DTC Diagnosis Vehicle Work Items and Spare Parts Retrieval Method Based on Decision Tree Classification

A decision tree classification and fault code technology, applied in the field of information retrieval, can solve problems such as maintenance labor costs for detailed solutions to failures, and achieve the effect of solving the problem of limited experience

Active Publication Date: 2020-03-24
DALIAN ROILAND SCI & TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

General OBD on-board equipment can only read relevant vehicle fault information, but cannot make detailed solutions to the fault and related maintenance labor costs and spare parts costs, thus causing car owners to enter the store blindly and consume blindly

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • DTC Diagnosis Vehicle Work Items and Spare Parts Retrieval Method Based on Decision Tree Classification
  • DTC Diagnosis Vehicle Work Items and Spare Parts Retrieval Method Based on Decision Tree Classification
  • DTC Diagnosis Vehicle Work Items and Spare Parts Retrieval Method Based on Decision Tree Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0012] Example 1 : A fault code diagnosis vehicle item and spare parts retrieval method based on decision tree classification, including

[0013] Step 1. Collect vehicle information data;

[0014] Step 2. Analyze the vehicle VIN code to obtain variables, and the variables include engine displacement, body type, and engine gearbox type obtained by VIN code analysis;

[0015] Step 3. Perform a decision tree analysis on the spare part codes corresponding to the variables, complete the classification of variable data to form spare part information, and establish an index to form a diagnostic knowledge base;

[0016] Step 4. Create a language model, set up a cell thesaurus, cut words in the cell thesaurus to retrieve the cell words, and arrange the cell words, and use the decision classification of the decision tree model to form a diagnostic database for the corresponding work item of the fault code;

[0017] Step 5. Associate the diagnostic database with the diagnostic knowled...

Embodiment 2

[0019] Example 2: Have the same technical scheme as embodiment 1, more specifically, for step 4 of embodiment 1,

[0020] In the step 3, the historical records of the maintenance spare parts table are used as the data basis, and the spare parts are classified through the decision tree model, and the maintenance spare parts table sample is shown in Table 1:

[0021] Table I

[0022]

[0023]

[0024] The basic principles of the decision tree model are as follows:

[0025] First: Determine the entropy of different categories of spare parts in each dimension. Taking VIN4 as an example, the entropy is defined as

[0026] E=sum(-p(I)*log(p(I)))

[0027] Wherein I=1:N (N category results, such as this example 1, that is, the spare part belongs to this model, so the probability P(I)=1)

[0028] Then E(5)=-(1 / 1) Log2(1 / 1)-(0 / 1) Log2(0 / 1)=0+0=0

[0029] E(3)=-(1 / 1) Log2(1 / 1)-(0 / 1) Log2(0 / 1)=0+0=0

[0030] E(4)=-(1 / 1) Log2(1 / 1)-(0 / 1) Log2(0 / 1)=0+0=0

[0031] If the entropy...

Embodiment 3

[0048] Example 3: Have the same technical scheme as embodiment 1 or 2, more specifically, for step 4 of embodiment 1,

[0049] The creation of the language model in the step 4 and the establishment of the cell lexicon include the following steps:

[0050] S1.1 Collect professional fault description language;

[0051] S1.2 Perform word vector decomposition on the professional fault description language.

[0052] The creation of the language model is based on the assumption that the occurrence of the nth cell word is only related to the previous n-1 cell words; the calculation formula for the occurrence weight of the fault description sentence T is:

[0053] P(T)=P(w 1 ,w 2 ,w 3 ,...,w n )

[0054] =P(w 1 )×P(w 2 |w 1 )×P(w 3 |w 1 ,w 2 )×…×P(w n |w 1 ,w 2 ,...,w n-1 )

[0055] ≈P(w 1 )×P(w 2 |w 1 )×P(w 3 |w 2 )…P(w n |w n-1 );

[0056] Wherein, P(T) is the weight of the fault description sentence T, P(w n |w 1 ,w 2 ,...,w n-1) is the weight of the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a fault code diagnosis vehicle working item and spare part retrieval method based on decision tree classification, and belongs to the field of information retrieval. Since the subgroup numbers of different spare parts are still different under a situation that main group numbers are the same, the method has the following technical key points in order to solve the problem of the accurate matching of the spare parts: analyzing a VIN (Vehicle Identification Number) to obtain a variable, wherein the variable comprises engine capacity, a vehicle body type and an engine gearbox type by analyzing the VIN; carrying out decision tree analysis on a spare part code corresponding to the variable to finish variable data classification so as to form spare part information, establishing an index, and forming a diagnosis knowledge base; creating a language model, establishing a cell word bank, carrying out word segmentation in the cell word bank to retrieve cell words, arranging the cell words, utilizing the decision classification of the decision tree model to form a diagnosis database of the working item corresponding to the fault item; and associating the diagnosis database with the diagnosis knowledge base, and establishing a major key. The method has the effects that a solution of common faults and the corresponding spare part and working item can be quickly found after the fault code is obtained.

Description

technical field [0001] The invention belongs to the field of information retrieval and relates to a method for vehicle remote diagnosis and spare parts retrieval Background technique [0002] At present, my country's automobile maintenance industry has developed from the stage of diagnosis based entirely on the feeling and practical experience of inspectors to the stage of comprehensive detection and diagnosis using special equipment. However, there are many problems in the traditional automobile maintenance industry, such as the technical aging of maintenance workers. , It is often impossible to quickly and economically use various technical forces to solve the fault; with the increasing number of automobiles, various services in the automobile aftermarket have sprung up like mushrooms after rain. So from the perspective of the car owner, how can we better and more comprehensively understand the car condition, how to quickly obtain the car’s pending solution and the required...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/901G06F16/903G06N5/02G06Q10/00
CPCG06F16/901G06F16/903G06N5/022G06N5/027G06Q10/20
Inventor 田雨农刘亮
Owner DALIAN ROILAND SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products