Path guidance method, device, storage medium and electronic device

Abstract

The present disclosure relates to a path guidance method, device, storage medium and electronic device. The method comprises: obtaining multiple route trajectories from a target entrance to an indoor target destination; obtaining the guidance points of each of the multiple route trajectories, and each guidance point in the same route trajectory has a sequential passing order; clustering the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain the target guidance points of each position; based on the guidance point information of the target guidance points of each position, generating path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target destination. By adopting this method of the present disclosure, the difficulty of user path finding can be reduced, thereby improving the efficiency of users reaching the target destination and reducing the path finding time.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a path guidance method, device, storage medium and electronic device. Background Art

[0002] Currently, when users are looking for stores indoors, they have difficulty finding their way around due to unfamiliarity with the environment and complex indoor structures, which leads to low efficiency and a long time to reach the store.

[0003] In the related art, although GPS positioning technology can be used to help find stores and find directions, due to the characteristics of GPS positioning technology and the characteristics of the indoor environment, store and direction finding based on GPS assistance will have large errors, which increases the difficulty of users finding directions, and still leads to the problem of low efficiency and long time to reach the store. Summary of the invention

[0004] The purpose of the present disclosure is to provide a path guidance method, device, storage medium and electronic device to solve the problems existing in the related art.

[0005] In order to achieve the above-mentioned purpose, the first part of the embodiment of the present disclosure provides a path guidance method, the method comprising:

[0006] Obtain multiple trajectories from the target entrance to the indoor target end point;

[0007] Obtaining respective guidance points of the plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order;

[0008] Clustering the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain target guidance points at each position;

[0009] Based on the guidance point information of the target guidance points at each position, path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target end point is generated.

[0010] Optionally, the step of obtaining multiple path trajectories from a target entrance to an indoor target end point includes:

[0011] Acquire the initial heading of each target object at the target entrance, and acquire the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance;

[0012] The path trajectory corresponding to each target object is constructed based on the initial heading, the real-time heading change, and the real-time position movement of each target object.

[0013] Optionally, obtaining the initial heading of each target object corresponding to the target entrance includes:

[0014] Obtaining the GPS trajectory of the target object when it moves from a preset range from the indoor and outdoor boundaries to the indoor and outdoor boundaries;

[0015] The movement direction corresponding to the GPS track of the target object is determined as the initial heading of the target object at the target entrance.

[0016] Optionally, the heading change includes a horizontal heading change, and constructing the path trajectory corresponding to each target object based on the initial heading, the real-time heading change, and the real-time position movement of each target object includes:

[0017] Based on the route type determination strategy corresponding to the real-time state change of the data acquisition device of the target object and the real-time horizontal heading change, determine the route type corresponding to the target object, the route type including a turning route and a straight route;

[0018] Based on the initial heading of the target object, the real-time position movement amount corresponding to the turning distance, and the real-time position movement amount corresponding to the straight distance, a corresponding distance trajectory of the target object in the horizontal direction is generated.

[0019] Optionally, the determining the route type corresponding to the target object based on the route type determination strategy corresponding to the real-time state change of the data acquisition device of the target object and the real-time horizontal heading change amount includes:

[0020] When the real-time state remains stable, determining the distance type of the target object based on the magnitude relationship between the sum of the real-time horizontal heading changes of the target object within a preset time period and a first heading threshold;

[0021] When the real-time state changes, the sum of the real-time horizontal heading changes of the target object in the time period when the real-time state changes is corrected based on the heading change compensation amount to obtain a corrected heading change amount, and based on the magnitude relationship between the corrected heading change amount and the first heading threshold, the type of the distance of the target object is determined; or

[0022] When the real-time state changes, the difference between the sum of the real-time heading change amounts of the target object within the time period when the real-time state changes and the heading change compensation amount is obtained, and the distance type of the target object is determined based on the relationship between the difference and the second heading threshold.

[0023] Optionally, the method further comprises:

[0024] Acquire the real-time gravity acceleration of the target object;

[0025] Based on the real-time gravitational acceleration, decomposing the real-time angular velocity collected by the data collection device;

[0026] The horizontal component obtained by decomposing the real-time angular velocity is integrated to obtain the real-time horizontal heading change.

[0027] Optionally, the route trajectory includes a first sub-trajectory with a changed vertical height and a second sub-trajectory corresponding to a turning route, and obtaining the respective guidance points of the plurality of route trajectories includes:

[0028] The starting point and the end point of the first sub-trajectory are determined as the guiding points of the path trajectory corresponding to the target object, and the starting point and the end point of the second sub-trajectory are determined as the guiding points of the path trajectory corresponding to the target object.

[0029] Optionally, the method further comprises:

[0030] Determine the first sub-trajectory based on the real-time floor height of the target object; or

[0031] The first sub-trajectory is determined based on the real-time motion state of the target object.

[0032] Optionally, the method further comprises:

[0033] Obtain a subpath consisting of two adjacent guiding points;

[0034] Clustering is performed on each sub-path to obtain each sub-path in the same position segment;

[0035] The starting points of the sub-paths in the same position segment are determined to be the guiding points in the same position, and the ending points of the sub-paths in the same position segment are determined to be the guiding points in the same position.

[0036] Optionally, clustering the sub-paths to obtain the sub-paths in the same position segment includes:

[0037] Based on the real-time heading change amount corresponding to each sub-path at a unit time node, clustering the sub-paths to obtain sub-paths in the same position segment; and / or

[0038] Based on the real-time environmental signals corresponding to the sub-paths at the unit time nodes, clustering processing is performed on the sub-paths to obtain the sub-paths in the same position segment.

[0039] Optionally, the guidance point information includes the distance between the current guidance point and the next adjacent guidance point in the passing sequence, and the heading change between the current guidance point and the next adjacent guidance point.

[0040] The second part of the embodiment of the present disclosure provides a path guidance device, the device comprising:

[0041] A first acquisition module is configured to acquire multiple path trajectories from a target entrance to an indoor target end point;

[0042] The second acquisition module is configured to acquire the respective guidance points of the plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order;

[0043] A clustering module is configured to cluster the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain target guidance points at each position;

[0044] The path guidance information generating module is configured to generate path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target destination based on the guidance point information of the target guidance points at each position.

[0045] Optionally, the first acquisition module includes:

[0046] A first acquisition submodule is configured to acquire the initial heading of each target object at the target entrance, and acquire the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance;

[0047] The route trajectory construction submodule is configured to construct the route trajectory corresponding to each target object based on the initial heading, the real-time heading change and the real-time position movement of each target object.

[0048] Optionally, the first acquisition submodule includes:

[0049] A GPS trajectory acquisition unit is configured to acquire a GPS trajectory of the target object when it moves from a preset range from the indoor and outdoor boundary to the indoor and outdoor boundary;

[0050] The initial heading determination unit is configured to determine the movement direction corresponding to the GPS track of the target object as the initial heading of the target object at the target entrance.

[0051] Optionally, the heading change includes a horizontal heading change, and the route trajectory construction submodule includes:

[0052] a route type determination unit configured to determine the route type corresponding to the target object based on a route type determination strategy corresponding to a real-time state change of a data acquisition device of the target object and the real-time horizontal heading change, wherein the route type includes a turning route and a straight route;

[0053] The route trajectory construction unit is configured to generate a route trajectory of the target object in the horizontal direction based on the initial heading of the target object, the real-time position movement corresponding to the turning route, and the real-time position movement corresponding to the straight route.

[0054] Optionally, the route type determination unit includes:

[0055] A first determining unit is configured to determine the distance type of the target object based on a magnitude relationship between a sum of the real-time horizontal heading changes of the target object within a preset time period and a first heading threshold when the real-time state remains stable;

[0056] a second determining unit configured to correct, when the real-time state changes, a sum of the real-time horizontal heading changes of the target object within the time period in which the real-time state changes based on a heading change compensation amount to obtain a corrected heading change amount, and determine a distance type of the target object based on a magnitude relationship between the corrected heading change amount and the first heading threshold;

[0057] The third determination unit is configured to obtain, when the real-time state changes, the difference between the sum of the real-time heading changes of the target object within the time period when the real-time state changes and the heading change compensation, and determine the distance type of the target object based on the relationship between the difference and the second heading threshold.

[0058] Optionally, the device further comprises:

[0059] The module for determining the horizontal heading change is configured to obtain the real-time gravity acceleration of the target object; decompose the real-time angular velocity collected by the data acquisition device based on the real-time gravity acceleration; integrate the horizontal component obtained by decomposing the real-time angular velocity to obtain the real-time horizontal heading change.

[0060] Optionally, the route trajectory includes a first sub-trajectory with a changed vertical height and a second sub-trajectory corresponding to a turning route, and the second acquisition module includes:

[0061] The guidance point determination submodule is configured to determine the starting point and the end point of the first sub-trajectory as the guidance points of the path trajectory corresponding to the target object, and to determine the starting point and the end point of the second sub-trajectory as the guidance points of the path trajectory corresponding to the target object.

[0062] Optionally, the device further comprises:

[0063] The first sub-trajectory determining module is configured to determine the first sub-trajectory based on the real-time floor height of the target object; or determine the first sub-trajectory based on the real-time motion state of the target object.

[0064] Optionally, the device further comprises:

[0065] A sub-path construction module is configured to obtain a sub-path consisting of two sequentially adjacent guiding points;

[0066] The module for determining sub-paths of the same position segment is configured to perform clustering processing on the sub-paths to obtain the sub-paths of the same position segment;

[0067] The guidance point determination module is configured to determine the starting points of each sub-path in the same position segment as the guidance point in the same position, and to determine the end points of each sub-path in the same position segment as the guidance point in the same position.

[0068] Optionally, each sub-path determination module of the same location segment includes:

[0069] The sub-path determination submodule of the same position segment is configured to perform clustering processing on each sub-path based on the real-time heading change amount corresponding to each sub-path at a unit time node, so as to obtain each sub-path of the same position segment; and / or perform clustering processing on each sub-path based on the real-time environmental signal corresponding to each sub-path at a unit time node, so as to obtain each sub-path of the same position segment.

[0070] Optionally, the guidance point information includes the distance between the current guidance point and the next adjacent guidance point in the passing sequence, and the heading change between the current guidance point and the next adjacent guidance point.

[0071] The third part of the embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the methods described in the first part are implemented.

[0072] The fourth part of the embodiment of the present disclosure provides an electronic device, including:

[0073] a memory having a computer program stored thereon;

[0074] A processor, configured to execute the computer program in the memory to implement the steps of any one of the methods described in the first part.

[0075] By adopting the above technical solution, at least the following beneficial technical effects can be achieved:

[0076] By obtaining multiple route trajectories from the target entrance to the indoor target destination, and then obtaining the guidance points of each of the multiple route trajectories, the guidance points in the same route trajectory have a sequential passing order, and then clustering the guidance points corresponding to the same position in the guidance points of the multiple paths to obtain the target guidance points of each position, and finally, based on the guidance point information of the target guidance points at each position, the path guidance information starting from the target entrance and passing through each target guidance point to the target destination can be generated. By using multiple historical route trajectories to mine target guidance points and establishing guidance information from the target entrance through each target guidance point to the target destination, the user's path-finding process is guided, so that the user can accurately find the target destination according to the path guidance information, which improves the accuracy of path-finding, reduces the difficulty of user path-finding, and thus improves the efficiency of users reaching the target destination and reduces the path-finding time.

[0077] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0079] Figure 1 The figure is a flow chart of a path guidance method according to an exemplary embodiment of the present disclosure.

[0080] Figure 2 The figure is a flow chart of another path guidance method according to an exemplary embodiment of the present disclosure.

[0081] Figure 3 The figure is a block diagram of a path guidance device according to an exemplary embodiment of the present disclosure.

[0082] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0083] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0084] In the related technology, when a user needs to reach a target indoor store, the real-time location of the user at each moment can be calculated based on the store-seeking user's GPS positioning, and the current location of the user can be displayed. Then, through the base map information of the shopping mall area where the user is located, the basic structure of the shopping mall can be displayed to the user, thereby helping the user to find the way.

[0085] However, since GPS positioning is a general-purpose outdoor positioning technology, using it to locate the location of indoor store-seeking users will result in large errors or drift. Relying on GPS to locate store-seeking users makes it difficult to accurately determine the location of store-seeking users indoors, which greatly interferes with the path-finding of store-seeking users and increases the difficulty of user path-finding. In addition, some merchants currently lack base map information, and thus cannot correctly display the path from the starting point to the target store for users, further increasing the difficulty of user path-finding, resulting in low efficiency and long time to reach the store.

[0086] In view of this, the embodiments of the present disclosure provide a path guidance method, device, storage medium and electronic device to solve the above problems.

[0087] See also Figure 1 , Figure 1 is a flow chart of a path guidance method according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the path guidance method includes the following steps:

[0088] S110, obtaining multiple path trajectories from the target entrance to the indoor target end point.

[0089] The path guidance method in the embodiment of the present disclosure can be used to provide path guidance for an indoor path finding process. It can be understood that when performing path finding in an indoor environment, it can include a process from an indoor entrance to an indoor target destination.

[0090] There can be one or more indoor entrances. For example, a large shopping mall may have four entrances, namely, east, south, west, and north, as well as a parking lot entrance. For an indoor environment, when there is only one indoor entrance, the indoor entrance is the target entrance. When there are multiple indoor entrances, the target entrance can be understood as the indoor entrance selected by the wayfinding user to enter the indoor environment.

[0091] In the embodiment of the present disclosure, the multiple route trajectories obtained are real movement trajectories of one or more historical path-finding users from the target entrance to the indoor target destination.

[0092] In the disclosed embodiment, the wayfinding user may be a delivery rider who picks up goods from the target destination, or a consumer who arrives at the target destination, etc. In addition, the target destination may be a service point, an indoor ride point, etc. in addition to a store.

[0093] In some scenarios, the route trajectory from the target entrance to the indoor target destination can be obtained based on the data generated by the delivery rider in the process of reaching the target destination, or the route trajectory from the target entrance to the indoor target destination can be obtained based on the data generated by the consumers in the store in the process of reaching the target destination.

[0094] S120, obtaining respective guidance points of a plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order.

[0095] In the disclosed embodiment, each acquired route trajectory may be analyzed and mined separately to determine the guidance points of each route trajectory, wherein the guidance points may be understood as important points in the route trajectory, for example, turning points, up-and-down stairs points, up-and-down escalator points, etc.

[0096] It can be understood that the route trajectory is the trajectory route from the target entrance to the target end point. Therefore, the various guidance points analyzed and mined from the same route trajectory may have a sequence of paths.

[0097] S130, clustering the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain target guidance points at the respective positions.

[0098] It is understandable that the multiple journey trajectories from the target entrance to the target end point are basically similar in the actual environment. There may be some differences in pace due to individual differences between historical path-finding users. At this time, in order to reduce the individual differences between historical path-finding users, multiple guidance points corresponding to the same location can be clustered, and then the target guidance points at each location can be mined.

[0099] Exemplarily, assume that 100 route trajectories are obtained, and among these 100 route trajectories, there are 7 guidance points from the target entrance (west gate of the mall) to the target end point (store A), for example, the west gate of the mall, the turning point, the elevator entrance, the elevator exit, the escalator entrance, the escalator exit and store A. Then, when clustering the guidance points corresponding to the same position in each guidance point of multiple paths, the west gate of the mall, the turning point, the elevator entrance, the elevator exit, the escalator entrance, the escalator exit and store A of each route trajectory are clustered separately, that is, the 100 turning points are clustered to obtain the target turning points, the 100 elevator entrances are clustered to obtain the target elevator entrance, the 100 elevator entrances are clustered to obtain the target elevator entrance, and so on.

[0100] S140, based on the guidance point information of the target guidance points at each position, generating path guidance information starting from the target entrance and passing through each target guidance point to reach the target end point.

[0101] After obtaining the target guidance points at each location, path guidance information starting from the target entrance and passing through each target guidance point to reach the target destination can be generated based on the guidance point information of the target guidance points at each location. The generated path guidance information can be used to provide path guidance to users to reduce the difficulty of users finding their way.

[0102] In some implementations, the guidance point information may include the distance between the current guidance point and the next adjacent guidance point in the passing sequence, and the heading change between the current guidance point and the next adjacent guidance point.

[0103] Continuing with the above example, let's take the example of reaching the target destination from the west gate of the mall, which includes 7 target guidance points. The path guidance information obtained at this time can be, for example: the first guidance point is the west gate of the mall, go straight for 30 meters from the west gate of the mall (equivalent to a heading change of 0 degrees) to reach the turning point, turn left 90 degrees after reaching the turning point (equivalent to a heading change of 90 degrees to the left) and go straight for 10 meters to reach the elevator entrance, take the elevator at the elevator entrance to the 3rd floor (equivalent to the distance between the elevator entrance and the elevator exit) to reach the elevator exit, turn around at the elevator entrance (equivalent to a heading change of 180 degrees) and go straight for 10 meters from the elevator exit to the escalator entrance, take the escalator at the escalator entrance and go straight for 10 meters to the escalator exit, go straight for 5 meters from the escalator exit to reach store A.

[0104] The above method is adopted to obtain multiple route trajectories from the target entrance to the indoor target destination, and then obtain the guidance points of each of the multiple route trajectories. The guidance points in the same route trajectory have a sequential passing order, and then the guidance points corresponding to the same position in the guidance points of the multiple paths are clustered to obtain the target guidance points of each position. Finally, based on the guidance point information of the target guidance points at each position, the path guidance information starting from the target entrance and passing through each target guidance point to the target destination can be generated. By using multiple historical route trajectories to mine target guidance points and establishing guidance information from the target entrance through each target guidance point to the target destination, the user's pathfinding process is guided, so that the user can accurately find the target destination according to the path guidance information, which solves the problem of inaccurate pathfinding faced by indoor pathfinding based on GPS real-time positioning technology in the related technology, thereby improving the pathfinding accuracy, reducing the difficulty of user pathfinding, improving the efficiency of users reaching the target destination, and reducing the pathfinding time.

[0105] See also Figure 2 , Figure 2 is a flow chart of another path guidance method according to an exemplary embodiment of the present disclosure, such as Figure 2 As shown, the path guidance method includes the following steps:

[0106] S210, obtaining the initial heading of each target object at the target entrance, and obtaining the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance.

[0107] In the disclosed embodiment, the initial heading at the target entrance and the real-time heading change and real-time position movement of each target object during each journey from the target entrance to the target destination can be obtained, and a corresponding route track of the target object can be generated based on the initial heading, real-time heading change and real-time position movement of the target object. In other words, considering that the route tracks of the same user from the target entrance to the target destination at different times are not exactly the same, the multiple route tracks can include multiple route tracks of the same user.

[0108] In some embodiments, obtaining the initial heading of each target object at the target entrance may include the steps of: obtaining the GPS trajectory of the target object when it moves from a preset range from the indoor and outdoor boundaries to the indoor and outdoor boundaries; and determining the movement direction corresponding to the GPS trajectory of the target object as the initial heading of the target object at the target entrance.

[0109] Considering that the target object can usually be considered to move in a straight line for a period of time when approaching the indoor space, in the embodiment of the present disclosure, the GPS trajectory of the target object when it moves from the preset range of the indoor and outdoor boundaries to the indoor and outdoor boundaries can be obtained, so as to infer the initial heading of the target object at the target entrance based on the GPS trajectory within the preset range. For example, the preset range can be set to 30 cm, 50 cm, etc.

[0110] Exemplarily, the GPS trajectory of the target object is obtained starting from a preset range from the indoor and outdoor boundaries, and when it moves to the indoor and outdoor boundaries, it moves due east to the target entrance. It can be inferred that the initial heading of the target object at the target entrance is due east.

[0111] In addition, considering that the user is usually walking when approaching indoor and outdoor entrances, in order to avoid incorrect judgment of the indoor and outdoor boundaries, thereby incorrectly determining the initial heading of the target object at the target entrance, in some embodiments, the information of whether the target object is walking can be combined. That is to say, when it is judged that the target object is walking and the target object is within the preset range from the indoor and outdoor boundaries, the GPS trajectory of the target object is obtained when it moves from the preset range from the indoor and outdoor boundaries to the indoor and outdoor boundaries, thereby avoiding incorrect judgment that the target object is within the preset range of the indoor and outdoor boundaries, and then incorrectly determining the initial heading of the target object at the target entrance.

[0112] In addition, in some embodiments, during the initialization process of constructing the route trajectory, an electronic AOI fence can be set to obtain the behavior state of the target object when it enters the electronic AOI fence, that is, to determine whether the target object starts walking from the time it enters the electronic AOI fence.

[0113] It should be noted that although the GPS trajectory is used here, the GPS trajectory here is for outdoor environments and the GPS trajectory can be considered to be relatively accurate.

[0114] S220: constructing a path trajectory corresponding to each target object based on the initial heading, real-time heading change, and real-time position movement of each target object.

[0115] In the disclosed embodiment, after obtaining the initial heading, real-time heading change and real-time position movement of each target object, the pedestrian dead reckoning (PDR) technology can be used to construct the corresponding route trajectory of each target object based on the initial heading, real-time heading change and real-time position movement of each target object.

[0116] In some embodiments, the heading change includes a horizontal heading change. In this case, based on the initial heading, real-time heading change, and real-time position movement of each target object, a route trajectory corresponding to each target object is constructed, which may include the following steps: determining the route type corresponding to the target object based on a route type determination strategy and a real-time horizontal heading change corresponding to the real-time state change of a data acquisition device of the target object, wherein the route types include turning routes and straight routes; generating a route trajectory corresponding to the target object in the horizontal direction based on the initial heading of the target object, the real-time position movement corresponding to the turning route, and the real-time position movement corresponding to the straight route.

[0117] In the embodiment of the present disclosure, after the corresponding path trajectory of the target object in the horizontal direction is generated, the path trajectory of the target object in the vertical height change can be combined to form a complete path trajectory from the target starting point to the target end point.

[0118] In the embodiments of the present disclosure, the data acquisition device of the target object can be understood as a device carried by the target object that can be used to collect data, such as a mobile phone, a tablet, a smart watch, etc. These devices can be integrated with accelerometers, gyroscopes, magnetometers, light, distance sensors, etc. At the same time, the data acquisition device can also receive satellite signals and base station signals, etc.

[0119] In the disclosed embodiments, the real-time status of the data acquisition device carried by the target object can be varied. For example, the target object can hold the data acquisition device horizontally, hang it around the neck, put it in a trouser pocket, put it in a chest bag, hold it in the hand and swing it with the arm, etc. When the data acquisition device is in different real-time states, the way of determining whether the target object is in a turning route or a straight route is different.

[0120] In some embodiments, determining the type of route corresponding to the target object based on a route type determination strategy corresponding to the real-time state change of the data acquisition device of the target object and the real-time horizontal heading change may include the following steps: when the real-time state remains stable, determining the type of route of the target object based on the relationship between the sum of the real-time horizontal heading changes of the target object within a preset time period and a first heading threshold; when the real-time state changes, correcting the sum of the real-time horizontal heading changes of the target object within the time period when the real-time state changes based on the heading change compensation to obtain a corrected heading change, and determining the type of route of the target object based on the relationship between the corrected heading change and the first heading threshold; or when the real-time state changes, obtaining the difference between the sum of the real-time heading changes of the target object within the time period when the real-time state changes and the heading change compensation, and determining the type of route of the target object based on the relationship between the difference and the second heading threshold.

[0121] In the disclosed embodiment, if the real-time state of the data acquisition device remains stable, the data acquisition device will not affect the actual horizontal heading of the target object. In this case, the type of the target object's journey can be determined directly based on the relationship between the sum of the real-time horizontal heading changes of the target object within a preset time period and the first heading threshold.

[0122] Among them, the first heading threshold can be a pre-set standard for determining whether a turn occurs. If the sum of the real-time horizontal heading changes of the target object within the preset time period is greater than or equal to the first heading threshold, it can be determined that the distance type of the target object within the preset time period is a turning distance. If the sum of the real-time horizontal heading changes of the target object within the preset time period is less than the first heading threshold, it can be determined that the distance type of the target object within the preset time period is a straight distance.

[0123] If the real-time state of the data acquisition device changes, for example, from a flat end to a trouser pocket, the data acquisition device itself may have a heading change at this time. Therefore, the real-time horizontal heading change determined by the data acquisition device is not necessarily the real horizontal heading of the target object. In this case, a heading change compensation amount can be introduced to reduce the horizontal heading change caused by the change in the real-time state of the data acquisition device. Therefore, when the real-time state changes, the sum of the real-time horizontal heading changes of the target object in the time period when the real-time state changes can be corrected based on the heading change compensation amount to obtain a corrected heading change amount. It can be understood that the corrected heading change amount can more truly reflect the real horizontal heading change amount of the target object. Therefore, the type of the distance of the target object can be further determined based on the size relationship between the corrected heading change amount and the first heading threshold.

[0124] In combination with the above content, it can be known that when the real-time state of the data acquisition device changes, a heading change compensation amount can be introduced. It can be understood that the heading change compensation amount is only a correction. If the sum of the real-time heading changes of the target object in the time period when the real-time state changes is significantly greater than the heading change compensation amount, it can be determined that the target user has turned. Therefore, when the real-time state of the data acquisition device changes, the difference between the sum of the real-time heading changes of the target object in the time period when the real-time state changes and the heading change compensation amount can be obtained first, and then the distance type of the target object is determined based on the size relationship between the difference and the second heading threshold. Among them, the second heading threshold can be another standard pre-set to determine whether a turn occurs.

[0125] In some embodiments, the corresponding heading change compensation amount when each real-time state of the data acquisition device changes can be determined based on experimental statistics. For example, when determining the heading change compensation amount when the device changes from a flat end to a trouser pocket, the heading change amount when the device changes from a flat end to a trouser pocket can be obtained by adding the average value of the heading change amounts when the device remains in a stationary state. The corresponding heading change compensation amount when any other two real-time states change can be determined using the same method, which will not be repeated here.

[0126] In addition, in some implementations, in order to obtain the real-time horizontal heading change of the target object, the path guidance method of the embodiment of the present disclosure may further include the following steps:

[0127] The real-time gravity acceleration of the target object is obtained; based on the real-time gravity acceleration, the real-time angular velocity collected by the data acquisition device is decomposed; the horizontal component obtained by decomposing the real-time angular velocity is integrated to obtain the real-time horizontal heading change.

[0128] In some implementations, the data collected in real time by the gyroscope in the data acquisition device may be directly determined as the real-time angular velocity, and the data collected in real time by the accelerometer in the data acquisition device may be determined as the real-time gravity acceleration of the target object.

[0129] In addition, in order to improve the accuracy of the calculation of the horizontal heading change, in other embodiments, the sensor data collected by the data acquisition device can be encapsulated into frames of a predetermined length. For example, every 20 acceleration data are encapsulated into 1 frame of acceleration data, and every 20 angular velocity data are encapsulated into 1 frame of angular velocity data, so that the sum of the heading changes of a fixed number of frames is selected to determine whether a turn occurs, wherein the collection time length corresponding to the fixed number of frames here can be corresponding to the collection time length of the previous preset time period, that is, the two can be converted through the data collection time interval of each data included in each frame.

[0130] Specifically, the variance of each acceleration included in a frame can be calculated to estimate the gravitational acceleration. Optionally, if the variance of each acceleration included in a frame is large, it means that the real-time state of the data acquisition device has changed. At this time, the average of each acceleration included in multiple frames can be taken as the approximate value of the gravitational acceleration. If the variance of the acceleration in a frame is small, the average of each acceleration included in the frame can be directly taken as the approximate value of the gravitational acceleration.

[0131] In addition, in some embodiments, in order to further improve the accuracy of the route type judgment, after obtaining the real-time horizontal heading change, the real-time horizontal heading change can be converted to the frequency domain using a fast Fourier transform to eliminate the periodic signal formed by the swinging of the target object when the data acquisition device is placed in the trouser pocket or swinging the arm, etc., and only the non-periodic signal generated by walking is retained, and then the non-periodic real-time horizontal heading change is used in the subsequent process of determining the route type corresponding to the target object.

[0132] In addition, in some implementation manners, considering that multiple guidance points can be determined for a long turn (for example, for a long turn, the starting point, the middle point, and the end point of the long turn can be used as the turning guidance points respectively), and relatively fewer guidance points are determined for a short turn (for example, for a short turn, the starting point and the end point are close to overlapping, and at this time, a turning point can be determined as the guidance point), therefore, in order to further improve the accuracy of the subsequently determined path guidance information, the turns can be further subdivided into different types of turns, for example, long turns and short turns. For long turns and short turns, different preset time periods or different numbers of frames can be used for judgment. Exemplarily, the preset time period can be 4 seconds. If the determined turning distance is completed within 4 seconds, the turn can be determined to be a short turn. If the determined turning distance is completed within a time period greater than 4 seconds, the turn can be determined to be a long turn.

[0133] S230, obtaining respective guidance points of a plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order.

[0134] In combination with the foregoing content, it can be seen that the route trajectory includes a trajectory in which the vertical height changes, namely, the first sub-trajectory, and a trajectory corresponding to the turning route, namely, the second sub-trajectory. In this case, obtaining the guidance points of multiple route trajectories can include the following steps: determining the starting point and end point of the first sub-trajectory as the guidance points of the route trajectory corresponding to the target object, and determining the starting point and end point of the second sub-trajectory as the guidance points of the route trajectory corresponding to the target object.

[0135] Typically, the vertical height changes usually occur in locations such as elevators or escalators, which can guide users. Similarly, turning points can also guide users. Therefore, in the embodiment of the present disclosure, the starting point and the end point of the first sub-trajectory are determined as the guidance points of the path trajectory corresponding to the target object, and the starting point and the end point of the second sub-trajectory are determined as the guidance points of the path trajectory corresponding to the target object.

[0136] In addition, based on the content, it can be known that the turning distance can include long turns and short turns. Therefore, in some embodiments, for long turns, in addition to determining the starting point and the end point as the guidance points of the distance trajectory corresponding to the target object, the middle point of the turning distance can also be determined as the guidance point.

[0137] In some embodiments, the method of the embodiment of the present disclosure may further include the step of determining a first sub-trajectory, that is, the method of the embodiment of the present disclosure may further include the following steps: determining the first sub-trajectory based on the real-time floor height of the target object; or determining the first sub-trajectory based on the real-time motion state of the target object.

[0138] In the disclosed embodiment, the first sub-trajectory can be determined by judging whether the vertical height of the target object has changed according to the real-time floor height of the target object. For example, if the real-time floor height of the target object changes from the first floor to the third floor, the distance trajectory from the first floor to the third floor can be determined as the first sub-trajectory.

[0139] Alternatively, the first sub-trajectory may also be determined based on the real-time motion state of the target object.

[0140] Among them, the real-time motion states include staying, riding, going up and down stairs in an elevator, walking on flat ground, walking up and down stairs, etc. At this time, the path trajectory of the target object in the states of going up and down stairs in an elevator or walking up and down stairs can be determined as the first sub-trajectory.

[0141] S240: Clustering the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain target guidance points at the respective positions.

[0142] In some embodiments, in order to cluster the guidance points corresponding to the same position among the guidance points of multiple paths, the method of the embodiment of the present disclosure may also include a process of determining the guidance points at the same position, that is, the path guidance method of the embodiment of the present disclosure may also include the following steps: obtaining a sub-path consisting of two adjacent guidance points in sequence; clustering each sub-path to obtain each sub-path of the same position segment; determining the starting point of each sub-path of the same position segment as the guidance point at the same position, and determining the end point of each sub-path of the same position segment as the guidance point at the same position.

[0143] In the disclosed embodiment, after obtaining the respective guidance points of multiple route trajectories, a sub-path consisting of two guidance points that are sequentially adjacent to each other can be obtained for the same route trajectory. Using the aforementioned example, a sub-path from the west gate of the shopping mall to the turning point, a sub-path from the turning point to the elevator entrance, a sub-path from the elevator entrance to the elevator exit, a sub-path from the elevator exit to the escalator entrance, a sub-path from the escalator entrance to the escalator exit, and a sub-path from the escalator exit to store A can be obtained. In the same way, multiple sub-paths can be obtained for any of the multiple route trajectories.

[0144] Therefore, further considering the multiple journey trajectories from the target entrance to the target end point, corresponding to the routes in the actual environment are basically similar, and each sub-path can be clustered to obtain each sub-path corresponding to the same position segment.

[0145] For example, the subpath from the west gate of the mall to the turning point of each route trajectory can be clustered into one cluster, and the subpath from the turning point to the elevator entrance of each route trajectory can be clustered into one cluster, and the clustering results of other subpaths are similar.

[0146] Furthermore, after obtaining each sub-path of the same position segment, the starting point of each sub-path of the same position segment can be determined as the guiding point of the same position, and the end point of each sub-path of the same position segment can be determined as the guiding point of the same position.

[0147] For example, after clustering the sub-paths from the west gate of the mall to the turning point of each route trajectory into a cluster, the starting points of each sub-path included in the cluster can be determined as the guidance point at the same location, that is, the guidance point corresponding to the west gate of the mall, and the end points of each sub-path included in the cluster can be determined as the guidance point at the same location, that is, the guidance point corresponding to the turning point.

[0148] In some embodiments, clustering each sub-path to obtain each sub-path of the same position segment may include the following steps: clustering each sub-path based on the real-time heading change amount corresponding to each sub-path at a unit time node to obtain each sub-path of the same position segment; and / or clustering each sub-path based on the real-time environmental signal corresponding to each sub-path at a unit time node to obtain each sub-path of the same position segment.

[0149] In the disclosed embodiment, in order to improve the accuracy of clustering the sub-paths, each sub-path can be further divided according to the unit time to obtain data with smaller granularity, that is, the real-time heading change amount of each sub-path corresponding to the unit time node can be obtained. Then, the sub-paths can be clustered according to the real-time heading change amount of each sub-path corresponding to the unit time node to obtain the sub-paths in the same position segment.

[0150] Taking into account various reasons such as individual differences in target objects and differences in data acquisition devices, even sub-paths in the same cluster have strong fluctuations in their heading changes over time. Therefore, in some embodiments, the difference in the average value of the real-time heading change per unit time between different sub-paths can be used as an evaluation criterion for the similarity of two sub-paths to reduce the differences.

[0151] For example, assuming that the sub-path from the west gate of the mall to the turning point of rider A corresponds to 10 unit times, the 10 real-time heading changes of the sub-path from the west gate of the mall to the turning point of rider A can be determined. In the same way, the real-time heading changes of other sub-paths of rider A at the unit time nodes can be determined. Furthermore, the real-time heading changes of each sub-path of rider B, rider C, rider D, etc. at the unit time nodes can also be determined.

[0152] Next, the average value of the real-time heading change of each sub-path at the unit time node can be calculated, and then the difference between the average values ​​of the real-time heading change of each sub-path can be used as the clustering criterion to cluster each sub-path. That is, the smaller the difference between the average values ​​of the real-time heading change, the more likely the two sub-paths are to be clustered into one cluster.

[0153] In addition, considering that the real-time environmental signals corresponding to the sub-paths of the same position segment at each unit time node are similar, similarly, each sub-path can also be clustered according to the real-time environmental signals corresponding to each sub-path at the unit time node to obtain the sub-paths of the same position segment.

[0154] Among them, environmental signals may include WiFi signals, geomagnetic signals, etc.

[0155] In addition, considering the environmental signal fingerprint data collected by different target objects on the same physical path, due to differences in step length, height, speed, etc., the collected signal curves have certain differences in length and amplitude, but the curve fluctuation characteristics are similar. Therefore, in some embodiments, a dynamic time warping (DTW) algorithm can be used to better express the fluctuation characteristics of the environmental signal curve and reduce the impact of different sample lengths.

[0156] In addition, in some embodiments, each sub-path can also be clustered in combination with the real-time heading change amount corresponding to each sub-path at the unit time node and the real-time environmental signal corresponding to each sub-path at the unit time node to obtain each sub-path of the same position segment. In this case, the clustering results obtained by clustering each sub-path based on the real-time environmental signal corresponding to each sub-path at the unit time node can be used to supplement the clustering results obtained by clustering each sub-path based on the real-time heading change amount corresponding to each sub-path at the unit time node, so as to improve the accuracy of obtaining each sub-path of the same position segment.

[0157] S250, based on the guidance point information of the target guidance points at each position, generating path guidance information starting from the target entrance and passing through each target guidance point to reach the target end point.

[0158] The detailed description of step S250 can refer to the specific description of the aforementioned step S140, which will not be repeated here.

[0159] In some implementations, the motion state of the aforementioned target object may be determined in the following manner.

[0160] Optionally, the three-axis accelerometer data and GPS speed data included in the data acquisition device can be obtained, and a peak detection algorithm can be used to determine whether the target object is walking based on the number of peaks and the amplitude of data fluctuations.

[0161] If the target is in a walking state, the walking state and the walking upstairs and downstairs state are subdivided into detection. The azimuth of the target object is calculated by the gravity acceleration and geomagnetic data included in the data acquisition device, and the gyroscope and other data included in the data acquisition device are combined to construct features, and the CNN model is used to determine whether the target object is walking on flat ground or walking upstairs.

[0162] If it is not walking, it means it is in a relatively static state. Manual features are constructed using GPS speed data, GPS positioning accuracy, three-axis accelerometer, light sensing data, and base station data. The XGBoost model is used for training to output three states: staying, riding, or going up and down the elevator.

[0163] In some implementations, the aforementioned indoor and outdoor boundary determination may be performed using sensor data (satellite, base station, light sensor) included in a data acquisition device.

[0164] Optionally, the satellite signals acquired by the sensor of the data acquisition device will be very different indoors and outdoors, which is mainly reflected in the strength, number and positioning accuracy of satellite signals scanned by the data acquisition device. For the light sensor of the data acquisition device, it is usually under the irradiation of natural light outdoors, but under the irradiation of artificial light indoors, and there is a big difference between the two. The base station signal is reflected in the signal strength of the data acquisition device. From outdoors to indoors, the number of base stations scanned and the signal strength will change greatly. The collectible sensor data of the above-mentioned data acquisition device is cleaned and feature processed, and then trained through the XGBoost model to output the indoor / outdoor binary classification results.

[0165] In some implementations, the aforementioned floor height may be determined in the following manner.

[0166] Optionally, the current floor of the target object can be identified in combination with the environmental sensor data of the data acquisition device (air pressure, Wi-Fi, Bluetooth and other environmental signals).

[0167] Specifically, the XGBoost model can be used to heuristically fuse the Wi-Fi-based floor positioning method with the air pressure-based floor positioning method. That is, when the Wi-Fi signal distinguishability is high, that is, when the confidence of the floor result output by the Wi-Fi-based floor positioning method is high, for example, when it is greater than or equal to a preset threshold, the Wi-Fi fingerprint is used for floor positioning. On the contrary, when the confidence of the floor result output by the Wi-Fi-based floor positioning method is low, for example, when it is less than a preset threshold, the air pressure-based floor positioning method is used.

[0168] Among them, the floor positioning method based on air pressure refers to pre-establishing a mapping relationship between air pressure and floor height. Then, when the air pressure at a certain location is collected, the floor height can be directly obtained based on the mapping relationship.

[0169] In addition, considering that there may be positioning errors when using either the Wi-Fi-based floor positioning method or the air pressure-based floor positioning method, in order to eliminate the positioning error, in some embodiments, the floor height obtained by the Wi-Fi-based floor positioning method can be substituted into the hidden Markov method to eliminate the floor height error, and the floor height obtained by the air pressure-based floor positioning method can be substituted into the hidden Markov method to eliminate the floor height error.

[0170] It should be noted that, in the embodiments of the present disclosure, the floor height can be directly expressed as the number of floors, and can also be expressed as the vertical height, for example, the floor height is 5 meters, 6 meters, 10 meters, etc.

[0171] In some implementations, the real-time status of the aforementioned data acquisition device can be determined in the following manner.

[0172] Optionally, features can be constructed by using sensor data such as acceleration, gyroscope, magnetometer, light, distance, etc. collected by the data acquisition device, and classification and recognition training can be performed using the XGBoost model to output several states: horizontal end, hanging around the neck, trouser pocket, chest bag, and swinging arm.

[0173] In some embodiments, the aforementioned real-time position movement amount in the process of reaching the target end point from the target entrance can be determined according to the product of the number of steps taken by the target object in the process and the step length.

[0174] When determining the pace of the target object, different pace detection algorithms may be used according to different states of the data acquisition device.

[0175] Taking into account that the movement amplitude of the data acquisition device is small when the target object holds the data acquisition device horizontally or places the data acquisition device on a chest bag, the walking cycle is relatively stable, and the acceleration collected by the data acquisition device is basically consistent with the acceleration of the target object's own movement. Therefore, a motion state model can be constructed according to the three-axis acceleration modeling when the target object moves, and the entire walking cycle of the target object can be decomposed into multiple state transition processes such as heel lifting, toes off the ground, suspended in the air, heels touching the ground, and soles touching the ground. The walking cycle of the target object can be accurately identified according to the state transition situation, so as to determine the number of steps when the target object holds the data acquisition device horizontally or places the data acquisition device on a chest bag according to the walking cycle.

[0176] However, when the target object starts to swing his arms and puts the data acquisition device in his trouser pocket or hangs it around his neck, the motion state of the data acquisition device is difficult to correspond to the walking cycle of the target object. Therefore, a peak detection algorithm is adopted to identify the peaks and troughs of the gyroscope axis data collected by the data acquisition device according to different states, complete the step detection, identify the walking cycle of the target object, and then determine the number of steps when the target object starts to swing his arms and puts the data acquisition device in his trouser pocket or hangs it around his neck according to the walking cycle.

[0177] Figure 3 is a block diagram of a path guidance device according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the path guidance device 300 includes:

[0178] The first acquisition module 310 is configured to acquire multiple path trajectories from a target entrance to an indoor target destination;

[0179] The second acquisition module 320 is configured to acquire the respective guidance points of the plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order;

[0180] The clustering module 330 is configured to cluster the guidance points corresponding to the same position among the guidance points of the multiple paths to obtain target guidance points at each position;

[0181] The path guidance information generating module 340 is configured to generate path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target destination based on the guidance point information of the target guidance points at each position.

[0182] Optionally, the first acquisition module 310 includes:

[0183] A first acquisition submodule is configured to acquire the initial heading of each target object at the target entrance, and acquire the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance;

[0184] The route trajectory construction submodule is configured to construct the route trajectory corresponding to each target object based on the initial heading, the real-time heading change and the real-time position movement of each target object.

[0185] Optionally, the first acquisition submodule includes:

[0186] A GPS trajectory acquisition unit is configured to acquire a GPS trajectory of the target object when it moves from a preset range from the indoor and outdoor boundary to the indoor and outdoor boundary;

[0187] The initial heading determination unit is configured to determine the movement direction corresponding to the GPS track of the target object as the initial heading of the target object at the target entrance.

[0188] Optionally, the heading change includes a horizontal heading change, and the route trajectory construction submodule includes:

[0189] a route type determination unit configured to determine the route type corresponding to the target object based on a route type determination strategy corresponding to a real-time state change of a data acquisition device of the target object and the real-time horizontal heading change, wherein the route type includes a turning route and a straight route;

[0190] The route trajectory construction unit is configured to generate a route trajectory of the target object in the horizontal direction based on the initial heading of the target object, the real-time position movement corresponding to the turning route, and the real-time position movement corresponding to the straight route.

[0191] Optionally, the route type determination unit includes:

[0192] A first determining unit is configured to determine the distance type of the target object based on a magnitude relationship between a sum of the real-time horizontal heading changes of the target object within a preset time period and a first heading threshold when the real-time state remains stable;

[0193] a second determining unit configured to correct, when the real-time state changes, a sum of the real-time horizontal heading changes of the target object within the time period in which the real-time state changes based on a heading change compensation amount to obtain a corrected heading change amount, and determine a distance type of the target object based on a magnitude relationship between the corrected heading change amount and the first heading threshold;

[0194] The third determination unit is configured to obtain, when the real-time state changes, the difference between the sum of the real-time heading changes of the target object within the time period when the real-time state changes and the heading change compensation, and determine the distance type of the target object based on the relationship between the difference and the second heading threshold.

[0195] Optionally, the apparatus 300 further includes:

[0196] The module for determining the horizontal heading change is configured to obtain the real-time gravity acceleration of the target object; decompose the real-time angular velocity collected by the data acquisition device based on the real-time gravity acceleration; integrate the horizontal component obtained by decomposing the real-time angular velocity to obtain the real-time horizontal heading change.

[0197] Optionally, the route trajectory includes a first sub-trajectory with a changed vertical height and a second sub-trajectory corresponding to a turning route, and the second acquisition module 320 includes:

[0198] The guidance point determination submodule is configured to determine the starting point and the end point of the first sub-trajectory as the guidance points of the path trajectory corresponding to the target object, and to determine the starting point and the end point of the second sub-trajectory as the guidance points of the path trajectory corresponding to the target object.

[0199] Optionally, the apparatus 300 further includes:

[0200] The first sub-trajectory determining module is configured to determine the first sub-trajectory based on the real-time floor height of the target object; or determine the first sub-trajectory based on the real-time motion state of the target object.

[0201] Optionally, the apparatus 300 further includes:

[0202] A sub-path construction module is configured to obtain a sub-path consisting of two sequentially adjacent guiding points;

[0203] The module for determining sub-paths of the same position segment is configured to perform clustering processing on the sub-paths to obtain the sub-paths of the same position segment;

[0204] The guidance point determination module is configured to determine the starting points of each sub-path in the same position segment as the guidance point in the same position, and to determine the end points of each sub-path in the same position segment as the guidance point in the same position.

[0205] Optionally, each sub-path determination module of the same location segment includes:

[0206] The sub-path determination submodule of the same position segment is configured to perform clustering processing on each sub-path based on the real-time heading change amount corresponding to each sub-path at a unit time node, so as to obtain each sub-path of the same position segment; and / or perform clustering processing on each sub-path based on the real-time environmental signal corresponding to each sub-path at a unit time node, so as to obtain each sub-path of the same position segment.

[0207] Optionally, the guidance point information includes the distance between the current guidance point and the next adjacent guidance point in the passing sequence, and the heading change between the current guidance point and the next adjacent guidance point.

[0208] The above method is adopted to obtain multiple route trajectories from the target entrance to the indoor target destination, and then obtain the guidance points of each of the multiple route trajectories. The guidance points in the same route trajectory have a sequential passing order, and then the guidance points corresponding to the same position in the guidance points of the multiple paths are clustered to obtain the target guidance points of each position. Finally, based on the guidance point information of the target guidance points at each position, the path guidance information starting from the target entrance and passing through each target guidance point to the target destination can be generated. By using multiple historical route trajectories to mine target guidance points and establish guidance information from the target entrance through each target guidance point to the target destination, the user's path finding process is guided, so that the user can accurately find the target destination according to the path guidance information, which improves the accuracy of path finding, reduces the difficulty of user path finding, and thus improves the efficiency of users reaching the target destination and reduces the path finding time.

[0209] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0210] Figure 4 4 is a block diagram of an electronic device 400 according to an exemplary embodiment. For example, the electronic device 400 may be provided as a server. Figure 4 The electronic device 400 includes a processor 422, which may be one or more, and a memory 432 for storing a computer program executable by the processor 422. The computer program stored in the memory 432 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 422 may be configured to execute the computer program to perform the above-mentioned path guidance method.

[0211] In addition, the electronic device 400 may further include a power supply component 426 and a communication component 450. The power supply component 426 may be configured to perform power management of the electronic device 400, and the communication component 450 may be configured to implement communication of the electronic device 400, for example, wired or wireless communication. In addition, the electronic device 400 may further include an input / output (I / O) interface 458. The electronic device 400 may operate based on an operating system stored in the memory 432, such as Windows Server 2008. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0212] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned path guidance method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 432 including program instructions, and the above-mentioned program instructions can be executed by the processor 422 of the electronic device 400 to complete the above-mentioned path guidance method.

[0213] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned path guidance method when executed by the programmable device.

[0214] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0215] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0216] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A path guidance method, characterized in that: The method comprises: Acquire multiple route trajectories from a target entrance to an indoor target destination, wherein the target destination is a store where a delivery rider picks up goods, and the route trajectories are based on data generated during the delivery rider's arrival at the target destination; Acquire the respective guidance points of the plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order, and the guidance points include important points in the route trajectory, and the important points include turning points, stair and escalator points; Clustering the guidance points corresponding to the same position among the guidance points of the multiple route trajectories to obtain target guidance points at each position; Based on the guidance point information of the target guidance points at each position, generating path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target end point; The method further comprises: Obtain a subpath consisting of two adjacent guiding points; Clustering is performed on each sub-path to obtain each sub-path in the same position segment; Determine the starting points of each sub-path of the same position segment as the guiding point of the same position, and determine the end points of each sub-path of the same position segment as the guiding point of the same position; The step of obtaining multiple path trajectories from the target entrance to the indoor target end point includes: Acquire the initial heading of each target object at the target entrance, and acquire the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance; The path trajectory corresponding to each target object is constructed based on the initial heading, the real-time heading change, and the real-time position movement of each target object.

2. The method according to claim 1, characterized in that The obtaining of the initial heading of each target object corresponding to the target entrance includes: Obtaining the GPS trajectory of the target object when it moves from a preset range from the indoor and outdoor boundaries to the indoor and outdoor boundaries; The movement direction corresponding to the GPS track of the target object is determined as the initial heading of the target object at the target entrance.

3. The method according to claim 1, characterized in that The real-time heading change includes a real-time horizontal heading change, and constructing the path trajectory corresponding to each target object based on the initial heading, the real-time heading change, and the real-time position movement of each target object includes: Based on the route type determination strategy corresponding to the real-time state change of the data acquisition device of the target object and the real-time horizontal heading change, determine the route type corresponding to the target object, the route type including a turning route and a straight route; Based on the initial heading of the target object, the real-time position movement amount corresponding to the turning distance, and the real-time position movement amount corresponding to the straight distance, a corresponding distance trajectory of the target object in the horizontal direction is generated.

4. The method according to claim 3, characterized in that The determining of the route type corresponding to the target object based on the route type determination strategy corresponding to the real-time state change of the data acquisition device of the target object and the real-time horizontal heading change amount comprises: When the real-time state remains stable, determining the distance type of the target object based on the magnitude relationship between the sum of the real-time horizontal heading changes of the target object within a preset time period and a first heading threshold; When the real-time state changes, the sum of the real-time horizontal heading changes of the target object in the time period when the real-time state changes is corrected based on the heading change compensation amount to obtain a corrected heading change amount, and based on the magnitude relationship between the corrected heading change amount and the first heading threshold, the distance type of the target object is determined; Alternatively, when the real-time state changes, the difference between the sum of the real-time heading changes of the target object during the time period when the real-time state changes and the heading change compensation is obtained, and based on the relationship between the difference and the second heading threshold, the distance type of the target object is determined.

5. The method according to claim 3, characterized in that: The method further comprises: Acquire the real-time gravity acceleration of the target object; Based on the real-time gravitational acceleration, decomposing the real-time angular velocity collected by the data collection device; The horizontal component obtained by decomposing the real-time angular velocity is integrated to obtain the real-time horizontal heading change.

6. The method according to claim 1, characterized in that The route trajectory includes a first sub-trajectory with a changed vertical height and a second sub-trajectory corresponding to a turning route, and obtaining the respective guidance points of the plurality of route trajectories includes: The starting point and the end point of the first sub-trajectory are determined as the guiding points of the path trajectory corresponding to the target object, and the starting point and the end point of the second sub-trajectory are determined as the guiding points of the path trajectory corresponding to the target object.

7. The method according to claim 6, characterized in that The method further comprises: The first sub-trajectory is determined based on the real-time floor height of the target object; or the first sub-trajectory is determined based on the real-time motion state of the target object.

8. The method according to claim 1, characterized in that The clustering process is performed on each sub-path to obtain each sub-path in the same position segment, including: Based on the real-time heading change corresponding to each sub-path at a unit time node, each sub-path is clustered to obtain each sub-path in the same position segment; and / or based on the real-time environmental signal corresponding to each sub-path at a unit time node, each sub-path is clustered to obtain each sub-path in the same position segment.

9. The method according to any one of claims 1 to 8, characterized in that: The guidance point information includes the distance between the current guidance point and the next adjacent guidance point in the passing sequence, and the heading change amount between the current guidance point and the next adjacent guidance point.

10. A path guidance device, characterized in that: The device comprises: A first acquisition module is configured to acquire a plurality of route trajectories from a target entrance to an indoor target destination, wherein the target destination is a store where a delivery rider picks up goods, and the route trajectories are based on data generated during the delivery rider's arrival at the target destination; The second acquisition module is configured to acquire the respective guidance points of the plurality of route trajectories, wherein the guidance points in the same route trajectory have a sequential passing order, and the guidance points include important points in the route trajectory, and the important points include turning points, stair and escalator points; A clustering module is configured to cluster the guidance points corresponding to the same position among the guidance points of the plurality of route trajectories to obtain a target guidance point at each position; A path guidance information generating module is configured to generate path guidance information starting from the target entrance and passing through each of the target guidance points to reach the target destination based on the guidance point information of the target guidance points at each position; The device also includes: A sub-path construction module is configured to obtain a sub-path consisting of two sequentially adjacent guiding points; The module for determining sub-paths of the same position segment is configured to perform clustering processing on the sub-paths to obtain the sub-paths of the same position segment; A guidance point determination module is configured to determine the starting points of each sub-path of the same position segment as the guidance point of the same position, and to determine the end points of each sub-path of the same position segment as the guidance point of the same position; The step of obtaining multiple path trajectories from the target entrance to the indoor target end point includes: Acquire the initial heading of each target object at the target entrance, and acquire the real-time heading change and real-time position movement of each target object in the process of reaching the target end point from the target entrance; The path trajectory corresponding to each target object is constructed based on the initial heading, the real-time heading change, and the real-time position movement of each target object.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.

12. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 9.

Images