note that the weight ω, whose magnitude represents the importance of the corresponding preset feature, can be trained to obtain the optimal weight combination through data-driven training.

Specifically, the optimal weight combination is obtained by training in a sliding window form, where if the window size is N, that is, N times are included, there are N observations inside the window, corresponding to N states. Based on this, the best value of each state, i.e. the best link id of each state, can be determined by means of determining the state chain (i.e. transition path) of the maximum probability inside the window. Here, it should be noted that, in the above process, the training is implemented by using the real road information as the reference information, so that the optimal weight combination is obtained.

Specifically, based on the similarity probability and the transition probability, the following formula is obtained:

(similar probability at time t) × (transition probability from time t to time t + 1) × (similar probability at time t + 1) × … × (similar probability at time t + N-1) × (transition probability from time t + N-1 to time t + N) × (similar probability at time t + N).

For each transition path (i.e., chain), the probability is a function of ω, and after the probability normalization processing of all chains, the proportion of the chain in all options can be seen, for example, the chain is characterized by means of a probability vector a.

Further, the above formula is also rewritten into the probability vector B by performing the labeling of the true value of the real scene, for example, when the probability of the road on which the target vehicle is located is 1 and the probability of the road to which the target vehicle does not travel is 0 in the real scene. In this case, the loss function may be the square of the difference between the normalized probability (probability vector a) and the true value (probability vector B). Thus, by a simple gradient descent method, the optimal omega parameter can be trained, so that the road selected by the multiplication of the probability expressed by omega is the road with the highest accuracy.

For example, as shown in fig. 3, suppose N is equal to 3, that is, 3 time instants are included in the sliding window, where the road associated withtime instant 1 includes a road a and a road D, and the probability value of the road a attime instant 1 is ρ_1AThe probability value of the road D attime 1 is ρ_1D(ii) a Similarly, the roads associated withtime 2 include road a, road B, and road C, and accordingly, the probability values are ρ_2A，ρ_2BAnd ρ_2C(ii) a The roads associated with thetime 3 include a road B and a road D, and accordingly, the probability values are ρ_3BAnd ρ_3D. At this time, based on the scheme of the present application, the probabilities of all the links in the sliding window, that is, ρ (AAB) (the probability value representing the transition route corresponding to the road a fromtime 1 totime 2 and then to the road C from time 3), ρ (AAD), ρ (ABB), etc. may be obtained. Further, the p (aab) ═ ρ_1A×T_AA×ρ_2A×T_AB×ρ_2BHere, T is as defined_AAI.e. the probability value of the transition route corresponding to the road a fromtime 1 totime 2, for example, equal ρ_1A×ρ_2A. Thus, the chain with the maximum probability is determined, and the initial road is obtained.

In conclusion, the scheme of the application emphasizes the problem of initialization of the hidden Markov model based on the sliding window, and compared with the current situation that the initialization stage is lack of discussion and realization in the traditional technology, the scheme of the application makes a complete abstraction on the initialization technology, makes full use of the related information of multiple sensors of the target vehicle, simplifies the initialization into the classification model problem, and further obtains the initial road with higher accuracy. At present, the accuracy rate of the test data of 1w kilometer in the scheme of the application can basically reach more than 99.9%.

This application scheme still provides a road positioner, as shown in fig. 4, the device includes:

the prediction unit 401 is configured to predict and obtain location feature information of target vehicles at N adjacent moments, where the predicted location feature information represents a probability value that the target vehicle is located in at least one associated candidate road at a current moment; n is an integer greater than or equal to 2;

a transfer characteristic determining unit 402, configured to obtain transfer characteristic information of the target vehicle from a time t to a time t +1 of the N times based on the location characteristic information of the target vehicle at the N times, where the transfer characteristic information at least represents a probability value of a transfer path corresponding to the transfer of the target vehicle from at least one candidate road associated with the time t to at least one candidate road associated with thetime t + 1;

an initial road determining unit 403, configured to predict, based on the location characteristic information and the road diversion information, an initial road on which the target vehicle is located in a time period corresponding to the N times from all the candidate roads.

In a specific example of the scheme of the present application, the method further includes:

and the optimization unit is used for optimizing the predicted position characteristic information based on the predicted difference characteristics between the initial road and the real initial road of the target vehicle in the time period corresponding to the N moments.

In a specific example of the application, the prediction unit is further configured to obtain road image information and geographical location information of the target vehicle at the time t; predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle in the associated candidate road based on the road image information and the geographic position information; and taking at least one candidate road associated with the target vehicle at the time t and the probability value of the target vehicle at the associated candidate road as the position characteristic information of the target vehicle at the time t so as to predict the position characteristic information of the target vehicle at N times.

In a specific example of the application, the prediction unit is further configured to determine at least two preset features required for locating the road where the target vehicle is located, and initial weights of the preset features; determining an initial characteristic value of the preset characteristic, wherein the initial characteristic value is determined based on road image information of the target vehicle at the time t of the N times and geographical position information of the target vehicle; and obtaining a probability value of the target vehicle at the associated candidate road at the time t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the time t.

In a specific example of the solution of the present application, the optimizing unit is further configured to optimize an initial weight of the preset feature to obtain a target weight for the preset feature; wherein the initial road predicted based on the target weight matches the true initial road.

In a specific example of the scheme of the application, the transfer characteristic determining unit is further configured to obtain the position characteristic information at the time t and the position characteristic information at thetime t + 1; multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at thetime t + 1; and taking the multiplication processing result as transfer characteristic information of the target vehicle from the time t to the time t +1 in the N moments.

In a specific example of the scheme of the application, the initial road determining unit is further configured to obtain probability values of all transition paths based on the location characteristic information and the road transition information; and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.

The functions of each unit in the road positioning device according to the embodiment of the present invention may refer to the corresponding description in the above method, and are not described herein again.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an exampleelectronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, theelectronic device 500 includes acomputing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from astorage unit 508 into a Random Access Memory (RAM) 503. In theRAM 503, various programs and data required for the operation of theelectronic apparatus 500 can also be stored. Thecalculation unit 501, theROM 502, and theRAM 503 are connected to each other by abus 504. An input/output (I/O)interface 505 is also connected tobus 504.

A number of components in theelectronic device 500 are connected to the I/O interface 505, including: aninput unit 506 such as a keyboard, a mouse, or the like; anoutput unit 507 such as various types of displays, speakers, and the like; astorage unit 508, such as a magnetic disk, optical disk, or the like; and acommunication unit 509 such as a network card, modem, wireless communication transceiver, etc. Thecommunication unit 509 allows theelectronic device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Thecomputing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of thecomputing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. Thecalculation unit 501 performs the respective methods and processes described above, such as a road positioning method. For example, in some embodiments, the road location method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such asstorage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto theelectronic device 500 via theROM 502 and/or thecommunication unit 509. When the computer program is loaded into theRAM 503 and executed by thecomputing unit 501, one or more steps of the road locating method described above may be performed. Alternatively, in other embodiments, thecomputing unit 501 may be configured to perform the road location method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 foregoing.

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

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A road locating method comprising:

2. The method of claim 1, further comprising:

and optimizing the predicted position characteristic information based on the difference characteristics between the predicted initial road and the real initial road of the target vehicle in the time period corresponding to the N moments.

3. The method of claim 2, further comprising:

acquiring road image information and geographical position information of the target vehicle at the time t;

predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle in the associated candidate road based on the road image information and the geographic position information;

and taking at least one candidate road associated with the target vehicle at the time t and the probability value of the target vehicle at the associated candidate road as the position characteristic information of the target vehicle at the time t so as to predict the position characteristic information of the target vehicle at N times.

4. The method of claim 2 or 3, further comprising:

determining at least two preset features required for positioning the road where the target vehicle is located and initial weights of the preset features;

determining an initial characteristic value of the preset characteristic, wherein the initial characteristic value is determined based on road image information of the target vehicle at the time t of the N times and geographical position information of the target vehicle;

and obtaining a probability value of the target vehicle at the associated candidate road at the time t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the time t.

5. The method of claim 4, wherein the optimizing the predicted location feature information comprises:

optimizing the initial weight of the preset feature to obtain a target weight for the preset feature; wherein the initial road predicted based on the target weight matches the true initial road.

6. The method of claim 3, wherein the obtaining transfer characteristic information of the target vehicle from time t to time t +1 of the N times based on the position characteristic information of the target vehicle at the N times comprises:

acquiring the position characteristic information at the time t and the position characteristic information at the time t + 1;

multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t + 1;

and taking the multiplication processing result as transfer characteristic information of the target vehicle from the time t to the time t +1 in the N moments.

7. The method according to claim 3, wherein the predicting an initial road on which the target vehicle is located in a time period corresponding to the N moments from all the candidate roads based on the position feature information and the road diversion information comprises:

obtaining probability values of all transfer paths based on the position characteristic information and the road transfer information;

and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.

8. A road locating device comprising:

9. The apparatus of claim 8, further comprising:

10. The device of claim 9, wherein the prediction unit is further configured to obtain road image information and geographical location information of the target vehicle at the time t; predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle in the associated candidate road based on the road image information and the geographic position information; and taking at least one candidate road associated with the target vehicle at the time t and the probability value of the target vehicle at the associated candidate road as the position characteristic information of the target vehicle at the time t so as to predict the position characteristic information of the target vehicle at N times.

11. The device according to claim 9 or 10, wherein the prediction unit is further configured to determine at least two preset features required for locating the road on which the target vehicle is located, and initial weights of the preset features; determining an initial characteristic value of the preset characteristic, wherein the initial characteristic value is determined based on road image information of the target vehicle at the time t of the N times and geographical position information of the target vehicle; and obtaining a probability value of the target vehicle at the associated candidate road at the time t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the time t.

12. The apparatus of claim 11, wherein the optimizing unit is further configured to optimize an initial weight of the preset feature to obtain a target weight for the preset feature; wherein the initial road predicted based on the target weight matches the true initial road.

13. The apparatus according to claim 10, wherein the transfer characteristic determining unit is further configured to obtain the location characteristic information at the time t and the location characteristic information at the time t + 1; multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t + 1; and taking the multiplication processing result as transfer characteristic information of the target vehicle from the time t to the time t +1 in the N moments.

14. The apparatus of claim 10, wherein the initial road determining unit is further configured to obtain probability values of all transition paths based on the location feature information and the road transition information; and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.

15. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-7.

17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.