CN112968946A

CN112968946A - Scene identification method and device for internet connection vehicle and electronic equipment

Info

Publication number: CN112968946A
Application number: CN202110137539.1A
Authority: CN
Inventors: 向鹏; 蒋虎; 袁志俊; 石善文
Original assignee: Zebra Network Technology Co Ltd
Current assignee: Zebra Network Technology Co Ltd
Priority date: 2021-02-01
Filing date: 2021-02-01
Publication date: 2021-06-15
Anticipated expiration: 2041-02-01
Also published as: CN112968946B

Abstract

The invention provides a scene identification method and device for internet connection, electronic equipment, a computer readable storage medium and an internet connection service providing method. The scene identification method of the internet connection vehicle comprises the following steps: step S1, obtaining a dependent signal, wherein the dependent signal comprises one or more of a system signal, an application signal and a cloud service signal; step S2, carrying out stream calculation on the dependence signal, and outputting the scene state based on the configuration relation between the dependence signal and the scene state; and step S3, performing stream calculation on the scene state, and identifying and obtaining the scene based on the configuration relationship between the scene state and the scene. According to the scene recognition method of the internet vehicle, the development difficulty can be reduced, and dynamic updating and scene expansion calculation are convenient to realize.

Description

Scene identification method and device for internet connection vehicle and electronic equipment

Technical Field

The invention relates to the field of internet connection, in particular to a scene recognition method and device of internet connection and electronic equipment.

Background

At present, the threshold and complexity of scene calculation on the internet vehicle are high, and the cost of continuous iteration of scene functions after the vehicle is on hand of a user is high.

To realize scene calculation on the internet vehicle, professional research and development personnel need to know details of vehicle bottom layer signals or other source signals on which the scene calculation depends, and after a certain scene function (such as a function of reminding a user of strip sticking risks in a parking scene) is realized, if a vehicle leaves a factory, the function needs to be optimized and upgraded, for example, the calculation of the parking scene is more meticulous, a vehicle machine system may need to be upgraded, and the cost is higher.

Disclosure of Invention

In view of this, the present invention provides a method and an apparatus for identifying a scene of a networked vehicle, an electronic device, and a computer-readable storage medium, which can reduce development difficulty and facilitate dynamic update and extended scene calculation.

In order to solve the above technical problem, in a first aspect, the present invention provides a scene recognition method for internet connection, including the following steps:

step S1, obtaining a dependent signal, wherein the dependent signal comprises one or more of a system signal, an application signal and a cloud service signal;

step S2, carrying out stream calculation on the dependence signal, and outputting the scene state based on the configuration relation between the dependence signal and the scene state;

and step S3, performing stream calculation on the scene state, and identifying and obtaining the scene based on the configuration relationship between the scene state and the scene.

Further, the system signal comprises one or more of a vehicle machine signal, a vehicle speed signal, a camera signal and a vehicle component state signal,

the application signal comprises a navigation signal and/or a music signal,

the cloud service signal comprises a weather condition signal and/or a parking order signal,

the scene comprises one or more of an oil filling scene, a parking scene and a car repairing scene.

Further, the dependent signal includes a listening signal and/or an inquiry signal, wherein the listening signal is an actively received signal, and the inquiry signal is an actively inquired signal.

Further, the step S2 includes:

the listening signal is subjected to a streaming calculation,

when the monitoring signal meets a preset condition, triggering an inquiry signal required by a scene state corresponding to the monitoring signal;

and performing stream type calculation on the monitoring signal and the query signal, and performing aggregate calculation on the result to obtain the scene state.

Further, the scene states include a high scene state, a medium scene state and a low scene state.

Further, the scene identification method of the internet vehicle further comprises the following steps:

and step S4, updating the configuration relation between the dependence signal and the scene state according to the feedback of the user to the identified scene.

Further, the streaming computation is implemented by an extensible markup language.

In a second aspect, the invention provides a method for providing internet connection service, which includes providing internet connection service based on a scene identified by any one of the above methods.

The third method, the invention provides a scene recognition device for internet connection, comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a dependent signal, and the dependent signal comprises one or more of a system signal, an application signal and a cloud service signal;

the scene state output module is used for carrying out streaming calculation on the dependence signal and outputting the scene state based on the configuration relation between the dependence signal and the scene state;

and the scene identification module is used for performing streaming calculation on the scene state and identifying and obtaining the scene based on the configuration relation between the scene state and the scene.

In a fourth aspect, the present invention provides an electronic device for identifying a scene of a networked vehicle, including:

one or more processors;

one or more memories having computer readable code stored therein, which when executed by the one or more processors, causes the processors to perform the steps of:

In a fourth aspect, the present invention provides a computer readable storage medium having stored therein computer readable code which, when executed by one or more processors, causes the processors to perform the steps of:

The technical scheme of the invention at least has one of the following beneficial effects:

according to the scene recognition method of the internet vehicle, the development difficulty can be reduced, and dynamic updating and scene expansion calculation are convenient to realize.

Drawings

Fig. 1 is a flowchart of a scene recognition method for internet connection according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of streaming computing according to an embodiment of the invention;

FIG. 3 is a schematic diagram of an operator chain according to an embodiment of the invention;

FIG. 4 is a diagram illustrating a scene configuration definition according to an embodiment of the invention;

fig. 5 is an architecture diagram of a scene recognition method of a networked vehicle according to an embodiment of the present invention;

fig. 6 is a schematic view of a scene recognition device of a networked vehicle according to an embodiment of the present invention;

fig. 7 is a schematic view of an electronic device for identifying a scene of a networked vehicle according to an embodiment of the present invention.

Detailed Description

The following detailed description of embodiments of the present invention will be made with reference to the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.

The inventor finds that the common practice of the prior art is to implement the process of scene calculation by using a computer high-level programming language or by using a dynamic scripting language, and the defects of the methods are that:

1. the realization threshold is high, and the realization threshold can only be implemented by professional research personnel who know the car machine bottom signal and other dependence signals very much, and development cost is high, and development cycle is long.

2. The upgrading cost is high, and for the issued scene function upgrading, the vehicle machine system may need to be upgraded together.

3. The method cannot be opened to three-party developers, and high-level languages or dynamic scripts are easy to introduce the risk of system stability and are difficult to open to the outside.

In view of these disadvantages, the present invention aims to reduce the threshold of scene calculation, provide a dynamic update mechanism, and enable application developers who do not know the signal mechanism of the vehicle bottom layer very well, even product operators, to participate in the function of implementing scene recognition. After the vehicle leaves the factory, the scene calculation can be dynamically updated and expanded, and the purpose of continuously optimizing and enhancing the scene function is achieved.

The following describes a scene recognition method for a networked vehicle according to an embodiment of the present invention with reference to fig. 1.

As shown in fig. 1, the scene recognition method for internet vehicles according to the embodiment of the present invention includes the following steps:

step S1, obtaining a dependency signal, where the dependency signal includes one or more of a system signal, an application signal, and a cloud service signal. For example, the dependent signal may be acquired by wired or wireless means.

The system signal may include one or more of a vehicle-mounted device signal, a vehicle speed signal, a camera signal and a vehicle component status signal, the application signal may include a navigation signal and/or a music signal, and the cloud service signal may include a weather condition signal and/or a parking order signal.

The adapter mode can be used to implement adaptation of signals from different sources, such as vehicle body signals, map signals, cloud service signals, and the like, through a common high-level language, and the implementation is a common practice, and the implementation process is not described in detail here, and for an adapted signal, field information of the signal needs to be described, and for a signal that needs to be queried, query entry and exit information needs to be described.

And step S2, performing streaming calculation on the dependence signal, and outputting the scene state based on the configuration relationship between the dependence signal and the scene state.

For the calculation of the scene state, a certain state item of the state machine is often output as an output, and the output value is a result value currently calculated by the state.

The signals on the internet vehicle are in a data stream form, the recognition of the internet vehicle scene is to calculate a plurality of data streams, large-scale flowing data can be well analyzed in real time in the constantly changing motion process, possible useful information can be captured, and the result is sent to the next computing node. Based on the definition of the original dependence signal and the scene state, the high-order scene state needing to be processed is identified, the reusability can be improved, and the implementation details of the bottom layer are shielded for the subsequent scene arrangement.

As shown in fig. 2, the streaming calculation is described by taking fueling as an example, and it is determined that a certain calculation rule has been satisfied by a scene-dependent signal at a certain time according to a certain rule. And receiving a cruising mileage signal, filtering out a signal with the cruising mileage being more than 600KM, receiving the signal once in 300 seconds, obtaining the mileage of the user from the destination and the refueling expectation of the user, and considering that refueling is needed if the distance between the cruising mileage and the destination is less than 50KM and the cruising mileage is 440 less than 50 KM.

For the calculation of scene recognition, the output is usually the target of an application entry, and the output value is the input parameter value required by the application entry.

The invention uses the flow type calculation operator which is mature in the industry to complete the processing work of the original signal on the vehicle networking. In signal and aggregation calculation, the processing of original data is mainly completed through an operator chain, the operator chain is formed by sequentially connecting a plurality of operators in series, data is sequentially processed according to the order of the operators, and each operator represents an operation on the data, for example, as shown in the schematic diagram of the operator chain shown in fig. 3.

The identification of a scene is defined by the orchestration between high-order scene states, which can be done without the need for specialized developers. And processing the signal into a scene state, and arranging the scene state into a scene, wherein the whole process is described by using a domain language conforming to a streaming computation model, the domain language can be dynamically distributed to a vehicle machine, and a scene engine on the vehicle machine generates and executes a program instance. Moreover, the subsequent update can realize the update of the scene identification by updating the configuration relationship between the dependency signal and the scene state and/or the configuration relationship between the scene state and the scene. Therefore, the development difficulty can be reduced, and dynamic updating and scene expansion calculation are convenient to realize.

Optionally, the streaming computation is implemented by an extensible markup language. The domain language designed by the scene computation process following the streaming computation model may be implemented in different forms, for example, the domain language designed by the extensible markup language (XML) following the streaming computation model, and the like.

The scene recognition method of the internet vehicle is described below by specific examples.

For example, the original signal (percentage of oil quantity) of the oil quantity is obtained by taking the dependence signal as an oil quantity signal, the oil quantity signal is calculated in a flow mode, when the oil quantity is more than 70%, the output oil quantity state (scene state) is a high oil quantity state, when the oil quantity is between 30% and 70% in a certain driving distance, the output oil quantity state is a medium oil quantity state, the driving is continued for a certain distance, the oil quantity is less than 30%, and the output oil quantity state is a low oil quantity state. Such a state shields much details of the bottom layer, such as removing jitter of the original signal, which is easy for defining the scene later.

The method comprises the steps of carrying out flow calculation on a fuel quantity state and fuel stations near a vehicle journey, identifying a fuel filling scene when a vehicle just passes through one fuel station and is in a low fuel quantity state, and recommending a user to fill fuel at the fuel station.

According to some embodiments of the invention, the dependent signal comprises a listening signal and/or an inquiry signal, wherein the listening signal is an actively received signal and the inquiry signal is an actively inquired signal.

The configuration of the input signal part describes the original signal category, the mode of acquiring the original signal, and the processing step of the original signal result, which are depended on by the scene calculation, and the depended signals are divided into two types according to the types of the signals:

monitoring signals (active), which are event-driven, signals actively transmitted from the outside, such as vehicle status signals, weather anomaly signals, order event signals, etc.

The query signal (passive) is a parameter that is relied on for the scene calculation, and in a certain scene, the value of the query signal needs to be actively queried in the calculation process, such as the gender state of the user.

Further, the step S2 includes:

the listening signal is subjected to a streaming calculation,

Therefore, the scene state can be calculated more accurately and comprehensively.

For example, the time of continuous driving of the vehicle is subjected to streaming calculation, when the time of continuous driving of the vehicle exceeds 3 hours, the gender and age of the user are acquired by triggering, when the user is a senior female, the high fatigue driving state of the user is output, and when the user is a young male, the moderate fatigue driving state of the user is output, so that the scene state is more pertinent.

According to some embodiments of the present invention, the method for identifying a scene of a networked vehicle further includes step S4, updating the configuration relationship between the dependency signal and the scene state according to the feedback of the user on the identified scene.

For example, a recognized refueling scenario, but the user does not refuel, but refuels in another scenario state, the configuration relationship between the fuel quantity signal and the fuel quantity state is updated.

As shown in fig. 4, after the configuration definition of the state calculation and the scene identification is completed, the configuration may be issued to the cloud storage, the vehicle may arrive at the cloud end to synchronously acquire the latest scene calculation configuration, and analyze the configuration file, and when the scene engine monitors the corresponding signal, the calculation process of the configuration definition may be executed.

Next, an implementation architecture of the scene calculation method for internet connection vehicles according to the embodiment of the present invention is described with reference to fig. 5.

The implementation architecture of the scene calculation method of the internet connection vehicle comprises an application layer, a connection layer, a calculation layer and a perception level data layer.

The data layer is used for receiving vehicle signals, environment signals, visual signals, order signals, map signals and user signals.

The sensing layer comprises a system signal butt-joint device, an application signal butt-joint device and a cloud service signal butt-joint device. The signal dockee is primarily responsible for docking dependent signals. The system signal docking device can dock system signals of the vehicle, such as vehicle speed, component state signals and the like; the application signal butt-joint device is mainly responsible for accessing signals generated by application on the vehicle, if the signals are navigation signals; the cloud service docking connector is mainly responsible for accessing signals of cloud service, such as weather conditions, parking order states and the like.

The compute layer includes a scene recognition engine. The scene recognition engine is mainly responsible for analyzing the scene calculation configuration and running the calculation process defined by the scene calculation configuration in a streaming calculation mode.

The connection layer includes an application trigger. The application trigger is mainly responsible for notifying the applications subscribing to the scene of the scene calculation result.

The application layer comprises map, music, radio station, fuel filling, parking and other applications.

The following describes a method for providing internet connection service according to an embodiment of the present invention, which provides internet connection service based on a scene identified by any one of the above-described scene identification methods for internet connection. Therefore, the use experience of the user can be improved, and the required service can be accurately acquired.

Next, a scene recognition apparatus for a networked vehicle according to an embodiment of the present invention will be described with reference to fig. 6.

As shown in fig. 6, a scene recognition apparatus 1000 for internet vehicles according to an embodiment of the present invention includes: an acquisition module 1001, a scene state output module 1002 and a scene identification module 1003.

The obtaining module 1001 is configured to obtain a dependent signal, where the dependent signal includes one or more of a system signal, an application signal, and a cloud service signal.

The scene state output module 1002 is configured to perform streaming calculation on the dependency signal, and output the scene state based on a configuration relationship between the dependency signal and the scene state.

The scene recognition module 1003 performs streaming calculation on the scene state, and recognizes the scene based on the configuration relationship between the scene state and the scene.

Further, the scene recognition device of the internet vehicle can be respectively used for corresponding steps in the scene recognition method of the internet vehicle, and detailed description thereof is omitted here.

In addition, an electronic device 1400 for identifying a scene of a networked vehicle according to an embodiment of the present invention is described with reference to fig. 7.

As shown in fig. 7, an electronic device 1400 for identifying a scene of internet surfing according to an embodiment of the present invention includes:

a processor 1401 and a memory 1402, in which memory 1402 computer program instructions are stored, wherein the computer program instructions, when executed by the processor, cause the processor 1401 to perform the steps of:

Further, the processor 1401 may also perform corresponding steps in a scene recognition method of the internet connection, and a detailed description thereof is omitted herein.

The various interfaces and devices described above may be interconnected by a bus architecture. A bus architecture may be any architecture that may include any number of interconnected buses and bridges. Various circuits of one or more Central Processing Units (CPUs), represented in particular by processor 1401, and one or more memories, represented by memory 1402, are coupled together. The bus architecture may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like. It will be appreciated that a bus architecture is used to enable communications among the components. The bus architecture includes a power bus, a control bus, and a status signal bus, in addition to a data bus, all of which are well known in the art and therefore will not be described in detail herein.

The network interface 1403 may be connected to a network (e.g., the internet, a local area network, etc.), obtain relevant data from the network, and store the relevant data in the hard disk 1405.

The input device 1404 may receive various instructions from an operator and send them to the processor 1401 for execution. The input device 1404 may include a keyboard or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.

The display device 1406 may display a result obtained by the processor 1401 executing the instruction.

The memory 1402 is used for storing programs and data necessary for operating the operating system, and data such as intermediate results in the calculation process of the processor 1401.

It will be appreciated that the memory 1402 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. The memory 1402 of the apparatus and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 1402 stores elements, executable modules or data structures, or a subset thereof, or an expanded set thereof as follows: an operating system 14021 and application programs 14014.

The operating system 14021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 14014 includes various applications, such as a Browser (Browser), and the like, for implementing various application services. A program implementing a method according to an embodiment of the invention may be included in the application 14014.

When the processor 1401 invokes and executes an application program and data stored in the memory 1402, specifically, a program or an instruction stored in the application 14014, first, obtain a dependency signal, where the dependency signal includes one or more of a system signal, an application signal, and a cloud service signal; then, carrying out stream type calculation on the dependent signal, and outputting a scene state based on a configuration relation between the dependent signal and the scene state; and finally, performing stream type calculation on the scene state, and identifying and obtaining the scene based on the configuration relationship between the scene state and the scene.

The methods disclosed by the above-described embodiments of the present invention may be applied to the processor 1401, or may be implemented by the processor 1401. Processor 1401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by instructions in the form of hardware integrated logic circuits or software in the processor 1401. The processor 1401 may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, and may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory 1402, and a processor 1401 reads information in the memory 1402 and performs the steps of the above method in combination with hardware thereof.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the processor is caused to execute the following steps:

Further, the processor may also perform corresponding steps in the scene recognition method of the internet connection vehicle, and a detailed description thereof is omitted herein.

Still further, the present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the electronic device (which may be, for example, a server, a cloud server, or a part of a server, etc.) may read the execution instruction from the readable storage medium, and execute the execution instruction, so that the scenario identification apparatus 1000 of the internet connection vehicle implements the scenario identification method of the internet connection vehicle provided in the foregoing various embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A scene recognition method of internet vehicles is characterized by comprising the following steps:

2. The scene recognition method of the Internet vehicle according to claim 1,

the system signal comprises one or more of a vehicle machine signal, a vehicle speed signal, a camera signal and a vehicle component state signal,

the application signal comprises a navigation signal and/or a music signal,

3. The method for scene recognition of the internet vehicle as claimed in claim 1, wherein the dependent signal comprises a listening signal and/or an inquiry signal, wherein the listening signal is an actively received signal, and the inquiry signal is an actively inquired signal.

4. The method according to claim 3, wherein the step S2 includes:

the listening signal is subjected to a streaming calculation,

5. The scene recognition method of the internet vehicle as claimed in claim 1, wherein the scene states include three scene states of high, medium and low.

6. The scene recognition method of the internet vehicle as claimed in claim 1, further comprising:

7. The method for scene recognition of the internet vehicle as claimed in claim 1, wherein the streaming calculation is implemented by an extensible markup language.

8. A method for providing internet vehicle service, wherein the internet vehicle service is provided based on the scene identified by the method of any one of claims 1 to 7.

9. The utility model provides a scene recognition device of internet connection car which characterized in that includes:

10. An electronic device for recognizing a scene of a networked vehicle, comprising:

one or more processors;

11. A computer readable storage medium having computer readable code stored therein, which when executed by one or more processors, causes the processors to perform the steps of: