CN116126547A - Vehicle data processing method and system - Google Patents
Vehicle data processing method and system Download PDFInfo
- Publication number
- CN116126547A CN116126547A CN202310408692.2A CN202310408692A CN116126547A CN 116126547 A CN116126547 A CN 116126547A CN 202310408692 A CN202310408692 A CN 202310408692A CN 116126547 A CN116126547 A CN 116126547A
- Authority
- CN
- China
- Prior art keywords
- processed
- processing
- vehicle data
- data
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a vehicle data processing method and system, and belongs to the technical field of vehicle data feature recognition and processing. The method comprises the following steps of S100: receiving vehicle data to be processed; the vehicle data to be processed includes dialogue data and non-dialogue data; the dialogue data is data to be processed received after being activated by a voice dialogue engine; the non-dialogue data is data to be processed which is directly input by a user; s200: starting a process to be processed based on the processing attribute of the vehicle data to be processed; s300: and processing the vehicle data to be processed through the process to be processed to obtain a processing result. The vehicle data processing system comprises a vehicle data receiving unit, a process starting unit, a data processing unit and a result feedback unit. The invention can identify the processing attributes to be processed of different vehicles so as to determine the processing requirements, can improve the user experience of the vehicle-mounted system, and can adaptively learn and update along with the feedback of the user.
Description
Technical Field
The invention belongs to the technical field of vehicle data feature recognition and processing, and particularly relates to a vehicle data processing method and system.
Background
The vehicle-mounted terminal device generally refers to processing equipment at the periphery of a network, is a carrier for inputting data and outputting operation results by a user, can be widely understood as common intelligent equipment such as a PC (personal computer), a smart phone and a platform computer, is applied to an automobile, and belongs to front-end equipment of a vehicle monitoring and management system. The vehicle-mounted terminal is generally an embedded device with limited resources, and has limited processing capacity and available storage space compared with the traditional desktop terminal and even the mobile terminal due to the limitation of a vehicle body and the control of cost.
The vehicle-mounted terminal of the traditional automobile only needs to complete simple man-machine instruction operation, such as functions of telephone book calling, text message voice broadcasting, fault reminding and the like, and the resources of the embedded vehicle-mounted terminal are enough to cope with the requirements; however, as the intelligent automobile age comes, the types of data and command interaction to be processed by the vehicle-mounted terminal are various, and especially many man-machine command interactions, automatic driving recognition and the like are required to accurately recognize the types of data, execute interaction commands, autonomously control and the like, and the recognition process is required to be timely and quick. At this time, the traditional vehicle-mounted terminal data processing and instruction interaction processing modes can not meet the vehicle data processing requirements of the intelligent automobile.
Disclosure of Invention
In order to solve the technical problems, the invention provides a vehicle data processing method and a system.
In a first aspect of the present invention, a vehicle data processing method is provided, the method comprising steps S100-S300, each step being specifically performed as follows:
s100: receiving vehicle data to be processed;
s200: starting a process to be processed based on the processing attribute of the vehicle data to be processed;
s300: and processing the vehicle data to be processed through the process to be processed to obtain a processing result.
Wherein, the vehicle data to be processed received in the step S100 includes dialogue data and non-dialogue data;
the dialogue data is data to be processed received after being activated by a voice dialogue engine;
the non-dialogue data is to-be-processed data directly input by a user.
The step S200 specifically includes:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
The processing attribute of the vehicle data to be processed in step S200 specifically includes:
if the vehicle data to be processed is dialogue data, processing attributes of the vehicle data to be processed comprise single instruction processing and multi-instruction processing;
and if the vehicle data to be processed is non-dialogue data, the processing attribute of the vehicle data to be processed comprises plain text processing, static image-text processing and multimedia processing.
If the vehicle data to be processed is dialogue data and the processing attribute is multi-instruction processing, distributing a second process to be processed comprising a plurality of main threads for the vehicle data to be processed;
and if the vehicle data to be processed is non-dialogue data and the processing attribute is plain text processing, distributing a first process to be processed comprising a main thread and at least one auxiliary thread for the vehicle data to be processed.
If the vehicle data to be processed is non-dialogue data and the processing attribute is multimedia processing, distributing a first process to be processed comprising a first main thread and a plurality of auxiliary threads for the vehicle data to be processed;
the plurality of assist threads includes a first assist thread and a second assist thread;
and the S300 processes the vehicle data to be processed through the process to be processed to obtain a processing result, and specifically comprises the following steps:
transmitting the vehicle data to be processed to the first main thread, wherein the first main thread divides the vehicle data to be processed into a first sub-part and a second sub-part which are sequentially executed based on the processing attribute of the vehicle data to be processed;
processing the first sub-portion by the first main thread; sending the result of the first sub-part processed by the first main thread to the second auxiliary thread for processing; processing, by the first assist thread, the second sub-portion;
summarizing the processing results of the first auxiliary thread and the second auxiliary thread to obtain the processing result of the vehicle data to be processed.
If the vehicle data to be processed is non-dialogue data and the processing attribute is graphic processing, judging whether the image data to be processed and the text data to be processed of the vehicle to be processed are associated or not;
if no association exists, a second to-be-processed process comprising a second main thread and a third main thread is distributed to the to-be-processed vehicle data, wherein the second main thread is used for processing to-be-processed graph data of the to-be-processed vehicle, and the third main thread is used for processing to-be-processed text data of the to-be-processed vehicle;
and if the association exists, allocating a first to-be-processed process comprising a third main thread and at least one fourth auxiliary thread for the to-be-processed vehicle data.
In a second aspect of the present invention, to implement the vehicle data processing method according to the first aspect, a vehicle data processing system is provided, where the vehicle data processing system includes a vehicle data receiving unit, a process starting unit, a data processing unit, and a result feedback unit;
the vehicle data receiving unit is used for receiving vehicle data to be processed, and the received vehicle data to be processed comprises dialogue data and non-dialogue data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed and starting different types of processes to be processed based on the processing attribute;
the data processing unit is used for processing the vehicle data to be processed through the process to be processed to obtain a processing result;
the result feedback unit is used for receiving feedback data of the processing result of the user and training the process starting unit based on the feedback data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed, and starting different types of processes to be processed based on the processing attribute, and specifically comprises the following steps:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
The process starting unit is realized based on a deep learning model, takes the processing attribute of the vehicle data to be processed as the input of the deep learning model, and outputs the number of main threads and auxiliary threads contained in the process to be started.
If the vehicle data to be processed is dialogue data, processing attributes of the vehicle data to be processed comprise single instruction processing and multi-instruction processing;
and if the vehicle data to be processed is non-dialogue data, the processing attribute of the vehicle data to be processed comprises plain text processing, static image-text processing and multimedia processing.
In a third aspect of the present invention, there is provided an in-vehicle terminal device including a memory and a processor, the memory storing computer-executable program instructions, the executable program instructions being executed by the processor for implementing all the steps of the vehicle data processing method of the first aspect.
According to the technical scheme, after the vehicle data to be processed are received, whether the vehicle data to be processed come from dialogue data or non-dialogue data is identified, so that the processing attribute of the vehicle data to be processed is determined, a process to be processed is distributed for the vehicle data to be processed based on the processing attribute, the classification resource scheduling and processing of the vehicle data with different types/different processing requirements are realized, and the classification resource scheduling and processing process can be further optimized and self-learned based on received user result feedback, so that a closed-loop self-adaptive learning process is formed, and the user experience of the vehicle-mounted terminal is continuously improved.
Further advantages of the invention will be further elaborated in the description section of the embodiments in connection with the drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed 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 invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a main flow chart of a vehicle data processing method according to an embodiment of the present invention
FIG. 2 is a schematic illustration of types and processing attributes of vehicle data processed by various embodiments of the invention
FIG. 3 is a schematic diagram of the unit composition of a vehicle data processing system according to one embodiment of the invention
FIG. 4 is a schematic diagram of the unit composition of a vehicle data processing system according to another preferred embodiment of the present invention
Detailed Description
The invention will be further described with reference to the drawings and detailed description.
Fig. 1 is a main flow chart of a vehicle data processing method according to an embodiment of the present invention. The method comprises the steps of S100-S300, wherein each step is specifically implemented as follows:
s100: receiving vehicle data to be processed;
s200: starting a process to be processed based on the processing attribute of the vehicle data to be processed;
s300: and processing the vehicle data to be processed through the process to be processed to obtain a processing result.
Next, a specific implementation manner of each step is further described with reference to fig. 2.
As a specific example, the method is executed by a vehicle-mounted terminal device, where the vehicle-mounted terminal device is a man-machine interaction device, and the man-machine interaction device includes a man-machine interaction component, and the man-machine interaction component includes at least a touch input component and a voice input component.
And the vehicle-mounted terminal equipment receives and receives vehicle data to be processed through the man-machine interaction assembly.
In particular, the vehicle data processed by the various embodiments of the present invention can be divided into two categories, conversational data and non-conversational data.
The dialogue data is data input by the vehicle-mounted terminal user in a dialogue form.
It is appreciated that in the smart car age, voice interaction has become a basic configuration. The user can input voice interaction data and instructions through the voice input component so as to realize the operation of part of the vehicle.
The voice interaction data and instructions herein are referred to as "dialog data" in the present invention.
Specifically, the dialogue data is to-be-processed data received after being activated by the voice dialogue engine.
As a specific adaptive example, the session data may be generated by:
"xx hello" -the instruction can activate a voice dialog engine, at which time the voice input component can receive user instructions;
and the vehicle-mounted terminal can turn on the vehicle-mounted air conditioner after the voice input assembly receives the instruction.
The non-dialogue data is the data to be processed which is directly input by the user, namely the data which is directly input on the man-machine interaction component without activating the voice dialogue engine.
For example, the user may directly start the in-vehicle camera to take a landscape shot, and then select a target landscape shot through touch input, requiring the in-vehicle terminal to send the target landscape shot to the user's mobile phone through bluetooth. The various vehicle data generated by this process are referred to herein as "non-conversational data" because the generation of data does not involve "car-to-machine conversations" and pertains to unilateral operation by the user.
Further, referring to fig. 2, processing attributes of data to be processed of different types of vehicles are further shown.
For dialogue data, the data processing attribute is single instruction processing and multi-instruction processing.
Single instruction processing means that the current dialog data contains only one instruction to be executed, for example:
"xx you good", "please turn on the air conditioner" -the dialog only needs to execute one instruction (turn on the air conditioner);
multi-instruction processing refers to that the current session data includes a plurality of instructions to be executed, for example:
"xx you good", "please close the air conditioner", "please open the window" -the dialog contains a number of instructions to be executed (open window/close air conditioner).
For non-conversational data, the processing attributes of the vehicle data to be processed include plain text processing, static graphics processing, and dynamic multimedia processing.
One example of the plain text processing is search input of the vehicle-mounted terminal, for example, a user inputs a text keyword through a touch input component to search for a certain function of the vehicle-mounted terminal;
one example of still picture processing is the taking of pictures by a vehicle-mounted terminal, for example, a user starts a vehicle-mounted camera to take a landscape, and the vehicle-mounted terminal is required to send the landscape to a mobile phone of the user through Bluetooth;
one example of dynamic multimedia processing is in-vehicle event data recorder video clipping, for example, a user selects a video start time period and a video end time period by an instruction, requests an in-vehicle terminal to identify a target video paragraph, compresses the target video paragraph, and sends the compressed target video paragraph to a user mobile phone through bluetooth.
Obviously, the processing modes of the vehicle data of different types are different, the resource requirements required by the different processing modes are different, the requirements of users on the instantaneity and the accuracy of the different processing modes of the data of different types are different, and the different resources are required to be scheduled and the different targeted processing modes are required to be started.
Thus, as a first advantage of the present invention, the step S200 specifically includes:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
As a first improvement of the above advantages, if the vehicle data to be processed is dialogue data and the processing attribute is multi-instruction processing, a second process to be processed including a plurality of main threads is allocated to the vehicle data to be processed;
taking the vehicle data to be processed as "xx you good", "please close the air conditioner", "please open the window" -the dialogue includes a plurality of instructions to be executed (window opening/air conditioner closing), the main thread 1 is used for opening the window, and the main thread 2 is used for closing the air conditioner, where no distinction of sequence or priority exists among the plurality of instructions to be executed;
and if the vehicle data to be processed is non-dialogue data and the processing attribute is plain text processing, distributing a first process to be processed comprising a main thread and at least one auxiliary thread for the vehicle data to be processed.
Taking an example of the above-mentioned plain text processing as a search input of the vehicle-mounted terminal, for example, a user inputs a text keyword through a touch input component to search a certain function of the vehicle-mounted terminal, the main thread is used for capturing the keyword which the user has currently input, and the plurality of auxiliary threads respectively give a plurality of different input recommendation results based on different histories, so as to accelerate the input speed of the user.
As a second improvement of the above advantages, if the vehicle data to be processed is non-session data and the processing attribute is dynamic multimedia processing, a first process to be processed including a first main thread and a plurality of auxiliary threads is allocated to the vehicle data to be processed;
the plurality of assist threads includes a first assist thread and a second assist thread;
and the S300 processes the vehicle data to be processed through the process to be processed to obtain a processing result, and specifically comprises the following steps:
transmitting the vehicle data to be processed to the first main thread, wherein the first main thread divides the vehicle data to be processed into a first sub-part and a second sub-part which are sequentially executed based on the processing attribute of the vehicle data to be processed;
taking the compressed video paragraph as an example, the target video paragraph may be divided into a first sub-portion and a second sub-portion;
processing the first sub-portion by the first main thread, i.e. effecting compression of the first sub-portion; sending the result of the first main thread processing the first sub-part (namely the compressed result of the first sub-part) to the second auxiliary thread for processing; the second auxiliary thread sends the compression result of the first sub-part to a mobile phone of a user through Bluetooth and receives feedback of the user;
processing, by the first assist thread, the second sub-portion; specifically, the first auxiliary thread compresses the second word portion based on feedback of the user, and the processing results of the first main line Cheng Huizong and the second auxiliary thread obtain the processing result of the vehicle data to be processed.
As a third improvement of the above advantages, if the vehicle data to be processed is non-dialogue data and the processing attribute is graphic processing, determining whether there is a correlation between the map data to be processed and the text data to be processed of the vehicle to be processed;
if no association exists, a second to-be-processed process comprising a second main thread and a third main thread is distributed to the to-be-processed vehicle data, wherein the second main thread is used for processing to-be-processed graph data of the to-be-processed vehicle, and the third main thread is used for processing to-be-processed text data of the to-be-processed vehicle;
and if the association exists, allocating a first to-be-processed process comprising a third main thread and at least one fourth auxiliary thread for the to-be-processed vehicle data.
As a second advantage of the present invention, the method further includes step S400: and receiving feedback data of the user for the processing result, and re-executing the step S200 based on the feedback data.
The feedback data comprise whether accuracy is satisfactory, whether real-time performance is satisfactory and the like; as an example, if real-time processing is not satisfactory for certain session data, more processes and the like need to be scheduled for the session data.
To achieve the above-described method, referring to fig. 3-4, schematic block diagrams of a vehicle data processing system according to various embodiments of the present invention are shown, respectively.
In fig. 3, the vehicle data processing system includes a vehicle data receiving unit, a process starting unit, a data processing unit, and a result feedback unit.
The vehicle data receiving unit is used for receiving vehicle data to be processed, and the received vehicle data to be processed comprises dialogue data and non-dialogue data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed and starting different types of processes to be processed based on the processing attribute;
the data processing unit is used for processing the vehicle data to be processed through the process to be processed to obtain a processing result;
the result feedback unit is used for receiving feedback data of the processing result of the user and training the process starting unit based on the feedback data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed, and starting different types of processes to be processed based on the processing attribute, and specifically comprises the following steps:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
In fig. 3, it is further shown that the process starting unit realizes self-learning update based on a deep learning model, specifically, the processing attribute of the vehicle data to be processed and the user feedback data may be used as input of the deep learning model, where the deep learning model outputs the number of main threads and auxiliary threads included in the process to be started and the starting sequence of different auxiliary threads.
Specifically, if the vehicle data to be processed is dialogue data, the processing attribute of the vehicle data to be processed comprises single instruction processing and multi-instruction processing;
and if the vehicle data to be processed is non-dialogue data, the processing attribute of the vehicle data to be processed comprises plain text processing, static image-text processing and multimedia processing.
The process scheduling manners corresponding to different processing attributes of different data to be processed may refer to the foregoing method embodiments of fig. 1-2, and will not be repeated herein.
According to the technical scheme, after the vehicle data to be processed are received, whether the vehicle data to be processed come from dialogue data or non-dialogue data is identified, so that the processing attribute of the vehicle data to be processed is determined, a process to be processed is distributed for the vehicle data to be processed based on the processing attribute, the classification resource scheduling and processing of the vehicle data with different types/different processing requirements are realized, and the classification resource scheduling and processing process can be further optimized and self-learned based on received user result feedback, so that a closed-loop self-adaptive learning process is formed, and the user experience of the vehicle-mounted terminal is continuously improved.
In the various embodiments of the present invention, the embodiments of the present invention have been shown and described, but it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principle and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.
Claims (10)
1. A vehicle data processing method, characterized in that the method comprises the steps of:
s100: receiving vehicle data to be processed;
s200: starting a process to be processed based on the processing attribute of the vehicle data to be processed;
s300: processing the vehicle data to be processed through the process to be processed to obtain a processing result;
the vehicle data to be processed received in the step S100 includes dialogue data and non-dialogue data;
the step S200 specifically includes:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
2. A vehicle data processing method according to claim 1, wherein,
the dialogue data is data to be processed received after being activated by a voice dialogue engine;
the non-dialogue data is to-be-processed data directly input by a user.
3. A vehicle data processing method according to claim 1, wherein,
the processing attribute of the vehicle data to be processed in step S200 specifically includes:
if the vehicle data to be processed is dialogue data, processing attributes of the vehicle data to be processed comprise single instruction processing and multi-instruction processing;
and if the vehicle data to be processed is non-dialogue data, the processing attribute of the vehicle data to be processed comprises plain text processing, static image-text processing and multimedia processing.
4. A vehicle data processing method according to claim 3, wherein,
the step S200 starts a process to be processed based on the processing attribute of the vehicle data to be processed, and specifically includes:
if the vehicle data to be processed is dialogue data and the processing attribute is multi-instruction processing, distributing a second process to be processed comprising a plurality of main threads for the vehicle data to be processed;
and if the vehicle data to be processed is non-dialogue data and the processing attribute is plain text processing, distributing a first process to be processed comprising a main thread and at least one auxiliary thread for the vehicle data to be processed.
5. A vehicle data processing method according to claim 3, wherein,
the step S200 starts a process to be processed based on the processing attribute of the vehicle data to be processed, and specifically includes:
if the vehicle data to be processed is non-dialogue data and the processing attribute is multimedia processing, distributing a first process to be processed comprising a first main thread and a plurality of auxiliary threads for the vehicle data to be processed;
the plurality of assist threads includes a first assist thread and a second assist thread;
and the S300 processes the vehicle data to be processed through the process to be processed to obtain a processing result, and specifically comprises the following steps:
transmitting the vehicle data to be processed to the first main thread, wherein the first main thread divides the vehicle data to be processed into a first sub-part and a second sub-part which are sequentially executed based on the processing attribute of the vehicle data to be processed;
processing the first sub-portion by the first main thread; sending the result of the first sub-part processed by the first main thread to the second auxiliary thread for processing; processing, by the first assist thread, the second sub-portion;
summarizing the processing results of the first auxiliary thread and the second auxiliary thread to obtain the processing result of the vehicle data to be processed.
6. A vehicle data processing method according to claim 3, wherein,
the step S200 starts a process to be processed based on the processing attribute of the vehicle data to be processed, and specifically includes:
if the vehicle data to be processed is non-dialogue data and the processing attribute is graphic processing, judging whether the image data to be processed and the text data to be processed of the vehicle to be processed are associated or not;
if no association exists, a second to-be-processed process comprising a second main thread and a third main thread is distributed to the to-be-processed vehicle data, wherein the second main thread is used for processing to-be-processed graph data of the to-be-processed vehicle, and the third main thread is used for processing to-be-processed text data of the to-be-processed vehicle;
and if the association exists, allocating a first to-be-processed process comprising a third main thread and at least one fourth auxiliary thread for the to-be-processed vehicle data.
7. A vehicle data processing system including a vehicle data receiving unit, a process starting unit, a data processing unit, and a result feedback unit, characterized in that:
the vehicle data receiving unit is used for receiving vehicle data to be processed, and the received vehicle data to be processed comprises dialogue data and non-dialogue data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed and starting different types of processes to be processed based on the processing attribute;
the data processing unit is used for processing the vehicle data to be processed through the process to be processed to obtain a processing result;
the result feedback unit is used for receiving feedback data of the processing result of the user and training the process starting unit based on the feedback data;
the process starting unit is used for analyzing the processing attribute of the received vehicle data to be processed, and starting different types of processes to be processed based on the processing attribute, and specifically comprises the following steps:
distributing a first to-be-processed process to the to-be-processed vehicle data based on a first processing attribute of the to-be-processed vehicle data, wherein the first to-be-processed process comprises a main thread and an auxiliary thread;
or, based on a second processing attribute of the vehicle data to be processed, distributing a second process to be processed for the vehicle data to be processed, wherein the second process to be processed only comprises a main thread;
the schedulable resource priority of the auxiliary thread is lower than that of the main thread; different main threads schedule resources in parallel according to the same priority.
8. A vehicle data processing system as claimed in claim 7, wherein:
the process starting unit is realized based on a deep learning model, takes the processing attribute of the vehicle data to be processed as the input of the deep learning model, and outputs the number of main threads and auxiliary threads contained in the process to be started.
9. A vehicle data processing system as claimed in claim 7, wherein:
if the vehicle data to be processed is dialogue data, processing attributes of the vehicle data to be processed comprise single instruction processing and multi-instruction processing;
and if the vehicle data to be processed is non-dialogue data, the processing attribute of the vehicle data to be processed comprises plain text processing, static image-text processing and multimedia processing.
10. An in-vehicle terminal device comprising a memory and a processor, the memory having stored thereon computer executable program instructions, the executable program instructions being executed by the processor for carrying out all the steps of the vehicle data processing method of any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310408692.2A CN116126547B (en) | 2023-04-18 | 2023-04-18 | Vehicle data processing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310408692.2A CN116126547B (en) | 2023-04-18 | 2023-04-18 | Vehicle data processing method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116126547A true CN116126547A (en) | 2023-05-16 |
CN116126547B CN116126547B (en) | 2023-06-27 |
Family
ID=86312148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310408692.2A Active CN116126547B (en) | 2023-04-18 | 2023-04-18 | Vehicle data processing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116126547B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130019085A1 (en) * | 2011-07-12 | 2013-01-17 | International Business Machines Corporation | Efficient Recombining for Dual Path Execution |
CN113903339A (en) * | 2021-10-29 | 2022-01-07 | 上海洛轲智能科技有限公司 | Vehicle-mounted voice remote interaction method and system |
WO2023045207A1 (en) * | 2021-09-27 | 2023-03-30 | 上海商汤智能科技有限公司 | Task processing method and apparatus, electronic device, storage medium, and computer program |
-
2023
- 2023-04-18 CN CN202310408692.2A patent/CN116126547B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130019085A1 (en) * | 2011-07-12 | 2013-01-17 | International Business Machines Corporation | Efficient Recombining for Dual Path Execution |
WO2023045207A1 (en) * | 2021-09-27 | 2023-03-30 | 上海商汤智能科技有限公司 | Task processing method and apparatus, electronic device, storage medium, and computer program |
CN113903339A (en) * | 2021-10-29 | 2022-01-07 | 上海洛轲智能科技有限公司 | Vehicle-mounted voice remote interaction method and system |
Non-Patent Citations (1)
Title |
---|
马广;柯锦超;陈娜佳;王震;周伟志;: "基于车载自组网(VANET)的车辆协作***", 计算机技术与发展, no. 06 * |
Also Published As
Publication number | Publication date |
---|---|
CN116126547B (en) | 2023-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107481719B (en) | Non-deterministic task initiation for personal assistant modules | |
CN106328148B (en) | Natural voice recognition method, device and system based on local and cloud hybrid recognition | |
CN109712624A (en) | A kind of more voice assistant coordination approach, device and system | |
US20110093158A1 (en) | Smart vehicle manuals and maintenance tracking system | |
EP2081113A2 (en) | System and method | |
US11501755B2 (en) | Apparatus and method for providing voice assistant service | |
WO2023005516A1 (en) | Method and apparatus for controlling smart appliances, computer device, and storage medium | |
WO2006076304A1 (en) | Method and system for controlling input modalties in a multimodal dialog system | |
CN110336892B (en) | Multi-device cooperation method and device | |
CN111261151A (en) | Voice processing method and device, electronic equipment and storage medium | |
CN113228074A (en) | Urgency and emotional state matching for automatic scheduling by artificial intelligence | |
CN113486170B (en) | Natural language processing method, device, equipment and medium based on man-machine interaction | |
CN113261268B (en) | Generating and/or prioritizing pre-call content while waiting to accept an incoming call for rendering | |
CN110232924A (en) | Vehicle-mounted voice management method, device, vehicle and storage medium | |
KR20220143683A (en) | Electronic Personal Assistant Coordination | |
CN114724566A (en) | Voice processing method, device, storage medium and electronic equipment | |
CN116126547B (en) | Vehicle data processing method and system | |
CN113539261A (en) | Man-machine voice interaction method and device, computer equipment and storage medium | |
CN112420043A (en) | Intelligent awakening method and device based on voice, electronic equipment and storage medium | |
US11620994B2 (en) | Method for operating and/or controlling a dialog system | |
CN110633037B (en) | Man-machine interaction method and device based on natural language and computer storage medium | |
CN112489644A (en) | Voice recognition method and device for electronic equipment | |
US20200219508A1 (en) | Method for commanding a plurality of virtual personal assistants and associated devices | |
CN112802471B (en) | Voice voice zone switching method, device, equipment and storage medium | |
CN108346431A (en) | Vehicle intelligent voice extension system based on TCP channel and expanding method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |