Positioning method, device, electronic device and computer storage medium

Abstract

The embodiment of the present application provides a positioning method, device, electronic device and computer storage medium, the positioning method includes: based on the network positioning position of the target object at the current moment and the historical positioning position at the previous moment, selecting at least two candidate positioning sections located in front of the historical positioning position from the target navigation route; based on the historical network position of the target object at the previous N moments and the historical positioning position, determining the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory containing the network positioning position; according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section, determining the target positioning section matching the network positioning position; using the mapping position of the network positioning position on the target positioning section as the positioning position at the current moment. This method ensures positioning accuracy.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of positioning technology, and in particular to a positioning method, device, electronic device and computer storage medium. Background Art

[0002] In location-based application scenarios, such as navigation and map rendering, it is necessary to determine the location of the target object (such as smart devices, vehicle-mounted devices, etc.) through the positioning signal received by the target object (such as smart devices, vehicle-mounted devices, etc.), and then support the corresponding application requirements based on the positioning position. The existing positioning methods mainly include satellite positioning based on satellite signals and network positioning based on network access signals, where the network access signal includes the signal of the network access device such as wifi and base station that the target object accesses or scans.

[0003] Normally, satellite positioning is preferred. However, in scenarios where satellite positioning cannot be used (such as when satellite signals are blocked), the device's location can be determined through network positioning. However, network positioning has the problem that the location cannot be output continuously and the accuracy is not enough. For example, only one location may be obtained every ten meters or even several kilometers. This location may deviate from the actual location, and most application scenarios based on location require continuous and high-precision positioning. Therefore, how to ensure the accuracy of the location when using network positioning for positioning is a problem that technicians in this field need to solve. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a positioning solution to at least partially solve the above-mentioned problem.

[0005] According to a first aspect of an embodiment of the present application, a positioning method is provided, comprising: based on a network positioning position of a target object at a current moment and a historical positioning position at a previous moment, selecting at least two candidate positioning sections located in front of the historical positioning position from a target navigation route; based on the historical network positions of the target object at previous N moments and the historical positioning position, determining an estimated moving distance of the network positioning position relative to the historical positioning position and a confidence level of a network point trajectory containing the network positioning position; determining a target positioning section matching the network positioning position according to the estimated moving distance, the confidence level of the network point trajectory, the network positioning position, and position information of each of the candidate positioning sections; and using a mapping position of the network positioning position on the target positioning section as the positioning position at the current moment.

[0006] According to a second aspect of an embodiment of the present application, a positioning device is provided, comprising: a selection module, for selecting at least two candidate positioning sections located in front of the historical positioning position from the target navigation route based on the network positioning position of the target object at the current moment and the historical positioning position at the previous moment; a first determination module, for determining the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory containing the network positioning position based on the historical network positions of the target object at the previous N moments and the historical positioning position; a second determination module, for determining a target positioning section matching the network positioning position based on the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each of the candidate positioning sections; and a mapping module, for using the mapped position of the network positioning position on the target positioning section as the positioning position at the current moment.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the positioning method described in the first aspect.

[0008] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the positioning method as described in the first aspect is implemented.

[0009] According to the positioning solution provided in the embodiment of the present application, a candidate positioning section is obtained from the target navigation route based on the network positioning position, and the estimated moving distance and the confidence of the network point trajectory containing the network positioning position are determined based on the historical network position, etc., and then the target positioning section that matches the network positioning position is determined from the candidate positioning sections based on the confidence and the estimated moving distance, etc. Since the historical network position is combined in the process of determining the target positioning section, the problem that the existing network positioning position is prone to drift and the network positioning position is not updated within a long distance is solved, and the network positioning position is mapped to the target positioning section to obtain the positioning position of the target object at the current moment, thereby ensuring the positioning accuracy and avoiding excessive deviation from the target road route. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0011] Figure 1A This is a flowchart of the steps of a positioning method in Embodiment 1 of the present application;

[0012] Figure 1B for Figure 1A A schematic diagram of selecting a candidate positioning section in a usage scenario;

[0013] Figure 2A This is a flowchart of a positioning method according to Embodiment 2 of the present application;

[0014] Figure 2B This is a schematic diagram of selecting the first candidate positioning section in the second embodiment of the present application;

[0015] Figure 2C This is a schematic diagram of selecting the second candidate positioning section in the second embodiment of the present application;

[0016] Figure 2D A curve chart of the accuracy confidence when the accuracy radius confidence value is 250 in Example 2 of the present application;

[0017] Figure 2E A curve chart of the accuracy confidence when the accuracy radius confidence value is 65 in Example 2 of the present application;

[0018] Figure 2F A schematic diagram of selecting a candidate matching road segment in the second embodiment of the present application;

[0019] Figure 2G A schematic diagram of distances between multiple historical network locations and corresponding historical matching road segments according to the second embodiment of the present application;

[0020] Figure 2H A schematic diagram of the distance between historical network locations adjacent in time sequence according to the second embodiment of the present application;

[0021] Fig.2I A schematic diagram of the angles between historical network positions that are adjacent in time sequence according to the second embodiment of the present application;

[0022] Figure 2J A schematic diagram of a distToRouteR curve of the second embodiment of the present application;

[0023] Figure 2K A dist2LastPosR curve schematic diagram of the second embodiment of the present application;

[0024] Figure 2L A schematic diagram of a moveTrendR curve of Example 2 of the present application;

[0025] Figure 2MA tripDistR curve diagram of Example 2 of the present application;

[0026] Figure 2N A schematic diagram of a posAccR1 curve of the second embodiment of the present application;

[0027] Fig.2O This is a schematic diagram of a first network point trajectory in a deviated state in Embodiment 2 of the present application;

[0028] Figure 2P This is a schematic diagram of a second network point trajectory in a deviated state in Embodiment 2 of the present application;

[0029] Figure 2Q A schematic diagram of the distances between the network positioning position and different candidate positioning sections in Example 2 of the present application;

[0030] Figure 3 This is a structural block diagram of a positioning device according to Embodiment 3 of the present application;

[0031] Figure 4 This is a schematic diagram of the structure of an electronic device according to the fourth embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0033] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0034] Embodiment 1

[0035] Reference Figure 1A , Figure 1A A flowchart of the steps of the positioning method of the first embodiment of the present application is shown.

[0036] In this embodiment, the positioning method includes the following steps:

[0037] Step S102: Based on the current network positioning position of the target object and the historical positioning position at the previous moment, at least two candidate positioning sections located ahead of the historical positioning position are selected from the target navigation route.

[0038] The target object can be any device that can collect network signals, including but not limited to mobile phones, PADs, smart watches, etc. In this embodiment, the application to the navigation scene is used as an example for explanation. In the navigation scene, if the target object is in a position where the satellite signal is poor, it is difficult to obtain a complete and accurate satellite signal, and it is difficult to determine the accurate position and navigate based on the satellite signal. In order to solve this problem, network positioning can be performed based on the network information of the target object to obtain the network positioning position. For example, based on the information such as WiFi and base stations collected by the target object, a neural network model trained with big data is used to determine the network positioning position.

[0039] Compared with the satellite positioning position based on satellite signals, the network positioning position has a relatively lower frequency, lower accuracy, and is prone to position drift. When the obtained network positioning position is not on the target navigation route (i.e., the route selected when starting navigation), in order to correct the network positioning position and obtain a more accurate positioning position, at least two candidate positioning sections can be determined from the target navigation route based on the network positioning position and the historical positioning position at the previous moment (which can be the current vehicle logo position). The candidate positioning section is the section that the target object may move to during the period from the current moment to the previous moment.

[0040] Since the historical positioning position (that is, the position of the target object on the target navigation route at the previous moment) is referred to when determining the candidate positioning sections, the problem that the network positioning position deviates far from the actual position and the candidate positioning section determined only based on the network positioning position may not contain the actual position of the target object is avoided, thereby improving the accuracy of the candidate positioning section selection.

[0041] Step S104: Based on the historical network positions of the target object at the previous N moments and the historical positioning position, determine the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory including the network positioning position.

[0042] N is a positive integer, and its value can be determined as needed, and this embodiment does not limit this. For example, if the time interval between the previous moment and the current moment is 1 second, the value of N can be 60, that is, the historical network position is the historical network position within the last 60 seconds before the current moment. The historical network position and the network positioning position at the current moment can constitute a network point trajectory. Of course, the positions included in the network point trajectory are not limited to this.

[0043] Based on the network positioning position and the historical network position, it is possible to determine the degree of deviation of the target object's network-based position relative to the target navigation route and the degree of deviation between the various positions over a period of time in the past. Based on this information, the target object's current section and its position on the section can be predicted from the sections included in the target navigation route, so as to determine the estimated movement distance of the target object based on the predicted position on the section and the historical positioning position.

[0044] In addition, the confidence of the network point trajectory containing the network positioning position can also be determined based on the information of the degree of deviation. The confidence of the network point trajectory represents the accuracy of the network positioning position to a certain extent.

[0045] Step S106: Determine a target positioning section that matches the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section.

[0046] For each candidate positioning section, the degree of deviation of the network positioning position relative to the candidate positioning section can be determined based on the network positioning position, the position information of the candidate positioning section, and the confidence of the network point trajectory. In addition, the probability of the target object being on the candidate positioning section is determined based on the estimated moving distance, the confidence of the network point trajectory, etc., and then the matching target positioning section can be determined based on this information. The target positioning section can be understood as the positioning section where the target object is located at the current moment.

[0047] Step S108: Using the mapping position of the network positioning position on the target positioning section as the positioning position at the current moment.

[0048] The mapped position is obtained by mapping the network positioning position to the target positioning section, and the mapped position is used as the positioning position at the current moment. In this way, the network positioning position can be adjusted to the target navigation route, which solves the problem of easy drift of the network positioning position to a certain extent, and can achieve accurate positioning of the target object, ensuring that the target object can be positioned through the network when the satellite signal is lost, so as to ensure the reliability and accuracy of navigation.

[0049] like Figure 1B As shown, the following takes a specific usage scenario as an example to illustrate:

[0050] In this usage scenario, taking navigation through a target object (such as a mobile phone) as an example, a target navigation route is planned based on the obtained starting point and end point of the trip during navigation, and the location of the target object can be determined at regular intervals during movement along the target navigation route. The location can be determined based on satellite signals, or based on network location when satellite signals are lost.

[0051] When determining based on the network positioning position, assume that the current time is the tth time, and determine at least two candidate positioning sections (such as Figure 1B The candidate positioning segment is located in front of the historical positioning position, which means that the target object may move to the segment on the target navigation route at time t.

[0052] Based on the network positioning position, the historical network position of the previous N moments, and the historical positioning position, the estimated moving distance of the target object and the confidence of the network point trajectory containing the network positioning position can be determined. The estimated moving distance is used to indicate the moving distance of the target object relative to the positioning position along the target navigation route calculated based on the network positioning position at the current moment. The confidence of the network point trajectory is used to indicate the reliability of the network positioning position.

[0053] For each candidate positioning segment, the probability of the target object moving to the candidate positioning segment at time t is calculated based on the obtained estimated moving distance, the confidence of the network point trajectory containing the network positioning position, the network positioning position and the position information of each candidate positioning segment.

[0054] Based on the calculated probabilities of each candidate positioning section, the target positioning section that matches the network positioning position can be determined, that is, the section where the target object is more likely to appear. In order to ensure accurate positioning and solve the problem of network positioning position drift, after determining the target positioning section, the network positioning position is mapped to the target positioning section to obtain the mapping position, and the mapping position is used as the positioning position at the current moment. This can solve the problem of the network positioning position deviating from the target navigation section and improve positioning accuracy.

[0055] Through this embodiment, candidate positioning sections are obtained from the target navigation route based on the network positioning position, and the estimated moving distance and the confidence of the network point trajectory containing the network positioning position are determined based on the historical network position, etc., and then the target positioning section that matches the network positioning position is determined from the candidate positioning sections based on the confidence and the estimated moving distance, etc. Since the historical network position is combined in the process of determining the target positioning section, the problems of the existing network positioning position being prone to drift and the network positioning position not being updated within a long distance are solved, and the network positioning position is mapped to the target positioning section to obtain the positioning position of the target object at the current moment, thereby ensuring the positioning accuracy and avoiding excessive deviation from the target road route.

[0056] The solution provided in this embodiment can be executed by any electronic device, such as a chip, mobile phone, computer, etc. installed inside an unmanned vehicle, or other intelligent devices such as a server, cloud, etc.

[0057] Embodiment 2

[0058] Reference Figure 2A , showing a schematic diagram of the step flow of the positioning method of Example 2 of the present application.

[0059] In this embodiment, the positioning method includes the following steps:

[0060] Step S200: Determine whether to enter network positioning.

[0061] In the process of navigating or positioning the target object, positioning can be performed through satellite signals, or network positioning can be performed based on the WiFi, base station and other information collected by the target object through big data training. There are differences between network positioning and satellite signal positioning in terms of update frequency and position accuracy. For example, the accuracy of network positioning is relatively low and the update frequency is relatively small. However, the anti-interference ability of network positioning is improved compared to satellite signal positioning. For example, in urban canyons, tunnels and other environments, satellite signals may be lost. In this case, network positioning can be used.

[0062] In order to accurately determine the timing of adopting network positioning, step S200 may include the following sub-steps:

[0063] Sub-step S2001: Determine whether the received detection signal is a network signal.

[0064] If there is a mark in the detection signal indicating that it is a network signal or a satellite signal, it is determined according to the mark. For example, for a target device equipped with an operating system that exposes WiFi, base station and other acquisition interfaces to the outside, the location of the target object is calculated from the WiFi, base station and other information obtained from the operating system to form a detection signal. This signal can be directly configured with a mark to indicate the category.

[0065] For the operating system that does not disclose this information to the outside, the operating system itself integrates the network positioning position and the satellite positioning position. Since there is no mark indicating the category in the detection signal, it can be determined based on the signal speed carried in the detection signal. For example, if the signal speed is <0km / h, it is determined to be a network signal, otherwise, if the signal speed is >=0km / h, it is a satellite signal.

[0066] If the detected signal is a network signal, that is, the obtained network positioning position is, sub-step S2002 is executed to determine whether navigation is performed based on the network positioning position.

[0067] Sub-step S2002: Determine whether to perform navigation based on the network positioning position.

[0068] Navigation is based on network positioning when any of the following conditions are met:

[0069] (1) The current network positioning position mapped to the target navigation route is 200m away from the starting point of the target navigation route, and the satellite signal was lost for more than 5s before the network positioning position was obtained. Or,

[0070] (2) The network positioning position is based on the network point inference point inferred by the network point inference module (which can be any appropriate module with network point inference function, without limitation).

[0071] In one feasible manner, if any of the following conditions is met, the condition that "the mapping position of the current network positioning position mapped to the target navigation route is 200m outside the starting point of the target navigation route" can be relaxed and navigation can be performed based on the network positioning position.

[0072] 1) The navigation type of the target navigation route at the current moment is deviation or parallel road switching, and this state can be determined in an appropriate manner as needed.

[0073] 2) The network positioning position is calculated based on the L algorithm or the M algorithm.

[0074] 3) The signal accuracy of the network positioning position is within 65m, and its mapping position on the target navigation route is more than 65m from the starting point.

[0075] 4) The prediction confidence of the network positioning position is greater than 0.8. This prediction confidence refers to the confidence obtained when making big data predictions based on information such as Wi-Fi and base stations.

[0076] 5) The road section type corresponding to the historical positioning position at the previous moment in the target navigation route is highway, main street, and urban expressway.

[0077] When any of the above conditions is met, it can be determined that the target object is not moving indoors, so navigation can be performed based on the network positioning position, thereby solving the problem of the target object moving indoors but mistakenly matching it to an outdoor road for navigation.

[0078] Optionally, in order to further improve navigation accuracy, the state of navigating based on the network positioning position may be exited when at least one of the following conditions is met:

[0079] A) Three consecutive detection signals are not network signals.

[0080] B) When in the state of navigation based on network positioning and within 10m or less from the tunnel entrance, exit the state of navigation based on network positioning and enter the state of tunnel dead reckoning navigation to navigate more accurately in the tunnel.

[0081] C) Determine that the navigation based on the network positioning position is exited in the yaw state.

[0082] When determining to perform navigation based on the network positioning position, the following steps 202 to S206 are executed.

[0083] Step S202: Based on the current network positioning position of the target object and the historical positioning position at the previous moment, at least two candidate positioning sections located ahead of the historical positioning position are selected from the target navigation route.

[0084] Wherein, step S202 can be implemented by the following sub-steps:

[0085] Sub-step S2021: Determine whether there is a position jump in the network positioning position according to the network positioning position and the historical positioning position.

[0086] In one example, whether there is a position jump can be determined based on the distance between the network positioning position and the historical positioning position. If the distance between the two is greater than a certain set distance (which can be determined as needed and is not limited to this, such as 200 meters, 500 meters, etc.), it is determined that there is a bitmap jump, and sub-steps S2023 and S2024 are executed; otherwise, it is determined that there is no position jump, and sub-step S2022 is executed.

[0087] Sub-step S2022: If there is no position jump, at least two sections in the target navigation route that are in front of the historical positioning position and whose distances from the network positioning position are less than or equal to a set value are selected as the candidate positioning sections.

[0088] For the case where there is no position jump, a method for selecting at least two sections whose distance from the network positioning position is less than or equal to the set value is: with the network positioning position as the center, use a 500m*500m selection box to select the target navigation route, and select the section of the target navigation route that is selected by the selection box and is at least partially located in front of the historical positioning position as the candidate positioning section (such as Figure 2B shown).

[0089] Sub-step S2023: If there is a position jump, the network positioning position is adjusted according to the historical positioning position.

[0090] like Figure 2CAs shown, since the network positioning position may drift, jump, etc., when the candidate positioning section is selected directly based on the network positioning position, the selected section cannot cover the actual position of the target object. The actual position may be between the historical positioning position and the network positioning position, resulting in inaccurate positioning.

[0091] In order to overcome this problem and make the selected candidate positioning section contain the real position of the target object with a greater probability, the network positioning position and the historical positioning position can be comprehensively adjusted to adjust the network positioning position.

[0092] A feasible adjustment method can be implemented as follows: moving the network positioning position by a target length toward the direction close to the historical positioning position, and making the adjusted network positioning position located on the line connecting the network positioning position and the historical positioning position.

[0093] like Figure 2C As shown, the historical positioning position is Figure 2C At point A, the network positioning position is Figure 2C Point B in the middle, the adjusted network positioning position is Figure 2C Middle point C.

[0094] The target length is determined according to the offset distance between the network positioning position and the historical positioning position, the set benchmark probability, the signal accuracy benchmark value and the accuracy radius confidence of the network signal for obtaining the network positioning position.

[0095] For example, the target length is recorded as moveDist, and its calculation method is, for example:

[0096] moveDist=dist*ratio*posAccR.

[0097] dist is the offset distance between the network positioning position and the historical positioning position.

[0098] ratio is the set benchmark probability. If the network point trajectory including the network positioning position is in a retreat state (the state can be determined by the method described in step 204) or the moving distance of the network positioning position relative to the historical positioning position on the target navigation route is less than 200 meters, the ratio value is 0.5; otherwise, the ratio value is 0.3. By determining whether the network point trajectory is in a retreat state or the moving distance is less than 200 meters, it can be determined whether the network positioning position is drifting or jumping, and the situation where the target object is indoors (i.e., the moving distance is less than 200 meters) can be excluded, thereby making the calculation more accurate.

[0099] posAccR is the accuracy confidence, which is determined based on the signal accuracy reference value and the accuracy radius confidence of the network signal of the network positioning position. The calculation method of posAccR is:

[0100] posAccR=1-1.0 / (1.0+exp(0.03*(sigPosAcc-basePosAcc))).

[0101] basePosAcc precision radius confidence. If the network point trajectory containing the network positioning position is in a backward state (the state can be determined by the method described in step **) or the moving distance of the network positioning position relative to the historical positioning position on the target navigation route is less than 200 meters, the basePosAcc value is 65; otherwise, the basePosAcc value is 250.

[0102] sigPosAcc is the signal accuracy reference value. When basePosAcc is 250, the corresponding relationship between posAccR and sigPosAcc is as follows: Figure 2D When basePosAcc is 65, the corresponding relationship between posAccR and sigPosAcc is as follows: Figure 2E shown.

[0103] exp(0.03*(sigPosAcc-basePosAcc)) refers to the exponential of e.

[0104] Sub-step S2024: selecting a section in the target navigation route that is in front of the historical positioning position and whose distance to the adjusted network positioning position is less than or equal to a set value as the candidate positioning section.

[0105] In a feasible method of selecting a road section whose distance from the adjusted network positioning position is less than or equal to a set value as the candidate positioning road section, the target navigation route can be framed with a 500m*500m selection box centered on the adjusted network positioning position, and the road section in the target navigation route selected by the selection box and at least partially located in front of the historical positioning position is selected as the candidate positioning road section (e.g. Figure 2C shown).

[0106] In the above manner, based on the historical positioning position, the road segments intersecting with the selection box (in this embodiment, the selection box is a square box of 500*500, of course, in other methods, the selection box can be other shapes, such as a circle, a rectangle, etc.) are obtained as candidate positioning sections along the forward direction. The candidate positioning sections determined in this way are more accurate.

[0107] Step S204: Based on the historical network positions of the target object at the previous N moments and the historical positioning position, determine the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory including the network positioning position.

[0108] In one feasible manner, step S204 includes the following sub-steps:

[0109] Sub-step S2041: determining a plurality of candidate matching sections from the target navigation route according to the network positioning position.

[0110] The difference between the candidate matching segment and the candidate positioning segment is that the candidate matching segment is a segment obtained by omnidirectional matching on the target navigation route.

[0111] like Figure 2F As shown, a 500m*500m selection box is established with the network positioning position as the center, and the sections on the target navigation route that intersect with the selection box are selected, and at least one section is selected from these sections as a candidate matching section.

[0112] The candidate matching segments can be divided into backward segments, forward segments and current segments according to their relative position relationship with the historical positioning positions.

[0113] The back segment is the vertical projection of the network positioning position falling on the intersecting road segment, and the vertical point is the closest to the historical positioning position and is located behind the historical positioning position. In some cases, the back segment may not exist. Figure 2F The road section shown in does not include the reverse section.

[0114] The forward segment is the segment where the vertical projection of the network positioning position falls on the intersecting road segment, and the vertical point is closest to the historical positioning position and is located in front of the historical positioning position. Figure 2F A road section before the road section where point A is located is the forward section. Of course, the forward section may not exist in some cases.

[0115] The current segment is the segment where the historical positioning position is located.

[0116] Sub-step S2042: Based on the historical network positions at the previous N moments and the historical matching sections of each of the historical network positions in the target navigation route, predict the current matching section that matches the network positioning position and the confidence of the current matching section from the multiple candidate matching sections.

[0117] For each candidate matching segment, its confidence as the current matching segment can be calculated based on the historical network positions at the previous N moments and the historical matching segments of each historical network position in the target navigation route, and then the current matching segment can be determined from these candidate matching segments.

[0118] For example, Figure 2F In the example shown, the candidate matching segments include the current segment and the forward segment, and the confidence of the two is calculated separately. The calculation process takes the forward segment as an example:

[0119] Process A1: Determine an average segment distance based on the distance of each of the historical network positions relative to the historical matching segment.

[0120] like Figure 2G As shown, it shows 10 historical network locations (historical network location 10-1) and a current network location ( Figure 2G Schematic diagram of label 0) shown in FIG.

[0121] The distance of the historical network location relative to the historical matching road segment is recorded as dist_*, where * is the ID number of the historical network location. The distances dist_* corresponding to multiple historical network locations form a distance list. Figure 2G The distance between the nearest point of the historical network location and the corresponding historical matching road segment is shown in .

[0122] In this example, the average segment distance can be calculated based on the corresponding distance from historical network location 10 to historical network location 1.

[0123] Process B1: Determine the average network location distance based on the network location distance between two of the historical network locations that are adjacent in time sequence.

[0124] like Figure 2H The network location distance between two historical network locations adjacent in time sequence is shown. Based on the network location distance from the historical network location 10 to the historical network location 1, the average network location distance can be calculated.

[0125] Process C1: determining, according to two historical network positions adjacent in time sequence, the movement angle corresponding to each of the historical network positions.

[0126] The movement angle can be Figure 2H The angle between the line connecting two adjacent historical network positions in the time series (azi_* in the figure) and the reference line. The reference line can be a horizontal line in the forward direction or other appropriate reference lines, which are not limited.

[0127] Process D1: For each candidate matching segment, the confidence of the candidate matching segment is determined based on the distance from the network positioning position to the candidate matching segment, the distance between the network positioning position and the historical network position at the previous moment, the average segment distance, the average network position distance, and the moving angle of the historical network position.

[0128] In this embodiment, the confidence of the candidate matching road segment is recorded as ratio1, which can be calculated in the following way:

[0129] ratio1=1.0 / (1.0+exp(2.0*sumTypeR-5)).

[0130] Among them, if the candidate matching section is a forward section or a current section, sumTypeR is the sum of multiple probabilities (the probabilities will be described in detail later); if the candidate matching section is a backward section, the value of sumTypeR is a fixed value, such as 5. The fixed value can be determined as needed, so as to avoid matching the backward section as much as possible, thereby improving accuracy.

[0131] When the candidate matching segment is the forward segment or the current segment, sumTypeR is the sum of multiple probabilities. The multiple probabilities include but are not limited to: relative route distance probability (denoted as distToRouteR), signal moving distance probability (denoted as dist2LastPosR), signal accuracy probability (denoted as posAccR1), moving distance probability (denoted as tripDistR) and turning trend probability (denoted as moveTrendR).

[0132] The calculation method of sumTypeR can be expressed as:

[0133] sumTypeR=distToRouteR+dist2LastPosR+moveTrendR+tripDistR+posAccR1.

[0134] Among them, distToRouteR can be determined according to the following method:

[0135] distToRouteR=1-(62.0 / (sqrt(2*PI)*25.0)*exp(-pow(diffDist1,2) / (2*pow(25,2)))).

[0136] Among them, diffDist1 is the smaller one of the distance difference between the selected candidate matching segment and the average segment and the average segment distance. It can be expressed as:

[0137] diffDist1=min(abs(distToRouteVer[0]-mean(distToRouteVer)),distToRouteVer[0])

[0138] distToRouteVer[0] is the distance between the network positioning position and the candidate matching section (such as the forward section), that is, Figure 2G shown in dist_0. mean(distToRouteVer) is the average road distance.

[0139] pow(diffDist1,2) is the square of diffDist1. PI is the circumference of a circle. sqrt(2*PI) is the square root of 2*PI. exp(-pow(diffDist1,2) / (2*pow(25,2)) is the exponent of e. The determined distToRouteR curve is as follows: Figure 2J As shown, Figure 2J The diffDist in is diffDist1.

[0140] dist2LastPosR can be determined as follows:

[0141] dist2LastPosR=1-(62.0 / (sqrt(2*PI)*25.0)*exp(-pow(diffDist2,2) / (2*pow(25,2)))).

[0142] in,

[0143] diffDist2=min(abs(dist2LastPosVer[0]-mean(dist2LastPosVer)),dist2LastPosVer[0]).

[0144] dist2LastPosVer[0] is the distance between the network location and the historical network location at the previous moment. mean(dist2LastPosVer) is the average network location distance. The determined curve of dist2LastPosR is as follows: Figure 2K As shown, diffDist is diffDist2.

[0145] moveTrendR can be determined as follows:

[0146]

[0147] When tripAzi*crossAzi<0, moveTrendR takes the value of 1.

[0148] When tripAzi*crossAzi≥0, moveTrendR=1-(112.0 / (sqrt(2*pi)*45.0)*exp(-pow(tripAzi-crossAzi,2) / (2*pow(45,2)))).

[0149] Among them, tripAzi is the angle change between the selected candidate matching segment (such as the current segment) and the current segment where the historical positioning position is located. crossAzi is the angle change between the position within a set range (such as 50m) before the historical positioning position and the candidate matching segment (such as the current segment). The curve of moveTrendR is determined as follows Figure 2L shown.

[0150] tripDistR can be determined as follows:

[0151] tripDistR=2-5 / sqrt(2*S_PI)*exp(-0.125*pow(max(tripDist-150,0),2) / 5000).

[0152] Among them, tripDist is the distance between the selected candidate matching segment (such as the forward segment) and the historical positioning position along the target navigation route. The determined tripDist curve is as follows Figure 2M shown.

[0153] posAccR1 can be determined as follows:

[0154] posAccR1=1-min(1.2 / (1.0+exp(0.03*(sig.posAcc-65))),0.8).

[0155] Among them, sig.posAcc is the accuracy probability of the network signal of the target object to obtain the network positioning position. It can be obtained from the device that collects the network signal. The curve of the determined posAccR1 is as follows Figure 2N As shown, Figure 2N The posAccR in is posAccR1.

[0156] Process E1: According to the weight of each candidate matching segment and the positional relationship of each candidate matching segment relative to the historical positioning position, the current matching segment is selected from the candidate matching segments, and the confidence of the current matching segment is determined.

[0157] In one feasible manner, the current matching road segment corresponding to the network positioning position is determined based on the following conditions:

[0158] Condition 1: The confidence of the current segment is greater than the confidence of the previous segment, and the confidence of the previous segment is less than 0.8.

[0159] Condition 2: The moving distance of the forward segment relative to the historical positioning position exceeds 600 meters, and the distance between the current segment and the network positioning position is less than 500 meters, and the confidence value of the forward segment is greater than the confidence value of the current segment by no more than 0.2.

[0160] Condition 3: The network positioning position is within 100m ahead of the matching point on the target navigation route and is straight, or the forward section is not straight.

[0161] Based on the above three conditions, case 1: if condition 1 or condition 2 is met, the preset current matching section is the current section; otherwise, the current matching section is the forward section.

[0162] Case 2: If there is no backward segment, and both conditions 2 and 3 are met, the current matching segment is the forward segment; otherwise, it is the current matching segment determined in case 1.

[0163] Case 3: If there is a backward segment and no forward segment, or the moving distance of the forward segment is more than 20m greater than both the current segment and the backward segment, the current matching segment is the backward segment. Otherwise, it is the current matching segment determined in Case 1.

[0164] The confidence level corresponding to the current matching road segment is determined as the obtained confidence level of the current matching road segment.

[0165] Sub-step S2043: Determine whether the network point trajectory including the network positioning position is in a deviation state.

[0166] In one feasible manner, sub-step S2043 can be implemented as follows: determining whether the set deviation condition is met based on the historical network position, the corresponding historical matching section, the network positioning position and the current matching section; if the deviation condition is met, determining that it is in the deviation state.

[0167] The deviation conditions include the following conditions corresponding to case 1 where a deviation state occurs and conditions corresponding to case 2 where a deviation state occurs.

[0168] Case 1 of deviation: If the distance list of the route is traversed and it is determined that there are three consecutive historical network locations with a distance of more than 50m to the corresponding historical matching section, and the longitudinal distance between two adjacent historical network locations in time sequence is greater than 5m, then the network point trajectory is determined to be in a deviation state, such as Fig.2O shown.

[0169] The network positioning position and its corresponding current matching section are stored in the route distance list. At the next moment, the network positioning position and its corresponding current matching section can be used as one of the aforementioned historical network positions and historical matching sections.

[0170] It should be noted that the number of historical network locations stored in the route distance list may be fixed, for example, storing historical network locations within the last 60 seconds. Of course, it may not be fixed and there is no limitation on this.

[0171] Case 2 of deviation: If the distance list of the route is traversed and it is determined that there are three consecutive historical network locations with a distance to the corresponding historical matching section of more than 500m, then the network point trajectory is determined to be in a deviation state, such as Figure 2P shown.

[0172] Sub-step S2044: Determine the estimated moving distance based on the positional relationship of the current matching segment on the target navigation route relative to the historical positioning position, and / or the deviation determination result, and use the confidence of the current matching segment as the confidence of the network point trajectory.

[0173] In one feasible manner, if the positional relationship of the current matching section relative to the historical positioning position is backward and / or the deviation determination result is a deviation state, the estimated movement distance is 0. In other words, if the mapping position of the network positioning position on the current matching section is located behind the historical positioning position, or the network point trajectory is determined to be in a deviation state, the estimated movement distance is 0.

[0174] or,

[0175] If the positional relationship of the current matching section relative to the historical positioning position is forward, the estimated moving distance is the track distance between the mapping position of the network positioning position on the current matching section and the historical positioning position. In other words, if the mapping position of the network positioning position on the current matching section is ahead of the historical positioning position, the estimated moving distance is the track distance. The track distance refers to the distance from the mapping position of the network positioning position on the current matching section to the historical positioning position along the target navigation route.

[0176] Step S206: Determine a target positioning section that matches the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section.

[0177] In one feasible manner, step S206 includes the following sub-steps:

[0178] Sub-step S2061: for each candidate positioning segment, determining the actual moving distance between the matching position of the network positioning position on the candidate positioning segment and the historical positioning position.

[0179] like Figure 2B As shown in , the candidate positioning sections include 4 sections, and the actual moving distance can be determined for each candidate positioning section. Taking the candidate positioning section near point A as an example, when calculating the actual moving distance, the nearest point from the network positioning position (i.e. point B in the figure) to the candidate positioning section is determined, and the nearest point is used as the mapping position on it. The distance between the mapping position and the historical positioning position is determined along the target navigation route as the actual moving distance.

[0180] The actual moving distances of the remaining candidate positioning segments can be obtained in a similar manner, so they will not be described in detail.

[0181] Sub-step S2062: Determine a first weight of each candidate positioning segment according to the actual moving distance of each candidate selected segment, the estimated moving distance and the confidence of the network point trajectory.

[0182] The first weight may be determined according to the difference between the actual moving distance and the estimated moving distance and the credibility, wherein the credibility is max(1-confidence of the network point trajectory, 0.4).

[0183] If the difference between the actual moving distance and the estimated moving distance is greater than 1, the first weight = (actual moving distance - estimated moving distance) * credibility. Or,

[0184] If the difference between the actual moving distance and the estimated moving distance is less than or equal to 1, the first weight = credibility.

[0185] Sub-step S2063: Determine the second weight of each candidate positioning segment according to the distance from the network positioning position to each candidate positioning segment and the confidence of the network point trajectory.

[0186] The second weight = the distance from the network positioning position to each of the candidate positioning sections * max (confidence of the network point trajectory, 0.3). The distance from the network positioning position to each of the candidate positioning sections can be Figure 2Q Among them, dist_A, dist_B and dist_C etc.

[0187] In addition, optionally, if VDR turning angle information is received, there is an angle increment, and the third weight can be calculated at this time. The third weight can be determined according to the angle between two historical network positions that are adjacent in time sequence in the network point trajectory. The determination method can be any appropriate method, which is not limited to this.

[0188] If the VDR angle information is not received, the angle increment is 0, and the third weight is directly determined to be 0.

[0189] Sub-step S2064: Determine the target positioning section that matches the network positioning position based on at least the first weight and the second weight.

[0190] When the third weight is 0, the candidate positioning section with the smaller sum is selected as the target positioning section according to the sum of the first weight and the second weight.

[0191] Alternatively, when the third weight is not 0, the first weight, the second weight and the third weight are summed, and the candidate positioning section with the smaller sum result is selected as the target positioning section.

[0192] Step S208: Using the mapping position of the network positioning position on the target positioning section as the positioning position at the current moment.

[0193] After determining the target positioning section, the network positioning position is mapped to the target positioning section to obtain the mapping position, and this is used as the positioning position at the current moment.

[0194] Optionally, in order to ensure the accuracy of positioning, the method may further include step S210.

[0195] Step S210: If it is determined that the network point trajectory including the network positioning position is in a deviated state, and the distance between the network positioning position and the target positioning section is greater than or equal to a preset threshold, it is determined to suppress the output of the positioning position at the current moment.

[0196] The method of determining whether the network point trajectory is in a deviation state is as described in the aforementioned sub-step S2043, and whether it is in a deviation state can be determined based on the deviation determination result.

[0197] If it is determined that the network point trajectory is in a deviation state, and the distance between the network positioning position and the target positioning section is greater than or equal to a preset threshold (denoted as deviationDist), it is considered necessary to suppress the matching point update, that is, the determined positioning position is not output.

[0198] The preset threshold is determined as follows:

[0199] If the signal accuracy radius sigPosAcc is less than or equal to 200, the preset threshold value is 200; if the signal accuracy radius sigPosAcc is greater than 200 and less than or equal to 200, the preset threshold value is If the signal accuracy radius sigPosAcc is greater than 2000, the preset threshold value is 500.

[0200] When the above conditions are not met, it is determined that matching suppression is not performed, and the positioning position of the target object is output.

[0201] Through the above method, the network positioning position is combined with the information of the target navigation route to locate the position, and a more accurate display position is output to the outside, which solves the problem that the device cannot receive satellite signals normally for a long time due to factors such as hardware and environmental occlusion during the navigation process, resulting in the inability to navigate normally.

[0202] In the absence of satellite signals, the Wi-Fi, base station and other information scanned by the target object (i.e. smart device) is combined with the network positioning position obtained through big data training. Based on the downgraded positioning of the network positioning position, combined with driving behavior, device sensor information, etc., a more accurate positioning position is given during the navigation process.

[0203] In addition, before navigating based on the network positioning position, a judgment can be made to avoid users entering navigation when indoors, ensuring the accuracy and effect of positioning. By matching the network positioning position to the target navigation route, the problem of position drift caused by the positioning position deviating too much from the target navigation route is avoided, ensuring the navigation effect. The accuracy, timeliness and coverage of positioning are all good, avoiding the problem of missed intersections due to untimely broadcasts during navigation and stuck icons in the navigation interface.

[0204] Based on the historical network position, the confidence of the estimated moving distance and network point trajectory is obtained. Then, the target positioning section matching the network positioning position is determined based on the estimated moving distance, the confidence and the distance between the network positioning position and the candidate positioning section, further improving the accuracy of positioning.

[0205] Embodiment 3

[0206] Figure 3 This is a structural block diagram of a positioning device according to Embodiment 3 of the present application.

[0207] In this embodiment, it includes:

[0208] A selection module 302 is used to select at least two candidate positioning sections located in front of the historical positioning position from the target navigation route based on the network positioning position of the target object at the current moment and the historical positioning position at the previous moment;

[0209] A first determination module 304 is used to determine, based on the historical network locations of the target object at the previous N moments and the historical positioning location, the estimated moving distance of the network positioning location relative to the historical positioning location and the confidence of the network point trajectory including the network positioning location;

[0210] A second determination module 306 is used to determine a target positioning section that matches the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section;

[0211] The mapping module 308 is used to use the mapping position of the network positioning position on the target positioning section as the positioning position at the current moment.

[0212] Optionally, the selection module 302 is used to determine whether there is a position jump in the network positioning position based on the network positioning position and the historical positioning position; if there is no position jump, at least two sections in the target navigation route that are in front of the historical positioning position and whose distance from the network positioning position is less than or equal to a set value are selected as the candidate positioning sections.

[0213] Optionally, the selection module 302 is also used to adjust the network positioning position according to the historical positioning position if there is a position jump; and select a section from the target navigation route that is in front of the historical positioning position and whose distance to the adjusted network positioning position is less than or equal to a set value as the candidate positioning section.

[0214] Optionally, when adjusting the network positioning position according to the historical positioning position, the selection module 302 moves the network positioning position by a target length in a direction close to the historical positioning position, and makes the adjusted network positioning position located on a line connecting the network positioning position and the historical positioning position; wherein the target length is determined based on an offset distance between the network positioning position and the historical positioning position, a set benchmark probability, a signal accuracy benchmark value, and an accuracy radius confidence level of a network signal for obtaining the network positioning position.

[0215] Optionally, the first determination module 304 is used to determine multiple candidate matching sections from the target navigation route based on the network positioning position; predict the current matching section that matches the network positioning position and the confidence of the current matching section from the multiple candidate matching sections based on the historical network positions at the previous N moments and the historical matching sections of each of the historical network positions in the target navigation route; determine whether the network point trajectory containing the network positioning position is in a deviation state; determine the estimated moving distance based on the positional relationship of the current matching section on the target navigation route relative to the historical positioning position, and / or the deviation determination result, and use the confidence of the current matching section as the confidence of the network point trajectory.

[0216] Optionally, the first determination module 304 is used to determine an average segment distance based on the distance of each historical network position relative to the historical matching segment when predicting the current matching segment that matches the network positioning position and the confidence of the current matching segment from the multiple candidate matching segments based on the historical network positions at the previous N moments and the historical matching segments of each historical network position in the target navigation route; determine the average network position distance based on the network position distance between two historical network positions that are adjacent in time sequence; determine based on two historical network positions that are adjacent in time sequence, The moving angle corresponding to each of the historical network positions; for each of the candidate matching segments, determine the confidence of the candidate matching segment according to the distance from the network positioning position to the candidate matching segment, the distance between the network positioning position and the historical network position at the previous moment, the average segment distance, the average network position distance, and the moving angle of the historical network position; select the current matching segment from the candidate matching segments according to the weight of each of the candidate matching segments and the positional relationship of each of the candidate matching segments relative to the historical positioning position, and determine the confidence of the current matching segment.

[0217] Optionally, the first determination module 304 is used to determine whether the network point trajectory including the network positioning position is in a deviation state, based on the historical network position, and the corresponding historical matching section, the network positioning position and the current matching section, whether the set deviation condition is met; if the deviation condition is met, it is determined to be in the deviation state.

[0218] Optionally, the first determination module 304 is used to determine the calculated moving distance based on the positional relationship of the current matching section on the target navigation route relative to the historical positioning position, and / or the deviation determination result. If the positional relationship of the current matching section relative to the historical positioning position is backward and / or the deviation determination result is a deviation state, the calculated moving distance is 0; or, if the positional relationship of the current matching section relative to the historical positioning position is forward, the calculated moving distance is the trajectory distance between the mapping position of the network positioning position on the current matching section and the historical positioning position.

[0219] Optionally, the second determination module 306 is used to determine, for each candidate positioning segment, the actual moving distance between the matching position of the network positioning position on the candidate positioning segment and the historical positioning position; determine the first weight of each candidate positioning segment based on the actual moving distance of each candidate selected segment, the estimated moving distance and the confidence of the network point trajectory; determine the second weight of each candidate positioning segment based on the distance from the network positioning position to each candidate positioning segment and the confidence of the network point trajectory; and determine the target positioning segment matched by the network positioning position based on at least the first weight and the second weight.

[0220] Optionally, the device further comprises:

[0221] The matching suppression module 310 is used to determine to suppress the output of the positioning position at the current moment if it is determined that the network point trajectory including the network positioning position is in a deviation state and the distance between the network positioning position and the target positioning section is greater than or equal to a preset threshold.

[0222] The positioning device of the embodiment of the present application is used to implement the corresponding positioning method in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here. In addition, the functional implementation of each module in the positioning device of this embodiment can refer to the description of the corresponding part in the aforementioned method embodiment, which will not be repeated here.

[0223] Embodiment 4

[0224] Reference Figure 4 , shows a schematic diagram of the structure of an electronic device according to the fourth embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device.

[0225] like Figure 4 As shown, the electronic device may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 , and a communication bus 408 .

[0226] in:

[0227] The processor 402 , the communication interface 404 , and the memory 406 communicate with each other via a communication bus 408 .

[0228] The communication interface 404 is used to communicate with other electronic devices or servers.

[0229] The processor 402 is used to execute the program 410, and specifically can execute the relevant steps in the above positioning method embodiment.

[0230] Specifically, the program 410 may include program codes, which include computer operation instructions.

[0231] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0232] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0233] The specific implementation of each step in program 410 can refer to the corresponding description of the corresponding steps and units in the above positioning method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0234] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0235] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the positioning method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the positioning method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the positioning method shown here.

[0236] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0237] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A positioning method, wherein: include: Based on the current network positioning position of the target object and the historical positioning position at the previous moment, selecting at least two candidate positioning sections located in front of the historical positioning position from the target navigation route; Based on the historical network positions of the target object at the previous N moments and the historical positioning position, determine the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory including the historical network position and the network positioning position, wherein the confidence of the network point trajectory is used to indicate the reliability of the network positioning position; Determine a target positioning section that matches the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section; The mapping position of the network positioning position on the target positioning section is used as the positioning position at the current moment.

2. The method according to claim 1, wherein: The method of selecting at least two candidate positioning sections located ahead of the historical positioning position from the target navigation route based on the current network positioning position of the target object and the historical positioning position at the previous moment includes: Determining whether there is a position jump in the network positioning position according to the network positioning position and the historical positioning position; If there is no position jump, at least two sections in front of the historical positioning position and whose distances from the network positioning position are less than or equal to a set value are selected from the target navigation route as the candidate positioning sections.

3. The method according to claim 2, wherein: The method further comprises: If there is a position jump, adjusting the network positioning position according to the historical positioning position; A section in front of the historical positioning position and having a distance from the adjusted network positioning position less than or equal to a set value is selected from the target navigation route as the candidate positioning section.

4. The method according to claim 3, wherein: The adjusting the network positioning position according to the historical positioning position includes: The network positioning position is moved by a target length toward a direction close to the historical positioning position, and the adjusted network positioning position is located on a line connecting the network positioning position and the historical positioning position; The target length is determined according to the offset distance between the network positioning position and the historical positioning position, the set benchmark probability, the signal accuracy benchmark value and the accuracy radius confidence of the network signal for obtaining the network positioning position.

5. The method according to claim 1, wherein: The determining, based on the historical network positions of the target object at the previous N moments and the historical positioning position, the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory including the network positioning position comprises: Determining a plurality of candidate matching sections from the target navigation route according to the network positioning position; According to the historical network positions at the previous N moments and the historical matching sections of each of the historical network positions in the target navigation route, predicting a current matching section that matches the network positioning position and a confidence level of the current matching section from the multiple candidate matching sections; Determining whether a network point trajectory including the network positioning position is in a deviated state; The estimated moving distance is determined based on the positional relationship of the current matching section on the target navigation route relative to the historical positioning position, and / or the deviation determination result, and the confidence of the current matching section is used as the confidence of the network point trajectory.

6. The method according to claim 5, wherein: The predicting, based on the historical network positions at the previous N moments and the historical matching sections of each of the historical network positions in the target navigation route, of a current matching section matching the network positioning position and a confidence level of the current matching section from the multiple candidate matching sections includes: Determining an average segment distance based on the distance of each of the historical network locations relative to the historical matching segment; Determining an average network location distance based on the network location distance between two of the historical network locations that are adjacent in time sequence; Determining, according to two historical network positions adjacent in time sequence, a movement angle corresponding to each of the historical network positions; For each candidate matching road segment, determine the confidence of the candidate matching road segment according to the distance from the network positioning position to the candidate matching road segment, the distance between the network positioning position and the historical network position at the previous moment, the average road segment distance, the average network position distance, and the moving angle of the historical network position; According to the weight of each candidate matching segment and the positional relationship of each candidate matching segment relative to the historical positioning position, the current matching segment is selected from the candidate matching segments, and the confidence of the current matching segment is determined.

7. The method according to claim 5, wherein: The determining whether the network point trajectory including the network positioning position is in a deviation state includes: Determining whether a set deviation condition is met according to the historical network position, the corresponding historical matching road section, the network positioning position and the current matching road section; If the deviation condition is met, it is determined to be in the deviation state.

8. The method according to claim 5, wherein: The determining the estimated moving distance according to the positional relationship of the current matching road section on the target navigation route relative to the historical positioning position and / or the deviation determination result comprises: If the positional relationship of the current matching road segment relative to the historical positioning position is backward and / or the deviation determination result is a deviation state, the estimated moving distance is 0; or, If the positional relationship of the current matching section with respect to the historical positioning position is forward, the estimated moving distance is the track distance between the mapping position of the network positioning position on the current matching section and the historical positioning position.

9. The method according to claim 1, wherein: The step of determining a target positioning section matching the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section includes: For each of the candidate positioning sections, determining an actual moving distance between a matching position of the network positioning position on the candidate positioning section and the historical positioning position; Determining a first weight of each candidate positioning segment according to the actual moving distance of each candidate positioning segment, the estimated moving distance and the confidence of the network point trajectory; Determining a second weight of each of the candidate positioning sections according to the distance from the network positioning position to each of the candidate positioning sections and the confidence of the network point trajectory; A target positioning section that matches the network positioning position is determined based on at least the first weight and the second weight.

10. The method according to claim 1, wherein: The method further comprises: If it is determined that the network point trajectory including the network positioning position is in a deviated state, and the distance between the network positioning position and the target positioning section is greater than or equal to a preset threshold, it is determined to suppress the output of the positioning position at the current moment.

11. A positioning device, comprising: A selection module, configured to select at least two candidate positioning sections located ahead of the historical positioning position from the target navigation route based on the network positioning position of the target object at the current moment and the historical positioning position at the previous moment; A first determination module is used to determine, based on the historical network positions of the target object at the previous N moments and the historical positioning position, the estimated moving distance of the network positioning position relative to the historical positioning position and the confidence of the network point trajectory including the historical network position and the network positioning position, wherein the confidence of the network point trajectory is used to indicate the reliability of the network positioning position; A second determination module is used to determine a target positioning section that matches the network positioning position according to the estimated moving distance, the confidence of the network point trajectory, the network positioning position, and the position information of each candidate positioning section; A mapping module is used to use the mapping position of the network positioning position on the target positioning section as the positioning position at the current moment.

12. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the positioning method according to any one of claims 1 to 10 is implemented.

Images