the location query text for describing a location; obtains candidate location information corresponding to the plurality of location element texts; sorts the candidate location information corresponding to the plurality of location element texts according to at least one of a number of times that the plurality of location element texts appear in the location query text and a clustering score of the candidate location information corresponding to the plurality of location element texts; and obtains location recommendation information for the location query text according to a sorting result. The location recommendation information obtaining method provided in the first embodiment sorts the candidate location information corresponding to the plurality of location element texts based on the plurality of location element texts, which can ensure that the candidate location information in the location recommendation information for the location query text corresponds to the plurality of location element texts, thereby improving the accuracy of the location recommendation information when there are a plurality of location element texts in the location query text.

[0127] Second embodiment

[0128] Corresponding to the application scenario of the position recommendation information obtaining method provided by the embodiment of the present application and the position recommendation information obtaining method provided by the first embodiment, the second embodiment of the present application further provides a position recommendation information obtaining method. Since the device embodiment is basically similar to the application scenario of the position recommendation information obtaining method provided by the embodiment of the present application and the position recommendation information obtaining method provided by the first embodiment, it is described more simply, and the related parts can be referred to the part of the description of the application scenario of the position recommendation information obtaining method provided by the embodiment of the present application and the position recommendation information obtaining method provided by the first embodiment. The device embodiment described below is only illustrative.

[0129] Please refer to Figure 3 , which is a schematic diagram of a position recommendation information obtaining device provided in the second embodiment of the present application.

[0130] The position recommendation information obtaining device comprises:

[0131] The position element text obtaining unit 301 is configured to obtain a plurality of position element texts in the position query text, wherein the plurality of position element texts are texts in the position query text for describing positions.

[0132] The candidate position obtaining unit 302 is configured to obtain candidate position information corresponding to the plurality of position element texts for the plurality of position element texts.

[0133] The position recommendation information obtaining unit 303 is configured to sort the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to the sorting result.

[0134] Optionally, the position recommendation information obtaining device provided in the second embodiment of the present application further comprises:

[0135] The first clustering unit is configured to cluster the candidate position information corresponding to different position element texts in the plurality of position element texts to obtain a first clustering cluster of the candidate position information corresponding to the different position element texts.

[0136] The first clustering center obtaining unit is configured to obtain a clustering cluster center of the first clustering cluster according to the first clustering cluster.

[0137] The second clustering unit is configured to cluster the clustering cluster centers of the first clustering cluster to obtain a second clustering cluster of the clustering cluster centers of the first clustering cluster.

[0138] a second cluster center obtaining unit, configured to obtain, according to the second cluster, a cluster with the most position element text types as a cluster center of the second cluster;

[0139] a cluster score obtaining unit, configured to obtain a cluster score of the candidate position information corresponding to the plurality of position element texts according to distances between the candidate position information corresponding to the plurality of position element texts and the cluster center of the second cluster.

[0140] Optionally, the position recommendation information obtaining apparatus provided in the second embodiment of the present application further includes:

[0141] a first occurrence number obtaining unit, configured to obtain occurrence numbers of different position element texts in the position query text in the plurality of position element texts;

[0142] a second occurrence number obtaining unit, configured to obtain occurrence numbers of the plurality of position element texts in the position query text according to the occurrence numbers of the different position element texts in the position query text.

[0143] Optionally, the position recommendation information obtaining unit 303 is specifically configured to sort the candidate position information corresponding to the plurality of position element texts according to the occurrence numbers of the plurality of position element texts in the position query text and the cluster scores of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to a sorting result.

[0144] Optionally, the sorting of the candidate position information corresponding to the plurality of position element texts according to the occurrence numbers of the plurality of position element texts in the position query text and the cluster scores of the candidate position information corresponding to the plurality of position element texts, and the obtaining of the position recommendation information for the position query text according to the sorting result include:

[0145] obtaining text similarities between the plurality of position element texts and the candidate position information corresponding to the plurality of position element texts, and / or text similarities between the position query text and the candidate position information corresponding to the plurality of position element texts as target text similarities of the plurality of position element texts;

[0146] sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the occurrence numbers of the plurality of position element texts in the position query text and the cluster scores of the candidate position information corresponding to the plurality of position element texts, and the target text similarities of the plurality of position element texts, and obtaining the position recommendation information according to a sorting result.

[0147] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate position information corresponding to the plurality of location element texts, and the target text similarity corresponding to the plurality of location element texts.

[0148] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate position information corresponding to the plurality of location element texts, and the target text similarity corresponding to the plurality of location element texts.

[0149] The user current position information is obtained, and the user current position information is the position information when the user corresponding to the user equipment sends the location query text;

[0150] The distance between the candidate position information corresponding to the plurality of location element texts and the user current position information is obtained according to the user current position information and the candidate position information corresponding to the plurality of location element texts.

[0151] The position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate position information corresponding to the plurality of location element texts, the target text similarity corresponding to the plurality of location element texts, and the distance between the candidate position information corresponding to the plurality of location element texts and the user current position information.

[0152] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate position information corresponding to the plurality of location element texts, the target text similarity corresponding to the plurality of location element texts, and the distance between the candidate position information corresponding to the plurality of location element texts and the current position information of the user.

[0153] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate position information corresponding to the plurality of location element texts, the target text similarity corresponding to the plurality of location element texts, and the distance between the candidate position information corresponding to the plurality of location element texts and the current position information of the user.

[0154] The number of occurrences of the plurality of location element texts in the location query text is normalized to obtain a first sorting weight for sorting the candidate position information corresponding to the plurality of location element texts;

[0155] The clustering score of the candidate position information corresponding to the plurality of location element texts is normalized to obtain a second sorting weight for sorting the candidate position information corresponding to the plurality of location element texts;

[0156] The target text similarity corresponding to the plurality of location element texts is taken as a third sorting weight for sorting the candidate position information corresponding to the plurality of location element texts;

[0157] The distance between the candidate position information corresponding to the plurality of location element texts and the current position information of the user is normalized to obtain a fourth sorting weight for sorting the candidate position information corresponding to the plurality of location element texts;

[0158] The candidate position information corresponding to the plurality of location element texts is sorted according to the first sorting weight, the second sorting weight, the third sorting weight, and the fourth sorting weight, and the position recommendation information is obtained according to the sorting result.

[0159] Optionally, the sorting the candidate location information corresponding to the plurality of location element texts according to the first sorting weight, the second sorting weight, the third sorting weight and the fourth sorting weight, and obtaining the location recommendation information according to a sorting result comprises: summing the first sorting weight, the second sorting weight, the third sorting weight and the fourth sorting weight to obtain a sorting score of the candidate location information corresponding to the plurality of location element texts.

[0160] According to the sorting score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to a sorting result.

[0161] Optionally, the sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the occurrence times of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to a sorting result comprises:

[0162] According to the occurrence times of the plurality of location element texts in the location query text, a sorting score of the candidate location information corresponding to the plurality of location element texts is obtained.

[0163] According to the sorting score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to a sorting result.

[0164] Optionally, the sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the occurrence times of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtaining the location recommendation information for the location query text according to a sorting result comprises:

[0165] According to the clustering scores of the candidate location information corresponding to the plurality of location element texts, a sorting score of the candidate location information corresponding to the plurality of location element texts is obtained.

[0166] According to the sorting score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information is obtained according to a sorting result.

[0167] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to the sorting scores of the candidate position information corresponding to the plurality of location element texts.

[0168] Optionally, the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts according to the sorting scores of the candidate position information corresponding to the plurality of location element texts from high to low in order, and the position recommendation information is obtained according to the sorting result of the candidate position information corresponding to the plurality of location element texts from high to low in order.

[0169] Optionally, the candidate position obtaining unit 302 is specifically configured to obtain a preset number of candidate position information corresponding to different location element texts in the plurality of location element texts; and obtain the candidate position information corresponding to the plurality of location element texts according to the preset number of candidate position information corresponding to the different location element texts.

[0170] Optionally, the position recommendation information obtaining apparatus provided in the second embodiment of the present application further comprises a position recommendation information providing unit configured to provide the position recommendation information to a user equipment.

[0171] Optionally, the plurality of location element texts in the location query text are obtained by obtaining a location query instruction issued by a user equipment for the location query text, and the location query instruction carries the location query text.

[0172] The position recommendation information is provided to the user equipment by providing the position recommendation information to the user equipment according to the location query instruction.

[0173] Optionally, the position recommendation information obtaining apparatus provided in the second embodiment of the present application further comprises a position recommendation information display unit configured to display the position recommendation information.

[0174] Third embodiment

[0175] Corresponding to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the third embodiment of the present application further provides an electronic device. Since the third embodiment is basically similar to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the description is relatively simple, and the related parts can be referred to the part of the description of the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment. The third embodiment described below is only illustrative.

[0176] Please refer to Figure 4 which is a schematic diagram of an electronic device provided in the embodiments of the present application.

[0177] The electronic device comprises a processor 401;

[0178] and a memory 402 for storing the program of the information processing method. After the device is powered on and the processor runs the program of the information processing method, the following steps are performed:

[0179] obtaining a plurality of position element texts in the position query text, the plurality of position element texts being texts in the position query text for describing positions;

[0180] obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts;

[0181] According to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, the candidate position information corresponding to the plurality of position element texts is sorted, and the position recommendation information for the position query text is obtained according to the sorting result.

[0182] It should be noted that the detailed description of the electronic device provided in the eighth embodiment of the present application can refer to the related description of the application scenario of the live service system provided in the embodiments of the present application, the live service system provided in the first embodiment and the above method embodiments, which will not be repeated here.

[0183] Fourth embodiment

[0184] Corresponding to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the fourth embodiment of the present application further provides a storage medium. Since the fourth embodiment is basically similar to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the description is relatively simple, and the related parts refer to the part of the description of the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment. The device embodiments described below are only schematic.

[0185] The storage medium stores a computer program, and the computer program is run by a processor to execute the following steps:

[0186] Obtain a plurality of position element texts in the position query text, and the plurality of position element texts are texts in the position query text for describing positions;

[0187] For the plurality of position element texts, obtain candidate position information corresponding to the plurality of position element texts;

[0188] According to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, the candidate position information corresponding to the plurality of position element texts is sorted, and the position recommendation information for the position query text is obtained according to the sorting result.

[0189] It should be noted that the detailed description of the storage medium provided in the ninth embodiment of the present application can refer to the related description of the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, which will not be repeated here.

[0190] Fifth Embodiment

[0191] Corresponding to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the fifth embodiment of the present application further provides another position recommendation information obtaining method. Since the device embodiment is basically similar to the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment, the description is relatively simple, and the related parts refer to the part of the description of the application scenario of the position recommendation information obtaining method provided in the embodiments of the present application and the position recommendation information obtaining method provided in the first embodiment. The method embodiments described below are only schematic.

[0192] The position recommendation information obtaining method provided in the fifth embodiment of the present application is described below in combination with Figure 5 .

[0193] Figure 5 A flowchart of a position recommendation information obtaining method provided in a fifth embodiment of the present application. Figure 5 The position recommendation information obtaining method shown is applied to an electronic map application, and the method comprises steps S501 to S505.

[0194] In step S501, position query audio data obtained by a user device is identified to obtain position query text.

[0195] In the fifth embodiment of the present application, the so-called user device is a user device installed with an electronic map application, such as a mobile phone, a tablet computer, etc. installed with an electronic map application. The so-called position query audio data obtained by a user device is position query audio data collected by a user device after an audio collection trigger operation triggered by the electronic map application is obtained by the user device.

[0196] The so-called position query audio data is audio information used for position query, and the so-called position query text is text used for position query. The position query audio data can specifically be position query instructions issued by a user in a voice manner to the client 101, such as “I am near a certain street in Chaoyang District, Beijing, please find a gas station near the certain street in Chaoyang District, Beijing” and “search for a food shop near the certain street in Chaoyang District, Beijing”, etc. At this time, the position query text can specifically be “I am near a certain street in Chaoyang District, Beijing, please find a gas station near the certain street in Chaoyang District, Beijing” and “search for a food shop near the certain street in Chaoyang District, Beijing”, etc. In addition, the position query audio data can also be user dialogue audio data or communication dialogue audio data, such as communication dialogue audio data “A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou, please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes; B: OK”. At this time, the position query text can specifically be communication dialogue text, such as “A: Hello, I am now at a certain hotel near a certain street in Yuhang District, Hangzhou, please wait for me at the hotel downstairs; B: Are you waiting for me at the hotel downstairs? A: Yes; B: OK”.

[0197] The specific implementation process of identifying the position query audio data obtained by the user device to obtain the position query text is as follows: inputting the position query audio data into a speech recognition model based on a neural network to obtain the position query text, so as to realize the conversion of the position query audio data to the position query text.

[0198] In step S502, a plurality of position element texts in the position query text are obtained, and the plurality of position element texts are texts in the position query text used for describing positions.

[0199] In the fifth embodiment of the present application, the text used to describe the position is generally a position keyword in the position query text, such as "Beijing City", "Chaoyang District", "certain street", and "gas station" in "I am near a certain street in Chaoyang District, Beijing City. Please find a gas station near the certain street in Chaoyang District, Beijing City". For example, "Hangzhou City", "Yuhang District", "certain street", and "certain hotel" in "A: Hello, I am now near a certain hotel in a certain street in Yuhang District, Hangzhou City. Please wait for me at the hotel downstairs; B: Are you waiting at the certain hotel downstairs? A: Yes; B: OK".

[0200] In the fifth embodiment of the present application, the process of obtaining the plurality of position element texts in the position query text can be based on a preset word segmentation strategy to obtain the word segmentation.

[0201] In step S503, for the plurality of position element texts, candidate position information corresponding to the plurality of position element texts is obtained.

[0202] In the specific implementation process, first, candidate position information corresponding to a preset number of different position element texts in the plurality of position element texts is obtained; and then, the candidate position information corresponding to the plurality of position element texts is obtained according to the candidate position information corresponding to the preset number of different position element texts. For example, first, the different position element texts in the plurality of position element texts are sorted according to the similarity between the position element text and the text of the searched candidate address information, and the candidate position information corresponding to a preset number of different position element texts is obtained; and then, the candidate position information corresponding to the plurality of position element texts is obtained according to the candidate position information corresponding to the preset number of different position element texts.

[0203] In step S504, the candidate position information corresponding to the plurality of position element texts is sorted according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and the position recommendation information for the position query text is obtained according to the sorting result.

[0204] In the specific implementation process, the number of occurrences of the plurality of position element texts in the position query text needs to be obtained first. Specifically, first, the number of occurrences of different position element texts in the plurality of position element texts in the position query text is obtained; and then, the number of occurrences of the plurality of position element texts in the position query text is obtained according to the number of occurrences of the different position element texts in the position query text.

[0205] In addition, in the implementation process, the clustering scores of the candidate location information corresponding to the plurality of location element texts are obtained. Specifically, first, the candidate location information corresponding to different location element texts in the plurality of location element texts is clustered to obtain a first clustering cluster of the candidate location information corresponding to different location element texts; second, the clustering cluster center of the first clustering cluster is obtained according to the first clustering cluster; third, the clustering cluster center of the first clustering cluster is clustered to obtain a second clustering cluster of the clustering cluster center of the first clustering cluster; fourth, the cluster containing the most location element text types in the second clustering cluster is obtained as the clustering cluster center of the second clustering cluster according to the second clustering cluster; and fifth, the clustering scores of the candidate location information corresponding to the plurality of location element texts are obtained according to the distance between the candidate location information corresponding to different location element texts and the clustering cluster center of the second clustering cluster.

[0206] In step S505, the location recommendation information is displayed through the man-machine interaction interface of the user equipment.

[0207] After the electronic map application obtains the location recommendation information, the location recommendation information is displayed through the man-machine interaction page of the user equipment.

[0208] Sixth embodiment

[0209] Corresponding to the application scenario of the location recommendation information obtaining method provided by the embodiments of the present application and the location recommendation information obtaining method provided by the first embodiment, the sixth embodiment of the present application further provides a vehicle-mounted device. Since the embodiment is basically similar to the application scenario of the location recommendation information obtaining method provided by the embodiments of the present application and the location recommendation information obtaining method provided by the first embodiment, the description is relatively simple, and the related parts can be referred to the part of the description of the application scenario of the location recommendation information obtaining method provided by the embodiments of the present application and the location recommendation information obtaining method provided by the first embodiment. The sixth embodiment described below is only illustrative.

[0210] Please refer to Figure 6 which is a schematic diagram of a vehicle-mounted device provided in the sixth embodiment of the present application.

[0211] The vehicle-mounted device comprises an audio acquisition module 601, an audio recognition module 602, and a location recommendation information obtaining module 603.

[0212] The audio acquisition module 601 is configured to acquire location query audio data.

[0213] The audio recognition module 602 is configured to perform audio recognition on the location query audio data to obtain location query text corresponding to the location query audio data.

[0214] The position recommendation information obtaining module 603 is configured to: obtain a plurality of position element texts in the position query text, the plurality of position element texts being texts in the position query text for describing positions; obtain candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; sort the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to a sorting result; and display the position recommendation information.

[0215] Seventh embodiment

[0216] Corresponding to the application scenario of the position recommendation information obtaining method provided by the embodiments of the present application and the position recommendation information obtaining method provided by the first embodiment, the seventh embodiment of the present application further provides another position recommendation information obtaining method. Since the device embodiment is basically similar to the application scenario of the position recommendation information obtaining method provided by the embodiments of the present application and the position recommendation information obtaining method provided by the first embodiment, it is described more simply, and the related parts can be referred to the part of the description of the application scenario of the position recommendation information obtaining method provided by the embodiments of the present application and the position recommendation information obtaining method provided by the first embodiment. The method embodiment described below is only illustrative.

[0217] The position recommendation information obtaining method provided by the seventh embodiment of the present application is applied to an electronic map application, which is generally an electronic map application installed on a user device. The so-called user device includes but is not limited to a mobile phone, a tablet computer, and a computer. In addition, the electronic map application can also be an online electronic map application running on a webpage. The specific implementation mode of the position recommendation information obtaining method provided by the seventh embodiment of the present application is as follows: first, obtaining a trigger operation of a user for an electronic map application; second, obtaining a plurality of position element texts in a position query text input by the user based on the trigger operation, the plurality of position element texts being texts in the position query text for describing positions; third, obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; fourth, sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering scores of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to a sorting result; and fifth, displaying the position recommendation information of the position query text.

[0218] When obtaining the plurality of position element texts in the position query text input by the user based on the trigger operation, the following two methods can generally be used:

[0219] The first mode is: based on the position query text input trigger operation, obtaining the position query text input by the user, at this time, the trigger operation is a position query text input trigger operation for the electronic map application.

[0220] The second mode is: based on the voice query trigger operation, collecting the position query audio data of the user; performing audio recognition on the position query audio data to obtain the position query text. At this time, the trigger operation is a voice query trigger operation for the electronic map application by the user.

[0221] Although the application is disclosed as above with preferred embodiments, it is not intended to limit the application, and any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the application, therefore, the protection scope of the application should be subject to the scope defined by the claims of the application.

[0222] In one typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0223] The memory can include non-persistent memory in the computer readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or Flash memory. The memory is an example of computer readable media.

[0224] 1. Computer readable media includes permanent and non-permanent, removable and non-removable media can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage media or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition in this paper, computer readable media does not include non-transitory computer readable media (transitory media), such as modulated data signals and carriers.

[0225] 2. Those skilled in the art will appreciate that the embodiments of the present application can be devised for as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon for use by or in connection with an instruction execution system.

Claims

1. A position recommendation information obtaining method characterized by comprising: The method comprises: obtaining a plurality of location element texts in a location query text, the plurality of location element texts being texts in the location query text for describing a location; obtaining candidate location information corresponding to the plurality of location element texts for the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, and obtaining location recommendation information for the location query text according to a sorting result; wherein the sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, and obtaining location recommendation information for the location query text according to a sorting result comprises: determining a sorting score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to the sorting score of the candidate location information corresponding to the plurality of location element texts to obtain a sorting result; and obtaining the location recommendation information according to the sorting result; The method further comprises: clustering the candidate location information corresponding to different location element texts in the plurality of location element texts based on a neighborhood of first clustering, a minimum number of points of the first clustering, and the longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain first clustering clusters of the candidate location information corresponding to the different location element texts; clustering the cluster center of the first clustering cluster of the different location element texts based on a neighborhood of second clustering, a minimum number of points of the second clustering, and the longitude and latitude of the cluster center of the first clustering cluster, to obtain second clustering clusters of the cluster center of the first clustering cluster; and obtaining a clustering score of the candidate location information corresponding to the plurality of location element texts according to the distance between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering cluster.

2. The location recommendation information obtaining method according to claim 1, characterized by, Further comprising: obtaining the cluster center of the first clustering cluster according to the first clustering cluster; obtaining, as the cluster center of the second clustering cluster, a cluster containing the most location element text types in the second clustering cluster according to the second clustering cluster.

3. The location recommendation information obtaining method according to claim 1, characterized by, Further comprising: obtaining the number of occurrences of different location element texts in the plurality of location element texts in the location query text; obtaining the number of occurrences of the plurality of location element texts in the location query text according to the number of occurrences of the different location element texts in the location query text.

4. The location recommendation information obtaining method according to claim 1, characterized by, The step of determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts comprises: determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts.

5. The location recommendation information obtaining method according to claim 1 or 4, characterized by, The step of determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts comprises: obtaining text similarities between the plurality of location element texts and the candidate location information corresponding to the plurality of location element texts, and / or text similarities between the location query text and the candidate location information corresponding to the plurality of location element texts as target text similarities of the plurality of location element texts; determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarities of the plurality of location element texts.

6. The location recommendation information obtaining method according to claim 5, characterized by, The step of determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarities of the plurality of location element texts comprises: ranking the candidate location information corresponding to the plurality of location element texts according to the number of occurrences of the plurality of location element texts in the location query text, the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarities of the plurality of location element texts, and determining the ranking scores of the candidate location information corresponding to the plurality of location element texts.

7. The location recommendation information obtaining method according to claim 5, characterized by, The step of determining the ranking scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and the target text similarities of the plurality of location element texts comprises: obtaining user current location information, the user current location information being location information when a user device corresponding to a user sends a location query text; obtaining distances between the candidate location information corresponding to the plurality of location element texts and the user current location information according to the user current location information and the candidate location information corresponding to the plurality of location element texts; obtaining distances between the candidate location information corresponding to the plurality of location element texts and the user current location information according to the user current location information and the candidate location information corresponding to the plurality of location element texts; Determine a ranking score of the candidate location information corresponding to the plurality of location element texts according to at least one of a number of occurrences of the plurality of location element texts in the location query text and a clustering score of the candidate location information corresponding to the plurality of location element texts, a target text similarity of the candidate location information corresponding to the plurality of location element texts, and a distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user.

8. The location recommendation information obtaining method according to claim 7, characterized by, The determining of the ranking score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity of the candidate location information corresponding to the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user includes: determining the ranking score of the candidate location information corresponding to the plurality of location element texts according to the number of occurrences of the plurality of location element texts in the location query text, the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity of the candidate location information corresponding to the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user.

9. The location recommendation information obtaining method according to claim 8, characterized by, The determining of the ranking score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the target text similarity of the candidate location information corresponding to the plurality of location element texts, and the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user includes: normalize the number of occurrences of the plurality of location element texts in the location query text to obtain a first ranking weight for ranking the candidate location information corresponding to the plurality of location element texts; normalize the clustering score of the candidate location information corresponding to the plurality of location element texts to obtain a second ranking weight for ranking the candidate location information corresponding to the plurality of location element texts; take the target text similarity of the candidate location information corresponding to the plurality of location element texts as a third ranking weight for ranking the candidate location information corresponding to the plurality of location element texts; normalize the distance between the candidate location information corresponding to the plurality of location element texts and the current location information of the user to obtain a fourth ranking weight for ranking the candidate location information corresponding to the plurality of location element texts; determine the ranking score of the candidate location information corresponding to the plurality of location element texts according to the first ranking weight, the second ranking weight, the third ranking weight, and the fourth ranking weight.

10. The location recommendation information obtaining method according to claim 9, characterized by, The determining of the ranking score of the candidate location information corresponding to the plurality of location element texts according to the first ranking weight, the second ranking weight, the third ranking weight, and the fourth ranking weight includes: Summing the first ranking weight, the second ranking weight, the third ranking weight and the fourth ranking weight to obtain a ranking score of the candidate location information corresponding to the plurality of location element texts.

11. The location recommendation information obtaining method according to claim 10, characterized by, The position recommendation information for the location query text is obtained according to the ranking result, and the position recommendation information includes: The ranking score of the candidate location information corresponding to the plurality of location element texts is obtained according to the number of occurrences of the plurality of location element texts in the location query text. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result.

12. The location recommendation information obtaining method according to claim 11, characterized by, The position recommendation information for the location query text is obtained according to the ranking result, and the position recommendation information includes: The ranking score of the candidate location information corresponding to the plurality of location element texts is obtained according to the number of occurrences of the plurality of location element texts in the location query text. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result.

13. The location recommendation information obtaining method according to claim 10, 11 or 12, characterized by, The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result.

14. The location recommendation information obtaining method according to claim 13, characterized by, The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result.

15. The location recommendation information obtaining method according to claim 1, characterized by, The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. The candidate location information corresponding to the plurality of location element texts is ranked according to the ranking score of the candidate location information corresponding to the plurality of location element texts, and the position recommendation information is obtained according to the ranking result. According to the candidate position information corresponding to the preset number of different position element texts, candidate position information corresponding to the plurality of position element texts is obtained.

16. The location recommendation information obtaining method of claim 1, characterized by, Further comprising: The position recommendation information is provided to a user equipment.

17. The location recommendation information obtaining method according to claim 16, characterized by, The plurality of position element texts in the position query text are obtained, including: obtaining a position query instruction issued by a user equipment for the position query text, the position query instruction carrying the position query text; The position recommendation information is provided to the user equipment for the position query instruction.

18. The location recommendation information obtaining method of claim 1, characterized by, Further comprising: The position recommendation information is displayed.

19. A position recommendation information obtaining apparatus characterized by comprising: Comprise: A position element text obtaining unit is configured to obtain a plurality of position element texts in a position query text, the plurality of position element texts being texts in the position query text for describing a position; A candidate position obtaining unit is configured to obtain candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; A position recommendation information obtaining unit is configured to sort the candidate position information corresponding to the plurality of position element texts according to at least one of the number of times that the plurality of position element texts appear in the position query text and a clustering score of the candidate position information corresponding to the plurality of position element texts, and obtain position recommendation information for the position query text according to a sorting result; The position recommendation information obtaining unit is configured to determine a sorting score of the candidate position information corresponding to the plurality of position element texts according to at least one of the number of times that the plurality of position element texts appear in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, sort the candidate position information corresponding to the plurality of position element texts according to the sorting score of the candidate position information corresponding to the plurality of position element texts, and obtain the position recommendation information according to the sorting result, so as to realize sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of times that the plurality of position element texts appear in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and obtaining the position recommendation information for the position query text according to a sorting result. The position recommendation information obtaining apparatus is further configured to perform the following steps: clustering the candidate position information corresponding to different position element texts in the plurality of position element texts respectively based on the neighborhood of the first clustering, the minimum number of points of the first clustering, and the longitude and latitude of the candidate position information corresponding to different position element texts; clustering the cluster center of the first clustering corresponding to different position element texts respectively based on the neighborhood of the second clustering, the minimum number of points of the second clustering, and the longitude and latitude of the cluster center of the first clustering corresponding to different position element texts; and obtaining the clustering score of the candidate position information corresponding to the plurality of position element texts according to the distance between the candidate position information corresponding to different position element texts and the cluster center of the second clustering.

20. An electronic device, comprising: comprise: a processor; and a memory for storing a program of a position recommendation information obtaining method, after the device is powered on and the program of the position recommendation information obtaining method is executed by the processor, the following steps are performed: obtaining a plurality of position element texts in a position query text, the plurality of position element texts being texts in the position query text for describing positions; obtaining candidate position information corresponding to the plurality of position element texts for the plurality of position element texts; sorting the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and obtaining position recommendation information for the position query text according to the sorting result; wherein the sorting of the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts, and the obtaining of the position recommendation information for the position query text according to the sorting result, comprises: determining the sorting score of the candidate position information corresponding to the plurality of position element texts according to at least one of the number of occurrences of the plurality of position element texts in the position query text and the clustering score of the candidate position information corresponding to the plurality of position element texts; sorting the candidate position information corresponding to the plurality of position element texts according to the sorting score of the candidate position information corresponding to the plurality of position element texts to obtain a sorting result; and obtaining the position recommendation information according to the sorting result. The step further comprises: clustering the candidate location information corresponding to the different location element texts respectively based on the neighborhood of the first clustering, the minimum number of points of the first clustering, and the longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain the first clustering cluster of the candidate location information corresponding to the different location element texts; clustering the cluster center of the first clustering cluster corresponding to the different location element texts respectively based on the neighborhood of the second clustering, the minimum number of points of the second clustering, and the longitude and latitude of the cluster center of the first clustering cluster, to obtain the second clustering cluster of the cluster center of the first clustering cluster; and obtaining the clustering score of the candidate location information corresponding to the plurality of location element texts according to the distance between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering cluster.

21. A storage medium, characterized by A program of a location recommendation information obtaining method is stored, and the program is run by a processor to execute the following steps: obtaining a plurality of location element texts in a location query text, the plurality of location element texts being texts in the location query text for describing a location; obtaining candidate location information corresponding to the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, and obtaining location recommendation information for the location query text according to a sorting result; wherein the sorting the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, and obtaining location recommendation information for the location query text according to a sorting result, comprises: determining a sorting score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to the sorting score of the candidate location information corresponding to the plurality of location element texts to obtain a sorting result; and obtaining the location recommendation information according to the sorting result; The step further comprises: clustering the candidate location information corresponding to the different location element texts respectively based on the neighborhood of the first clustering, the minimum number of points of the first clustering, and the longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain the first clustering cluster of the candidate location information corresponding to the different location element texts; clustering the cluster center of the first clustering cluster corresponding to the different location element texts respectively based on the neighborhood of the second clustering, the minimum number of points of the second clustering, and the longitude and latitude of the cluster center of the first clustering cluster, to obtain the second clustering cluster of the cluster center of the first clustering cluster; and obtaining the clustering score of the candidate location information corresponding to the plurality of location element texts according to the distance between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering cluster.

22. A position recommendation information obtaining method applied to an electronic map application, characterized by, Comprise: Identify the location query audio data obtained by the user equipment, obtain the location query text; Obtain a plurality of location element texts in the location query text, the plurality of location element texts being texts in the location query text for describing a location; For the plurality of location element texts, obtain the candidate location information corresponding to the plurality of location element texts; According to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information for the location query text is obtained according to the sorting result; Display the location recommendation information through the man-machine interface of the user equipment; Wherein, according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information for the location query text is obtained according to the sorting result, comprising: determining the sorting score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering score of the candidate location information corresponding to the plurality of location element texts; according to the sorting score of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted to obtain the sorting result; and according to the sorting result, the location recommendation information is obtained; The method further comprises: clustering the candidate location information corresponding to different location element texts in the plurality of location element texts respectively based on a neighborhood of the first clustering, a minimum number of points of the first clustering, and the longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain a first clustering cluster of the candidate location information corresponding to the different location element texts; clustering the cluster center of the first clustering cluster corresponding to the different location element texts respectively based on a neighborhood of the second clustering, a minimum number of points of the second clustering, and the longitude and latitude of the cluster center of the first clustering cluster, to obtain a second clustering cluster of the cluster center of the first clustering cluster; and obtaining a clustering score of the candidate location information corresponding to the plurality of location element texts according to the distance between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering cluster.

23. An in-vehicle device characterized by comprising: Comprise: An audio acquisition module, an audio recognition module, and a location recommendation information obtaining module; The audio acquisition module is configured to acquire location query audio data. The audio recognition module is configured to perform audio recognition on the location query audio data to obtain location query text corresponding to the location query audio data. The location recommendation information obtaining module is configured to obtain a plurality of location element texts in the location query text, the plurality of location element texts being texts in the location query text for describing a location; obtain candidate location information corresponding to the plurality of location element texts for the plurality of location element texts; sort the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtain location recommendation information for the location query text according to a sorting result; and display the location recommendation information. The location recommendation information obtaining module is configured to sort the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, and obtain the location recommendation information for the location query text according to a sorting result, by performing the following steps: determining a sorting score of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to the sorting score of the candidate location information corresponding to the plurality of location element texts to obtain a sorting result; and obtaining the location recommendation information according to the sorting result. The vehicle-mounted device is further configured to perform the following steps: clustering candidate location information corresponding to different location element texts in the plurality of location element texts based on a neighborhood of first clustering, a minimum number of the first clustering, and longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain first clustering clusters of the candidate location information corresponding to the different location element texts; clustering cluster center of the first clustering clusters corresponding to the different location element texts based on a neighborhood of second clustering, a minimum number of the second clustering, and longitude and latitude of the cluster center of the first clustering clusters, to obtain second clustering clusters of the cluster center of the first clustering clusters; and obtaining clustering scores of the candidate location information corresponding to the plurality of location element texts according to distances between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering clusters.

24. A position recommendation information obtaining method applied to an electronic map application, characterized by, Comprise: Obtaining a trigger operation of a user for the electronic map application; Based on the trigger operation, obtaining a plurality of location element texts in the location query text input by the user, the plurality of location element texts being texts in the location query text for describing locations; For the plurality of location element texts, obtaining candidate location information corresponding to the plurality of location element texts; According to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information for the location query text is obtained according to the sorting result; Displaying the location recommendation information of the location query text; According to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts, the candidate location information corresponding to the plurality of location element texts is sorted, and the location recommendation information for the location query text is obtained according to the sorting result, comprising: determining the sorting scores of the candidate location information corresponding to the plurality of location element texts according to at least one of the number of occurrences of the plurality of location element texts in the location query text and the clustering scores of the candidate location information corresponding to the plurality of location element texts; sorting the candidate location information corresponding to the plurality of location element texts according to the sorting scores of the candidate location information corresponding to the plurality of location element texts to obtain a sorting result; and obtaining the location recommendation information according to the sorting result; The method further comprises: clustering the candidate location information corresponding to different location element texts in the location query text respectively based on a neighborhood of the first clustering, a minimum number of points of the first clustering, and longitude and latitude of the candidate location information corresponding to the different location element texts, to obtain first clustering clusters of the candidate location information corresponding to the different location element texts; clustering the cluster center of the first clustering cluster corresponding to the different location element texts respectively based on a neighborhood of the second clustering, a minimum number of points of the second clustering, and longitude and latitude of the cluster center of the first clustering cluster, to obtain second clustering clusters of the cluster center of the first clustering cluster; and obtaining clustering scores of the candidate location information corresponding to the multiple location element texts according to distances between the candidate location information corresponding to the different location element texts and the cluster center of the second clustering cluster.

25. The location recommendation information obtaining method according to claim 24, characterized by, The trigger operation comprises a location query text input trigger operation of the electronic map application; The obtaining of the multiple location element texts in the location query text input by the user based on the trigger operation comprises: obtaining the location query text input by the user based on the location query text input trigger operation.

26. The location recommendation information obtaining method according to claim 24, characterized by, The trigger operation comprises a voice query trigger operation of the electronic map application by the user; The obtaining of the multiple location element texts in the location query text input by the user based on the trigger operation comprises: acquiring location query audio data of the user based on the voice query trigger operation; obtaining the location query text by performing audio recognition on the location query audio data.

Images