KR20170065156A - Electronic System Mounted on Vehicle And Operation Method Thereof - Google Patents

Abstract

An electronic system mounted on a vehicle is disclosed. The system includes at least one sensing section for sensing sensing information and at least one learning section, and at least one case is generated by clustering sensing information for each of the selected learning sections The control unit analyzes the learning data corresponding to the user operation related to the convenience function for each at least one event and searches the matching event during the running of the vehicle based on the analyzed learning data, Thus, a user operation pattern can be derived. Thus, the reliability of the apparatus can be improved.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an electronic system mounted on a vehicle,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to an electronic system mounted on a vehicle, and more particularly, to an electronic system and a driving method thereof that provide functions in a vehicle.

Due to the breakthrough of electronic control technology, various devices which were operated by mechanical methods in vehicles have been driven by electrical methods for reasons such as convenience of the driver and safety of operation, and automobile systems are gradually advanced and advanced It is going.

The vehicle electronics system provides convenience functions while driving. When the air conditioning function operation, the seat adjustment operation, the humidity adjustment operation, and the like are inputted by user operation, the electronic system transmits a control command to the corresponding electronic control unit (ECU) so that the corresponding function is performed.

However, the driver's attention can be dispersed as various convenience functions are provided. Thus, the emergence of an electronic system that considers more user safety and convenience is required.

Published Japanese Patent Application No. 10-2003-0090605 (Published Jun. 2005, 17)

It is an object of the present invention to provide an electronic system for receiving environment information and user operation information and analyzing a user pattern.

In addition, an object of an embodiment related to the present invention is to provide an electronic system to which a neural network algorithm for clustering environment information and analyzing a user operation pattern based on clustered environment information is applied.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, unless further departing from the spirit and scope of the invention as defined by the appended claims. It will be possible.

According to an embodiment of the present invention. An electronic system mounted on a vehicle includes a sensing unit for sensing sensing information; And a control unit for selecting at least one learning target section and generating at least one case by clustering sensing information for each of the selected learning target sections, The method includes analyzing learning data corresponding to a user operation associated with a convenience function for each of the at least one event, searching for an event that is matched during running of the vehicle based on the analyzed learning data, Can be derived.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, And can be understood and understood.

Effects of the method and the apparatus according to an embodiment of the present invention will be described as follows.

First, an electronic system for analyzing a user pattern by receiving environment information and user operation information is provided, so that device stability and user convenience can be improved.

Second, an electronic system that provides a function beyond analyzing a user operation pattern and automatically adjusting a switch can be provided, thereby ensuring more user convenience and device stability.

The effects obtained by the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those skilled in the art from the following description will be.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. It is to be understood, however, that the technical features of the present invention are not limited to the specific drawings, and the features disclosed in the drawings may be combined with each other to constitute a new embodiment.
1 is a block diagram of an electronic system according to an embodiment.
2 is a flowchart showing a driving method of the electronic system of Fig.
3 is a diagram showing a method of selecting a learning target section.
4 is a diagram showing a method of collecting and clustering sensing information.
5 is a diagram illustrating a method of analyzing a user operation corresponding to sensing information using a neural network algorithm.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an apparatus and various methods to which embodiments of the present invention are applied will be described in detail with reference to the drawings. The suffix "module" and " part "for the components used in the following description are given or mixed in consideration of ease of specification, and do not have their own meaning or role.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to perform a part or all of the functions in one or a plurality of hardware. As shown in FIG. The codes and code segments constituting the computer program may be easily deduced by those skilled in the art. Such a computer program can be stored in a computer-readable storage medium, readable and executed by a computer, thereby realizing an embodiment of the present invention. As the storage medium of the computer program, a magnetic recording medium, an optical recording medium, a carrier wave medium, or the like may be included.

Hereinafter, a configuration of an electronic system according to an embodiment of the present invention will be described.

1 is a block diagram of an electronic system mounted in a vehicle according to an embodiment.

1, the electronic system 100 is mounted on a vehicle.

The electronic system 100 includes a sensing unit 110, a switch module 120, an AVN (Audio Video Navigation Module) 130, a memory 140, an air conditioner 150, a sheet heating line driver 160, And may include a control unit 180.

The sensing unit 110 may include various sensors. The sensing unit 110 may sense environmental information of the inside / outside of the vehicle. The sensing unit 110 may include an illuminance sensor, a temperature sensor, a humidity sensor, a pressure sensor, a heat sensor, I never do that.

When the On / Off command is input by a user operation, the switch module 120 may transmit an operation command to an ECU (Electronic Control Unit) corresponding to the user operation so that the user operation is performed. At this time, the switch module 120 can transmit the operation command through CAN (Controller Area Network) communication under the control of the controller 180. [ However, in the present specification, it is assumed that the control unit 180 directly controls the switch module 120 to include the above-described contents.

The AVN 130 is a module that generally manages driving of audio, video, and navigation of a vehicle, or a telematics module integrally, and can receive the GPS position information of the vehicle and provide it to the controller 180.

The memory 140 may store a program for the operation of the controller 180. [ The memory 140 may be a flash memory type, a hard disk type, an SSD type, an SDD type (Silicon Disk Drive type), a multimedia card micro type ), Card type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read memory, a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and / or an optical disk.

The air conditioner 150 generally refers to a device related to the cold airing of a vehicle. An air conditioner, a heater, a cooling module, a radiator, and the like. The sheet heating line driver 160 is a device for driving the heating line provided in the sheet. The ventilator 170 is a device for air circulation inside the vehicle.

The control unit 180 may include a module control unit 181, a sheet heating line control unit 183, a ventilation control unit 185, and a user operation pattern analysis module 187 for overall control of the electronic system 100.

The air conditioning control unit 181 is a module for controlling the air conditioner 150. The sheet heating line control unit 183 is a module for controlling the sheet heating line driver 160. [ The ventilation control unit 185 is a module for controlling the ventilator 170.

The user operation pattern analyzing module 187 analyzes the operation pattern of the user when the switch module 120 is operated by a user operation.

In addition, the user operation pattern analysis module 187 can analyze the operation pattern of the user based on the sensing information obtained by sensing the environment inside and outside the vehicle.

2 is a flow chart showing a driving method of the electronic system.

First, the control unit 180 of the electronic system 100 selects a learning target section (S210). Will be described with reference to FIG.

3, the controller 180 may receive the geographical information 310 from the AVN 130 and may select a road from the AVN 130 to the roads 320a to 320b.

The control unit 180 can divide the learning target roads into the learning target sections 330-1 to 330-6 for each road type and distance. The road to be studied may be a road with a high frequency of use of the vehicle, but the present invention is not limited thereto.

When the vehicle is actually moved to the learning target road, the control unit 180 can collect user operation data under various environment information and corresponding environment information.

For example, when the vehicle is traveling in the first learning object section 330-1, the controller 180 can collect temperature, humidity, air pressure, illuminance information, time information, driving situation information, have.

Also, the control unit 180 can monitor that the vehicle convenience function is driven by a user operation in the learning subject sections 330-1 to 330-6. For example, the control unit 180 can monitor that the air conditioner is turned on when the vehicle enters the highway, and can monitor that the heater is turned on when the vehicle enters the city. As described above, the controller 180 may collect sensing information received through various sensors and collect user operations corresponding to the sensing information. The control unit 180 may store the collected sensing information and the user operation information in the memory 140.

In addition, the controller 180 monitors the switch module 120 to monitor the operation of the switch related to the user's convenience.

For example, the control unit 180 can monitor whether the air conditioner is driven when the temperature and the humidity are specific, and monitor the headlight driving according to the specific illuminance.

That is, the control unit 180 can monitor various ECU driving related to the convenience function

Referring back to FIG. 2, the controller 180 determines whether the number of times of repeated learning is insufficient for the predetermined number of times (S220). If the vehicle enters the learning target section (S230) (S240). Will be described with reference to FIG.

According to FIG. 4, the control unit 180 can collect environmental information when the vehicle travels in the learning target section. Specifically, the controller 180 may perform clustering based on the sensing information for each of the sections 410 to 430 when the vehicle travels the learning target section. Clustering is the clustering of data with similar properties.

The control unit 180 collects data through a plurality of sensors for each section. For example, the control unit 180 may control the humidity of the room, the outdoor temperature, the outdoor illuminance / temperature, etc. by controlling the sensing unit 110 (e.g., the illuminance sensor, the temperature sensor, the humidity sensor, the air pressure sensor, Can be collected.

The control unit 180 clusters the sensing information collected during the running of the vehicle. The control unit 180 clusters the collected data based on the set criteria. For example, the control unit 180 can group data by setting a specific sensing value range.

Here, the centroids of the clustering can be derived through a general K-Means clustering technique, but are not limited thereto.

The control unit 180 derives the first through third clusters in the first period 410 and derives the fourth through sixth clusters in the second period 420 and outputs the fourth through sixth clusters in the third period 430, 9 clusters can be derived. A cluster is a group of clusters.

As a result, nine clusters may be generated in the first to third intervals 410 to 430. [

Here, it is assumed that the cluster corresponds to one event (Case).

The controller 180 generates a plurality of cases for each section and collects the surrounding environment information when the vehicle travels the learning object sections 410 to 430. [

Referring back to FIG. 2, after step S240, the controller 180 learns a user operation pattern for each event (S250). At this time, a neural network algorithm can be used.

The controller 180 collects and clusters environmental information while the vehicle is traveling in a learning section, collects what user's operations are input according to a specific environment, and analyzes the collected user's operation information.

The user operation information corresponds to specific switch operation information. It may include, but is not limited to, an air conditioner On / Off, a headlight on / off, and a moisture remover on / off.

 According to FIG. 5, if there are six learning intervals as shown in FIG. 3B (330-1 to 330-6) and there are three clusters (events) for each learning interval, 18 events are generated .

The control unit 180 may determine a user operation pattern through a neural network algorithm for each event. Neural network algorithms (e.g., Supervised-Neural network algorithms) may be used.

For example, the control unit 180 sets a plurality of nodes receiving the sensed values from the auto light sensor, the outdoor temperature sensor, the indoor temperature sensor, and the auto deformer sensor as an input layer. The control unit 180 sets a plurality of nodes that output user operation corresponding to the sensed value, that is, the air conditioning temperature switch operation, the seat heat level switch operation, and the seat ventilation level switch operation information to the output layer. At this time, the number of hidden layers can be appropriately determined according to the system. Here, the relationship between the node and the link can be derived through a neural network algorithm, and the relationship between the most suitable node and the link is formed by continuous learning.

That is, the controller 180 analyzes the environment information and analyzes a user operation pattern using the convenience function according to the environment information.

Hereinafter, returning to FIG. 2, the description will be made of the mapping to the event when the actual vehicle is driven after the learning step is completed. However, the control unit 180 may be operated so that environmental information collection / clustering and user operation collection / analysis are not ended even if the actual vehicle is running.

If the number of learning iterations is insufficient (S220), the controller 180 analyzes the matched event in the actual running of the vehicle, not the learning (S260).

If the vehicle enters the road in the current learning section (assuming that there are three events per learning section), then the control section 180 sends environment information and user operation information collected from the actual vehicle to three Matching can be performed through the center vector of events and distance calculation. If the vehicle is not traveling within the learning interval, the controller 180 performs matching by calculating the distance between the center vector of the event (e.g., six learning intervals and three events for each interval) do. The formula is as follows.

[Equation]

Here, x _i can be defined as the i th sensor input vector, the cluster center vector of c _j = j-Case, ∥ x _i - c _j ∥ = sensor input vector and Euclidean distance of the cluster center vector.

After step S260, the controller 180 derives a user operation pattern through analysis of a matched event in the course of running (S270).

Then, the control unit 180 may adapt the specific situation during driving of the vehicle to drive the switch module related to the convenience function.

Accordingly, various situations are automatically performed, and the user's convenience can be improved. This is not a concept that the electronic system 100 automatically activates the system 100 by matching any user's operation to any environment information on a one-to-one basis, but uses environment information and user operation information adaptively, Can be provided.

Further, the electronic system 100 can stop the automatic control according to the intention of the user even during automatic control. For example, if intentional manipulation of the user is performed, the automatic control in the corresponding section is canceled and can be operated in the learning mode within the learning section. Further, if the vehicle is not a learning section, the automatic control can be canceled. At this time, the start-up may be turned on again, or automatic control may be performed when entering another learning section, but this is not limitative.

Also, the user's operation can be reflected during the automatic control even at the time of automatic control.

On the other hand, the electronic system 100 can visually provide the service through a display mounted on the AVN system or a display mounted on the AVN system. Further, even if the display is not operated, the learning data can be normally collected.

It will be apparent to those skilled in the art that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. Accordingly, the above description should not be construed in a limiting sense in all respects and should be considered illustrative. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

The method according to the above-described embodiments may be implemented as a program to be executed by a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include a ROM, a RAM, a CD- , A floppy disk, an optical data storage device, and the like, and may also be implemented in the form of a carrier wave (for example, transmission over the Internet).

The computer readable recording medium may be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner. And, functional program, code, and code segments for implementing the above-described method can be easily inferred by programmers in the technical field to which the embodiment belongs.

100: Electronic system
110: sensing unit
120: Switch module
130: AVN
140: Memory
180:

Claims (20)

A driving method of an electronic system mounted on a vehicle,
Selecting at least one learning target section;
Generating at least one case by clustering sensing information for each of the selected learning target sections;
Analyzing learning data corresponding to a user operation related to a convenience function for each of the at least one event;
Searching for an event that is matched during running of the vehicle based on the analyzed learning data; And
And deriving a user operation pattern based on the retrieved event. The method according to claim 1,
And controlling the vehicle automatically by operating a switch associated with the vehicle convenience function based on the derived user operation pattern. The method according to claim 1,
Wherein the step of selecting the at least one learning target section comprises:
Wherein the at least one learning target section is selected based on at least one of a user preference frequency, a distance segment and a road segment. The method according to claim 1,
CC = LC * CLC (CLC) when the sum of the at least one event is a case count, the at least one learning target interval is a learning count and the number of clusters per learning target interval is CLC Of the electronic system mounted on the vehicle. The method according to claim 1,
Wherein the generating the at least one event comprises:
Collecting a plurality of sensing information through at least one sensor, and clustering the sensing information on a predetermined basis. The method according to claim 1,
Wherein the step of analyzing the learning data comprises:
Setting sensing information as an input node for each of the at least one event and setting user operation information associated with the convenience function as an output node;
And analyzing the learning data using a neural network algorithm. The method according to claim 6,
Wherein searching for a matching event during running of the vehicle comprises:
And comparing the sensed information and user operation information collected during actual driving with the analyzed learning data to search for an event during driving. The method according to claim 1,
Wherein searching for a matching event during running of the vehicle comprises:
And searches for an event that is matched based on a distance from at least one event corresponding to the subject section to be traveled when the vehicle travels in at least one learning object section. The method according to claim 1,
Wherein searching for a matching event during running of the vehicle comprises:
And searches for an event that is matched based on the distance from all the events if the vehicle is not traveling in at least one learning object section. In an electronic system mounted on a vehicle,
A sensing unit sensing sensing information; And
And a control unit for selecting at least one learning target section and generating at least one case by clustering sensing information for each of the selected learning target sections,
Wherein,
Analyzes learning data corresponding to a user operation related to the convenience function for each of the at least one event
Based on the analyzed learning data, searches for an event that is matched during travel, and derives a user operation pattern based on the retrieved event. 11. The method of claim 10,
Wherein,
And automatically controls the vehicle by operating a switch associated with the vehicle convenience function based on the derived user operation pattern. 11. The method of claim 10,
Wherein,
Based on at least one of a user preference frequency, a distance segment, and a road segment. 11. The method of claim 10,
CC = LC * CLC (CLC) when the sum of the at least one event is a case count, the at least one learning target interval is a learning count and the number of clusters per learning target interval is CLC Of the vehicle. 11. The method of claim 10,
Wherein,
Collecting a plurality of sensing information through at least one sensor, and clustering the sensing information on a predetermined basis. 11. The method of claim 10,
Wherein,
Wherein the sensing information is set as an input node and the user operation information related to a convenience function is set as an output node for each at least one event and the learning data is analyzed using a neural network algorithm. 16. The method of claim 15,
Wherein,
And comparing the sensed information and the user operation information collected during actual driving with the analyzed learning data to search for an event during driving. 11. The method of claim 10,
Wherein,
And searches for an event that is matched based on a distance from at least one event corresponding to the subject section to be traveled when the vehicle travels in at least one learning object section. 11. The method of claim 10,
Wherein,
And searches for an event that is matched based on the distance from all the events if the vehicle is not traveling in at least one learning target section. A program recorded on a recording medium for realizing a method of driving an electronic system mounted on a vehicle according to claim 1. A recording medium on which the program according to claim 19 is recorded.

Images