CN113873637A

CN113873637A - Positioning method, positioning device, terminal and storage medium

Info

Publication number: CN113873637A
Application number: CN202111248781.2A
Authority: CN
Inventors: 裴璇
Original assignee: Shanghai Jinsheng Communication Technology Co ltd
Current assignee: Shanghai Jinsheng Communication Technology Co ltd
Priority date: 2021-10-26
Filing date: 2021-10-26
Publication date: 2021-12-31
Also published as: WO2023071615A1

Abstract

The application relates to a positioning method, a positioning device, a terminal and a storage medium. The method comprises the following steps: acquiring inertial measurement data acquired by at least one user device; inputting the inertia measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured; the speed prediction network is obtained by training sample inertial measurement data acquired by a plurality of user equipment; and determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected. By adopting the method, the positioning precision can be improved, and the indoor positioning and navigation application requirements can be met.

Description

Positioning method, positioning device, terminal and storage medium

Technical Field

The present application relates to the field of positioning technologies, and in particular, to a positioning method, an apparatus, a terminal, and a storage medium.

Background

With the rapid development of science and technology, people have more and more functional requirements on the intelligent terminal, and positioning and navigation by using the intelligent terminal are one of the requirements.

In the conventional technology, Inertial navigation data is collected by an Inertial Measurement Unit (IMU) installed in an intelligent terminal, and position information or a motion trajectory of the intelligent terminal is determined according to the Inertial navigation data. However, the positioning accuracy of the above positioning method is difficult to meet the requirements of indoor positioning and navigation applications.

Disclosure of Invention

Therefore, it is necessary to provide a positioning method, an apparatus, a terminal and a storage medium, which can improve positioning accuracy and meet the requirements of indoor positioning and navigation applications, in order to solve the above technical problems.

In a first aspect, an embodiment of the present disclosure provides a positioning method, where the method includes:

acquiring inertial measurement data acquired by at least one user device;

inputting the inertia measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured; the speed prediction network is obtained by training sample inertial measurement data acquired by a plurality of user equipment;

and determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected.

In one embodiment, the acquiring inertial measurement data collected by at least one user equipment includes:

acquiring original inertial measurement data acquired by at least one user device;

and carrying out attitude conversion and coordinate conversion on the original inertia measurement data to obtain the inertia measurement data.

In one embodiment, the performing attitude transformation and coordinate transformation on the raw inertial measurement data to obtain the inertial measurement data includes:

converting the original inertial measurement data into first inertial measurement data of the user equipment under a standard posture;

and converting the first inertial measurement data into a world coordinate system to obtain inertial measurement data.

In one embodiment, the converting the raw inertial measurement data into the first inertial measurement data of the user equipment at the standard posture includes:

acquiring an attitude angle of the user equipment according to the original inertia measurement data;

according to the attitude angle of the user equipment, mapping the original inertial measurement data to a coordinate system of the user equipment under a standard attitude to obtain first inertial measurement data.

In one embodiment, the converting the first inertial measurement data into the world coordinate system to obtain the inertial measurement data includes:

converting the first inertia measurement data into a coordinate system of the terminal to be measured according to the corresponding relation between the coordinate system of the user equipment in the standard posture and the coordinate system of the terminal to be measured to obtain second inertia measurement data;

and converting the second inertia measurement data into the world coordinate system according to the corresponding relation between the coordinate system of the terminal to be measured and the world coordinate system to obtain inertia measurement data.

In one embodiment, the inertial measurement data collected by at least one user device includes inertial measurement data collected by a plurality of user devices, and the method further includes:

according to the time stamp of the inertial measurement data acquired by each user equipment, time alignment is carried out on the inertial measurement data acquired by each user equipment to obtain the aligned inertial measurement data;

inputting the inertia measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured, wherein the method comprises the following steps:

and inputting the aligned inertial measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured.

In one embodiment, the determining the positioning data of the terminal to be tested according to the speed of the terminal to be tested includes:

acquiring track information of the terminal to be detected according to the speed of the terminal to be detected;

and matching the track information with a preset scene map to obtain and output the position information of the terminal to be tested.

In one embodiment, the method further comprises:

obtaining and outputting service information according to the position information of the terminal to be tested and a preset scene map; wherein the service information includes at least one of route guidance information and item introduction information.

In one embodiment, the training process of the speed prediction network includes:

acquiring a training sample set; the training sample set comprises a plurality of sample inertia measurement data and labels corresponding to the sample inertia measurement data, and the labels are marked as actual speeds;

training a neural network model based on a training sample set to obtain an initial prediction network;

testing the initial prediction network based on the training sample set, and determining a plurality of test tracks according to the prediction speed obtained by testing;

and determining the initial prediction network as the speed prediction network under the condition that the error among the plurality of test tracks is smaller than a preset error value.

In one embodiment, the obtaining of the training sample set includes:

respectively acquiring a plurality of original inertia measurement data acquired by data acquisition equipment and marking an actual track acquired by the data acquisition equipment;

respectively carrying out attitude conversion and coordinate conversion on each original inertia measurement data to obtain sample inertia measurement data corresponding to each original inertia measurement data;

after time alignment is carried out on the acquisition time of the inertia measurement data of the samples and the acquisition time of the actual track, the actual speed corresponding to the inertia measurement data of each sample is determined;

and obtaining a training sample set according to the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

In one embodiment, the at least one user device comprises at least one of a smartphone, an earpiece, a smart bracelet, a smart watch, and smart glasses.

In a second aspect, an embodiment of the present disclosure provides a positioning apparatus, including:

the inertial data acquisition module is used for acquiring inertial measurement data acquired by at least one piece of user equipment;

the speed prediction module is used for inputting the inertia measurement data into a speed prediction network to perform noise reduction and speed prediction to obtain the speed of the terminal to be measured; the speed prediction network is obtained by training sample inertial measurement data acquired by a plurality of user equipment;

and the positioning data determining module is used for determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected.

In one embodiment, the inertial data acquisition module includes:

the original data acquisition submodule is used for acquiring original inertial measurement data acquired by at least one piece of user equipment;

and the conversion submodule is used for carrying out attitude conversion and coordinate conversion on the original inertia measurement data to obtain the inertia measurement data.

In one embodiment, the conversion sub-module is specifically configured to convert the raw inertial measurement data into first inertial measurement data of the user equipment in a standard posture; and converting the first inertial measurement data into a world coordinate system to obtain inertial measurement data.

In one embodiment, the conversion submodule is specifically configured to obtain an attitude angle of the user equipment according to the original inertial measurement data; according to the attitude angle of the user equipment, mapping the original inertial measurement data to a coordinate system of the user equipment under a standard attitude to obtain first inertial measurement data.

In one embodiment, the conversion sub-module is specifically configured to convert the first inertial measurement data into the coordinate system of the terminal to be measured according to a correspondence between the coordinate system of the user equipment in the standard posture and the coordinate system of the terminal to be measured, so as to obtain second inertial measurement data; and converting the second inertia measurement data into the world coordinate system according to the corresponding relation between the coordinate system of the terminal to be measured and the world coordinate system to obtain inertia measurement data.

In one embodiment, the inertial measurement data collected by at least one user device includes inertial measurement data collected by a plurality of user devices, and the apparatus further includes:

the alignment module is used for performing time alignment on the inertia measurement data acquired by each user equipment according to the timestamp of the inertia measurement data acquired by each user equipment to obtain aligned inertia measurement data;

the speed prediction module is specifically configured to input the aligned inertial measurement data into a speed prediction network for noise reduction and speed prediction, so as to obtain a speed of the terminal to be measured.

In one embodiment, the positioning data determining module is configured to obtain track information of the terminal to be tested according to a speed of the terminal to be tested; and matching the track information with a preset scene map to obtain and output the position information of the terminal to be tested.

In one embodiment, the apparatus further comprises:

the service information output module is used for obtaining and outputting service information according to the position information of the terminal to be tested and a preset scene map; wherein the service information includes at least one of route guidance information and item introduction information.

In one embodiment, the apparatus further comprises:

the sample acquisition module is used for acquiring a training sample set; the training sample set comprises a plurality of sample inertia measurement data and labels corresponding to the sample inertia measurement data, and the labels are marked as actual speeds;

the training module is used for training the neural network model based on the training sample set to obtain an initial prediction network;

the test module is used for testing the initial prediction network based on the training sample set and determining a plurality of test tracks according to the prediction speed obtained by the test;

and the network determining module is used for determining the initial prediction network as the speed prediction network under the condition that the error among the plurality of test tracks is smaller than a preset error value.

In one embodiment, the sample acquiring module is specifically configured to acquire a plurality of original inertial measurement data acquired by the data acquiring device and mark an actual trajectory acquired by the acquiring device, respectively; respectively carrying out attitude conversion and coordinate conversion on each original inertia measurement data to obtain sample inertia measurement data corresponding to each original inertia measurement data; after time alignment is carried out on the acquisition time of the inertia measurement data of the samples and the acquisition time of the actual track, the actual speed corresponding to the inertia measurement data of each sample is determined; and obtaining a training sample set according to the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

In a third aspect, an embodiment of the present disclosure provides a terminal, including a memory and a processor, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:

acquiring inertial measurement data acquired by at least one user device;

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring inertial measurement data acquired by at least one user device;

The positioning method, the positioning device, the positioning terminal and the storage medium acquire inertial measurement data acquired by at least one user equipment, and input the inertial measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be detected; and determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected. According to the embodiment of the disclosure, in the process of positioning the terminal to be measured, the speed of the terminal to be measured is not obtained in an integral mode, but is obtained by adopting the speed prediction network, and the speed prediction network is adopted to realize noise reduction compared with the integral mode, so that the accuracy of the speed is improved, thus, the position information or track information determined according to the speed is more accurate, namely, the positioning precision is improved, and the requirements of indoor positioning and navigation application can be met.

Drawings

FIG. 1 is a diagram of an application environment of a positioning method in one embodiment;

FIG. 2 is a flow diagram illustrating a positioning method in one embodiment;

FIG. 3 is a schematic flow chart diagram illustrating the steps for obtaining inertial measurement data collected by at least one UE in one embodiment;

FIG. 4 is a schematic flow chart illustrating the steps of attitude transformation and coordinate transformation of raw inertial measurement data in one embodiment;

FIG. 5 is a schematic flow chart of a positioning method in another embodiment;

FIG. 6 is a flowchart illustrating the step of determining the positioning data of the terminal according to the speed of the terminal in one embodiment;

FIG. 7 is a flowchart illustrating the step of outputting service information in one embodiment;

FIG. 8 is a flow diagram that illustrates the training steps of the velocity prediction network in one embodiment;

FIG. 9 is a flowchart illustrating the steps of obtaining a training sample set in one embodiment;

FIG. 10 is a block diagram of a positioning device according to one embodiment;

FIG. 11 is a second block diagram of the positioning device according to one embodiment;

FIG. 12 is a third block diagram of the positioning apparatus in one embodiment;

FIG. 13 is a fourth block diagram illustrating the structure of the positioning device in one embodiment;

fig. 14 is an internal structural view of a terminal in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

First, before specifically describing the technical solution of the embodiment of the present disclosure, a technical background or a technical evolution context on which the embodiment of the present disclosure is based is described. In general, Inertial navigation data is collected by an Inertial Measurement Unit (IMU) installed in an intelligent terminal, and position information or a motion trajectory of the intelligent terminal is determined according to the Inertial navigation data. The method is characterized in that a dual integral method is often adopted for determining the position information or the motion track of the intelligent terminal according to the inertial navigation data, and the method is easy to generate track errors and influence the positioning precision, so that the positioning precision is difficult to meet the requirements of indoor positioning and navigation application.

In the technical scheme provided by the application, firstly, inertia measurement data collected by at least one user equipment is obtained; then inputting the inertia measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured; and finally, determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected. According to the method and the device, the speed of the terminal to be detected is obtained by adopting the speed prediction network instead of a double integral method, and then the positioning data of the terminal to be detected is obtained, so that the track error can be reduced, the positioning precision can be improved, and the requirements of indoor positioning and navigation application can be met.

The positioning method provided by the application can be applied to the application environment shown in fig. 1. The application environment includes a user equipment 102 and a terminal under test 104. The user equipment 102 may communicate with the terminal 104 to be tested through a plurality of communication methods. For example, the user equipment 102 communicates with the terminal 104 to be tested via a wireless network, or bluetooth. The embodiment of the present disclosure does not limit the communication method. The user devices 102 may include, but are not limited to, various smart phones, headsets, smart bracelets, smart watches, and smart glasses; the terminal 104 to be tested may include, but is not limited to, various smart phones, tablet computers and portable wearable devices such as earphones, smart watches, smart glasses, and the like.

In an embodiment, as shown in fig. 2, a positioning method is provided, which is described by taking the method as an example for being applied to the terminal to be tested in fig. 1, and includes the following steps:

step 201, obtaining inertial measurement data collected by at least one user equipment.

The IMU is a device for measuring the angular velocity and the acceleration of an object, one IMU generally comprises an accelerometer and a gyroscope which are respectively used for measuring the acceleration and the angular velocity of the object in a three-dimensional space, and the user equipment acquires inertial measurement data through the IMU.

The terminal to be tested is communicated with at least one user device, and inertia measurement data are obtained from the user device. For example, a user wears a terminal to be tested and user equipment at the same time, wherein the terminal to be tested is a smart phone, and the user equipment is a bluetooth wireless headset. The Bluetooth wireless earphone is provided with an IMU, and inertial measurement data are acquired by the IMU. The smart phone is communicated with the Bluetooth wireless earphone through a Bluetooth protocol, and inertia measurement data are obtained from the Bluetooth wireless earphone.

Optionally, the at least one user device comprises at least one of a smartphone, an earpiece, a smartband, a smartwatch, and smartglasses. In practical application, the inertia measurement data may also be acquired in other manners, and the acquisition manner is not limited in the embodiment of the disclosure.

Step 202, inputting the inertia measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured.

The terminal to be tested is provided with a pre-trained speed prediction network, and the speed prediction network is obtained by training sample inertia measurement data acquired by a plurality of user equipment.

After the terminal to be tested acquires the inertia measurement data, inputting the inertia measurement data into a speed prediction network, denoising the inertia measurement data by the speed prediction network, performing speed prediction according to the denoised inertia measurement data, and outputting the speed of the terminal to be tested by the speed prediction network.

In practical application, acceleration in inertial measurement data at a plurality of acquisition moments is generally combined into an acceleration sequence, and then the acceleration sequence is input into a speed prediction network to obtain the speed of a terminal to be measured. Wherein, the acceleration quantity in the acceleration sequence can be determined according to the data acquisition frequency. For example, in the case of an acquisition frequency of 200Hz, the number of accelerations in the acceleration sequence may be 200. The disclosed embodiment does not limit the amount of acceleration.

It should be noted that the above speed and acceleration are vectors, including magnitude and direction.

And step 203, determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected.

Wherein the positioning data comprises at least one of position information and trajectory information.

After the terminal to be measured obtains the speed, integral processing can be performed according to the speed and the angular velocity in the inertia measurement data, so that the positioning data of the terminal to be measured is obtained.

In the positioning method, inertia measurement data collected by at least one user device is obtained, and the inertia measurement data is input into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured; and determining the positioning data of the terminal to be detected according to the speed of the terminal to be detected. According to the embodiment of the disclosure, in the process of positioning the terminal to be measured, the speed of the terminal to be measured is not obtained in an integral mode, but is obtained by adopting the speed prediction network, and the speed prediction network is adopted to realize noise reduction compared with the integral mode, so that the accuracy of the speed is improved, thus, the position information or track information determined according to the speed is more accurate, namely, the positioning precision is improved, and the requirements of indoor positioning and navigation application can be met.

In an embodiment, as shown in fig. 3, the process of acquiring the inertial measurement data collected by the at least one user equipment may include the following steps:

step 301, raw inertial measurement data collected by at least one user equipment is obtained.

The user equipment acquires original inertia measurement data, and the terminal to be tested communicates with the user equipment to acquire the original inertia measurement data from the user equipment.

And 302, performing attitude conversion and coordinate conversion on the original inertia measurement data to obtain inertia measurement data.

The user equipment can be in different postures at different moments, for example, the Bluetooth wireless headset swings along with the swinging of the head of a user, and the smart bracelet swings along with the swinging of the arm of the user; as another example, a smartphone is held by a user or placed in a pocket of clothing by the user. Therefore, the original inertia measurement data acquired by the terminal to be tested from the user equipment is acquired by the user equipment under different postures, and the data is not beneficial to speed prediction of the speed prediction network. Therefore, the terminal to be measured needs to perform data preprocessing on the original inertial measurement data, for example, perform attitude conversion and coordinate conversion on the original inertial measurement data to obtain normalized inertial measurement data.

In the above embodiment, the raw inertial measurement data collected by at least one user equipment is obtained; and carrying out attitude conversion and coordinate conversion on the original inertia measurement data to obtain the inertia measurement data. According to the method and the device, attitude conversion and coordinate conversion are carried out on the inertial measurement data, namely, the original inertial measurement data collected at any time, any equipment orientation and any action state are projected to a unified world coordinate system, so that the speed prediction network can carry out speed prediction, and the robustness of the speed prediction network is improved.

In an embodiment, as shown in fig. 4, the process of performing the attitude transformation and the coordinate transformation on the raw inertial measurement data to obtain the inertial measurement data may include:

step 3021, converting the raw inertial measurement data into first inertial measurement data of the user equipment in a standard posture.

In practical application, the attitude of the user equipment for acquiring the original inertia measurement data may be different from the standard attitude, and therefore, the original inertia measurement data is converted into the standard attitude from the attitude during data acquisition to obtain the first inertia measurement data.

The process of gesture conversion may include: acquiring an attitude angle of the user equipment according to the original inertia measurement data; according to the attitude angle of the user equipment, mapping the original inertial measurement data to a coordinate system of the user equipment under a standard attitude to obtain first inertial measurement data.

For example, the angular velocity in the original inertial measurement data is integrated to obtain the attitude angle of the user equipment; and then, mapping the original inertial measurement data to a coordinate system of the user equipment under a standard posture according to the mapping relation to obtain first inertial measurement data.

And step 3022, converting the first inertial measurement data into a world coordinate system to obtain inertial measurement data.

After the first inertia measurement data of the user equipment in the standard posture is obtained, the first inertia measurement data can be converted into the world coordinate system according to the corresponding relation between the user equipment and the world coordinate system, and inertia measurement data required by the speed prediction network for speed prediction is obtained.

In one embodiment, the process of coordinate system conversion may further include: converting the first inertia measurement data into a coordinate system of the terminal to be measured according to the corresponding relation between the coordinate system of the user equipment in the standard posture and the coordinate system of the terminal to be measured to obtain second inertia measurement data; and converting the second inertia measurement data into the world coordinate system according to the corresponding relation between the coordinate system of the terminal to be measured and the world coordinate system to obtain inertia measurement data.

For example, the bluetooth wireless headset is attached to the smartphone in advance, so that the smartphone can acquire the standard posture of the bluetooth wireless headset and acquire the corresponding relationship between the coordinate system of the bluetooth wireless headset in the standard posture and the coordinate system of the smartphone. Then, the user wears the Bluetooth wireless earphone and the smart phone and moves, and the Bluetooth wireless earphone transmits the collected original inertia measurement data to the smart phone. Firstly, attitude conversion is carried out on original inertia measurement data by the smart phone to obtain first inertia measurement data; and then converting the first inertia measurement data into the coordinate system of the smart phone according to the corresponding relation between the coordinate system of the Bluetooth wireless earphone in the standard posture and the coordinate system of the smart phone, so as to obtain second inertia measurement data. And then, the smart phone converts the second inertia measurement data into a world coordinate system according to the corresponding relation between the coordinate system of the smart phone and the world coordinate system to obtain inertia measurement data required by the speed prediction network for speed prediction.

In the above embodiment, the original inertial measurement data is converted into first inertial measurement data of the user equipment in a standard posture; and converting the first inertial measurement data into a world coordinate system to obtain inertial measurement data. According to the method and the device, the attitude conversion is firstly carried out on the original inertia measurement data to obtain the first inertia measurement data, then the coordinate conversion is carried out on the first inertia measurement data to obtain the inertia measurement data, and the inertia measurement data are unified under a world coordinate system, so that the speed prediction can be conveniently carried out by the speed prediction network, and the robustness of the speed prediction network is improved.

In one embodiment, the inertial measurement data collected by at least one user device includes inertial measurement data collected by a plurality of user devices, as shown in fig. 5, the embodiment of the present disclosure may further include:

and 204, performing time alignment on the inertia measurement data acquired by each user equipment according to the time stamp of the inertia measurement data acquired by each user equipment to obtain the aligned inertia measurement data.

In practical applications, there are a plurality of user devices that may collect inertial measurement data. For example, the bluetooth wireless headset and the smart band simultaneously collect the inertia measurement data. Therefore, after the terminal to be tested acquires the inertia measurement data acquired by the plurality of user equipment, the inertia measurement data acquired by the plurality of user equipment is time-aligned according to the timestamp, and the aligned inertia measurement data is acquired.

For example, the smart phone performs time alignment on the inertia measurement data collected by the bluetooth wireless headset and the inertia measurement data collected by the smart band according to the timestamp to obtain the aligned inertia measurement data.

It can be understood that data collection is performed by a plurality of user devices simultaneously, so that the data quantity can be increased, and the prediction speed and the prediction efficiency of the speed prediction network are improved.

Correspondingly, step 203 may comprise: and inputting the aligned inertial measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured.

For example, the inertial measurement data after the bluetooth wireless headset is aligned and the inertial measurement data after the smart band is aligned are input into a speed prediction network for noise reduction and speed prediction, so that the speed of the smart phone is obtained.

In the above embodiment, under the condition of the inertial measurement data acquired by a plurality of user equipments, according to the timestamp of the inertial measurement data acquired by each user equipment, time alignment is performed on the inertial measurement data acquired by each user equipment to obtain aligned inertial measurement data; and inputting the aligned inertial measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured. According to the embodiment of the disclosure, the data volume can be expanded by the data acquisition of the plurality of user equipment, so that the prediction speed and the prediction efficiency of the speed prediction network are improved, and time alignment processing is required when the inertia measurement data acquired by the plurality of user equipment is used, so that the speed prediction network can more accurately predict the speed.

In an embodiment, as shown in fig. 6, the process of determining the positioning data of the terminal to be tested according to the speed of the terminal to be tested may include the following steps:

step 401, obtaining track information of the terminal to be tested according to the speed of the terminal to be tested.

After the speed prediction network outputs the speed of the terminal to be measured, integral operation can be performed according to the speed of the terminal to be measured and the angular velocity in the inertia measurement data to obtain the track information of the terminal to be measured.

And 402, matching the track information with a preset scene map to obtain and output the position information of the terminal to be tested.

Under the scene of indoor positioning and navigation application, the terminal to be tested can acquire a preset scene map, and track information is matched with the preset scene map to obtain position information of the terminal to be tested. For example, the smartphone acquires an indoor map of a certain museum, and matches the track information with the indoor map, so that the position information of the smartphone, that is, the specific position of the user in the museum, can be determined.

And then, the terminal to be tested can output the position information of the terminal to be tested in various modes. For example, position information can be displayed through a smart phone, smart glasses and the like, position information can also be played through the smart phone, a Bluetooth wireless earphone and the like, and the position information can also be prompted through vibration of a smart bracelet and a smart watch. The output mode is not limited in the embodiment of the disclosure, and can be set according to actual conditions.

On the basis of the above embodiment, as shown in fig. 7, an embodiment of the present disclosure may further include:

and 403, obtaining and outputting service information according to the position information of the terminal to be tested and a preset scene map.

Wherein the service information includes at least one of route guidance information and item introduction information.

The terminal to be tested can also obtain service information such as path guidance information, article introduction information and the like according to the position information and a preset scene map, and output the service information in various modes.

For example, the smart phone may obtain the route guidance information according to the location information and an indoor map of a museum, and then control the smart phone to display the route guidance information or control the bluetooth wireless headset to play the route guidance information, so as to guide the visitor to go to the next point of reference. The smart phone can also obtain article introduction information according to the position information and the indoor map of the museum, control the Bluetooth wireless earphone to play the article introduction information, and introduce the cultural relics at the current position for the visitor.

In one embodiment, the service information can also combine the functions of spatial audio, voice assistant and the like to provide indoor voice navigation service for the blind. The embodiment of the present disclosure does not limit the service information.

In the above embodiment, the track information of the terminal to be tested is obtained according to the speed of the terminal to be tested, and the track information is matched with the preset scene map, so as to obtain and output the position information of the terminal to be tested; and obtaining and outputting service information according to the position information of the terminal to be tested and a preset scene map. Through the embodiment of the disclosure, the terminal to be tested can provide services such as indoor voice navigation, voice navigation in a large building and the like for a user according to the preset scene map and the track information, and is in fit with various typical application scenes, so that the use experience of the user is improved.

In one embodiment, as shown in fig. 8, the training process of the speed prediction network may include the following steps:

step 501, a training sample set is obtained.

The training sample set comprises a plurality of sample inertia measurement data and labels corresponding to the sample inertia measurement data, and the labels are marked as actual speeds.

And acquiring data by adopting a plurality of user equipment to obtain a plurality of sample inertia measurement data and actual speeds corresponding to the sample inertia measurement data, and forming a training sample set by the plurality of sample inertia measurement data and the actual speeds corresponding to the sample inertia measurement data.

Step 502, training a neural network model based on a training sample set to obtain an initial prediction network.

Inputting one sample inertia measurement data in the training sample set into a neural network model for training to obtain a training result output by the neural network model; calculating a loss value between the training result and a label corresponding to the sample inertia measurement data by using a preset loss function; if the loss value does not accord with the preset convergence condition, adjusting the adjustable parameters in the neural network model, and inputting the other sample inertia measurement data into the neural network model with the modified parameters for continuous training. And ending the training until the loss value between the training result output by the neural network model and the corresponding label meets the preset convergence condition, and determining the neural network model after ending the training as the initial prediction network.

Step 503, testing the initial prediction network based on the training sample set, and determining a plurality of test tracks according to the prediction speed obtained by the test.

And testing the initial prediction network by adopting the sample inertial measurement data which does not participate in training in the training sample set. Specifically, a plurality of sample inertial measurement data which do not participate in training are sequentially input into the initial prediction network, and the prediction speed corresponding to each sample inertial measurement data output by the initial prediction network is obtained. And carrying out integral operation according to the plurality of predicted speeds to obtain a plurality of test tracks.

And step 504, determining the initial prediction network as a speed prediction network under the condition that the error among the plurality of test tracks is smaller than a preset error value.

And calculating errors among the plurality of test tracks, and if the errors among the plurality of test tracks are smaller than a preset error value, which indicates that the prediction accuracy of the initial prediction network is higher, determining the initial prediction network as a speed prediction network. If the error between the plurality of test trajectories is greater than or equal to the predetermined error value, which indicates that the prediction accuracy of the initial prediction network is not high enough, step 502 and step 504 may be repeated until the error between the plurality of test trajectories is less than the predetermined error value, and the training is ended to obtain the speed prediction network.

For example, the preset error value is that the error generated by walking 100m is within 3m, and if the error between the plurality of test tracks is smaller than the prediction error value, the initial prediction network is determined as the speed prediction network. The prediction error value is not limited in the embodiments of the present disclosure.

In the above embodiment, a training sample set is obtained; training a neural network model based on a training sample set to obtain an initial prediction network; testing the initial prediction network based on the training sample set, and determining a plurality of test tracks according to the prediction speed obtained by testing; and determining the initial prediction network as the speed prediction network under the condition that the error among the plurality of test tracks is smaller than a preset error value. According to the embodiment of the disclosure, the training of the neural network model and the testing of the initial prediction network are performed by using the training sample set, and the training is finished under the condition that the prediction accuracy of the initial prediction network is high enough, so that the prediction accuracy of the speed prediction network obtained by training is ensured.

In an embodiment, as shown in fig. 9, the process of obtaining the training sample set may include the following steps:

step 5011, respectively acquiring a plurality of original inertia measurement data acquired by the data acquisition equipment and marking actual tracks acquired by the data acquisition equipment.

In the process of obtaining the training sample set, a plurality of original inertia measurement data collected by the data collection equipment are obtained, and the actual track collected by the labeling equipment is obtained.

For example, a plurality of original inertia measurement data acquired by data acquisition devices such as a bluetooth wireless headset and a smart bracelet are acquired, and an actual track acquired by a labeling acquisition device such as a smart phone or a head-mounted display device (AR glasses) deployed with a visual odometer (VIO) algorithm is acquired.

Before data acquisition, the data acquisition equipment and the label acquisition equipment can be placed in a calibration device together, the calibration device is used for calibrating data acquisition time of the data acquisition equipment and the label acquisition equipment, and a coordinate mapping relation between the data acquisition equipment and the label acquisition equipment is established according to the relative position between the data acquisition equipment and the label acquisition equipment.

In the data acquisition process, the data acquisition equipment and the label acquisition equipment need to be worn together, and the label acquisition equipment needs to be tightly attached to an acquirer, so that the 6Dof (6 degrees of freedom, three degrees of freedom for describing position information and three degrees of freedom for describing posture information) motion trail output by the label acquisition equipment is ensured to be completely consistent with the human body. The data acquisition can adopt the acquisition modes of multiple persons, multiple equipment types, multiple batches and multiple scenes so as to ensure the randomness, the richness and the data volume of the original inertia measurement data. The data acquisition equipment and the label acquisition equipment are not limited by the embodiment of the disclosure, and can be set according to actual conditions.

And step 5012, respectively performing attitude conversion and coordinate conversion on each original inertia measurement data to obtain sample inertia measurement data corresponding to each original inertia measurement data.

Before training, attitude conversion is required to be carried out on each original inertia measurement data so as to convert each original inertia measurement data from a coordinate system of a data acquisition attitude to a coordinate system of a standard attitude; and then, carrying out coordinate conversion on each converted inertia measurement data so as to convert each converted inertia measurement data from a coordinate system of a standard attitude to a world coordinate system, and obtaining sample inertia measurement data corresponding to each original inertia measurement data. In the process of converting to the world coordinate system, the inertial measurement data under the standard posture can be converted into the coordinate system of the labeling acquisition equipment according to the coordinate mapping relation established in the calibration process before data acquisition, and then the coordinate system of the labeling acquisition equipment is converted into the world coordinate system. The gesture conversion and coordinate conversion processes may refer to the above embodiments, and the embodiments of the present disclosure are not described herein again.

Step 5013, after time alignment is performed on the acquisition time of the plurality of sample inertia measurement data and the acquisition time of the actual trajectory, determining the actual speed corresponding to each sample inertia measurement data.

Because the data acquisition equipment and the label acquisition equipment are subjected to time calibration in the calibration process, after sample inertia measurement data are obtained, time alignment can be carried out according to the acquisition time of the sample inertia measurement data and the acquisition time of an actual track, and therefore the actual speed corresponding to each sample inertia measurement data can be obtained.

Step 5014, obtaining a training sample set according to the multiple sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

After obtaining the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data, a training sample set is composed of the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

In the above embodiment, a plurality of original inertia measurement data acquired by the data acquisition device and an actual track acquired by the label acquisition device are respectively acquired; respectively carrying out attitude conversion and coordinate conversion on each original inertia measurement data to obtain sample inertia measurement data corresponding to each original inertia measurement data; after time alignment is carried out on the acquisition time of the inertia measurement data of the samples and the acquisition time of the actual track, the actual speed corresponding to the inertia measurement data of each sample is determined; and obtaining a training sample set according to the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data. According to the embodiment of the disclosure, before the sample is acquired, the coordinate mapping relation between the data acquisition equipment and the label acquisition equipment is established, and the time calibration is performed on the data acquisition equipment and the label acquisition equipment, so that after the data is acquired, the inertia measurement data can be normalized according to the coordinate mapping relation, and the corresponding relation between the sample inertia measurement data and the actual speed can be obtained, thereby obtaining the training sample set, and making early preparation for training the speed prediction network.

It should be understood that, although the steps in the flowcharts of fig. 2 to 9 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2 to 9 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the other steps or stages.

In one embodiment, as shown in fig. 10, there is provided a positioning device comprising:

an inertial data acquisition module 601, configured to acquire inertial measurement data acquired by at least one user equipment;

the speed prediction module 602 is configured to input the inertial measurement data into a speed prediction network to perform noise reduction and speed prediction, so as to obtain a speed of the terminal to be tested; the speed prediction network is obtained by training sample inertial measurement data acquired by a plurality of user equipment;

and the positioning data determining module 603 is configured to determine positioning data of the terminal to be tested according to the speed of the terminal to be tested.

In one embodiment, the inertial data acquiring module 601 includes:

In one embodiment, the inertial measurement data collected by at least one user device includes inertial measurement data collected by a plurality of user devices, and as shown in fig. 11, the apparatus further includes:

an alignment module 604, configured to perform time alignment on the inertia measurement data acquired by each user equipment according to the timestamp of the inertia measurement data acquired by each user equipment, to obtain aligned inertia measurement data;

the speed prediction module 603 is specifically configured to input the aligned inertial measurement data into a speed prediction network for noise reduction and speed prediction, so as to obtain a speed of the terminal to be measured.

In one embodiment, the positioning data determining module 603 is configured to obtain track information of the terminal to be tested according to a speed of the terminal to be tested; and matching the track information with a preset scene map to obtain and output the position information of the terminal to be tested.

In one embodiment, as shown in fig. 12, the apparatus further comprises:

a service information output module 605, configured to obtain and output service information according to the position information of the terminal to be tested and a preset scene map; wherein the service information includes at least one of route guidance information and item introduction information.

In one embodiment, as shown in fig. 13, the apparatus further comprises:

a sample obtaining module 606, configured to obtain a training sample set; the training sample set comprises a plurality of sample inertia measurement data and labels corresponding to the sample inertia measurement data, and the labels are marked as actual speeds;

a training module 607, configured to perform training of the neural network model based on the training sample set to obtain an initial prediction network;

a test module 608, configured to test the initial prediction network based on the training sample set, and determine a plurality of test trajectories according to a prediction speed obtained through the test;

and the network determining module 609 is configured to determine the initial prediction network as the speed prediction network when the error between the plurality of test tracks is smaller than a preset error value.

In one embodiment, the sample obtaining module 606 is specifically configured to obtain a plurality of original inertial measurement data collected by the data collecting device and an actual trajectory collected by the label collecting device respectively; respectively carrying out attitude conversion and coordinate conversion on each original inertia measurement data to obtain sample inertia measurement data corresponding to each original inertia measurement data; after time alignment is carried out on the acquisition time of the inertia measurement data of the samples and the acquisition time of the actual track, the actual speed corresponding to the inertia measurement data of each sample is determined; and obtaining a training sample set according to the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

For the specific definition of the positioning device, reference may be made to the above definition of the positioning method, which is not described herein again. The modules in the positioning device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the terminal, and can also be stored in a memory in the terminal in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a terminal is provided, an internal structure of which may be as shown in fig. 14. The terminal comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the terminal is configured to provide computing and control capabilities. The memory of the terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the terminal is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a positioning method. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen, and the input device of the terminal can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the terminal, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the configuration shown in fig. 14 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the terminal to which the present application is applied, and that a particular terminal may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a terminal comprising a memory and a processor, the memory having a computer program stored therein, the processor when executing the computer program implementing the steps of:

acquiring inertial measurement data acquired by at least one user device;

In one embodiment, the processor, when executing the computer program, further performs the steps of:

In one embodiment, the inertial measurement data collected by the at least one user device comprises inertial measurement data collected by a plurality of user devices, and the processor when executing the computer program further implements the steps of:

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring inertial measurement data acquired by at least one user device;

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, the inertial measurement data collected by the at least one user device comprises inertial measurement data collected by a plurality of user devices, the computer program when executed by the processor further implementing the steps of:

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method of positioning, the method comprising:

acquiring inertial measurement data acquired by at least one user device;

2. The method of claim 1, wherein the obtaining inertial measurement data collected by at least one user device comprises:

acquiring original inertial measurement data acquired by the at least one user equipment;

and performing attitude conversion and coordinate conversion on the original inertia measurement data to obtain the inertia measurement data.

3. The method of claim 2, wherein the performing an attitude transformation and a coordinate transformation on the raw inertial measurement data to obtain the inertial measurement data comprises:

and converting the first inertial measurement data into a world coordinate system to obtain the inertial measurement data.

4. The method of claim 3, wherein converting the raw inertial measurement data into first inertial measurement data of the user device at a standard attitude comprises:

and mapping the original inertial measurement data to a coordinate system of the user equipment under a standard posture according to the posture angle of the user equipment to obtain the first inertial measurement data.

5. The method of claim 3, wherein transforming the first inertial measurement data into a world coordinate system to obtain the inertial measurement data comprises:

converting the first inertia measurement data into the coordinate system of the terminal to be measured according to the corresponding relation between the coordinate system of the user equipment in the standard posture and the coordinate system of the terminal to be measured to obtain second inertia measurement data;

and converting the second inertia measurement data into the world coordinate system according to the corresponding relation between the coordinate system of the terminal to be measured and the world coordinate system to obtain the inertia measurement data.

6. The method according to any of claims 1-5, wherein the inertial measurement data collected by the at least one user device comprises inertial measurement data collected by a plurality of user devices, the method further comprising:

according to the time stamp of the inertial measurement data acquired by each user equipment, time alignment is carried out on the inertial measurement data acquired by each user equipment to obtain aligned inertial measurement data;

the step of inputting the inertial measurement data into a speed prediction network for noise reduction and speed prediction to obtain the speed of the terminal to be measured includes:

7. The method according to claim 1, wherein the determining the positioning data of the terminal to be tested according to the speed of the terminal to be tested comprises:

acquiring track information of the terminal to be tested according to the speed of the terminal to be tested;

8. The method of claim 7, further comprising:

obtaining and outputting service information according to the position information of the terminal to be tested and the preset scene map; wherein the service information includes at least one of route guidance information and item introduction information.

9. The method of claim 1, wherein the training process of the velocity prediction network comprises:

acquiring a training sample set; the training sample set comprises a plurality of sample inertia measurement data and labels corresponding to the sample inertia measurement data, wherein the labels are actual speeds;

training a neural network model based on the training sample set to obtain an initial prediction network;

10. The method of claim 9, wherein the obtaining a training sample set comprises:

after time alignment is carried out on the acquisition time of the plurality of sample inertia measurement data and the acquisition time of the actual track, the actual speed corresponding to each sample inertia measurement data is determined;

and obtaining the training sample set according to the plurality of sample inertia measurement data and the actual speed corresponding to each sample inertia measurement data.

11. The method of claim 1, wherein the at least one user device comprises a headset.

12. A positioning device, the device comprising:

13. A terminal comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 11.

14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 11.