Map construction method, positioning method, device, storage medium and electronic equipment

Abstract

The present disclosure provides a map construction method, a positioning method, a map construction device, a positioning device, a computer readable storage medium and an electronic device, and relates to the technical field of computers. The map construction method comprises: acquiring inertial data and WiFi data sensed for a plurality of map construction behaviors; determining trajectory data of each map construction behavior by using the inertial data; determining a position of a point of interest in a map construction scene according to the trajectory data of each map construction behavior; and performing similarity clustering on the WiFi data of each point of interest position to construct a point of interest map. The present disclosure can reduce the processing cost of the map construction and positioning tasks.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular, to a map construction method, a positioning method, a map construction device, a positioning device, a computer readable storage medium and an electronic device. BACKGROUND

[0002] With the development of the technical field of Internet of Things, the demand for positioning services has surged. In the related tasks of positioning services, it is often necessary to provide an environment map or a beacon position in advance, and a laser sensor or a vision sensor can be used to realize mapping and positioning.

[0003] However, whether the sensor is a laser or a vision, scanning, feature matching and other operations need to be performed, and the overall cost is high. SUMMARY

[0004] The present disclosure provides a map construction method, a positioning method, a map construction device, a positioning device, a computer readable storage medium and an electronic device, thereby at least partially overcoming the problem of high cost of positioning tasks.

[0005] According to a first aspect of the present disclosure, a map construction method is provided, comprising: acquiring inertial data and WiFi data sensed for a plurality of map construction behaviors; determining trajectory data of each map construction behavior using the inertial data; determining a location of a point of interest in a map construction scene according to the trajectory data of each map construction behavior; and performing similarity clustering on the WiFi data of each point of interest location to construct a point of interest map.

[0006] According to a second aspect of the present disclosure, a positioning method is provided, comprising: acquiring current WiFi data; comparing the current WiFi data with WiFi data in a point of interest map, and determining a current point of interest positioning result according to the comparison; wherein the point of interest map is constructed according to the above map construction method.

[0007] According to a third aspect of the present disclosure, a map construction device is provided, comprising: a data acquisition module configured to acquire inertial data and WiFi data sensed for a plurality of map construction behaviors; a trajectory determination module configured to determine trajectory data of each map construction behavior using the inertial data; a point of interest determination module configured to determine a location of a point of interest in a map construction scene according to the trajectory data of each map construction behavior; and a point of interest map construction module configured to perform similarity clustering on the WiFi data of each point of interest location to construct a point of interest map.

[0008] According to a fourth aspect of the present disclosure, a positioning device is provided, comprising: a WiFi data acquisition module configured to acquire current WiFi data; a point of interest positioning module configured to compare the current WiFi data with WiFi data in a point of interest map, and determine a current point of interest positioning result according to the comparison; wherein the point of interest map is constructed according to the above map construction method.

[0009] According to a fifth aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program, the program being executed by a processor to implement the above map construction method or positioning method.

[0010] According to a sixth aspect of the present disclosure, an electronic device is provided, comprising a processor; a memory configured to store one or more programs, the one or more programs being executed by the processor to implement the above map construction method or positioning method.

[0011] In the technical solution provided by some embodiments of the present disclosure, the inertial data and WiFi data sensed for a plurality of map construction behaviors are acquired, the trajectory data of each map construction behavior is determined by using the inertial data, the positions of points of interest in a map construction scene are determined according to the trajectory data of each map construction behavior, and the WiFi data of each point of interest position is subjected to similarity clustering to construct a point of interest map. On the one hand, compared with the scheme of visual mapping and positioning, the present scheme can reduce the calculation cost and the time consumption of mapping and positioning to a certain extent, since there is no operation such as visual feature matching. On the other hand, the present scheme can realize data acquisition of mapping and positioning by using only an inertial unit and a WiFi unit, so that the data acquisition cost can be reduced. On the other hand, the present scheme can guarantee the correctness and accuracy of data processing by performing similarity clustering of WiFi data on the trajectory determined based on the inertial data.

[0012] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0013] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings. In the drawings:

[0014] Figure 1 a schematic diagram showing the system architecture of the positioning scheme of the embodiment of the present disclosure;

[0015] Figure 2A schematic diagram of a map building system according to an embodiment of the present disclosure is shown;

[0016] Figure 3 A flowchart illustrating a map construction method according to an exemplary embodiment of the present disclosure is shown schematically;

[0017] Figure 4 A schematic diagram of a map building scenario according to an embodiment of this disclosure is shown;

[0018] Figure 5 A schematic diagram of a map building scenario according to another embodiment of this disclosure is shown;

[0019] Figure 6 A schematic diagram illustrating the identification of behavior types for map building activities according to an embodiment of this disclosure is shown;

[0020] Figure 7 A schematic diagram illustrating the use of inertial data to determine a trajectory according to an embodiment of this disclosure is shown;

[0021] Figure 8 A schematic diagram of the trajectory alignment process according to an embodiment of this disclosure is shown;

[0022] Figure 9 It shows the relationship with Figure 4 A schematic diagram showing the effect of trajectory alignment for the corresponding scene;

[0023] Figure 10 It shows the relationship with Figure 5 A schematic diagram showing the effect of trajectory alignment for the corresponding scene;

[0024] Figure 11 A flowchart illustrating the determination of a dataset of points of interest according to an embodiment of this disclosure is shown;

[0025] Figure 12 A flowchart illustrating the modification of a point-of-interest dataset to construct a point-of-interest map according to an embodiment of this disclosure is shown;

[0026] Figure 13 A flowchart illustrating the entire process of the map construction method according to an embodiment of this disclosure is provided.

[0027] Figure 14 A flowchart illustrating a positioning method according to an exemplary embodiment of the present disclosure is shown schematically;

[0028] Figure 15 A block diagram of a map building apparatus according to an exemplary embodiment of the present disclosure is shown schematically;

[0029] Figure 16 A block diagram of a map building apparatus according to another exemplary embodiment of the present disclosure is shown schematically;

[0030] Figure 17A block diagram of a positioning device according to an example embodiment of the present disclosure is schematically shown;

[0031] Figure 18 A block diagram of a positioning device according to another example embodiment of the present disclosure is schematically shown;

[0032] Figure 19 A block diagram of an electronic device according to an example embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0033] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in one or more embodiments. In the following description, numerous specific details are recited to provide a thorough understanding of embodiments of the disclosure. One skilled in the relevant art, however, will recognize that the disclosure can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures have not been described in detail to avoid obscuring aspects of the present disclosure.

[0034] Furthermore, the accompanying drawings are only schematic and are non-limiting exact representations of embodiments of the present disclosure. Identical components have been given the same reference numerals, and thus will not be described again. Some of the blocks in the flowcharts are functional blocks that can be implemented by software, hardware, or a combination of software and hardware. Some of the blocks in the flowcharts can be implemented as software code to be executed by a processor using the facilities of the operating system and / or device drivers.

[0035] The flowcharts shown in the figures are merely examples and do not necessarily include all steps. For example, some steps can be combined, some steps can be omitted, and some steps can be performed in a different order than shown. In addition, all terms "first", "second", and the like, are used for the purpose of differentiating between two or more items, and should not be construed as limiting the present disclosure.

[0036] The point of interest map of the embodiments of the present disclosure can include the following: on the one hand, the positional relationship of the user in the scene relative to the position of each point of interest, wherein the position information of the point of interest and the trajectory information between the points of interest are unified into the same coordinate system (such as the world coordinate system); on the other hand, the semantic information (such as bed, sofa, etc.) of the position of the point of interest is determined according to the WiFi radio fingerprint information, the user behavior information (such as the static / moving state, the duration, etc.), and the system-side monitoring to application information (the terminal use state of the user, such as listening to music, watching movies, etc.); on the other hand, the semantic information of different points of interest, the positional relationship, and the WiFi radio fingerprint information required for positioning are stored.

[0037] Figure 1 A schematic diagram of the system architecture of the positioning scheme of the embodiments of the present disclosure is shown. Referring to Figure 1 The system architecture of the positioning scheme of the embodiments of the present disclosure can include a terminal device 11, a terminal device 12, and a cloud 13. The present disclosure does not limit the device type of the terminal device 11 and the terminal device 12, which can be, for example, a smart phone, a tablet computer, a smart wearable device, a robot, a robotic dog, etc. The device type of the terminal device 11 and the terminal device 12 can be the same or different.

[0038] In addition, the terminal device can also be referred to as a mobile device, a mobile terminal, etc. The cloud can also be referred to as a server, a service end, etc.

[0039] Referring to Figure 1 The terminal device 11 can be a device for building a point of interest map, and the terminal device 12 can be a device for positioning using the point of interest map.

[0040] According to some embodiments of the present disclosure, the terminal device 11 can build a point of interest map using the map building scheme of the embodiments of the present disclosure, and directly send the point of interest map to the terminal device 12, so that the terminal device 12 realizes point of interest positioning according to the point of interest map. It can be seen that in these embodiments, the cloud 13 can not be involved.

[0041] According to other embodiments of the present disclosure, the terminal device 11 can build a point of interest map using the map building scheme of the embodiments of the present disclosure, and send the point of interest map to the cloud 13. Thus, the terminal device 12 can obtain the point of interest map from the cloud 13, so that the terminal device 12 realizes point of interest positioning according to the point of interest map.

[0042] Furthermore, terminal device 11 and terminal device 12 can be the same device. That is, terminal device 11 can construct a point-of-interest map using the map construction scheme disclosed herein. This point-of-interest map can be stored on terminal device 11 or sent by terminal device 11 to cloud 13 for storage. When terminal device 11 re-enters the scene, terminal device 11 can locate itself based on the point-of-interest map.

[0043] It should be noted that, in addition to the terminal device 11 being able to execute the scheme for constructing point-of-interest maps according to the present disclosure, the cloud 13 can also execute the scheme for constructing point-of-interest maps according to the present disclosure.

[0044] refer to Figure 1 Terminal device 11 can function as a data acquisition device to collect data required for implementing the map construction scheme of this disclosure, namely inertial data and WiFi data. In this case, to accelerate algorithm implementation, there can be multiple terminal devices 11 collecting data, so as to collect multiple sets of data simultaneously. Terminal device 11 can send the collected data to cloud 13, which will then execute the map construction scheme of this disclosure to construct a point-of-interest map. Subsequently, cloud 13 can send the constructed point-of-interest map to terminal device 11 and / or terminal device 12 for subsequent positioning tasks.

[0045] The following description uses a terminal device executing the map construction method of this disclosure as an example.

[0046] Figure 2 A schematic diagram of a map building system according to an embodiment of the present disclosure is shown. (Reference) Figure 2 The map building system 20 can be configured in a terminal device. Specifically, the map building system 20 may include an inertial unit 21, a WiFi unit 22, and a processor 23. The inertial unit 21 may also be referred to as an IMU (Inertial Measurement Unit) 21, an inertial sensor 21, etc.

[0047] In the map building scheme of this disclosure, for each of the multiple map building behaviors, inertial data can be collected using the inertial unit 21 and WiFi data can be collected using the WiFi unit 22.

[0048] The processor 23 can acquire inertial data collected by the inertial unit 21 and WiFi data collected by the WiFi unit 22. In addition, the processor 23 can also acquire inertial data and WiFi data sensed by other terminal devices in response to other map building activities.

[0049] Next, the processor 23 can determine trajectory data of each map construction behavior by using the obtained inertial data, and determine the location of the point of interest in the map construction scene according to the trajectory data of each map construction behavior.

[0050] Subsequently, the processor 23 can determine WiFi data of each point of interest location, and perform similarity clustering on the WiFi data to construct a point of interest map.

[0051] Based on the map construction system of the embodiments of the present disclosure, on the one hand, compared with the scheme of visual mapping and positioning, the scheme of the present disclosure can reduce the calculation cost and reduce the time consumption of mapping and positioning to a certain extent due to the absence of visual feature matching and other operations; on the other hand, the scheme of the present disclosure can realize data acquisition of mapping and positioning by using only inertial units and WiFi units, thereby reducing the data acquisition cost; on the other hand, the scheme of the present disclosure can perform similarity clustering on WiFi data based on the trajectory determined based on inertial data, thereby ensuring the correctness and accuracy of data processing.

[0052] In order to illustrate the details of the embodiments of the present disclosure, the map construction method and the positioning method of the embodiments of the present disclosure are still described by taking the terminal device as an example.

[0053] Figure 3 A flowchart of a map construction method of an exemplary embodiment of the present disclosure is schematically shown. Referring to Figure 3 The map construction method can include the following steps:

[0054] S32. Obtain the inertial data and WiFi data sensed for a plurality of map construction behaviors.

[0055] In the exemplary embodiments of the present disclosure, the map construction behavior can be a behavior for obtaining data required for map construction. Specifically, in the map construction scene, the map construction behavior can be a behavior of the terminal device collecting data in the scene. For example, a user can hold the terminal device to travel or be stationary in the scene. For another example, the terminal device can be configured on an automatic traveling device (such as a robot), and the automatic traveling device can travel or be stationary in the scene. For another example, the terminal device can be an automatic traveling device, which can travel or be stationary in the scene by itself. In addition, the traveling or stationary manner corresponding to different map construction behaviors is different.

[0056] The map construction scene is a scene for constructing a map, and the map construction scene of the embodiments of the present disclosure includes but is not limited to indoor positioning scenes such as home scenes, school scenes, hospital scenes, and shopping mall scenes, and can also include outdoor scenes such as squares and parks, which are not limited by the present disclosure.

[0057] Figure 4A schematic diagram of a map construction scenario is shown. Referring to Figure 4 , the scenario includes three adjacent rooms, and there are walls between the rooms. One or two seats in each room are as the point of interest positions, for example, the point of interest positions of room A include 1 seat and 2 seat; the point of interest positions of room B include 3 seat and 4 seat; and the point of interest positions of room C include 5 seat.

[0058] For the map construction scenario of Figure 4 , referring to Table 1, 16 map construction behaviors are exemplarily given taking a mobile phone as an example.

[0059] Table 1

[0060]

[0061]

[0062] Figure 5 A schematic diagram of a map construction scenario of another embodiment of the present disclosure is shown. Compared with the scenario of Figure 4 , the scenario shown in Figure 5 may be a scenario without wall barriers in space. The points 1, 2 and 3 are all point of interest positions.

[0063] For the map construction scenario of Figure 5 , referring to Table 2, 3 map construction behaviors are exemplarily given taking a mobile phone as an example.

[0064] Table 2

[0065]

[0066]

[0067] It should be understood that the above Table 1 and Table 2 are only exemplary descriptions of map construction behaviors, and the present disclosure does not limit the type, number, moving / stationary manner, behavior holding time, etc. of the map construction behaviors.

[0068] In the process of performing the map construction behaviors, the terminal device can sense the inertial data through the inertial unit equipped therein and sense the WiFi data through the WiFi unit equipped therein. It should be noted that for each map construction behavior, the inertial data and the WiFi data are sensed.

[0069] For example, the frame rate of the inertial data is 200 Hz, and the data format is phone_timestamp(ns)gyrox gyroy gyroz accx accy accz magx magy magz gravx gravy gravz qx qy qz qw flag, where phone_timestamp(ns) represents the timestamp (ns) of collecting the mobile phone, {gyrox gyroy gyroz} represents the gyroscope data (rad / s) in the mobile phone sensor coordinate system, {accx accy accz} represents the accelerometer data (m / s^2) in the mobile phone sensor coordinate system, {magx magy magz} represents the magnetometer data (μT) in the mobile phone sensor coordinate system, {gravx gravy gravz} represents the gravitational acceleration (m / s^2) in the mobile phone sensor coordinate system, {qx qy qz qw} represents the rotation from the mobile phone sensor coordinate system to the north-east-sky coordinate system, and flag is the timestamp flag.

[0070] The frame rate of the WiFi data is 0.7 Hz, and the data format is phone_timestamp(ns)timestamp_from_wifi_scan(μs)bssid level ssid, where phone_timestamp(ns) has the same meaning as above, timestamp_from_wifi_scan(μs) represents the mobile phone timestamp (μs) of scanning to the AP (Access Point), bssid represents the mac address of the AP, level represents the received signal strength, and ssid represents the AP name.

[0071] After obtaining the inertial data, the terminal device can identify the behavior type of the map construction behavior based on the inertial data. In the embodiments of the present disclosure, the behavior type of the map construction behavior can be divided into a static state and a motion state.

[0072] Figure 6 The schematic diagram of identifying the behavior type of the map construction behavior in the embodiments of the present disclosure is shown. Referring to Figure 6 , the inertial unit can include an accelerometer, a gyroscope, and a magnetometer. The inertial data output by the inertial unit can be input into the behavior recognition model, and the behavior recognition result of the map construction behavior can be obtained by the behavior recognition model online inference. The behavior recognition model may, for example, be an LSTM (Long Short-Term Memory) model, and the structure, parameters, etc. of the model are not limited by the present disclosure.

[0073] S34. Determine the trajectory data of each map construction behavior using the inertial data.

[0074] In the example embodiment of the present disclosure, the terminal device can determine the trajectory of each map construction behavior by using the inertial data obtained in step S32. That is, the terminal device can complete PDR (Pedestrian Dead Reckoning) by using the inertial data.

[0075] Specifically, on one hand, the terminal device can perform direction estimation on the map construction behavior by using the inertial data to obtain a direction estimation result. On the other hand, the terminal device can perform translation estimation on the map construction behavior by using the inertial data to obtain a translation estimation result. For the translation estimation process, the terminal device can multiply the direction estimation result by the inertial data to obtain intermediate data, and perform translation estimation on the map construction behavior by using the intermediate data to obtain the translation estimation result.

[0076] Next, the terminal device can determine the trajectory data of the map construction behavior in combination with the direction estimation result and the translation estimation result.

[0077] Figure 7 A schematic diagram of the process of determining the trajectory data according to the embodiment of the present disclosure is shown. Referring to Figure 7 The model can be composed of two parts. One part is for direction estimation, including a sensor denoising network and a Kalman filter, wherein the difference between the integral rotation result output by the Kalman filter and the true value is taken as an error function. The other part is for translation estimation, including a multiplier and a translation regression network, wherein the difference between the translation result output by the translation regression network and the true value is taken as an error function. It can be understood that the true value required by the model can be obtained through artificial fine-tuning and correction, which is not limited in the present disclosure.

[0078] After the inertial data output by the inertial unit is processed by the model composed of the above two parts, 6DOF (6 degrees of freedom) pose data can be obtained, i.e., the trajectory data of the map construction behavior.

[0079] S36. Determine the location of the point of interest in the map construction scene according to the trajectory data of each map construction behavior.

[0080] Since the coordinate systems of the trajectory data of each map construction behavior can be inconsistent, before determining the location of the point of interest, the terminal device can perform trajectory alignment on each trajectory data. For example, the trajectory data of each map construction behavior can be converted to the world coordinate system.

[0081] The terminal device can perform BA (Bundle Adjustment) optimization on the trajectory data to achieve trajectory alignment. Specifically, the terminal device can take the trajectory data as the true value, and align the WiFi data along the time axis. The terminal device can down-sample the trajectory data, and calculate an n*n similarity matrix for n-dimensional WiFi data. If the similarity of two WiFi data is greater than a similarity threshold, the index, time and similarity of the WiFi are recorded. Subsequently, the terminal device can construct a Ceres solving problem in combination with the trajectory data, that is, construct a cost function, construct an optimization problem, and Solve to solve, where the optimization term is the initial point position X, Y and relative rotation of each trajectory. Thus, the trajectory alignment is completed.

[0082] Taking trajectory alignment of two trajectory data as an example, any two behaviors in the plurality of map construction behaviors are denoted as a first map construction behavior and a second map construction behavior. The first map construction behavior corresponds to first trajectory data, and the second map construction behavior corresponds to second trajectory data.

[0083] The terminal device can determine the similarity of the first WiFi data corresponding to the first trajectory data and the second WiFi data corresponding to the second trajectory data, and construct a residual function according to the similarity and the two-dimensional coordinates of the first trajectory data and the second trajectory data. In addition, the terminal device can determine an optimization term according to the initial point positions of the trajectory data of the plurality of map construction behaviors. Subsequently, the terminal device can perform trajectory alignment on the first trajectory data and the second trajectory data according to the residual function, the optimization term and the Ceres loss function. The residual function is shown in formula 1:

[0084]

[0085] wherein e i represents the residual function of the i th point position; and represent the two-dimensional coordinates of the i th point position corresponding to the first trajectory data and the second trajectory data, respectively; X m and X n represent the initial two-dimensional coordinates corresponding to the first trajectory data and the second trajectory data, respectively; sim mnn represents the similarity value of the WiFi data corresponding to the first trajectory data and the second trajectory data.

[0086] The Solve solving can be completed based on the above residual function, loss function and optimization term, and thus the trajectory alignment is completed.

[0087] For the above process of calculating the similarity of WiFi data, the disclosure can calculate in the manner of cosine similarity. In addition, when using RSSI values to calculate the similarity, it is difficult to effectively determine the correlation of each other due to the problems such as the data collected at adjacent times being similar when the distance is close. After multiple experiments, it is found that combining RSSI and MAC address can effectively improve the calculation accuracy of the similarity. Therefore, the embodiment of the disclosure calculates the similarity matrix of WiFi data in the manner of combining RSSI and MAC data.

[0088] The calculation of the similarity of WiFi data can include point similarity calculation and line similarity calculation. The WiFi point similarity can be determined by referring to formula 2 and formula 3.

[0089]

[0090]

[0091] Wherein, map_a[i], map_b[i] are the WiFi fingerprints corresponding to the two variables a, b at the index i, that is, the RSSI value; cnt_a[i], cnt_b[i] corresponding to the WiFi address are the number of times of appearance of WiFi corresponding to the two variables a, b at the index i.

[0092] The WiFi line similarity can be determined by referring to formula 4 and formula 5.

[0093] cosine = cosine + (map_a[i] + 90.0) * (map_b[i] + 90.0) (formula 4)

[0094]

[0095] The following refers to Figure 8 The process of trajectory alignment of the embodiment of the disclosure is described. Referring to Figure 8 , the WiFi data and the trajectory data are input as data, and the terminal device can align the WiFi data with the trajectory data as the axis of time. The terminal device can downsample the trajectory data and obtain the radius (mag) and the angle (theta). In addition, the terminal device can calculate the point similarity and the line similarity respectively. Subsequently, the terminal device can sum (save) the above data to perform BA optimization, thereby realizing trajectory alignment.

[0096] Figure 9 The trajectory alignment effect diagram corresponding to the scene is shown. Figure 4 The trajectory alignment effect diagram corresponding to the scene is shown. Referring to Figure 10 The trajectory alignment effect diagram corresponding to the scene is shown. Figure 5 The trajectory alignment effect diagram corresponding to the scene is shown. Referring to Figure 9 andFigure 10 By means of the above trajectory alignment processing, trajectory data of different map construction behaviors can be unified into a unified coordinate system (e.g., a world coordinate system) so as to apply the trajectory data to subsequent algorithms.

[0097] After obtaining the aligned trajectory data, the terminal device can determine a point of interest position in the map construction scene according to the aligned trajectory data of each map construction behavior.

[0098] According to some embodiments of the present disclosure, the terminal device can determine trajectory data representing static from the aligned trajectory data of each map construction behavior, and determine a scene position corresponding to the trajectory data representing static as a point of interest position in the map construction scene. The trajectory data representing static can include trajectory data corresponding to the terminal device being parked in a small area for a predetermined length of time. For example, the trajectory data corresponding to the terminal device being parked in an area with an area less than an area threshold for a predetermined length of time can be defined.

[0099] Specifically, the terminal device can determine the trajectory data representing static in combination with the above determined behavior type. For example, for data with a determined behavior type of static, the trajectory data representing static can be obtained after the alignment conversion operation in the world coordinate system.

[0100] According to other embodiments of the present disclosure, the terminal device can determine trajectory data representing the terminal device moving violently in a predetermined area from the aligned trajectory data of each map construction behavior, and determine a scene position corresponding to the data as a point of interest position in the map construction scene. For example, in a sports scene (e.g., a gym), the user's movement position can also be a point of interest position.

[0101] S38. Perform similarity clustering on the WiFi data of each point of interest position to construct a point of interest map.

[0102] First, the terminal device can determine a joint point set of the point of interest position through a similarity matrix of the WiFi data.

[0103] It can be understood that the similarity matrix of the WiFi data mentioned here is the similarity matrix determined in step S36 for the trajectory alignment process, i.e., the similarity matrix determined by the cosine similarity and according to the WiFi address data and the WiFi name data.

[0104] For each value in the n*n similarity matrix, the value is 0 to 1. The terminal device can determine a position association point corresponding to a similarity greater than a similarity threshold (e.g., 0.99, etc.) from the similarity matrix, and generate an association point set of the point of interest position using the position association points.

[0105] Next, the terminal device can cluster the associated point sets of the respective point of interest locations to construct a point of interest map.

[0106] According to some embodiments of the present disclosure, the terminal device can determine the intersection over union of the associated point sets of the respective point of interest locations, where the intersection over union represents the ratio of the intersection to the union of the sets. Subsequently, the terminal device can cluster the associated point sets of the respective point of interest locations according to the intersection over union to construct a point of interest map. Specifically, if the intersection over union is greater than an intersection over union threshold, the two point locations are classified into the same class. In addition, the terminal device can also eliminate ambiguous point locations.

[0107] In addition to clustering by using the intersection over union, the terminal device can also implement clustering in the manner of, for example, graph cut, which is not limited by the present disclosure.

[0108] Reference Figure 11 The process of determining the point of interest data set according to the embodiments of the present disclosure is described by taking WiFi data and trajectory data as inputs of the algorithm.

[0109] In step S1102, the terminal device can determine static data.

[0110] In step S1104, the terminal device can eliminate outliers in the static data, where the outliers refer to data that deviates significantly from other data.

[0111] In step S1106, the terminal device can obtain RSSI data and MAC data from the WiFi data.

[0112] In step S1108, the terminal device can calculate the cosine similarity of the WiFi data by using the RSSI data and the MAC data to determine a similarity matrix of the WiFi data.

[0113] In step S1110, the terminal device can determine the associated point sets according to the similarity matrix of the WiFi data.

[0114] In step S1112, the terminal device determines the intersection over union of the associated point sets and clusters the point locations according to the intersection over union.

[0115] In step S1114, the terminal device can establish a point of interest data set according to the clustering result based on the intersection over union.

[0116] The terminal device can directly generate a point of interest map according to the above point of interest data set to provide a positioning basis for subsequent algorithms. However, the above point of interest map can still have the problem of insufficient accuracy, for example, it is difficult to distinguish two point of interests in the same room. In view of this, the present disclosure also provides a scheme of modifying the above point of interest data set to obtain a point of interest map.

[0117] In the example embodiment of the present disclosure, the terminal device can determine the transformation matrix of the trajectory based on the trajectory data, and correct the point of interest data set by using the similarity between the transformation matrices. Since the present disclosure scheme is processed in the trajectory dimension rather than the point dimension, the clustering loss of the point of interest is small.

[0118] That is, after clustering the associated point set of each point of interest position to obtain the point of interest data set, the terminal device can correct the point of interest data set by using the trajectory data to obtain the point of interest map.

[0119] Since the blocking object (such as a wall) has a great influence on the construction process of the point of interest map, the scenes with and without the blocking object are processed respectively.

[0120] In the case where the map construction scene contains the blocking object, first, the terminal device can determine the first transformation matrix related to the trajectory according to the trajectory data. Specifically, each row of the trajectory data of the embodiment of the present disclosure represents position data, a trajectory contains multiple position data, and the first transformation matrix is a transformation matrix determined in units of trajectories.

[0121] Next, the terminal device can determine the similarity matrix of the first transformation matrix, and correct the point of interest data set according to the similarity matrix of the first transformation matrix to obtain the point of interest map. Specifically, the terminal device can cluster the points of interest corresponding to the similarity greater than the similarity threshold in the similarity matrix. The similarity threshold can be the same as the similarity threshold for constructing the associated point threshold, or it can be different, and the present disclosure does not limit the value.

[0122] In the case where the map construction scene does not contain the blocking object, first, the terminal device can determine the second transformation matrix related to the relative distance of each point in the trajectory according to the trajectory data. Specifically, the second transformation matrix is for the relative distance of each point in the trajectory.

[0123] Next, the terminal device can determine the similarity matrix of the second transformation matrix, and correct the point of interest data according to the similarity matrix of the second transformation matrix to obtain the point of interest map. Specifically, the terminal device can cluster the points of interest corresponding to the similarity greater than the similarity threshold in the similarity matrix.

[0124] Taking the point of interest data set as the input of the correction algorithm, the following refers to Figure 12 The process of correcting the point of interest data set according to the embodiment of the present disclosure is described.

[0125] In step S1202, the terminal device can solve the transformation matrix of the trajectory data.

[0126] In step S1204, the terminal device can determine whether there is a wall in the map construction scene. If yes, step S1206 is performed; if not, step S1208 is performed.

[0127] In step S1206, the terminal device can determine a similarity matrix related to the trajectory.

[0128] In step S1208, the terminal device can determine a similarity matrix related to the relative distance of the point.

[0129] In step S1210, the terminal device can cluster the point in the similarity matrix which is greater than the similarity threshold.

[0130] In step S1212, the terminal device can determine the point of interest map according to the clustering result of step S1210.

[0131] In addition, as the input of the correction algorithm, the terminal device can also optimize the point of interest data in advance, for example, the point with abnormal WiFi name can be removed according to the WiFi address, etc. The present disclosure does not make any limitation.

[0132] The point of interest map of the embodiment of the present disclosure can be output in the format of, for example, json, for positioning or other downstream calls.

[0133] The following refers to Figure 13 The map construction process of the embodiment of the present disclosure is described.

[0134] In step S1302, the terminal device can obtain the inertial data and WiFi data sensed for a plurality of map construction behaviors.

[0135] In step S1304, the terminal device can determine the behavior type contained in each map construction behavior according to the inertial data.

[0136] In step S1306, the terminal device can determine the trajectory data of each map construction behavior according to the inertial data.

[0137] In step S1308, the terminal device can perform trajectory alignment on the trajectory data of each map construction behavior according to the trajectory data and the WiFi data.

[0138] In step S1310, the terminal device can perform a data preprocessing process. In one aspect, the data preprocessing process can include determining static points and dynamic trajectories based on behavior types. In another aspect, the data preprocessing process can also include canceling a reset operation of an inertial unit to avoid the inertial unit repeatedly recording data at static points and causing data abnormalities, and filtering the time of the dynamic trajectories. In still another aspect, the data preprocessing process can further include determining the relative distance and total duration of adjacent time points on the trajectory.

[0139] In step S1312, for the static points, the terminal device can determine a set of associated points of the point of interest by using a similarity matrix of the WiFi data.

[0140] In step S1314, the terminal device can cluster the set of associated points to obtain a point of interest data set.

[0141] In step S1316, the terminal device can correct the point of interest data set to construct a point of interest map.

[0142] Based on the above map construction method of the present disclosure, on the one hand, only inertial data and WiFi data are used as inputs, which greatly reduces the cost of the acquisition device. On the other hand, the behavior recognition of trajectory data and trajectory alignment operations ensure the correctness and accuracy of the data. On the other hand, the similarity matrix of WiFi data and the clustering algorithm of the intersection over union provide the possibility for point of interest clustering. Through the subsequent correction process, the clustering accuracy is improved, and a point of interest map with high accuracy is further provided for positioning and downstream modules. Especially for indoor scenes such as home, hospital, and shopping mall, the map construction scheme of the present disclosure has wide application value.

[0143] Further, the example embodiment also provides a positioning method using the point of interest map constructed by the above map construction method.

[0144] Figure 14 The flowchart schematically shows the positioning method of the example embodiment of the present disclosure. Referring to Figure 14 , the positioning method can include the following steps:

[0145] S142. Obtain current WiFi data.

[0146] In the example embodiment of the present disclosure, the current WiFi data includes WiFi name data, i.e., RSSI data.

[0147] Based on the above map construction scheme, the terminal device can also acquire inertial data, and determine the current trajectory data based on the inertial data, and then align the trajectory data with the WiFi data in time. In some scenarios, the trajectory data can be used to verify the matching of the following WiFi data.

[0148] S144. Comparing the current WiFi data with the WiFi data in the point of interest map, and determining the current point of interest positioning result according to the comparison; wherein, the point of interest map is constructed according to the above map construction method.

[0149] In the exemplary embodiments of the present disclosure, the terminal device can determine the similarity of the WiFi name data of the current WiFi data and the WiFi name data of the WiFi data in the point of interest map, and determine the current point of interest positioning result based on the similarity of the WiFi name data. For example, the point corresponding to the similarity greater than the similarity threshold (such as 0.9) is determined as the point of interest positioning result.

[0150] After determining the point of interest positioning result, the terminal device can determine the point of interest task corresponding to the current point of interest positioning result, and execute the point of interest task. Wherein, the point of interest task can be pre-configured, and when being at the point of the point of interest, the point of interest task is triggered automatically by the terminal device. For example, the point of interest task is to play music corresponding to the point of interest, start an application program corresponding to the point of interest, adaptively adjust the volume or brightness of the terminal device, etc., and the type of the point of interest task is not limited in the present disclosure.

[0151] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired result. In addition or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.

[0152] Further, the present example embodiment also provides a map construction device.

[0153] Figure 15 The block diagram of the map construction device of the exemplary embodiments of the present disclosure is schematically shown. Referring to Figure 15 According to the map construction device 15 of the exemplary embodiments of the present disclosure, the map construction device 15 can include a data acquisition module 151, a trajectory determination module 153, a point of interest determination module 155 and a point of interest map construction module 157.

[0154] Specifically, the data obtaining module 151 can be configured to obtain inertial data and WiFi data sensed for a plurality of map construction behaviors; the trajectory determining module 153 can be configured to determine trajectory data of each map construction behavior by using the inertial data; the point of interest determining module 155 can be configured to determine a point of interest position in a map construction scene according to the trajectory data of each map construction behavior; and the point of interest map constructing module 157 can be configured to perform similarity clustering on the WiFi data of each point of interest position to construct a point of interest map.

[0155] According to an example embodiment of the present disclosure, the trajectory determining module 153 can be configured to perform: direction estimation on the map construction behavior by using the inertial data to obtain a direction estimation result; translation estimation on the map construction behavior by using the inertial data to obtain a translation estimation result; and combination of the direction estimation result and the translation estimation result to determine the trajectory data of the map construction behavior.

[0156] According to an example embodiment of the present disclosure, the trajectory determining module 153 can be configured to perform: multiplication of the direction estimation result and the inertial data to obtain intermediate data; and translation estimation on the map construction behavior by using the intermediate data to obtain the translation estimation result.

[0157] According to an example embodiment of the present disclosure, the point of interest determining module 155 can be configured to perform: trajectory alignment on the trajectory data of each map construction behavior to obtain aligned trajectory data; and determination of a point of interest position in a map construction scene according to the aligned trajectory data of each map construction behavior.

[0158] According to an example embodiment of the present disclosure, the plurality of map construction behaviors includes a first map construction behavior and a second map construction behavior, the first map construction behavior corresponding to first trajectory data, and the second map construction behavior corresponding to second trajectory data. In this case, the process of the point of interest determining module 155 performing trajectory alignment on the first trajectory data and the second trajectory data can be configured to perform: determination of similarity of first WiFi data corresponding to the first trajectory data and second WiFi data corresponding to the second trajectory data; construction of a residual function according to the similarity of the first WiFi data and the second WiFi data and two-dimensional coordinates of the first trajectory and the second trajectory; determination of an optimization term according to initial point positions of the trajectory data of the plurality of map construction behaviors; and trajectory alignment on the first trajectory data and the second trajectory data according to the residual function, the optimization term, and a Cauchy loss function.

[0159] According to an example embodiment of the present disclosure, the point of interest determining module 155 can be configured to perform: determination of trajectory data representing statics from the aligned trajectory data of each map construction behavior; and determination of a scene position corresponding to the trajectory data representing statics as a point of interest position in a map construction scene.

[0160] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: determining a set of location association points of the point of interest locations from the similarity matrix of the WiFi data; clustering the set of location association points of each point of interest location to construct the point of interest map.

[0161] According to an example embodiment of the present disclosure, referring to Figure 16 , compared with the map construction module 15, the map construction module 16 can further include a similarity matrix determination module 161.

[0162] Specifically, the similarity matrix determination module 161 can be configured to perform: determining WiFi address data and WiFi name data from the WiFi data; determining the similarity matrix of the WiFi data according to the WiFi address data and the WiFi name data.

[0163] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: determining a location association point corresponding to a similarity greater than a similarity threshold from the similarity matrix of the WiFi data; generating a set of location association points of the point of interest locations according to the location association point.

[0164] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: determining an intersection-over-union of the set of location association points of each point of interest location; clustering the set of location association points of each point of interest location according to the intersection-over-union of the set of location association points of each point of interest location to construct the point of interest map.

[0165] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: clustering the set of location association points of each point of interest location to obtain a point of interest data set; correcting the point of interest data set by using the trajectory data to obtain the point of interest map.

[0166] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: in a case where the map construction scene contains an obstacle, determining a first transformation matrix related to the trajectory according to the trajectory data; determining a similarity matrix of the first transformation matrix, and correcting the point of interest data set according to the similarity matrix of the first transformation matrix to obtain the point of interest map.

[0167] According to an example embodiment of the present disclosure, the point of interest map construction module 157 can be configured to perform: in a case where the map construction scene does not contain an obstacle, determining a second transformation matrix related to the relative distance of each point in the trajectory according to the trajectory data; determining a similarity matrix of the second transformation matrix, and correcting the point of interest data set according to the similarity matrix of the second transformation matrix to obtain the point of interest map.

[0168] Since the functional modules of the map building apparatus in this embodiment are the same as those in the above-described method embodiments, they will not be described again here.

[0169] Furthermore, this example embodiment also provides a positioning device.

[0170] Figure 17 A block diagram schematically illustrates a positioning device according to an exemplary embodiment of the present disclosure. (Reference) Figure 17 The positioning device 17 according to an exemplary embodiment of the present disclosure may include a WiFi data acquisition module 171 and a point of interest positioning module 173.

[0171] Specifically, the WiFi data acquisition module 171 can be used to acquire the current WiFi data; the point of interest (POI) positioning module 173 can be used to compare the current WiFi data with the WiFi data in the POI map, and determine the current POI positioning result based on the comparison; wherein, the POI map is constructed according to the above map construction method.

[0172] According to an exemplary embodiment of this disclosure, the point of interest localization module 173 can be configured to perform: determining the similarity between the WiFi name data of the current WiFi data and the WiFi name data of the WiFi data in the point of interest map; and determining the current point of interest localization result based on the similarity of the WiFi name data.

[0173] According to exemplary embodiments of this disclosure, reference is made to Figure 18 Compared to the positioning device 17, the positioning device 18 may also include a point of interest task execution module 181.

[0174] Specifically, the point of interest task execution module 181 can be configured to: determine the point of interest task corresponding to the current point of interest location result; and execute the point of interest task.

[0175] Since the functional modules of the positioning device in this embodiment are the same as those in the above-described method embodiments, they will not be described again here.

[0176] Figure 19 A schematic diagram is shown that is suitable for implementing exemplary embodiments of the present disclosure. The terminal device of the exemplary embodiments of the present disclosure can be configured as follows: Figure 19 In the form of. It should be noted that, Figure 19 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0177] The electronic device disclosed herein includes at least a processor and a memory, the memory being used to store one or more programs, which, when executed by the processor, enable the processor to implement the map building method or positioning method of the exemplary embodiments of this disclosure.

[0178] Specifically, such as Figure 19 As shown, the electronic device 190 may include: a processor 1910, internal memory 1921, external memory interface 1922, Universal Serial Bus (USB) interface 1930, charging management module 1940, power management module 1941, battery 1942, antenna 1, antenna 2, mobile communication module 1950, wireless communication module 1960, audio module 1970, sensor module 1980, display screen 1990, camera module 1991, indicator 1992, motor 1993, buttons 1994, and a Subscriber Identification Module (SIM) card interface 1995, etc. The sensor module 1980 may include inertial sensors, depth sensors, pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, accelerometers, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, and bone conduction sensors, etc.

[0179] It is understood that the structures illustrated in the embodiments of this disclosure do not constitute a specific limitation on the electronic device 190. In other embodiments of this disclosure, the electronic device 190 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0180] Processor 1910 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors. Additionally, processor 1910 may include memory for storing instructions and data.

[0181] The electronic device 190 can implement a photographing function through an ISP, a camera module 1991, a video codec, a GPU, a display screen 1990, and an application processor, and the like. In some embodiments, the electronic device 190 can include 1 or N camera modules 1991, N being a positive integer greater than 1, and if the electronic device 190 includes N cameras, one of the N cameras is a main camera.

[0182] The internal memory 1921 can be used to store computer executable program codes including instructions. The internal memory 1921 can include a program storage area and a data storage area. The external memory interface 1922 can be used to connect with an external memory card, such as a Micro SD card, to expand the memory capacity of the electronic device 190.

[0183] The present disclosure also provides a computer readable storage medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device.

[0184] The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0185] The computer readable storage medium can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber, RF, and the like, or any suitable combination of the above.

[0186] The computer readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the method as described in the embodiments of the present disclosure.

[0187] It should be noted that, although several modules or units of the devices for action execution are mentioned in the above detailed description, such division into modules or units is not mandatory. Indeed, according to an embodiment of the present disclosure, the features and functionalities of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functionalities of one of the above-described modules or units can be further divided into several modules or units.

[0188] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the concepts disclosed herein. It is intended that the present disclosure cover any and all variations of the present disclosure including combinations of features falling within the general scope of the disclosure and including equivalents thereof. The specification and examples are illustrative only and not restrictive of the present disclosure. The true scope and spirit of the present disclosure is indicated by the appended claims.

[0189] It should be understood that the present disclosure is not limited to the precise structures herein described and illustrated in the drawings and that various modifications and changes can be made therein without departing from the scope thereof. The scope of the present disclosure is indicated by the appended claims.

Claims

1. A map construction method characterized by comprising: The method comprises: acquiring inertial data and WiFi data sensed for a plurality of map construction behaviors; determining trajectory data of each of the map construction behaviors by using the inertial data; performing trajectory alignment on the trajectory data of each of the map construction behaviors to obtain aligned trajectory data, and determining a location of a point of interest in a map construction scene according to the aligned trajectory data of each of the map construction behaviors; performing similarity clustering on WiFi data of each of the locations of the points of interest to construct a point of interest map; wherein the plurality of map construction behaviors comprises a first map construction behavior and a second map construction behavior, the first map construction behavior corresponds to first trajectory data, and the second map construction behavior corresponds to second trajectory data; wherein the trajectory alignment on the first trajectory data and the second trajectory data comprises: determining a similarity of first WiFi data corresponding to the first trajectory data and second WiFi data corresponding to the second trajectory data; constructing a residual function according to the similarity of the first WiFi data and the second WiFi data and two-dimensional coordinates of the first trajectory data and the second trajectory data; determining an optimization item according to initial point locations of the trajectory data of each of the map construction behaviors; performing trajectory alignment on the first trajectory data and the second trajectory data according to the residual function, the optimization item, and a Cauchy loss function.

2. The map construction method according to claim 1, characterized by, The determination of the trajectory data of each of the map construction behaviors by using the inertial data comprises: performing direction estimation on the map construction behavior by using the inertial data to obtain a direction estimation result; performing translation estimation on the map construction behavior by using the inertial data to obtain a translation estimation result; combining the direction estimation result and the translation estimation result to determine the trajectory data of the map construction behavior.

3. The map construction method according to claim 2, characterized by, The translation estimation on the map construction behavior by using the inertial data to obtain a translation estimation result comprises: multiplying the direction estimation result and the inertial data to obtain intermediate data; performing translation estimation on the map construction behavior by using the intermediate data to obtain the translation estimation result.

4. The map construction method according to claim 1, characterized by, The determination of the location of the point of interest in the map construction scene according to the aligned trajectory data of each of the map construction behaviors comprises: determining trajectory data representing static from the aligned trajectory data of each of the map construction behaviors; determining a scene location corresponding to the trajectory data representing static as the location of the point of interest in the map construction scene.

5. The map construction method according to claim 1, characterized by, The similarity clustering on the WiFi data of each of the locations of the points of interest to construct the point of interest map comprises: determining a set of associated points of the locations of the points of interest through a similarity matrix of the WiFi data; performing clustering on the set of associated points of each of the locations of the points of interest to construct the point of interest map.

6. The map construction method according to claim 5, characterized by, The method further comprises: determining WiFi address data and WiFi name data from the WiFi data; determining a similarity matrix of the WiFi data according to the WiFi address data and the WiFi name data.

7. The map construction method according to claim 5, characterized by, The determination of the set of associated points of the locations of the points of interest through the similarity matrix of the WiFi data comprises: determine, from the similarity matrix of the WiFi data, a position association point corresponding to a similarity greater than a similarity threshold value with the point of interest position; generate a set of position association points of the point of interest position according to the position association point; 8. The map construction method according to claim 5, characterized by, cluster the set of position association points of each point of interest position to construct the point of interest map, including: determine an intersection and union ratio of the set of position association points of each point of interest position; cluster the set of position association points of each point of interest position according to the intersection and union ratio of the set of position association points of each point of interest position to construct the point of interest map.

9. The map construction method according to claim 5 or 8, characterized by, cluster the set of position association points of each point of interest position to construct the point of interest map, including: cluster the set of position association points of each point of interest position to obtain a point of interest data set; correct the point of interest data set using the trajectory data to obtain the point of interest map.

10. The map construction method according to claim 9, wherein, correct the point of interest data set using the trajectory data to obtain the point of interest map, including: in a case where the map construction scene contains an obstacle, determine a first transformation matrix related to a trajectory according to the trajectory data; determine a similarity matrix of the first transformation matrix, and correct the point of interest data set according to the similarity matrix of the first transformation matrix to obtain the point of interest map.

11. The map construction method according to claim 9, wherein correct the point of interest data set using the trajectory data to obtain the point of interest map, including: in a case where the map construction scene does not contain an obstacle, determine a second transformation matrix related to a relative distance of each point in a trajectory according to the trajectory data; determine a similarity matrix of the second transformation matrix, and correct the point of interest data set according to the similarity matrix of the second transformation matrix to obtain the point of interest map.

12. A positioning method characterized by, including: obtain current WiFi data; compare the current WiFi data with WiFi data in a point of interest map, and determine a current point of interest positioning result according to the comparison; wherein the point of interest map is constructed according to the map construction method of any one of claims 1 to 11.

13. The positioning method of claim 12, wherein, compare the current WiFi data with WiFi data in a point of interest map, and determine a current point of interest positioning result according to the comparison, including: determine a similarity of WiFi name data of the current WiFi data and WiFi name data of the WiFi data in the point of interest map; determine the current point of interest positioning result based on the similarity of the WiFi name data.

14. The positioning method of claim 12, wherein, The positioning method further includes: determine a point of interest task corresponding to the current point of interest positioning result; execute the point of interest task.

15. A map construction apparatus characterized by comprising: including: a data acquisition module configured to acquire inertial data and WiFi data sensed for a plurality of map construction behaviors; a trajectory determination module configured to determine trajectory data of each of the map construction behaviors using the inertial data; a point of interest determination module configured to perform trajectory alignment on the trajectory data of each of the map construction behaviors to obtain aligned trajectory data, and determine a point of interest position in a map construction scene according to the aligned trajectory data of each of the map construction behaviors; a point of interest map construction module configured to perform similarity clustering on WiFi data of each of the point of interest locations to construct a point of interest map; wherein the plurality of map construction behaviors comprise a first map construction behavior and a second map construction behavior, the first map construction behavior corresponding to first trajectory data, and the second map construction behavior corresponding to second trajectory data; wherein the process of the point of interest determination module of performing trajectory alignment on the first trajectory data and the second trajectory data is configured to: determine a similarity of first WiFi data corresponding to the first trajectory data and second WiFi data corresponding to the second trajectory data; construct a residual function according to the similarity of the first WiFi data and the second WiFi data and two-dimensional coordinates of the first trajectory data and the second trajectory data; determine an optimization term according to initial point locations of trajectory data of the plurality of map construction behaviors; and perform trajectory alignment on the first trajectory data and the second trajectory data according to the residual function, the optimization term, and a Cauchy loss function.

16. A positioning device, characterized by comprising: a WiFi data acquisition module configured to acquire current WiFi data; a point of interest positioning module configured to compare the current WiFi data with WiFi data in a point of interest map, and determine a current point of interest positioning result according to the comparison; wherein the point of interest map is constructed according to the map construction method of any one of claims 1 to 11.

17. A computer readable storage medium having stored thereon a computer program, characterized in that The program, when executed by a processor, implements the map construction method of any one of claims 1 to 11 or the positioning method of any one of claims 12 to 14.

18. An electronic device, comprising: comprising: a processor; a memory configured to store one or more programs, which, when executed by the processor, cause the processor to implement the map construction method of any one of claims 1 to 11 or the positioning method of any one of claims 12 to 14.

Images