Map guide point determination method, device, equipment, storage medium and program product

Abstract

The disclosure provides a map guide point determination method and device, electronic equipment, computer readable storage medium and computer program product, relating to image recognition, speech recognition, deep learning, map navigation and other artificial intelligence technical fields. The method comprises: determining candidate guide points corresponding to the interest points according to the travel trajectories with the same end point, the child interest points having a known parent-child relationship with the interest points and the road network topology; determining the travel mode corresponding to each candidate guide point by a preset multi-source verification method to obtain a target guide point sequence corresponding to each travel mode; wherein the multi-source verification method includes a plurality of sources that are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs. The method can better solve the last 500 meters of navigation problem, greatly improving the user's navigation experience.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular to the technical field of artificial intelligence such as image recognition, speech recognition, deep learning, map navigation, and the like, and more particularly to a map guide point determination method and device, an electronic device, a computer readable storage medium, and a computer program product. BACKGROUND

[0002] A map guide point refers to a connection point for a user to switch scenes when traveling. It is a connection point for the user to reach a destination, helping the user to accurately and efficiently reach the destination, covering multiple travel scenes such as driving (driving end point), public transportation (walking end point), and taking a taxi (getting on and off a taxi).

[0003] In a traditional map data production process, road network data mainly expresses the spatial road network topology and road elements (for example, road level, speed limit, and sign), and POI (Point of Interest) data mainly expresses interest points in the real objective world (for example, a POI can be a house, a shop, a mailbox, or a bus stop). In the existing data, there is no expression of walking into the interest point from which road, parking after driving to the interest point, and getting on and off a taxi, and the like, which is often one of the most core demands of users using map navigation. SUMMARY

[0004] Embodiments of the present disclosure provide a map guide point determination method, device, electronic device, computer readable storage medium, and computer program product.

[0005] In a first aspect, embodiments of the present disclosure provide a map guide point determination method, including: determining candidate guide points corresponding to an interest point according to travel trajectories with the same end point, child interest points having a known parent-child relationship with the interest point, and road network topology; and determining travel modes corresponding to each candidate guide point by a preset multi-source verification method to obtain a target guide point sequence corresponding to each travel mode, wherein the multi-source verification method includes multiple sources that are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

[0006] In a second aspect, the embodiments of the present disclosure provide a map guide point determination apparatus, which comprises: a candidate guide point determination unit configured to determine a candidate guide point corresponding to a point of interest according to travel trajectories with the same end point, a child point of interest having a known parent-child relationship with the point of interest, and a road network topology; and a multi-source verification unit configured to determine a travel mode corresponding to each candidate guide point by using a preset multi-source verification manner, and obtain a target guide point sequence corresponding to each travel mode; wherein the multi-source verification manner comprises a plurality of verification manners which are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

[0007] In a third aspect, the embodiments of the present disclosure provide an electronic device, which comprises: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the map guide point determination method described in any implementation manner of the first aspect.

[0008] In a fourth aspect, the embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to enable a computer to implement the map guide point determination method described in any implementation manner of the first aspect.

[0009] In a fifth aspect, the embodiments of the present disclosure provide a computer program product comprising a computer program, and the computer program is executable by a processor to implement the map guide point determination method described in any implementation manner of the first aspect.

[0010] The present disclosure provides a more scientific and comprehensive map guide point determination scheme based on the solution idea of first performing full quantity recall and then performing multi-source verification.

[0011] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the following drawings:

[0013] Figure 1is an exemplary system architecture to which the map guide point determination method of the present disclosure can be applied;

[0014] Figure 2 a flowchart of a map guide point determination method provided by an embodiment of the present disclosure;

[0015] Figure 3 a flowchart of another map guide point determination method provided by an embodiment of the present disclosure;

[0016] Figure 4 a schematic diagram of a specific proof method of several proof manners provided by an embodiment of the present disclosure;

[0017] Figure 5 a dialogue schematic diagram of a voice telephone inquiry by an artificial intelligence provided by an embodiment of the present disclosure;

[0018] Figure 6 an effect schematic diagram of guide points corresponding to each travel mode taken as an example of a point of interest A provided by an embodiment of the present disclosure;

[0019] Figure 7 a structural block diagram of a map guide point determination apparatus provided by an embodiment of the present disclosure;

[0020] Figure 8 a structural schematic diagram of an electronic device suitable for executing a map guide point determination method provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0022] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solutions comply with the relevant legal regulations and do not violate public order and good customs.

[0023] Figure 1 An exemplary system architecture 100 to which the embodiments of the map guide point determination method, apparatus, electronic device and computer readable storage medium of the present disclosure can be applied is shown.

[0024] As Figure 1As shown, the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0025] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 and the server 105 can be installed with various applications for realizing information communication between the two, such as map navigation applications, guide point determination applications, instant messaging applications, etc.

[0026] The terminal devices 101, 102, 103 and the server 105 can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc. When the terminal devices 101, 102, 103 are software, they can be installed in the above-mentioned electronic devices, and can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server 105 is software, it can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here.

[0027] The server 105 can provide various services through various built-in applications. Taking a guide point determination application that can provide guide point determination services for map navigation applications as an example, the server 105 can achieve the following effects when running the guide point determination application: First, the server 105 pulls the travel trajectories granted the use permission from the terminal devices 101, 102, 103 through the network 104; then, according to the travel trajectories with the same interest point as the destination, the child interest points having a known parent-child relationship with the interest point, and the road network topology, the server 105 determines the candidate guide points corresponding to the interest point; next, the server 105 determines the travel mode corresponding to each candidate guide point through a preset multi-source verification method, and obtains the target guide point sequence corresponding to each travel mode, wherein the multi-source verification method includes multiple sources that are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

[0028] It should be noted that the travel trajectories can be pre-stored in the server 105 locally through various ways in addition to being acquired from the terminal devices 101, 102, 103 through the network 104. Therefore, when the server 105 detects that the local has already stored these data, it can be selected to directly acquire these data from the local, and in this case, the exemplary system architecture 100 can also not include the terminal devices 101, 102, 103 and the network 104.

[0029] Since the determination of the guide point needs to be based on a large amount of raw data and through a complex calculation method, it needs to occupy more operation resources and stronger operation capability, so the map guide point determination method provided by each subsequent embodiment of the present disclosure is generally executed by the server 105 which has stronger operation capability and more operation resources, and accordingly, the map guide point determination apparatus is also generally arranged in the server 105. However, it should also be noted that when the terminal devices 101, 102, 103 also have operation capability and operation resources that meet the requirements, the terminal devices 101, 102, 103 can also complete the above-mentioned operations of the server 105 through the guide point determination application installed thereon, and then output the same result as the server 105. Especially in the case where there are multiple terminal devices with different operation capabilities, but the guide point determination application judges that the terminal device has strong operation capability and has more remaining operation resources, the terminal device can be allowed to execute the above-mentioned operation, so as to appropriately reduce the operation pressure of the server 105, and accordingly, the map guide point determination apparatus can also be arranged in the terminal devices 101, 102, 103. In this case, the exemplary system architecture 100 can also not include the server 105 and the network 104.

[0030] It should be understood that Figure 1 The number of terminal devices, networks and servers in

[0031] Reference can be made to Figure 2 , Figure 2 A flowchart of a map guide point determination method provided by an embodiment of the present disclosure is shown in FIG. 2, wherein the flow 200 includes the following steps:

[0032] Step 201: determining a candidate guide point corresponding to the interest point according to travel trajectories with the same end point, a child interest point having a known parent-child relationship with the interest point and a road network topology;

[0033] This step is intended to be executed by the execution subject of the map guide point determination method (for example Figure 1The server 105 shown determines as many as possible comprehensive and all candidate guide points corresponding to the interest point according to each travel trajectory having the same interest point as the trajectory endpoint, the child interest point having a known parent-child relationship with the interest point, and the road network topology.

[0034] The travel trajectory includes trajectories corresponding to different travel modes, and travel trajectories pointing to the same destination (interest point) are classified into a group for subsequent trajectory analysis. The travel trajectory can be obtained from the user's actual use of the legally authorized travel arrangement and historical travel information recorded in the electronic map application.

[0035] The child interest point and the interest point (or parent interest point) having a known parent-child relationship with the child interest point are described by the "parent-child" association relationship. For example, when a parent interest point is "XX Building", the child interest points in the present disclosure mainly include "North Gate", "West Gate", "South Gate", "North Ground Parking Lot", "South Underground Parking Lot", etc. The known parent-child relationship can be obtained from the official report of the interest point at that time.

[0036] The road network topology refers to the topology composed of the road network, and the interest point is often located at a certain position in the road network topology. Therefore, the guide points corresponding to the interest point that may exist can be found to some extent through the road network topology.

[0037] In order to achieve the purpose of obtaining as many as possible comprehensive candidate guide points corresponding to the interest point, other information or data that can help determine the guide points can also be combined to further improve the purpose of this step in addition to the travel trajectory, the known parent-child relationship of the interest point, and the road network topology given in this step.

[0038] Step 202: Determine the travel mode corresponding to each candidate guide point by a preset multi-source verification method to obtain a target guide point sequence corresponding to each travel mode.

[0039] On the basis of step 201, this step aims to determine the travel mode corresponding to each candidate guide point by a preset multi-source verification method to obtain a target guide point sequence corresponding to each travel mode by the above-mentioned execution subject. The multi-source verification method includes a plurality of sources that are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

[0040] That is, this step aims to determine as many as possible comprehensive and comprehensive travel modes to which each candidate guide point belongs by simultaneously using a plurality of independent sources of verification methods, so as to obtain an accurate target guide point sequence corresponding to each travel mode.

[0041] The map guide point determination method provided by the embodiments of the present disclosure is based on the solution idea of first performing full recall, and then based on the multi-source verification method, a more scientific and comprehensive map guide point determination scheme is provided. For the key multi-source verification method, various different data sources are designed to fully utilize the technical and data advantages of existing map applications and search engines, and with the help of artificial intelligence technology, the last 500 meters of navigation problem is better solved, and the user's navigation experience is greatly improved.

[0042] Reference is made to Figure 3 , Figure 3 The flowchart of another map guide point determination method provided by the embodiments of the present disclosure is shown in FIG. 3, wherein the flow 300 includes the following steps:

[0043] Step 301: performing clustering analysis on the trajectory endpoints of each travel trajectory with the same interest point as the endpoint to obtain a first candidate point;

[0044] This step aims to perform clustering analysis on the trajectory endpoints of each travel trajectory with the same interest point as the endpoint by the above execution subject to obtain a first candidate point. That is, although the endpoints of each travel trajectory correspond to the same interest point, the endpoints may be distributed at different positions of the same interest point, such as the south gate and the north gate, that is, although they all belong to the same interest point at the interest point level, the trajectory endpoints can be clustered at a more subdivided level to check whether there is an aggregation trend in different directions of the interest point.

[0045] Specifically, since the travel mode adopted along with the travel trajectory can be obtained or the travel mode (such as walking, driving, using a transportation tool, etc.) adopted can be calculated according to the speed information recorded in the trajectory, the first candidate point corresponding to each travel mode is determined through clustering analysis.

[0046] A specific execution step is included but not limited to:

[0047] According to the travel mode corresponding to different travel trajectories, the trajectory endpoints of each travel trajectory corresponding to the same travel mode are clustered and analyzed to obtain a clustering analysis result;

[0048] The first candidate point corresponding to each travel mode is determined according to the clustering analysis result.

[0049] Specifically, when performing clustering analysis, density can be simply selected as a clustering factor for clustering, and in order to adapt to the complex situation in the real world, other factors can also be added at the same time to improve the clustering accuracy. Taking the travel trajectory using the driving mode as an example, the weight of each clustering influence factor can also be adjusted in combination with the speed change near the endpoint of the trajectory.

[0050] Step 302: determining the second candidate point according to the intersection of the road network topology and the point of interest;

[0051] This step aims to determine the intersection of the road network topology and the point of interest as the second candidate point by the above-mentioned execution body.

[0052] Step 303: determining the third candidate point as the child point of interest having a known parent-child relationship with the point of interest;

[0053] This step aims to determine the third candidate point as the child point of interest having a known parent-child relationship with the point of interest by the above-mentioned execution body.

[0054] It should be noted that the points of interest described in steps 301-303 are the same points of interest, that is, all candidate guide points as points of interest are determined through steps 301-303 from the trip trajectory, the road network topology, and the known parent-child relationship.

[0055] Step 304: performing deduplication processing on the first candidate point, the second candidate point, and the third candidate point, and taking each candidate point obtained after the deduplication processing as a candidate guide point;

[0056] On the basis of steps 301-303, this step aims to filter out duplicate candidate points by deduplication processing by the above-mentioned execution body. It should be noted that when a candidate point is recognized as belonging to different travel modes at the same time through different ways, it will be represented as different candidate points due to the difference in the travel mode.

[0057] Step 305: determining the travel mode corresponding to each candidate guide point respectively through the expert experience-based verification method, the image-based verification method, the text-based verification method, and the voice-based verification method;

[0058] On the basis of step 304, this step aims to determine the travel mode corresponding to each candidate guide point respectively by the expert experience-based verification method, the image-based verification method, the text-based verification method, and the voice-based verification method by the above-mentioned execution body.

[0059] Among them, the expert experience-based verification method means that some results that are difficult to determine through automatic means are supplemented by experts based on their own relevant experience and cognition of guide points, and the confidence of the verification results obtained is the highest;

[0060] The image-based verification mode can include image information obtained from multiple independent channels, which can determine the guide point from the same or different angles, such as the guide point determination task based on the release of the crowd-sourcing user, the crowd-sourcing image for observing the surrounding of the interest point, the road video for confirming the guide point related information from the vehicle-mounted camera or the roadside device in the vehicle-mounted or roadside perspective, and the previously released internet public image data for helping to determine the guide point related information searched from the public internet database, etc.

[0061] The text-based verification mode mainly refers to the text form of question and answer information containing the guide point related information searched from the public internet database, which is previously released by the user for a certain problem.

[0062] The voice-based verification mode mainly initiates a voice inquiry for obtaining the guide point related information through the artificial intelligence technology (AI) based on a certain speech to some real user, and converts the obtained voice feedback into recognizable results through voice recognition. Specifically, the real user can be preferably the user who has passed the target interest point or the candidate guide point according to the historical travel trajectory.

[0063] In order to deepen the understanding of the process of implementing multi-source verification in step 305, the embodiment further shows the process of implementing the guide point verification based on the image mode, the voice mode and the text mode: Figure 4 The process of implementing the guide point verification based on the image mode, the voice mode and the text mode is shown: the travel mode corresponding to each candidate guide point is determined through the image information extracted from the crowd-sourcing image, the road video and the internet image respectively; the travel mode corresponding to each candidate guide point is determined through searching the internet public text form of question and answer information; and the travel mode corresponding to each candidate guide point is determined through the artificial intelligence telephone inquiry initiated to the alternative user. An exemplary voice inquiry speech can be seen in Figure 5 .

[0064] Step 306: The corresponding relationship between the candidate guide point and the travel mode determined by at least two verification modes is summarized to obtain the target guide point sequence corresponding to each travel mode.

[0065] On the basis of step 305, this step aims to summarize the corresponding relationship between the candidate guide point and the travel mode determined by as many verification modes as possible by the above-mentioned execution subject, so as to finally obtain the target guide point sequence corresponding to each travel mode. Since the credibility of the result determined by only one verification mode cannot meet the demand, at least two different verification modes are required.

[0066] A specific implementation mode can be:

[0067] determining the weight coefficients between each of the plurality of proof methods;

[0068] processing the classification results of the candidate guide points obtained through the corresponding proof methods according to the weight coefficients corresponding to each proof method to obtain the target guide point sequence corresponding to each travel mode. That is, by setting reasonable weight coefficients, the influence of different proof methods on the final ranking is reasonably reflected.

[0069] Since the above-mentioned multi-source proof methods are all independent, when relevant information can be obtained from various sources, the weight arrangement they should follow is: manual verification> crowd-sourced images, road images, Internet images> Internet text> intelligent phone inquiry. Due to actual conditions, the model based on deep learning can also determine a slightly different or partially conflicting actual weight arrangement. The influence can include: the information confidence of a certain source is low, etc.

[0070] Step 307: Based on the target guide point sequence corresponding to each travel mode, a guide point map based on interest points is constructed.

[0071] On the basis of step 306, this step aims to construct a guide point map based on interest points by the above-mentioned execution subject based on the target guide point sequence corresponding to each travel mode, so as to add more information through the form of the map, so that the guide point map can provide more rich travel navigation information.

[0072] The most basic guide point map is the guide points corresponding to each travel mode based on interest points and associated with interest points. Further, the position relationship of the guide points relative to the interest points can be added to the map to facilitate accurate positioning of the guide points. More information such as the group type, opening time, and opening direction of each guide point can also be added to the map in an appropriate manner to correspond to the complex situation in the real world and provide more rich information.

[0073] Further, in order to better represent the different corresponding relationships between interest points and guide points, different line colors, line types, line thicknesses, and different colors for different guide points can also be used to reflect the differences.

[0074] The steps 301-304 provided in this embodiment are a lower implementation scheme for step 201, steps 305-306 are a lower implementation scheme for step 202, and step 307 is an additional implementation scheme. The above three parts constitute a new complete implementation scheme of the embodiment, but it should be noted that there is no causal and dependent relationship between the above three parts, and the above three parts can be replaced independently in the corresponding upper scheme in flow 200, added in flow 200, to form different embodiments. This embodiment only exists as a preferred embodiment containing the above three preferred schemes.

[0075] To deepen understanding, the disclosure also provides a complete guide point map construction and application scheme in combination with a specific application scenario, which abstracts the guide point production problem into two-stage solving: retrieval and verification (which can also correspond to recall and ranking). After splitting into two stages, recall and ranking can be optimized independently. The following will be described in detail with respect to the two different stages:

[0076] 1) Recall problem

[0077] The recall stage mainly recalls as many and as accurate candidate points as possible that meet the requirements of the guide point. Based on travel trajectories, parent-child interest points, road networks, etc., candidate guide points are generated through spatial clustering of travel trajectories, child interest points (including gates and parking lots), and the intersection of road network topology and interest points. In the recall stage, candidate points that may meet different product requirements (including driving, walking, and taking a taxi) should be recalled as much as possible.

[0078] 2) Multi-modal ranking problem

[0079] The ranking stage is the most important part of generating guide points. Among the generated candidate points, multi-source signals are collected through "verification", and then multi-modal ranking is performed to finally obtain guide points that meet product requirements.

[0080] In this embodiment, multi-modal ranking includes the following verification methods: crowdsourcing images, road images, smart phones, Internet texts, expert experience, etc.

[0081] In the verification method based on crowdsourcing images, user uploaded UGC (User Generated Content, user generated content, i.e. user original content) image data can be used. The images taken by the user are associated with the interest point data, so that the required signal input can be obtained, such as whether the building or sign corresponding to the interest point can be seen, whether it is an entrance, etc., which can be used as important information for the user to observe the spatial position relationship with the interest point.

[0082] In road image verification, the signal affecting the passage can be confirmed, for example, the entrance can be distinguished from the road image, and the passage attribute of the gate can be judged.

[0083] In telephone verification, through the smart phone, the specific signal input can be obtained for different point of interest scenes, such as Figure 5 As shown, for example: which street does the point of interest face, whether the front of the point of interest can park, if it cannot park, where can the car be parked, such as Figure 5 As shown, the decision information is extracted from the smart phone content, and then the address and point of interest are processed in chain, so as to obtain the required information input.

[0084] In Internet text verification, structured information can be extracted from the powerful search and content ecology of search engines, for example: where can you park to go to a point of interest, which can be extracted by structuring the question and answer content, and then judged to the point of interest, and then the parking related information is obtained.

[0085] In expert experience verification, the existing work means is upgraded, and the pure manual annotation is changed into only relying on manual selection or judgment of the given actual image, so as to greatly simplify the work process and complexity, and improve the efficiency and accuracy of manual work.

[0086] After obtaining the above multi-source signal input, the system constructed by the embodiment can sort the whole based on the multi-modal signal input, and generate the final guide point graph, as shown in Figure 6 At the same time, the guide points meeting the different needs of driving, walking and taking a taxi are output.

[0087] Based on the multi-modal guide point graph construction, it can not only meet the needs of guide point construction in different scenes, but also extract the decision knowledge (such as parking related recommendation knowledge) for travel from various signal inputs to assist users in travel decision.

[0088] Further referring to Figure 7 As an implementation of the method shown in the above figures, the disclosure provides an embodiment of a map guide point determination device, which corresponds to the method embodiment shown in Figure 2 The device can be applied to various electronic devices.

[0089] As Figure 7As shown, the map guide point determination apparatus 700 in this embodiment can include a candidate guide point determination unit 701, and a multi-source verification unit 702. The candidate guide point determination unit 701 is configured to determine candidate guide points corresponding to the interest point according to travel trajectories with the same end point, child interest points having a known parent-child relationship with the interest point, and road network topology. The multi-source verification unit 702 is configured to determine travel modes corresponding to each candidate guide point by a preset multi-source verification manner, and obtain target guide point sequences corresponding to each travel mode. The multi-source verification manner includes multiple sources that are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

[0090] In this embodiment, the specific processing of the candidate guide point determination unit 701 and the multi-source verification unit 702 in the map guide point determination apparatus 700 and the technical effects brought by the specific processing can be respectively referred to Figure 2 The related description of steps 201-202 in the corresponding embodiment will not be repeated here.

[0091] In some optional implementations of this embodiment, the candidate guide point determination unit 701 can include:

[0092] A trajectory processing sub-unit configured to perform clustering analysis on the trajectory end points of the travel trajectories with the same end point to obtain first candidate points;

[0093] A road network data processing sub-unit configured to determine second candidate points according to the intersection of the road network topology and the interest point;

[0094] A parent-child relationship processing sub-unit configured to determine child interest points having a known parent-child relationship with the interest point as third candidate points;

[0095] A deduplication processing sub-unit configured to perform deduplication processing on the first candidate points, the second candidate points, and the third candidate points, and take each candidate point obtained after the deduplication processing as a candidate guide point.

[0096] In some optional implementations of this embodiment, the trajectory processing sub-unit can be further configured to:

[0097] According to the travel modes corresponding to different travel trajectories, perform clustering analysis on the trajectory end points of the travel trajectories corresponding to the same travel mode to obtain clustering analysis results;

[0098] According to the clustering analysis results, determine first candidate points corresponding to each travel mode.

[0099] In some optional implementations of this embodiment, the multi-source verification unit 702 can include:

[0100] The multi-source respectively proving sub-unit is configured to determine the travel mode corresponding to each candidate guide point respectively by an expert experience-based proving mode, an image-based proving mode, a text-based proving mode, and a voice-based proving mode.

[0101] The proving result aggregation sub-unit is configured to aggregate the correspondence between the candidate guide points and the travel modes respectively determined by the at least two proving modes to obtain a target guide point sequence corresponding to each travel mode.

[0102] In some optional implementations of the embodiment, the multi-source respectively proving sub-unit includes an image proving module configured to determine the travel mode corresponding to each candidate guide point by the image-based proving mode. The image proving module can be further configured to:

[0103] determine the travel mode corresponding to each candidate guide point by respectively extracting image information from the crowd-sourced images, the road videos, and the Internet images.

[0104] In some optional implementations of the embodiment, the multi-source respectively proving sub-unit includes a text proving module configured to determine the travel mode corresponding to each candidate guide point by the text-based proving mode. The text proving module can be further configured to:

[0105] determine the travel mode corresponding to each candidate guide point by searching the text-based Q&A data publicly available on the Internet.

[0106] In some optional implementations of the embodiment, the multi-source respectively proving sub-unit includes a voice proving module configured to determine the travel mode corresponding to each candidate guide point by the voice-based proving mode. The voice proving module can be further configured to:

[0107] determine the travel mode corresponding to each candidate guide point by conducting an artificial intelligence phone inquiry initiated by a candidate user.

[0108] In some optional implementations of the embodiment, the multi-source proving unit 702 can include a sequence generating sub-unit configured to obtain a target guide point sequence corresponding to each travel mode. The sequence generating sub-unit can be further configured to:

[0109] determine a weight coefficient between each proving mode constituting the multi-source proving mode respectively;

[0110] process the classification result of the candidate guide points obtained by the corresponding proving mode according to the weight coefficient corresponding to each proving mode to obtain a target guide point sequence corresponding to each travel mode.

[0111] In some optional implementations of the embodiment, the map guide point determination apparatus 700 can further include:

[0112] The guide point map construction unit is configured to construct a guide point map based on the target guide point sequence corresponding to each mode of transportation.

[0113] The embodiment provides a map guide point determination apparatus.

[0114] The embodiment provides a map guide point determination apparatus, which is based on the solution idea of first performing full recall and then based on a multi-source verification method, and provides a more scientific and comprehensive map guide point determination scheme. For the key multi-source verification method, a plurality of different data sources are designed, so that the advantages of existing map applications and search engine technology and data volume can be fully utilized, and the last 500 meters of navigation can be better solved with the help of artificial intelligence technology, so that the user's navigation experience can be greatly improved.

[0115] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the map guide point determination method described in any of the above embodiments when executed.

[0116] According to the embodiments of the present disclosure, the present disclosure further provides a readable storage medium, which stores computer instructions for enabling a computer to implement the map guide point determination method described in any of the above embodiments when executed.

[0117] According to the embodiments of the present disclosure, the present disclosure further provides a computer program product, which can implement the map guide point determination method described in any of the above embodiments when executed by a processor.

[0118] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0119] AsFigure 8 As shown, the device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0120] Various components in the device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc., an output unit 807, such as various types of displays, speakers, etc., a storage unit 808, such as a magnetic disk, an optical disk, etc., and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0121] The computing unit 801 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs various methods and processes described above, such as the map guide point determination method. For example, in some embodiments, the map guide point determination method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the map guide point determination method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the map guide point determination method by any other appropriate means, such as by means of firmware.

[0122] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0123] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0124] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0126] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0127] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical host and virtual private server (VPS, Virtual Private Server) services.

[0128] According to the technical scheme of the embodiment of the present disclosure, based on the solution idea of first performing full recall and then based on the multi-source verification method, a more scientific and comprehensive map guide point determination scheme is provided. For the key multi-source verification method, a plurality of different data sources are designed, so as to fully utilize the technical and data quantity advantages of existing map applications and search engines, and better solve the last 500 meters of navigation with the help of artificial intelligence technology, greatly improving the user's navigation experience.

[0129] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0130] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining a map guide point, comprising: determining candidate guide points corresponding to a same interest point according to travel trajectories with the same interest point as a terminal point, child interest points having a known parent-child relationship with the interest point, and a road network topology; determining travel modes corresponding to each of the candidate guide points by a preset multi-source verification mode, and obtaining a target guide point sequence corresponding to each travel mode, including: determining weight coefficients between each verification mode constituting the multi-source verification mode; processing classification results of the candidate guide points obtained by the corresponding verification mode according to the weight coefficients corresponding to each verification mode, and obtaining the target guide point sequence corresponding to each travel mode, wherein the multi-source verification mode includes multiple verification modes which are relatively independent and can be used to determine the travel mode to which the candidate guide point belongs.

2. The method according to claim 1, wherein, The determining of the candidate guide points corresponding to the same interest point according to the travel trajectories with the same interest point as a terminal point, the child interest points having a known parent-child relationship with the interest point, and the road network topology, includes: performing cluster analysis on the trajectory terminal points of each travel trajectory with the same interest point as a terminal point to obtain first candidate points; determining second candidate points according to the intersection of the road network topology and the interest point; determining third candidate points as the child interest points having a known parent-child relationship with the interest point; performing deduplication processing on the first candidate points, the second candidate points, and the third candidate points, and taking each candidate point obtained after the deduplication processing as the candidate guide point.

3. The method of claim 2, wherein, The cluster analysis on the trajectory terminal points of the travel trajectories to obtain the first candidate points, includes: performing cluster analysis on the trajectory terminal points of each travel trajectory corresponding to the same travel mode according to the travel modes corresponding to different travel trajectories to obtain a cluster analysis result; determining the first candidate points corresponding to each travel mode according to the cluster analysis result.

4. The method of claim 1, wherein, The determining of the travel modes corresponding to each of the candidate guide points by the preset multi-source verification mode, and the obtaining of the target guide point sequence corresponding to each travel mode, includes: determining the travel modes corresponding to each of the candidate guide points by an expert experience-based verification mode, an image-based verification mode, a text-based verification mode, and a voice-based verification mode; summarizing the corresponding relationship between the candidate guide points and the travel modes determined by at least two verification modes to obtain the target guide point sequence corresponding to each travel mode.

5. The method of claim 4, wherein, The determining of the travel modes corresponding to each of the candidate guide points by the image-based verification mode, includes: determining the travel modes corresponding to each of the candidate guide points by image information extracted from crowd-sourced images, road images, and Internet images.

6. The method of claim 4, wherein, The determining of the travel modes corresponding to each of the candidate guide points by the text-based verification mode, includes: determining the travel modes corresponding to each of the candidate guide points by searching for publicly available text-based question and answer materials on the Internet.

7. The method of claim 4, wherein, The determining of the travel modes corresponding to each of the candidate guide points by the voice-based verification mode, includes: determine the travel mode corresponding to each of the candidate guide points through an artificial intelligence phone inquiry initiated by a candidate user.

8. The method of any one of claims 1-7, further comprising: constructing a guide point atlas based on points of interest based on the target guide point sequence corresponding to each travel mode.

9. A map guide point determination apparatus, comprising: a candidate guide point determination unit configured to determine candidate guide points corresponding to an interest point according to travel trajectories with the interest point as a terminal point, child interest points having a known parent-child relationship with the interest point, and a road network topology; a multi-source proof unit configured to determine the travel mode corresponding to each of the candidate guide points through a preset multi-source proof mode to obtain a target guide point sequence corresponding to each travel mode; wherein the multi-source proof mode comprises a plurality of proof modes that are relatively independent of each other and can be used to determine the travel mode to which a candidate guide point belongs; the multi-source proof unit comprises a sequence generation subunit configured to obtain the target guide point sequence corresponding to each travel mode, and the sequence generation subunit is further configured to: determine the weight coefficients between each of the proof modes constituting the multi-source proof mode; process the classification results of the candidate guide points obtained through the corresponding proof mode according to the weight coefficients corresponding to each proof mode to obtain the target guide point sequence corresponding to each travel mode.

10. The apparatus of claim 9, wherein, The candidate guide point determination unit comprises: a trajectory processing subunit configured to perform cluster analysis on the trajectory terminal points of each travel trajectory with the same interest point as a terminal point to obtain first candidate points; a road network data processing subunit configured to determine second candidate points according to the intersection of the road network topology and the interest point; a parent-child relationship processing subunit configured to determine child interest points having a known parent-child relationship with the interest point as third candidate points; a de-duplication processing subunit configured to perform de-duplication processing on the first candidate points, the second candidate points, and the third candidate points, and to take each candidate point obtained after the de-duplication processing as the candidate guide point.

11. The apparatus of claim 10, wherein, The trajectory processing subunit is further configured to: perform cluster analysis on the trajectory terminal points of each travel trajectory corresponding to the same travel mode according to the travel mode corresponding to different travel trajectories to obtain a cluster analysis result; determine the first candidate points corresponding to each travel mode according to the cluster analysis result.

12. The apparatus of claim 9, wherein, The multi-source proof unit comprises: a multi-source separate proof subunit configured to determine the travel mode corresponding to each of the candidate guide points through an expert experience-based proof mode, an image-based proof mode, a text-based proof mode, and a voice-based proof mode; a proof result aggregation subunit configured to aggregate the correspondence between the candidate guide points and the travel modes determined through at least two proof modes to obtain the target guide point sequence corresponding to each travel mode.

13. The apparatus of claim 12, wherein, The multi-source separate proof subunit comprises an image proof module configured to determine the travel mode corresponding to each of the candidate guide points through an image-based proof mode, and the image proof module is further configured to: The travel mode corresponding to each candidate guide point is determined by image information extracted from crowd-sourced images, road images, and Internet images respectively.

14. The apparatus of claim 12, wherein, The multi-source separate proving subunit includes a text proving module configured to determine the travel mode corresponding to each candidate guide point by a text-based proving method. The text proving module is further configured to: The travel mode corresponding to each candidate guide point is determined by searching Internet public text-based question-and-answer materials.

15. The apparatus of claim 12, wherein, The multi-source separate proving subunit includes a voice proving module configured to determine the travel mode corresponding to each candidate guide point by a voice-based proving method. The voice proving module is further configured to: The travel mode corresponding to each candidate guide point is determined by an artificial intelligence phone inquiry initiated by a backup user.

16. The apparatus of any one of claims 9-15, further comprising: a guide point map construction unit configured to construct a point-of-interest-based guide point map based on the target guide point sequence corresponding to each travel mode.

17. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the map guide point determination method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the map guide point determination method of any one of claims 1-8.

19. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the map guide point determination method according to any one of claims 1-8.

Images