CN111866768A

CN111866768A - Message sending control method and device in perception base station

Info

Publication number: CN111866768A
Application number: CN201910357537.6A
Authority: CN
Inventors: 单单; 陈颖
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-04-29
Filing date: 2019-04-29
Publication date: 2020-10-30
Also published as: WO2020221023A1

Abstract

The embodiment of the application discloses a method and a device for controlling message sending in a perception base station, wherein the method comprises the following steps: the perception base station obtains definition information of a descriptor for describing characteristic elements of the vehicle; after a target vehicle is detected, obtaining characteristic elements related to the target vehicle; determining the type and value of a target descriptor for describing the characteristic elements of the target vehicle according to the definition information of the descriptor; and adding the type and the value information of the target description body into a message body for sending, so that the vehicle-mounted unit generates and outputs a natural sentence by performing natural language processing on the type and the value of the target description body. By the embodiment of the application, the driver can intuitively associate the vehicle described in the message with the vehicle in the real world, and the possibly dangerous situation can be more effectively dealt with.

Description

Message sending control method and device in perception base station

Technical Field

The present application relates to the field of message transmission control technologies, and in particular, to a method and an apparatus for controlling message transmission in a cognitive base station.

Background

In the Vehicle-Road cooperative system, a sensing result of a sensing base station (base station for short) is sent to nearby vehicles through a Road Side Unit (RSU) in a Vehicle to Everering (V2X) system. The sensing results mainly comprise information of positions, speeds, orientations and the like of traffic participants such as pedestrians, vehicles and the like, and the information is packaged in a message. After the vehicle receives the messages through the On-Board Unit (OBU), the danger in the driving process can be predicted in advance, and actions such as alarming and the like are taken to deal with the danger.

All vehicles detected by the base station include normal running vehicles and dangerous vehicles. Among them, a vehicle that poses a threat to the driving safety of surrounding vehicles is referred to as a dangerous vehicle. Hazardous vehicles include, but are not limited to: vehicles that violate traffic regulations, such as speeding, running red lights, etc.; a faulty vehicle such as a vehicle parked at a highway side, a vehicle with a tire burst, or the like; dangerous driving vehicles, such as drunk driving vehicles, vehicles which often change lanes maliciously or brake suddenly, and the like. Dangerous vehicles require high vigilance from surrounding vehicles. For example, a vehicle having an illegal behavior such as speeding or running a red light easily collides with another vehicle; vehicles which are stopped at the high-speed roadside are easy to be rear-ended by vehicles which normally run; vehicles which frequently change lanes maliciously need to avoid surrounding vehicles in time.

A vehicle that does not pose a threat to the driving safety of surrounding vehicles is referred to as a normal-travel vehicle. Normal-running vehicles include stationary vehicles that are legally parked at a designated place or parking space.

The base station is relatively simple to handle for normally traveling vehicles and typically periodically transmits their position and/or motion status. However, for dangerous vehicles, the base station needs to perform special handling of them, for example, defining special message formats for dangerous behaviors of these vehicles and sending these messages to the vehicles. After the vehicle receives the messages, the vehicle can acquire the dangerous behaviors from the corresponding fields and carry out corresponding emergency treatment.

In the prior art, such a message about a dangerous vehicle is mainly processed by an OBU provided to the vehicle, and therefore, information about the position, orientation, speed, size, and the like of the vehicle is mainly described. With this information, it is possible for the machine to locate precisely which of the surrounding vehicles is the vehicle described in the message, and in the case of fully autonomous driving, the autonomous driving system can respond precisely on the basis of this information.

However, in some situations, the specific vehicle-road coordination system may also provide a function of driving assistance, that is, the main actions of acceleration and deceleration, turning, etc. are still issued by the driver, and the vehicle-road coordination system is mainly used for providing the driver with some reference information, such as the information about the dangerous vehicle described above, so that the driver can react, take countermeasures, etc., which requires that the driver be clearly informed of which specific vehicle belongs to the dangerous vehicle. However, in the prior art, since the position, orientation, speed and size of the dangerous vehicle are carried in the message, the position, orientation, speed and other information of the vehicle are changed in real time, and mathematical descriptions are used, and the descriptions are difficult to be associated with the vehicle in the physical world perceived by the driver, so that accurate risk avoidance measures are difficult to be taken. The dimensional information of the vehicle also cannot uniquely define the identity of the vehicle, making it difficult to accurately identify the vehicle. For example, there are often vehicles on the road that are very similar in overall dimensions and travel side-by-side or very close together, and if one of them is a dangerous vehicle, it is difficult to identify it by size alone.

Disclosure of Invention

The application provides a message sending control method and device in a perception base station, which can enable a driver to intuitively associate a vehicle described in a message with a vehicle in the real world, and further more effectively deal with possible dangerous situations.

The application provides the following scheme:

a message sending control method in a perception base station comprises the following steps:

the perception base station obtains definition information of a vehicle description body, wherein the definition information comprises the type and value of the description body and corresponding meaning information, and is used for describing feature elements which can be recognized by human eyes on a vehicle through the description body;

after a target vehicle is detected, obtaining characteristic elements related to the target vehicle;

determining the type and value of a target descriptor for describing the characteristic elements of the target vehicle according to the definition information of the descriptor;

and adding the type and the value information of the target description body into a message body for sending, so that the vehicle-mounted unit generates and outputs a natural sentence by performing natural language processing on the type and the value of the target description body.

A method of providing vehicle information, comprising:

The vehicle-mounted unit obtains definition information of a vehicle description body, wherein the definition information comprises the type and value of the description body and corresponding meaning information, and is used for describing characteristic elements which can be recognized by human eyes on a vehicle through the description body;

receiving a message sent by a perception base station, and acquiring the type and value information of a target description body corresponding to a target vehicle from the message;

and determining corresponding meaning information according to the type and the value information of the target description body and the definition information, performing natural language processing according to the meaning information, generating a natural sentence comprising characteristic element information which can be recognized by human eyes, and outputting the natural sentence.

A message sending control device in an awareness base station is applied to the awareness base station and comprises the following components:

the system comprises a definition information obtaining unit, a feature element obtaining unit and a feature element analyzing unit, wherein the definition information obtaining unit is used for obtaining definition information of a description body for describing feature elements of a vehicle, the definition information comprises types, values and corresponding meaning information of the description body, and the feature elements comprise feature elements recognizable by human eyes;

a feature element obtaining unit configured to obtain a feature element regarding a target vehicle after the target vehicle is detected;

The information conversion unit is used for determining the type and value of a target description body for describing the characteristic elements of the target vehicle according to the definition information of the description body;

and the message generating unit is used for adding the type and the value information of the target description body into a message body so as to be sent, so that the vehicle-mounted unit generates and outputs a natural sentence by performing natural language processing on the type and the value of the target description body.

An apparatus for providing vehicle information, applied to an on-board unit, includes:

the information receiving unit is used for receiving the information sent by the perception base station and acquiring the type and value information of a target description body corresponding to a target vehicle from the information;

and the natural sentence output unit is used for determining corresponding meaning information according to the type and the value information of the target description body and the definition information, performing natural language processing according to the meaning information, generating and outputting a natural sentence comprising characteristic element information which can be identified by human eyes.

A message structure is disclosed, which is composed of a message structure,

the message is sent through a perception base station in the intelligent traffic system;

the message structure body comprises the type and value information of a target description body of the target vehicle, and the target description body is used for describing feature elements which can be recognized by human eyes on the target vehicle.

According to the specific embodiments provided herein, the present application discloses the following technical effects:

by the embodiment of the application, after a specific target vehicle (for example, a dangerous vehicle and the like) is identified, characteristic elements of the vehicle can be collected, the characteristic elements mainly comprise some characteristics recognizable by human eyes, such as related elements of colors, figures, shapes, texts and the like, and the characteristic elements can be described through a descriptor predefined for each characteristic element, so that the characteristic elements can be carried in a specific message body for transmission. The on-board unit or the like on the receiving side may analyze the received specific message, extract the descriptor information related to the vehicle from the analyzed message, convert the descriptor information according to the definition information, and perform natural language processing, thereby generating and outputting a natural sentence. In this way, since the specific feature elements are human-understandable features, rather than some information such as coordinates, the driver can intuitively associate the vehicle described in the message with the vehicle in the real world, and thus, the dangerous situation that may occur can be dealt with more effectively.

Of course, it is not necessary for any product to achieve all of the above-described advantages at the same time for the practice of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

FIG. 2 is a flow chart of a first method provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a first system provided by an embodiment of the present application;

FIG. 4 is a flow chart of a second method provided by embodiments of the present application;

FIG. 5 is a schematic diagram of a second system provided by embodiments of the present application;

FIG. 6 is a schematic diagram of a first apparatus provided by an embodiment of the present application;

fig. 7 is a schematic diagram of a second apparatus provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments that can be derived from the embodiments given herein by a person of ordinary skill in the art are intended to be within the scope of the present disclosure.

It should be noted that, in the process of implementing the present application, the inventor of the present application finds that, in order to provide more detailed information about a target vehicle (e.g., a dangerous vehicle, etc.) for a driver user, an implementation manner may be that a perception base station expands a message set, and a message carrying more original information such as a vehicle picture is used to describe the vehicle. However, this practice still faces at least two problems:

1. sending a message carrying a picture of a vehicle may consume a large amount of communication bandwidth, possibly resulting in network congestion;

2. the viewing angle of the base station is greatly different from the viewing angle of the driver, so that it is difficult to accurately match the picture of the vehicle taken by the base station with the vehicle observed by the driver.

Alternatively, another conceivable scheme is that after receiving the message with the information of the dangerous vehicle (including the position, orientation, speed and size information of the dangerous vehicle) sent by the base station, the vehicle extracts the information of the dangerous vehicle and sends the information to the man-machine interaction system, and the man-machine interaction system describes the dangerous vehicle and enables the driver to understand the dangerous vehicle through audio prompt, video prompt or vibration prompt and the like. However, the description of dangerous vehicles by the human-computer interaction system of the vehicle is a difficult matter, mainly because of the following reasons:

1. It is difficult to accurately describe a dangerous vehicle using audio cues or vibration cues. For example, if the audio system suggests a dangerous vehicle "30 meters in front of the right", but there are multiple vehicles in that direction, it is difficult for the driver to identify the actual dangerous vehicle. The use of vibration cues has the same problem.

2. The use of visual cues distracts the driver. For example, if the position or motion trajectory of a dangerous vehicle is displayed on the center control screen in real time, the attention of the driver needs to be frequently switched between the road surface and the screen, which brings a safety risk.

3. If the plurality of prompting modes are simply mixed, the complexity of the human-computer interaction system is increased, the difficulty of understanding the human-computer interaction system by a driver is improved, and even the normal operation of the driver is possibly interfered.

Based on the above analysis, the embodiment of the present application provides another more feasible implementation scheme, in which a feature element related to a target vehicle may be added to a message specifically sent by a sensing base station, and the feature element may be expressed by a predefined descriptor, where one descriptor may correspond to a field name and a specific value, and the field name may represent a type of information. In this way, the characteristic elements of the vehicle can be described through a plurality of fields and corresponding values, rather than carrying picture data such as specific photos, so that the consumption of the message on communication bandwidth can be reduced. In addition, such feature elements may specifically include information of feature elements recognizable by human eyes, so that, after receiving the message sent by the sensing base station at the vehicle-mounted unit side, natural language processing may be performed according to the information type, value and corresponding meaning information in the specific description body, and the natural language processing may be converted into natural sentences which are understandable by humans and include features recognizable by human eyes, and output the natural sentences, for example, "pay attention to white SUV with license plate number x on the front right", and the like. Therefore, the driver can conveniently link the acquired information with the vehicle in the real world and execute corresponding risk avoiding operation.

Specifically, as shown in fig. 1, in the embodiment of the present application, vehicle identification, acquisition of detailed feature description information, determination of a corresponding description body, generation of a message, and the like may be completed on the sensing base station side, and then the message may be sent; after the vehicle-mounted unit receives the sent message, the vehicle-mounted unit can extract detailed feature description information carried in the message, process related operations such as related natural language and the like, and further output the information through systems such as audio and video of the vehicle, so that a driver can obtain more intuitive and accurate information about the vehicle.

Specific implementations are described in detail below.

Example one

First, in the first embodiment, from the perspective of the cognitive base station, a method for controlling message transmission in the cognitive base station is provided, and referring to fig. 2, the method may specifically include:

s201: the perception base station obtains definition information of a vehicle description body, wherein the definition information comprises the type and value of the description body and corresponding meaning information, and is used for describing characteristic elements which can be recognized by human eyes on a vehicle through the description body;

in the embodiment of the present application, structural definitions of various types of messages transmitted by the base station may be defined in advance, where the structural definitions of messages about vehicles may be included. For example, the following may be specifically mentioned:

Wherein the fields associated with the embodiments of the present application are shown in bold. Where messageType is an identifier of a message class, and 6 indicates that the message carries information of a target vehicle(s) (e.g., a dangerous vehicle). For each vehicle, the message defines the number of descriptors (descriptors) for the vehicle, denoted by descriptor _ number. For each descriptor, the message defines its type and value, denoted by descriptor _ type and descriptor _ value, respectively, and their partial definitions are shown in table 1:

TABLE 1

The corresponding chinese definition can be as shown in table 2:

TABLE 2

With the development of technology, the contents in the table can be gradually expanded, but the existing contents can be kept unchanged.

Therefore, when describing various characteristic elements, the method can be realized in a quantization mode, namely, no matter the type of the information or the specific value of the information, the method can be expressed by a digital data format, so that the information quantity needing to be transmitted can be compressed, and the excessive occupation of transmission bandwidth is avoided. Of course, in particular implementations, some information may not be compressible, such as uniquely identifying information such as the license plate number of the vehicle. For such non-quantifiable description information, it may be stored in the properties field in the form of a character string.

S202: after a target vehicle is detected, obtaining characteristic elements related to the target vehicle;

the specific vehicle detection method may be various, for example, in a specific implementation, as shown in fig. 3, the specific vehicle detection method may include a map analysis module, a communication module, a historical data analysis module, a traffic rule analysis module, a perception module, and the like.

The map analysis function module can read map data stored locally or received from a cloud end and convert the map data into a data structure which can be read by a software program.

The historical data analysis function module can read statistical information about past traffic accidents stored locally or received from a cloud end as a part of judgment basis of vehicles or dangerous behaviors.

The traffic rules parsing function module may read traffic rules stored locally or received from transportation facilities and convert them into data structures that can be read by software programs as part of the basis for vehicle or dangerous behavior determination.

The data receiving function module may be responsible for receiving all data sent outside the cognitive base station. It may typically include wireless communication devices such as V2X, WiFi, LTE, etc., as well as wired communication devices such as ethernet, fiber optics, etc.

The perception function module can acquire original data through a sensor arranged on a base station, and obtains information of traffic participants, road environment and traffic environment through signal processing or image processing algorithm. The information of the traffic participants mainly includes information such as positions, speeds, orientations, accelerations of main bodies such as vehicles, pedestrians, bicycles, and the like. In the embodiment of the application, under the control of the cognitive function module, the sensing module can also sense characteristic elements of a designated traffic participant (for example, a vehicle), for example, information such as license plate number, defect, violation information (for example, overload, bare goods, and the like), personalized decoration, and the like is obtained.

The cognitive function module comprises submodules of information synthesis, analysis and reasoning, vehicle judgment, message encapsulation and the like. Wherein the vehicle determination is one sub-module related to a specific application, and the other sub-modules are general sub-modules of cognitive functions.

The information synthesis sub-module widely collects the preliminary sensing result of the sensing module, map data from local or remote, traffic regulation data, server data, historical data and the like, and converts the preliminary sensing result, the map data, the traffic regulation data, the server data, the historical data and the like into a unified time axis and coordinate system.

The analysis and inference submodule obtains the behavior and state of the target (such as a vehicle) in the perception result by analyzing the relative position and the time sequence logic among the information of various sources. For example, by comparing the highest speed limit in the traffic rules with the speed of the vehicle, it can be known whether the vehicle is in an overspeed state; whether the vehicle has the behavior of malicious overtaking is known by continuously observing the track of the vehicle.

The vehicle determination submodule receives outputs of the analysis and inference submodule, such as the state and behavior of the vehicle, and determines whether the vehicle is present. For example, a vehicle in an overspeed state or in the presence of malicious overtaking behavior is considered a vehicle. When the vehicle is judged as the vehicle, the sub-module can inform the sensing module to sense the details of the vehicle, such as identifying the license plate number, detecting defects or personalized decorations, and the like, obtain the detailed characteristics and transmit the detailed characteristics to the downstream module. The vehicle decision sub-module also forwards the output of the upstream module, i.e., the analysis and reasoning module, to the downstream module.

The message encapsulation submodule reads the output of the upstream module and the characteristic elements of the sensing module, encapsulates the information into messages and transmits the messages to the data sending submodule.

Finally, the data transmission submodule transmits the message received from the upstream module through the wireless communication system.

In addition, in a specific implementation, other methods for identifying the vehicle may be used, and are not limited herein.

In a specific implementation, after the vehicle is identified and the specific feature elements are obtained, specifically when the information is encapsulated into a message, the information may be converted according to the information such as the definition of the field recorded in the foregoing step S201, which is described below through step S203.

S203: determining the type and value of a target descriptor for describing the characteristic elements of the target vehicle according to the definition information of the descriptor;

after the characteristic elements of a particular vehicle are obtained, such detailed characteristics can be described to encapsulate information into a message for transmission. Specifically, when the description is performed, the description can be performed according to the definition of the descriptor saved in the foregoing step S201. For example, in the definition information shown in table 1, various types of features and values may be expressed in a quantitative manner. In specific implementation, all the quantifiable feature elements can be expressed in a quantification mode, so that the transmitted information quantity is compressed. The quantifiable detail features may be various, such as the type of vehicle, the type of dangerous behavior of the vehicle, the color of the vehicle, the information about the degree of old or new vehicle, the degree and location of vehicle defects, the location of personalized vehicle decorations, and the like. The information can be quantized regardless of the type of the information or specific values under specific types. For example, if a vehicle has a positive defect, a specific defect level may be determined, for example 2, and expressed in the descriptor as:

descriptor_type：4

descriptor_value：2

As another example, if a certain vehicle has an overload, it can be expressed in the descriptor as:

descriptor_type：8

descriptor_value：1

therefore, if the same vehicle has a plurality of different characteristic elements, the description can be performed through a plurality of description bodies, and information such as specific types and values can be respectively indicated in different description bodies.

In addition, the specific feature elements may also include information that is not quantifiable, and in this case, the value of the corresponding descriptor may be described by a data format of a string type. For example, if the specific detail feature is unique identification information such as a license plate number of a vehicle, the description may be directly made in the form of a character string without compression in the form of numbers.

S204: and adding the type and the value information of the target description body into a message body for sending, so that the vehicle-mounted unit generates and outputs a natural sentence by performing natural language processing on the type and the value of the target description body.

After the specifically collected characteristic elements are converted into description through the description body, the description can be correspondingly added into the message body, and then the message body can be sent through the data sending submodule. In a specific implementation, the message is generally sent in a form of transmission, so that a vehicle located near the base station can receive the message through the vehicle-mounted unit. Further, the on-board unit may extract a description body related to the vehicle from the message by parsing the message, and then convert the description body into a natural sentence described in a natural language according to the definition information shown in the table 1 stored in advance to output the natural sentence, so that the driver user can more clearly and intuitively associate the vehicle prompted in the message with the vehicle in the real world and make a more accurate response to avoid an accident.

By the embodiment of the application, after a specific target vehicle is identified, characteristic elements of the vehicle can be collected, the characteristic elements mainly comprise some characteristics recognizable by human eyes, such as related elements of colors, figures, shapes, texts and the like, and can be described by the descriptor defined for various characteristic elements in advance, so that the characteristic elements can be carried in a specific message body to be sent. The on-board unit or the like on the receiving side may analyze the received specific message, extract the descriptor information related to the vehicle from the analyzed message, convert the descriptor information according to the definition information, and perform natural language processing, thereby generating and outputting a natural sentence. In this way, since the specific feature elements are human-understandable features, rather than some information such as coordinates, the driver can intuitively associate the vehicle described in the message with the vehicle in the real world, and thus, the dangerous situation that may occur can be dealt with more effectively.

Example two

The second embodiment corresponds to the first embodiment, and provides a method for providing vehicle information from the perspective of the on-board unit, and referring to fig. 4, the method may specifically include:

S401: the vehicle-mounted unit obtains definition information of a vehicle description body, wherein the definition information comprises the type and value of the description body and corresponding meaning information, and is used for describing characteristic elements which can be recognized by human eyes on a vehicle through the description body;

in a specific implementation, the definition information about the specific description object may be stored in the on-board unit, and is consistent with the definition information stored in the sensing base station. When the definition information is updated or new entries are added, the information stored in the perception base station and the information stored in the vehicle-mounted unit can be synchronously updated through systems such as a cloud end.

S402: receiving a message sent by a perception base station, and acquiring the type and value information of a target description body corresponding to a target vehicle from the message;

since the specific message body may include a plurality of descriptors about the vehicle, the specific descriptors may be extracted from the message body, and the description information about the type and value of the information in the descriptors may be obtained. Specifically, the value information described in a numeric format or the value information described in a character string format may be included.

S403: and determining corresponding meaning information according to the type and the value information of the target description body and the definition information, performing natural language processing according to the meaning information, generating a natural sentence comprising characteristic element information which can be recognized by human eyes, and outputting the natural sentence.

After the type and the value information in the description body are determined, the type and the value information can be converted into corresponding characteristic elements according to the definition information stored before, and natural sentences including characteristic element information recognizable by human eyes are generated and output through natural language processing. For example, in the embodiment of the present application, a vehicle is located behind a vehicle on the left, and in this embodiment, information that coordinates of the vehicle and the like are difficult to visually recognize is not presented to the driver, but some feature elements related to the vehicle are presented to the driver in a natural sentence manner, so that the driver can more conveniently confirm which specific vehicle is the vehicle presented in the message.

In the specific implementation, information such as the country where the vehicle is located may be pre-configured in the on-board unit, so that the on-board unit may specifically perform natural language processing according to the meaning information and the information of the country where the vehicle is located, and generate a natural sentence expressed by a language of a corresponding country.

During specific implementation, the threat degree of the vehicle can be evaluated according to the type and value information of the target description body, and the threat degree grade is determined; and then the audio prompt volume or frequency or the vibration prompt amplitude or frequency can be converted according to the threat degree level. That is, in addition to describing the detailed characteristics of a specific vehicle through a specific natural language, the specific threat level can be conveyed to the driver through information such as the volume or frequency of a specific voice playing, so that richer information can be conveyed to the driver.

In addition, the direction information of the vehicle relative to the current vehicle can be determined according to the type and the value information of the target description body; in this way, the direction of the sound source, which is an audio cue or a vibration cue, relative to the driver can be determined from the orientation information. That is, after determining the direction information of a specific vehicle with respect to the current vehicle, the direction may be taken as the sound source direction for a specific audio or vibration, so that the driver's attention may be better attracted to the corresponding direction, helping the driver to more easily identify the specific vehicle.

In a specific implementation, after the message sent by the sensing base station is received by the vehicle-mounted unit, in order to implement the above functions, various specific processing modes may be used. For example, in one implementation, as shown in fig. 5, a message receiving module, a description module for a vehicle, a module for calculating a relative position, a self-vehicle positioning module, a threat assessment module, a voice synthesis module, a voice broadcast module, a magnitude and frequency adjustment module, a direction adjustment module, and the like may be included. The message receiving and self-positioning functions may be implemented by the V2X module of the vehicle, and other functions may be implemented by the human-computer interaction system of the vehicle, which should not be construed as limiting the scope of the present application.

The message receiving function is responsible for receiving messages from the vehicle's wireless communication system (e.g., V2X) and sending them to downstream functional modules in real time.

The self-vehicle positioning function obtains the absolute position of the vehicle relative to the ground through devices such as a GNSS (Global Navigation Satellite System) and a gyroscope.

The relative position calculating function can obtain the absolute position of the vehicle by analyzing the message, read the output of the vehicle positioning function, obtain the absolute position of the vehicle, calculate the relative position of the vehicle relative to the vehicle and obtain the information of the azimuth dimension.

The description function for the vehicle extracts the corresponding fields from the received message, obtains the danger types represented by each field and the description information of the vehicle according to the definition of table 1, reads the output of the function for calculating the relative position, and obtains the description text of the behavior of the vehicle, namely the information of the content dimension, which can be understood by the driver or the passenger according to the language and the grammar of the country where the vehicle is located.

The threat assessment function quantitatively assesses the severity of the hazard possibly caused by the vehicle according to the behavior of the vehicle and the relative position of the vehicle and by combining information such as the reason of traffic accidents caused by the past, statistical results and the like, and information of degree dimension is obtained.

The speech synthesis function converts the descriptive text of the behavior of the vehicle into an audio signal.

The voice broadcast function transmits the audio signal to a sound system of the vehicle so that the driver or passenger can hear the audio signal.

The amplitude and frequency adjustment function adjusts the amplitude/volume and frequency of the audio prompt and the amplitude and frequency of the vibration prompt according to the information of the degree dimension. For example, if the threat level is changed from low to high, the function may increase the volume of the audio prompt, increase the frequency of the alarm, or increase the amplitude of the vibration prompt.

And the direction adjusting function selectively activates audio prompts or vibration prompts in corresponding directions according to the information of the direction dimension, so that the direction of the prompts heard or sensed by the driver is consistent with the direction of the vehicle relative to the vehicle.

Corresponding to the first embodiment, an embodiment of the present application further provides a message sending control device in a cognitive base station, where the device is applied to the cognitive base station, and referring to fig. 6, the device may specifically include:

a definition information obtaining unit 601, configured to obtain definition information of a descriptor for describing feature elements of a vehicle, where the definition information includes types, values, and corresponding meaning information of the descriptor, and the feature elements include feature elements recognizable by human eyes;

A feature element obtaining unit 602 configured to obtain, after a target vehicle is detected, a feature element regarding the target vehicle;

an information conversion unit 603, configured to determine, according to the definition information of the descriptor, a type and a value of a target descriptor for describing a feature element of the target vehicle;

a message generating unit 604, configured to add the type of the target descriptor and the value information to a message body for sending, so that the vehicle-mounted unit generates a natural statement and outputs the natural statement by performing natural language processing on the type and the value of the target descriptor.

The characteristic elements comprise quantifiable information, and the values of the corresponding description bodies are described through a digital data format.

Wherein the quantifiable information includes: the type of the vehicle, the type of dangerous behaviors of the vehicle, the color of the vehicle, the information of the degree of the vehicle, the degree and the position of the vehicle defect and the position of the personalized decoration of the vehicle.

Or the characteristic elements comprise information which cannot be quantified, and the values of the corresponding description bodies are described through a data format of a character string type.

Wherein the quantifiable information includes: the unique identity of the vehicle.

Corresponding to the second embodiment, the embodiment of the present application further provides an apparatus for providing vehicle information, where the apparatus is applied to a vehicle-mounted unit, and referring to fig. 7, the apparatus may specifically include:

a definition information obtaining unit 701, configured to obtain definition information of a vehicle descriptor, where the definition information includes a type and a value of the descriptor and corresponding meaning information, and is used to describe a feature element that is recognizable to human eyes on a vehicle;

a message receiving unit 702, configured to receive a message sent by a sensing base station, and obtain a type and value information of a target description corresponding to a target vehicle from the message;

and a natural sentence output unit 703, configured to determine corresponding meaning information according to the type and value information of the target descriptor and the definition information, perform natural language processing according to the meaning information, generate a natural sentence including characteristic element information recognizable by human eyes, and output the natural sentence.

The natural language sentence output unit may be specifically configured to: and performing natural language processing according to the meaning information and the country information of the vehicle to generate a natural sentence expressed by a corresponding country language.

In a specific implementation, the apparatus may further include:

the threat degree grade determining unit is used for evaluating the threat degree of the vehicle according to the type and the value information of the target description body and determining the threat degree grade;

and the playing parameter control unit is used for converting the level into the volume or frequency of the audio prompt or the amplitude or frequency of the vibration prompt according to the threat degree level.

In addition, the apparatus may further include:

the direction information determining unit is used for determining the direction information of the vehicle relative to the current vehicle according to the type and the value information of the target description body;

and the sound source direction control unit is used for determining the direction of the sound source which is audio prompt or vibration prompt relative to the driver according to the azimuth information.

In addition, the embodiment of the application also provides a message structure body, wherein the message is sent through a perception base station in the intelligent traffic system;

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

The above detailed description is given to the message sending control method and device in the cognitive base station provided in the present application, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific embodiments and the application range may be changed. In view of the above, the description should not be taken as limiting the application.

Claims

1. A method for controlling message transmission in a cognitive base station, comprising:

2. The method of claim 1,

3. The method of claim 2,

the quantifiable information includes: the type of the vehicle, the type of dangerous behaviors of the vehicle, the color of the vehicle, the information of the degree of the vehicle, the degree and the position of the vehicle defect and the position of the personalized decoration of the vehicle.

4. The method of claim 1,

the characteristic elements comprise information which cannot be quantified, and the values of the corresponding description bodies are described through a data format of a character string type.

5. The method of claim 4,

the quantifiable information includes: the unique identity of the vehicle.

6. A method of providing vehicle information, comprising:

7. The method of claim 6,

The natural language processing according to the meaning information comprises:

and performing natural language processing according to the meaning information and the country information of the vehicle to generate a natural sentence expressed by a corresponding country language.

8. The method of claim 6, further comprising:

according to the type and value information of the target description body, evaluating the threat degree of the vehicle and determining the threat degree grade;

and converting into the volume or frequency of an audio prompt or the amplitude or frequency of a vibration prompt according to the threat degree grade.

9. The method of claim 6, further comprising:

determining the direction information of the vehicle relative to the current vehicle according to the type and the value information of the target description body;

and determining the direction of a sound source of the audio prompt or the vibration prompt relative to the driver according to the azimuth information.

10. A message sending control device in a perception base station is characterized in that the message sending control device is applied to the perception base station and comprises the following components:

11. An apparatus for providing vehicle information, applied to an on-board unit, comprising:

12. A message structure, characterized in that,