State prediction method and device of traffic signal lamp, equipment and medium

Abstract

The invention relates to a traffic signal lamp state prediction method, device and equipment and a medium, and the method comprises the steps: receiving the collection data, sent by a vehicle, of a traffic signal lamp, and the collection data comprises the collection time and the signal lamp state of the traffic signal lamp at the collection time; determining a lamp state time sequence of each traffic signal lamp according to the signal lamp state of the traffic signal lamp at each acquisition time; and according to the lamp state time sequence and the change rule information of each traffic signal lamp, generating a state prediction result of the traffic signal lamp in a specified time period. According to the technical scheme, the future signal lamp state of the traffic signal lamp can be predicted.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a method, device, equipment and medium for predicting the state of a traffic light. Background Art

[0002] Traffic lights are common facilities in the process of vehicle driving. Traffic lights are used to direct traffic operations and generally consist of red, green and yellow light states.

[0003] At present, some traffic lights do not display countdowns, and drivers cannot know when the status of the traffic lights changes, which affects the driving experience. How to predict the status of traffic lights is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and medium for predicting the state of a traffic light.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for predicting a state of a traffic light, comprising:

[0006] Receive the collected data of the traffic light sent by the vehicle; the collected data includes the collection time and the signal light state of the traffic light at the collection time;

[0007] Determining a light state time sequence of each of the traffic lights according to the light state of the traffic lights at each collection time;

[0008] According to the light state time series and change rule information of each traffic light, a state prediction result of the traffic light within a specified time period is generated.

[0009] In a second aspect, an embodiment of the present disclosure provides another method for predicting the state of a traffic light, including:

[0010] In the current time period when the vehicle drives to the traffic light, a sequence to be matched is obtained; the sequence to be matched includes the state of the traffic light in the current time period;

[0011] Querying a light state time sequence of the traffic light, and determining a subsequence corresponding to the current time period from the light state time sequence;

[0012] Generating a state prediction result of the traffic light according to a comparison result of the sequence to be matched and the subsequence;

[0013] Prompts are given based on the state prediction result of the traffic light.

[0014] In a third aspect, an embodiment of the present disclosure provides a state prediction device for a traffic light, comprising:

[0015] An acquisition module is used to receive the collected data of the traffic light sent by the vehicle; the collected data includes the collection time and the state of the traffic light at the collection time;

[0016] A determination module, used to determine a light state time sequence of each of the traffic lights according to the light state of the traffic lights at each collection time;

[0017] A generation module is used to generate a state prediction result of the traffic light within a specified time period according to the light state time series and change rule information of each traffic light.

[0018] In a fourth aspect, an embodiment of the present disclosure provides another traffic light state prediction device, comprising:

[0019] A collection module, used for acquiring a sequence to be matched within a current time period when the vehicle drives to the traffic light; the sequence to be matched includes the state of the traffic light within the current time period;

[0020] A query module, used for querying the light state time sequence of the traffic light, and determining a subsequence corresponding to the current time period from the light state time sequence;

[0021] A prediction module, used for generating a state prediction result of the traffic light according to a comparison result of the sequence to be matched and the subsequence;

[0022] A prompt module is used to provide prompts based on the state prediction result of the traffic light.

[0023] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the traffic light state prediction method described in the above aspects.

[0024] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the state of a traffic light described in the above aspects is implemented.

[0025] Compared with the prior art, the technical solution provided by the embodiments of the present invention has the following advantages: the signal light status of the traffic light at each collection time is collected by a vehicle, and the collection time and the signal light status are processed to obtain the light state time series of each traffic light, so as to predict the signal light status of the traffic light according to the light state time series and the change law information; thus, the future signal light status of the traffic light can be predicted based on the historical light state time series and the change law of the traffic light, thereby providing prompts for the user's driving and improving the driving convenience and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 A schematic diagram of a flow chart of a method for predicting the state of a traffic light provided by an embodiment of the present disclosure;

[0029] Figure 2 A schematic diagram of a flow chart of another method for predicting the state of a traffic light provided by an embodiment of the present disclosure;

[0030] Figure 3 A schematic diagram of the structure of a traffic light state prediction device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0033] Figure 1A flow chart of a method for predicting the state of a traffic light provided in an embodiment of the present disclosure. The method provided in an embodiment of the present disclosure can be executed by a device for predicting the state of a traffic light. The device can be implemented in software and / or hardware and can be integrated on any electronic device with computing capabilities.

[0034] like Figure 1 As shown, the state prediction method of a traffic light provided by an embodiment of the present disclosure may include:

[0035] Step 101, receiving the collected data of the traffic light sent by the vehicle.

[0036] In this embodiment, the collected data includes the collection time and the state of the traffic light at the collection time, and the state of the traffic light includes the color of the traffic light. During the driving process of the vehicle, the collected data of each traffic light is obtained through the environment perception method, and then each vehicle sends the collected data to the data processing end, and the data processing end receives the collected data sent by each vehicle to further establish a database of traffic lights according to the collected data.

[0037] As an example, a vehicle is provided with an image acquisition device, and the vehicle acquires images of the surrounding environment while driving, for example, the image in front of the vehicle is acquired through a front camera, and then the traffic lights in the image are identified through image processing, and the traffic light color, signal light type and other information of the traffic light are determined, the signal light colors include red, green, yellow and dark, the signal light types include straight, left turn, right turn, U-turn, pedestrian traffic light, non-motor vehicle light, and the time of acquiring the image is used as the acquisition time in the acquisition data, and the vehicle sends the acquisition data to the data processing end. In this example, the vehicle can send the acquisition data of each acquisition time to the data processing end, or send the acquisition data of multiple consecutive acquisition times as a sequence to the data processing end.

[0038] Among them, the data processing end can be a cloud server, for example, each vehicle sends all collected data to the cloud server, and the data processing end can also be a roadside unit. For example, the roadside unit is set at an intersection. After the vehicle collects the collected data of the traffic lights at the intersection, the collected data is sent to the roadside unit of the intersection. There is no limitation here.

[0039] Step 102: determining a light state time sequence of each traffic light according to the light state of the traffic light at each collection time.

[0040] In this embodiment, the collected data of each traffic light is arranged in the order of the collection time according to the light state at each collection time in the collected data to generate a traffic light state time sequence. The time interval for collecting data can be set as needed, for example, the time interval is one second.

[0041] In one embodiment of the present disclosure, the collected data also includes vehicle positioning information and vehicle travel direction at the collection time, and the light state time series of each traffic light is determined according to the traffic light state at each collection time, including: for each piece of collected data, determining the intersection sign corresponding to the vehicle positioning information, and then, among the multiple traffic lights under the intersection sign, determining the traffic light that matches the collected data according to the vehicle travel direction; further, for each traffic light, verifying the traffic light state at each collection time in all collected data matching the traffic light, and generating the traffic light state time series in the order of collection time.

[0042] In this embodiment, an intersection range is set corresponding to each intersection sign, and the collected data of the vehicle positioning information within the intersection range is determined as the intersection sign corresponding to the vehicle positioning information, wherein the vehicle positioning information is used to indicate the position of the vehicle, and the vehicle positioning information can be satellite positioning of ordinary accuracy or converted ordinary satellite positioning, or it can be vision-based positioning, or it can be point cloud-based positioning, or it can be a fusion positioning based on the above positioning, which is not limited here.

[0043] Among them, the intersection usually includes multiple traffic lights. For the method of obtaining traffic light information through image recognition, by determining the intersection logo and vehicle travel direction corresponding to each collected data, it can be determined which traffic light in the intersection the collected data matches. Then, after determining all the collected data matching each traffic light, since different vehicles may collect the information of the traffic light at the same collection time, the collected information may have errors, that is, there may be multiple traffic light states at the same collection time in the collected data. All traffic light states at the same collection time can be verified to obtain the traffic light state at the collection time. Optionally, the traffic light state at each collection time in all the collected data matching the traffic light is verified, including: for multiple traffic light states at the target collection time, determining the number of each traffic light state, and then determining the target traffic light state with the largest number from the multiple traffic light states as the traffic light state at the target collection time.

[0044] As an example, the collected data also includes traffic light types, which include straight ahead, left turn, and right turn. For each traffic light type of the same traffic light, the light state time series of the traffic light type can be determined separately. The determination method refers to the above explanation and will not be repeated here.

[0045] In this embodiment, by determining the light state time series of each traffic light, a database of traffic lights can be established, in which the light state time series of traffic lights is stored, and the light state time series is used to indicate the state of the traffic lights in chronological order. By obtaining the light state time series of traffic lights within a certain period of time and performing analysis and processing based on the light state time series, the change law information of the state change of the traffic lights can be obtained. The change law information can be based on the change law at the same time or based on the change law of the display duration, including the adjustment of the time period, the type of traffic lights, the color of traffic lights and the update of the corresponding display duration. Among them, after the database of traffic lights is established, the database can be stored at the data processing end or at the vehicle end.

[0046] Step 103: Generate a state prediction result of the traffic light within a specified time period according to the light state time series and change rule information of each traffic light.

[0047] In this embodiment, the state of a traffic light can be predicted based on the light state time series and the change rule information to obtain a traffic light state prediction result.

[0048] The prediction process is described below.

[0049] In one embodiment of the present disclosure, when a vehicle drives to an intersection, in the current time period before the vehicle drives to the traffic light, the vehicle collects the signal light state of the traffic light ahead, and constructs a sequence to be matched about the signal light state in chronological order according to the signal light state of the traffic light in the current time period, so as to generate a state prediction result about the signal light state based on the comparison result of the sequence to be matched with the light state time series.

[0050] Optionally, in response to obtaining a sequence to be matched about the state of the traffic light obtained by the vehicle in the current time period, the data processing end determines a subsequence corresponding to the current time period from the light state time series, and then, when the sequence to be matched is consistent with the subsequence, generates a state prediction result according to the first traffic light state change moment after the subsequence. The subsequence corresponding to the current time period may include a subsequence that is the same as the moment represented by the current time period and a subsequence that is the same as the time length represented by the current time period.

[0051] As an example, the database includes a light state time series within a week, and the light state time series is divided into time series with multiple time periods according to the change law information, for example, the light state time series within a week is divided into seven time series with a day as a period. The current time period is 5:00:00 to 5:00:10, a total of ten seconds, then the light state time series between 5:00:00 and 5:00:10 of the previous day is obtained as a subsequence corresponding to the current time period, and then the sequence to be matched is compared with the subsequence. When the sequence to be matched is consistent with the subsequence, for example, the sequence to be matched and the subsequence are both [1, 1, 1, 1, 1, 1, 1, 1, 1], where 1 represents a red light, the first signal light state change moment after the subsequence is determined from the light state time series to generate a state prediction result based on the signal light state change moment.

[0052] Optionally, after obtaining the sequence to be matched about the state of the traffic light collected by the vehicle in the current time period, if a subsequence consistent with the sequence to be matched is not matched in the light state time sequence, the light state time sequence of the traffic light is updated. Wherein, if a subsequence consistent with the sequence to be matched is not matched in the light state time sequence, the vehicle's current collected data is recorded to update the database of the traffic light based on the current collected data. Updating the database includes adding new data to the database, modifying existing data, and reintegrating existing data. When modifying and recombining the data, the validity of the new data is verified according to the number of times the new data occurs and the size of the difference between the new data and the existing data.

[0053] After predicting the state of a traffic light, and obtaining a state prediction result of the traffic light, the state prediction result can be applied to prompts, vehicle control, and the like.

[0054] According to the technical solution of the embodiment of the present disclosure, the signal light status of the traffic light at each collection time is collected by a vehicle, and is processed based on the collection time and the signal light status to obtain a light state time series of each traffic light, so as to predict the signal light status of the traffic light according to the light state time series and the change law information. Therefore, the future signal light status of the traffic light can be predicted based on the historical signal light status and change law of the traffic light, thereby providing prompts for the user's driving and improving driving convenience and comfort.

[0055] Based on the above embodiments, a method for predicting the state of a traffic light on a vehicle side is described below. Figure 2 A flow chart of another method for predicting the state of a traffic light provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the method comprises the following steps:

[0056] Step 201 : obtaining a sequence to be matched within the current time period when the vehicle is traveling to the traffic light.

[0057] The sequence to be matched includes the signal light status of the traffic light in the current time period.

[0058] In this embodiment, when the vehicle drives to the intersection, in the current time period before the vehicle drives to the traffic light, the vehicle collects the signal light status of the traffic light ahead, and constructs a sequence of signal light status to be matched in chronological order according to the signal light status of the traffic light in the current time period.

[0059] Step 202, query the light state time sequence of the traffic light, and determine the subsequence corresponding to the current time period from the light state time sequence.

[0060] In this embodiment, the light state time sequence of the traffic light can be implemented in the manner of the above-mentioned embodiment, and the light state time sequence can be stored in the data processing end, such as in the cloud server, the roadside unit, or in the vehicle end. Optionally, the vehicle determines the traffic light corresponding to the vehicle positioning information and the vehicle driving direction from the database according to the vehicle positioning information and the vehicle driving direction when the sequence to be matched is obtained, and then queries the light state time sequence of the traffic light, and determines the subsequence corresponding to the current time period from the light state time sequence, wherein the subsequence corresponding to the current time period may include a subsequence that is the same as the moment represented by the current time period and a subsequence that is the same as the time length represented by the current time period.

[0061] Step 203: Generate a traffic light state prediction result according to the comparison result of the sequence to be matched and the subsequence.

[0062] In this embodiment, the sequence to be matched is compared with the subsequence. When the sequence to be matched and the subsequence are consistent, the subsequent signal light state is output, and the first signal light state change moment after the subsequence is determined from the light state time series to generate a state prediction result based on the signal light state change moment.

[0063] In one embodiment of the present disclosure, when the sequence to be matched is consistent with the first subsequence, a state prediction result is generated according to the first signal light state change moment after the first subsequence. When the sequence to be matched is inconsistent with the first subsequence, the sequence to be matched is matched with the light state time sequence to determine at least one second subsequence consistent with the sequence to be matched from the light state time sequence, and then, for each second subsequence, a candidate state prediction result is determined according to the first signal light state change moment after the second subsequence, and further, the sequence to be matched is updated, and the candidate state prediction results that do not meet the sequence matching conditions are deleted from all candidate state prediction results to obtain the state prediction result of the traffic light.

[0064] Among them, the first subsequence is the same subsequence as the moment represented by the current time period. As an example, the database includes a light state time series within a week. The light state time series is divided into time series with multiple time periods according to the change law information. For example, the light state time series within a week is divided into seven time series with days as the period. The current time period is from 5:00:00 to 5:00:10, the first subsequence is the light state time series from 5:00:00 to 5:00:10 the previous day, the light state in the sequence to be matched is green, and the light state in the first subsequence is red. A second subsequence consistent with the sequence to be matched is further determined from other parts of the light state time series. At this time, multiple second subsequences are obtained, and the vehicle continuously collects the state of the traffic light and updates the sequence to be matched. For example, the current time period is continuously updated to 5:00:00 to 5:00:40, and the sequence to be matched is updated to the first ten seconds of green light and the last thirty seconds of red light. The light state time series includes two situations: twenty seconds of red light and fifty seconds of red light. At this time, based on sequence matching, the second subsequences and corresponding candidate state prediction results that do not meet the matching conditions can be deleted from all second subsequences and corresponding candidate state prediction results, and a final candidate state prediction result is obtained as the state prediction result of the traffic light.

[0065] Step 204: Prompt based on the traffic light status prediction result.

[0066] In this embodiment, the state prediction result is used to indicate the state of the traffic light within a certain period of time in the future. After predicting the state of the traffic light and obtaining the state prediction result of the traffic light, operations such as prompts and vehicle control can be performed based on the state prediction result. Optionally, in the case of a consistent comparison, the confidence of the state prediction result can be further determined to perform different operations for different confidences, wherein the confidence is used to indicate the credibility of the state prediction result, for example, the sequence fragment 101 is used as an identification bit, where 1 indicates a red light and 0 indicates a dark color. When the comparison is consistent and the identification bit exists, it is determined as the first confidence, and when the comparison is consistent and the identification bit does not exist, it is determined as the second confidence, wherein the first confidence is greater than the second confidence.

[0067] In the disclosed embodiment, when a vehicle drives to an intersection, the future state of the traffic light can be determined from the historical light state time series based on the comparison between the currently collected time series and the historical light state time series, thereby realizing traffic light state prediction, thereby providing prompts for the user's driving and improving driving convenience and comfort.

[0068] Based on the above embodiments, the present disclosure proposes a traffic light state prediction device. Figure 3 A schematic diagram of a traffic light state prediction device provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown, the traffic light state prediction device includes: an acquisition module 31 , a determination module 32 , and a generation module 33 .

[0069] The acquisition module 31 is used to receive the collected data of the traffic light sent by the vehicle; the collected data includes the collection time and the state of the traffic light at the collection time;

[0070] A determination module 32, for determining a light state time sequence of each traffic light according to the light state of the traffic light at each collection time;

[0071] The generating module 33 is used to generate the state prediction result of the traffic light within a specified time period according to the light state time series and change rule information of each traffic light.

[0072] In one embodiment of the present disclosure, the collected data also includes vehicle positioning information and vehicle driving direction at the collection time, and the determination module 32 is specifically used to:

[0073] For each piece of collected data, determine the intersection sign corresponding to the vehicle positioning information; the intersection range corresponding to the intersection sign includes the vehicle positioning information;

[0074] Among multiple traffic lights under the intersection sign, determine the traffic light that matches the collected data according to the vehicle's travel direction;

[0075] For each traffic light, the status of the traffic light at each collection time in all the collected data matching the traffic light is verified, and a time series of the light status of the traffic light is generated in the order of the collection time.

[0076] In one embodiment of the present disclosure, the determination module 32 is specifically configured to:

[0077] For multiple signal light states at the target collection time, determine the number of each signal light state;

[0078] The target signal light state with the largest number is determined from the multiple signal light states as the signal light state at the target collection time.

[0079] In one embodiment of the present disclosure, the generating module 33 is specifically used to:

[0080] In response to obtaining a sequence to be matched about the signal light state obtained by the vehicle in the current time period, determining a subsequence corresponding to the current time period from the light state time series;

[0081] When the sequence to be matched is consistent with the subsequence, the state prediction result is generated according to the first traffic light state change moment after the subsequence.

[0082] In one embodiment of the present disclosure, the device further includes:

[0083] The updating module is used to update the light state time sequence of the traffic light when a subsequence consistent with the sequence to be matched is not matched in the light state time sequence.

[0084] Based on the above embodiments, the present disclosure further proposes another device for predicting the state of a traffic light, which includes: a collection module, a query module, a prediction module, and a prompt module.

[0085] The acquisition module is used to obtain a sequence to be matched within a current time period when the vehicle drives to the traffic light; the sequence to be matched includes the state of the traffic light within the current time period;

[0086] A query module, used to query the light state time sequence of the traffic light, and determine the subsequence corresponding to the current time period from the light state time sequence;

[0087] A prediction module, used for generating a state prediction result of a traffic light according to the comparison result of the sequence to be matched and the subsequence;

[0088] The prompt module is used to provide prompts based on the state prediction results of the traffic light.

[0089] In one embodiment of the present disclosure, the prediction module is specifically used to:

[0090] When the sequence to be matched is consistent with the first subsequence, a state prediction result is generated according to the first signal light state change moment after the first subsequence; the first subsequence is the same as the moment represented by the current time period;

[0091] When the sequence to be matched is inconsistent with the first subsequence, matching the sequence to be matched with the light state time sequence to determine at least one second subsequence consistent with the sequence to be matched from the light state time sequence;

[0092] For each second subsequence, determining a candidate state prediction result according to the first traffic light state change moment after the second subsequence;

[0093] The sequence to be matched is updated, and the candidate state prediction results that do not meet the sequence matching condition are deleted from all candidate state prediction results to obtain the state prediction result of the traffic light.

[0094] The state prediction device for traffic lights provided in the embodiments of the present disclosure can execute any state prediction method for traffic lights provided in the embodiments of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method. Contents not fully described in the embodiments of the present disclosure device can refer to the description in any method embodiment of the present disclosure.

[0095] The present disclosure also provides an electronic device, which includes one or more processors and a memory. The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer-readable storage medium, and the processor may run the program instructions to implement the method of the above embodiment of the present disclosure and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0096] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms. In addition, the input device may also include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and a remote output device connected thereto, etc. In addition, according to the specific application, the electronic device may also include any other appropriate components such as a bus, an input / output interface, etc.

[0097] In addition to the above methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes any method provided by the embodiments of the present disclosure.

[0098] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0099] In addition, the embodiments of the present disclosure may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes any method provided by the embodiments of the present disclosure.

[0100] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0101] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0102] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the state of a traffic light, characterized in that: The method comprises: Receive the collected data of the traffic light sent by the vehicle; the collected data includes the collection time and the signal light state of the traffic light at the collection time; Determining a light state time sequence of each of the traffic lights according to the light state of the traffic lights at each collection time; According to the light state time series and change rule information of each of the traffic lights, a state prediction result of the traffic lights within a specified time period is generated.

2. The method according to claim 1, characterized in that The collected data also includes vehicle positioning information and vehicle driving direction at the collection time. The determining of the light state time sequence of each traffic light according to the light state of the traffic light at each collection time includes: For each piece of the collected data, determining an intersection mark corresponding to the vehicle positioning information; the intersection range corresponding to the intersection mark includes the vehicle positioning information; Among the multiple traffic lights under the intersection sign, determining a traffic light matching the collected data according to the driving direction of the vehicle; For each of the traffic lights, verification processing is performed on the status of the traffic light at each collection time in all the collection data matching the traffic light, and a light state time series of the traffic light is generated in the order of the collection time.

3. The method according to claim 2, characterized in that The verifying process of the traffic light status at each collection time in all the collected data matching the traffic light includes: For multiple signal light states at the target collection time, determine the number of each signal light state; The target signal light state with the largest number is determined from the multiple signal light states as the signal light state at the target collection time.

4. The method according to claim 1, characterized in that The step of generating a state prediction result of the traffic light within a specified time period according to the light state time series and change rule information of each traffic light comprises: In response to obtaining a sequence to be matched about the signal light state obtained by the vehicle in a current time period, determining a subsequence corresponding to the current time period from the light state time series; When the sequence to be matched is consistent with the subsequence, the state prediction result is generated according to the first traffic light state change moment after the subsequence.

5. The method according to claim 4, characterized in that After obtaining the sequence to be matched about the signal light state obtained by the vehicle in the current time period, the method further includes: When no subsequence consistent with the sequence to be matched is found in the light state time sequence, the light state time sequence of the traffic light is updated.

6. A method for predicting the state of a traffic light, characterized in that: The method comprises: In the current time period when the vehicle drives to the traffic light, a sequence to be matched is obtained; the sequence to be matched includes the state of the traffic light in the current time period; Querying a light state time sequence of the traffic light, and determining a subsequence corresponding to the current time period from the light state time sequence; Generating a state prediction result of the traffic light according to a comparison result of the sequence to be matched and the subsequence; Prompts are given based on the state prediction result of the traffic light.

7. The method according to claim 6, characterized in that The step of generating a state prediction result of the traffic light according to a comparison result of the sequence to be matched and the subsequence includes: In the case where the sequence to be matched is consistent with the first subsequence, generating the state prediction result according to the first signal light state change moment after the first subsequence; the first subsequence is the same as the moment represented by the current time period; In the case that the sequence to be matched is inconsistent with the first subsequence, matching the sequence to be matched with the light state time sequence to determine at least one second subsequence consistent with the sequence to be matched from the light state time sequence; For each of the second subsequences, determining a candidate state prediction result according to the first traffic light state change moment after the second subsequence; The sequence to be matched is updated, and candidate state prediction results that do not meet the sequence matching condition are deleted from all the candidate state prediction results to obtain the state prediction result of the traffic light.

8. A traffic light state prediction device, characterized in that: include: An acquisition module is used to receive the collected data of the traffic light sent by the vehicle; the collected data includes the collection time and the state of the traffic light at the collection time; A determination module, used to determine a light state time sequence of each of the traffic lights according to the light state of the traffic lights at each collection time; A generation module is used to generate a state prediction result of the traffic light within a specified time period according to the light state time series and change rule information of each traffic light.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the traffic light state prediction method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the state of a traffic light described in any one of claims 1 to 7 is implemented.

Images