CN109582670A - A kind of recommended method and relevant device of vehicle maintenance scheme - Google Patents
A kind of recommended method and relevant device of vehicle maintenance scheme Download PDFInfo
- Publication number
- CN109582670A CN109582670A CN201811287974.7A CN201811287974A CN109582670A CN 109582670 A CN109582670 A CN 109582670A CN 201811287974 A CN201811287974 A CN 201811287974A CN 109582670 A CN109582670 A CN 109582670A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- policy tree
- child node
- node
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses the recommended methods and relevant device of a kind of vehicle maintenance scheme, comprising: obtains the Fisrt fault diagnostic message of target vehicle first；Then according to the Fisrt fault diagnostic message, the association repair message of the target vehicle is determined；Then according to the association repair message and logic of propositions relationship library, maintenance policy tree is generated, the maintenance policy tree includes multiple child nodes, the corresponding maintenance step of each child node in the multiple child node；Finally selection target repairs the maintenance program that step constructs the target vehicle from the maintenance policy tree.Using the embodiment of the present application, vehicle maintenance efficiency can be improved.
Description
Technical field
This application involves vehicle maintenance field more particularly to a kind of recommended methods and relevant device of vehicle maintenance scheme.
Background technique
With the raising of productivity and economic level, the car ownership sharp increase in China, car is rapidly introduced into general
Common people family, logical China.Automobile is popularized while bringing great convenience for the trip of people, and automobile maintenance industry is also given
Bring numerous challenges.Currently, the technical level of the generally existing maintenance technician of Chinese automobile maintenance industry is very different and band
The problem of vehicle maintenance low efficiency come.
Summary of the invention
The embodiment of the present application provides the recommended method and relevant device of a kind of vehicle maintenance scheme.Vehicle maintenance can be improved
Efficiency.
The embodiment of the present application first aspect discloses a kind of recommended method of vehicle maintenance scheme, comprising:
Obtain the Fisrt fault diagnostic message of target vehicle；
According to the Fisrt fault diagnostic message, the association repair message of the target vehicle is determined；
According to the association repair message and logic of propositions relationship library, maintenance policy tree, the maintenance policy tree packet are generated
Multiple child nodes are included, the corresponding maintenance step of each child node in the multiple child node；
Selection target maintenance step constructs the maintenance program of the target vehicle from the maintenance policy tree.
Wherein, the maintenance policy tree further includes a root node, and the root node is that the source of the multiple child node is saved
Point；
It is described according to the association repair message and logic of propositions relationship library, generating maintenance policy tree includes:
Determine the incidence coefficient between the association repair message；
According to the incidence coefficient, the root node is determined；
According to the root node and logic of propositions relationship library, the maintenance policy tree is generated.
Wherein, the corresponding weight coefficient of each child node；
The maintenance program that the selection target from maintenance policy tree maintenance step constructs the target vehicle includes:
According to the weight coefficient, selection target maintenance step constructs the maintenance program from the maintenance policy tree.
Wherein, the weight coefficient is obtained by training data；
The method also includes:
Determining has the identical cumulative amount for repairing the corresponding child node of step；
According to the cumulative amount, frequency of each child node in the maintenance policy tree is determined；
According to the frequency, the weight coefficient of each child node is updated.
Wherein, described also to be wrapped after generating maintenance policy tree according to the association repair message and logic of propositions relationship library
It includes:
Obtain the second failure diagnosis information of the target vehicle；
According to second failure diagnosis information, child node is deleted or increased in the maintenance policy tree.
Wherein, including the first logical relation information between child node in the maintenance policy tree；
It is described according to second failure diagnosis information, deleted in the maintenance policy tree or increase child node and include:
Obtain the second logical relation information for including in second failure diagnosis information；
The first logical relation information and the second logical relation information are matched, determine the multiple sub- section
Redundant node in point；
The redundant node is deleted from the maintenance policy tree.
Wherein, described according to second failure diagnosis information, child node is deleted or increased in the maintenance policy tree
Include:
Obtain the faulty entity information for including in second failure diagnosis information；
According to the faulty entity information and logic of propositions relationship library, increase son section in the maintenance policy tree
Point.
Wherein, the maintenance program for selecting the maintenance step to form the target vehicle from the maintenance policy tree
Later, further includes:
Display reminding information, the prompt information is for prompting user to repair the target carriage according to the maintenance program
?.
The embodiment of the present application second aspect discloses a kind of recommendation apparatus of vehicle maintenance scheme, comprising:
Module is obtained, for obtaining the Fisrt fault diagnostic message of target vehicle；
Relating module, for determining the association repair message of the target vehicle according to the Fisrt fault diagnostic message；
Generation module, it is described for generating maintenance policy tree according to the association repair message and logic of propositions relationship library
Maintenance policy tree includes multiple child nodes, the corresponding maintenance step of each child node in the multiple child node；
Decision-making module, for from the maintenance policy tree selection target maintenance step construct the maintenance of the target vehicle
Scheme.
Wherein, the maintenance policy tree further includes a root node, and the root node is that the source of the multiple child node is saved
Point；
The generation module is also used to:
Determine the incidence coefficient between the association repair message；
According to the incidence coefficient, the root node is determined；
According to the root node and logic of propositions relationship library, the maintenance policy tree is generated.
Wherein, the corresponding weight coefficient of each child node；
The decision-making module is also used to:
According to the weight coefficient, selection target maintenance step establishes the maintenance program from the maintenance policy tree.
Wherein, the weight coefficient is obtained by training data；
The generation module is also used to:
Determining has the identical cumulative amount for repairing the corresponding child node of step；
According to the cumulative amount, frequency of each child node in the maintenance policy tree is determined；
According to the frequency, the weight coefficient of each child node is updated.
Wherein, the acquisition module is also used to:
Obtain the second failure diagnosis information of the target vehicle；
The generation module is also used to:
According to second failure diagnosis information, child node is deleted or increased in the maintenance policy tree.
Wherein, including the first logical relation information between child node in the maintenance policy tree；
The generation module is also used to:
Obtain the second logical relation information for including in second failure diagnosis information；
The first logical relation information and the second logical relation information are matched, determine the multiple sub- section
Redundant node in point；
The redundant node is deleted from the maintenance policy tree.
Wherein, the generation module is also used to:
Obtain the faulty entity information for including in second failure diagnosis information；
According to the faulty entity information and logic of propositions relationship library, increase son section in the maintenance policy tree
Point.
Wherein, described device further includes display module, is used for:
Display reminding information, the prompt information is for prompting user to repair the target carriage according to the maintenance program
?.
The embodiment of the present application third aspect discloses a kind of electronic equipment, comprising: processor, memory, communication interface and
Bus；
The processor, the memory are connected by the bus with the communication interface and complete mutual lead to
Letter；
The memory stores executable program code；
The processor is run by reading the executable program code stored in the memory can be performed with described
The corresponding program of program code, for executing a kind of recommendation of vehicle maintenance scheme disclosed in the embodiment of the present application first aspect
Operation in method.
Correspondingly, the embodiment of the present application discloses a kind of storage medium, wherein the storage medium applies journey for storing
Sequence, the application program for executing a kind of pushing away for vehicle maintenance scheme disclosed in the embodiment of the present application first aspect at runtime
Recommend method.
Correspondingly, the embodiment of the present application discloses a kind of application program, wherein the application program for holding at runtime
A kind of recommended method of vehicle maintenance scheme disclosed in row the embodiment of the present application first aspect.
Implement the embodiment of the present application, obtains the Fisrt fault diagnostic message of target vehicle first；Then according to described first
Failure diagnosis information determines the association repair message of the target vehicle；Then it is patrolled according to the association repair message with default
Relationship library is collected, maintenance policy tree is generated, the maintenance policy tree includes multiple child nodes, every height in the multiple child node
Node corresponds to a maintenance step；The maintenance step is finally selected to construct the target vehicle from the maintenance policy tree
Vehicle maintenance efficiency can be improved in maintenance program.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to required use in embodiment description
Attached drawing be briefly described.
Fig. 1 is a kind of flow diagram of the recommended method of vehicle maintenance scheme provided by the embodiments of the present application；
Fig. 2 is a kind of schematic diagram of logic transaction network provided by the embodiments of the present application；
Fig. 3 is a kind of schematic diagram of maintenance policy tree provided by the embodiments of the present application；
Fig. 4 is the flow diagram of the recommended method of another vehicle maintenance scheme provided by the embodiments of the present application；
Fig. 5 is a kind of schematic diagram of practical application process provided by the embodiments of the present application；
Fig. 6 is a kind of structural schematic diagram of the recommendation apparatus of vehicle maintenance scheme provided by the embodiments of the present application；
Fig. 7 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.
Referring to FIG. 1, Fig. 1 is a kind of process signal of the recommended method of vehicle maintenance scheme provided by the embodiments of the present application
Figure.Executing subject in the embodiment of the present application is electronic equipment, as shown, the method in the embodiment of the present application includes:
S101 obtains the Fisrt fault diagnostic message of target vehicle.
In the specific implementation, user can be first with vehicle fault detection equipment (such as golo vapour when vehicle breaks down
Vehicle failure diagnostic apparatus) fault diagnosis is carried out to vehicle, failure diagnosis information is obtained, may include failure in the failure diagnosis information
The information such as code, malfunctioning module, wherein error code is the identification information of vehicle trouble, such as C1203, P1270.Then user can
Failure diagnosis information is sent to electronic equipment in a manner of through voice or text.For example, failure diagnosis apparatus detects failure
Code C1203, then user can to electronic equipment input interactive voice information " how reading error code C1203? ".Wherein, may be used also
Electronic equipment and failure diagnosis apparatus to be attached, then electronic equipment directly receives the event of vehicle fault diagnosis equipment transmission
Hinder diagnostic message.
S102 determines the association repair message of the target vehicle according to the Fisrt fault diagnostic message.
In the specific implementation, the critical entities in Fisrt fault diagnostic message can be extracted first with entity recognition techniques
(X), relevant role's ingredient (Y) is determined using sentence structure analysis technology and analytical technology is intended to according to user, extract the
User in one failure diagnosis information is intended to key value (Z), wherein if electronic equipment obtain be user's input interactive voice
Information then first can carry out synonym standardization, homophonic word standardization to the voice messaging.
Such as: user input interactive voice information be " how reading error code C1203? ".Then the voice is handed over first
Mutual information word standardize obtain " what if reading error code C1203? ", then obtain critical entities X=and (read, failure
Code, C1203, what if), role's ingredient Y=(verb, noun, noun, interrogative) and Z=(interrogative of seeking help).
Then, it is intended to key value (Z) and logic of propositions relationship library in conjunction with critical entities (X), role's ingredient (Y), user
It carries out fault correlation, the field of physical network is predicted, determine the association repair message of vehicle maintenance, repair message will be associated with
It is denoted as Q=(Q1, Q2..., Qs).Wherein, X=(X1,X2,...,Xm), Y=(Y1,Y2,…,Ym), then Qi(i=1,2 ..., s)
Calculation method as shown in (1) formula,
Wherein, wxyFor the corresponding entity rule weight of critical entities, wzIt is intended to the corresponding intention rule of key value for user
Weight, wxy+wz=1.wxyAnd wzIt is binding isotherm and a large amount of data set, what training obtained.For
Associated frequencies distribution calculates function, and g (Z) is to be intended to frequency distribution to calculate function, and ψ can be dirichlet function.WhereinIt can be common probability-distribution function with g (Z).
S103 generates maintenance policy tree, the maintenance policy according to the association repair message and logic of propositions relationship library
Tree includes multiple child nodes, the corresponding maintenance step of each child node in the multiple child node.
In the specific implementation, being directed to multiple child nodes, one of child node can be the father node of another child node,
And being referred to as child node is with respect to for the root node in the maintenance policy tree.Association repair message can be determined first
(Q) incidence coefficient between, and determine according to incidence coefficient the best process inlet of maintenance policy tree, that is, determine maintenance policy tree
Root node generate maintenance policy tree then according to root node and logic of propositions relationship library.In the electronic device, the maintenance plan
Slightly tree can pass through tree structure sequence { O1, O2..., ONStored, O is considered as a node in maintenance policy tree.
Wherein, O1For best process inlet (root node), O1=max (W (Q1, Q2..., Qs)), W (Q1, Q2..., Qs) it is incidence coefficient, W
For associated weights function, there are many kinds of definition mode the embodiment of the present application by W with no restriction.Specific Oi=(Xr1,bi,Xr2,ω,
C,bc), wherein Xr1、Xr2Indicate specific maintenance step, biIndicate that the logic between the child node and the father node of the child node is closed
System, ω indicate the corresponding weight coefficient of the node, C Xr1、Xr2Type field, bcIndicate biThe class of the logical relation referred to
Type, it should be noted that OiIt can also include other added fields, the embodiment of the present application does not remake to be illustrated one by one.Then basis
O1O is successively determined in logic of propositions relationship library with repair message is associated with2, O3..., ON, wherein logic of propositions relationship library can be with
For logic things network, Fig. 2 gives a kind of possible logic things network.
Such as: receive user input interactive voice information be " what if reading error code C1203? ", then first really
The process inlet that Policy Tree is surveyed in fixed maintenance is C1203, then according to logic transaction network as shown in Figure 2, is generated as shown in Figure 3
Maintenance policy tree.Wherein, there are multipair father node and child nodes in the maintenance policy tree, for example, " checking ECM Part No. "
For father node, the child node of the father node includes " replacement ECM (3GR-FE) ", " replacement ECM (5GR-FE) " and " removes and store
System information ".3GR-FE and 5GR-FE indicates that the model of vehicle motor, dashed rectangle indicate father's section in the maintenance policy tree
Logical relation between point and child node, oval frame indicate the corresponding weight coefficient of child node.
Optionally, the Fisrt fault diagnostic message of user's input may only include the one of whole fault messages of target vehicle
Part.For example, golo vehicle trouble failure diagnostic apparatus has read error code C1203 and C1207, the first event of user's input simultaneously
Hinder that diagnostic message is " what if reading error code C1203? ".Therefore, the second fault diagnosis of target vehicle can be obtained again
Information, and according to the second failure diagnosis information, child node is deleted or increased in generated maintenance policy tree.Including two
Kind situation:
The first situation: obtaining the second logical relation information in the second failure diagnosis information, then closes the second logic
It is that information is matched with the first logical relation information (dashed rectangle in Fig. 3) in maintenance policy tree, determines multiple sub- sections
Redundant node in point, then deletes redundant node.
Such as: after generating maintenance policy tree as shown in Figure 3, user inputs the second failure diagnosis information and " needs replacing
Which accessory in ECM? ", then can therefrom extraction logic relation information " replacement ", which " matches with child node
The logical relation of part title " is identical, it is thus determined that subtree (as schemed) in all child nodes be redundant node, and from this be plan
Slightly subtree is deleted in tree.
Second situation: obtain the second failure diagnosis information in faulty entity information, faulty entity information can with but not
It is limited to include that the identification information of vehicle accessory or module is repairing then according to faulty entity information and logic of propositions relationship library
Increase child node in Policy Tree.For example, user inputs the second fault diagnosis letter after generating maintenance policy tree as shown in Figure 3
It ceases " XXX sensor abnormality ", then can carry out fault correlation for XXX sensor, and for plan in logic of propositions relationship library
Slightly increase the corresponding child node of corresponding maintenance step in tree.
S104 selects the maintenance step to construct the maintenance program of the target vehicle from the maintenance policy tree.
In the specific implementation, the corresponding weight coefficient of each child node in maintenance policy tree, wherein the weight coefficient is
What binding isotherm and the training of a large amount of data set obtained, the weight coefficient can be adjusted in subsequent operation.Wherein,
Maintenance step can be successively selected from maintenance policy tree, wherein can successively select since root node according to the weight coefficient
The corresponding maintenance step of the maximum child node of weight coefficient.Wherein, for maintenance policy tree { O1, O2..., ON, it can be from O1It opens
Beginning is traversed, and saves the corresponding maintenance step (S) of each selected child node, and return to Oout=(Xst,Bi,Xnext).Its
In, XstFor the O of current accessediXr1, BiFor the O of current accessediBi。Xnext=max (w (Qi)|Xst=Xr1), max (w (Qi)
|Xst=Xr1) indicate to work as Xst=Xr1When maximum w (Qi), w can be common probability function.It wherein, can also be by OoutTurn
It changes the intelligible structured statement of user into and shows.For example, structured statement can be " to first check whether normally, if just
Often, then, if abnormal, then.", wherein " " is needed according to OoutThe information such as module, part name or the operating procedure of filling.
Wherein, { O1, O2..., ONBe the storage mode of maintenance policy tree in the electronic device, in order to make it easy to understand, with
In lower example, it will be illustrated with maintenance policy tree as shown in Figure 3 according to the weight coefficient, successively selected from maintenance policy tree
Select maintenance step.
Such as: as shown in figure 3, since " C1203 " first in two child nodes of " C1203 " select weight coefficient compared with
Big " checking ECM part " (S1)；Then the maximum sub- section of weight coefficient is selected in 3 child nodes of " checking ECM part "
Point " removing simultaneously storing system information " (S2)；Then in the case where only considering Standard Operating Procedure, selection " is removed and is stored and be
Child node " reaffirming DTC " (S of system information "3), DTC indicates diagnostic trouble code；Finally in 2 sons of " reaffirming DTC "
Biggish " replacement brake actuator the assembly " (S of weight coefficient is selected in node4).Finally, it is selected according to from maintenance policy tree
Maintenance step, whether establish maintenance program: it is normal to first check for ECM part, if normal, then first removes and storage system letter
Breath, then reaffirm DTC, C1203, then replace brake actuator assembly if it exists.
It optionally, can be with the maintenance program of displaying target vehicle, to prompt user according to the maintenance program to target carriage
It repairs.
Optionally, entire maintenance policy tree can be shown, to recommend the maintenance program of plurality of optional to user, user is then
Suitable maintenance program can be selected from the Policy Tree according to the specific fault condition of self-technique strength and target vehicle.
Implement in embodiment in the application, obtains the Fisrt fault diagnostic message of target vehicle first；Then according to described
Fisrt fault diagnostic message determines the association repair message of the target vehicle；Then according to the association repair message and in advance
If logical relation library, maintenance policy tree is generated, the maintenance policy tree includes multiple child nodes, every in the multiple child node
The corresponding maintenance step of a child node；The maintenance step is finally selected to construct the target carriage from the maintenance policy tree
Maintenance program, to improve vehicle maintenance efficiency.
Referring to FIG. 4, the process that Fig. 4 is the recommended method of another vehicle maintenance scheme provided by the embodiments of the present application is shown
It is intended to.As shown, the method in the embodiment of the present application includes:
S401 obtains the second failure diagnosis information of target vehicle.This step is identical as the S101 in a upper embodiment, this
Step repeats no more.
S402 determines the association repair message of target vehicle according to Fisrt fault diagnostic message.This step and upper one is implemented
S102 in example is identical, this step repeats no more.
S403 generates maintenance policy tree according to association repair message and logic of propositions relationship library.This step and upper one is implemented
S103 in example is identical, this step repeats no more.
S404, selection maintenance step establishes maintenance program from maintenance policy tree.In this step and a upper embodiment
S104 is identical, this step repeats no more.
S405, determine target vehicle whether maintenance success.If so, executing S406.If it is not, then executing S407.
In the specific implementation, can receive the feedback information of user, and determine whether target vehicle is tieed up according to the feedback information
Accomplish function.
S406 updates the weight coefficient of the child node in maintenance policy tree.
In the specific implementation, the corresponding power of each child node in use and maintenance Policy Tree for the first time, in the maintenance policy tree
Weight coefficient is that binding isotherm is trained a large amount of data.Therefore, in the actual use process to the maintenance decision tree
In, can according to actual use situation update the weight coefficient, so as to weight coefficient determine it is more acurrate, more meet reality.It can be with
For each maintenance step in maintenance program, it is first determined the cumulative amount with the maintenance step child node；Then according to
Cumulative amount determines frequency (num) of each child node in the maintenance policy tree, wherein frequency is equal to cumulative amount；Then
According to frequency, the weight coefficient (ω) of child node is updated, wherein ω=1/ (1+e-(num-1)), wherein e is equal to 2.7182.Example
Such as, maintenance policy tree as shown in Figure 3 includes " replacement ECM (3GR-FE) " in the maintenance step of target vehicle, has the maintenance
The cumulative amount of the child node of step is 2, then the frequency of the two child nodes is 2, and weight coefficient is 1/ (1+e-1), wherein if
The corresponding maintenance step of child node is not included in the maintenance program of target vehicle, then the weight coefficient of the child node is kept not
Become.
S407 updates maintenance decision tree.
In the specific implementation, can be carried out at beta pruning according to maintenance program identified in step S404 to maintenance decision tree
Reason.Specifically, being based on maintenance policy tree { O1, O2..., ONAnd S404 in Oout=(Xst,Bi,Xnext), it can be by Xr1=
XnextOiIt is deleted from the maintenance policy tree.
Such as: maintenance program is replacement ECM (5GR-FE), will dimension if should fail for scheme repairs target vehicle
The child node that maintenance step corresponding in Policy Tree is " replacement ECM (5GR-FE) " is repaired all to delete.
Carry out the whole flow process of the recommended method to the vehicle maintenance scheme in the embodiment of the present application below by way of an example
It is illustrated.
Such as: as shown in figure 5, receiving user's input fault diagnostic message first；Then the failure diagnosis information is carried out
Information extraction obtains critical entities information, role's composition information and user intent information；Then according to the information that is drawn into and
Preset logic transaction network carries out fault correlation, obtains the association repair message for target vehicle, and determines that process enters
Mouth generates maintenance policy tree；Further according to weight coefficient priority principle, determine that optimal maintenance program is recommended from maintenance policy tree
User；Then the feedback information for receiving user, determines whether the scheme recommended solves the failure of target vehicle.If so, root
The weight coefficient of the child node in Policy Tree is updated according to optimal maintenance program.If it is not, being updated then using optimal maintenance program as foundation
Maintenance policy tree, redefines maintenance program.User can input interactive information at any time in the whole process, such as: additional event
Hinder diagnostic message, determine maintenance direction etc., so that electronic equipment updates Policy Tree.
In the embodiment of the present application, the Fisrt fault diagnostic message of target vehicle is obtained first；Then according to described first
Failure diagnosis information determines the association repair message of the target vehicle；Then it is patrolled according to the association repair message with default
Relationship library is collected, maintenance policy tree is generated, the maintenance policy tree includes multiple child nodes, every height in the multiple child node
Node corresponds to a maintenance step；The maintenance step is finally selected to construct the target vehicle from the maintenance policy tree
Vehicle maintenance efficiency can be improved in maintenance program.
Referring to FIG. 6, Fig. 6 is a kind of structural representation of the recommendation apparatus of vehicle maintenance scheme provided by the embodiments of the present application
Figure.As shown, the device in the embodiment of the present application includes:
Module 601 is obtained, for obtaining the Fisrt fault diagnostic message of target vehicle.
In the specific implementation, can be when vehicle breaks down, user can be first with vehicle fault detection equipment (golo
Automobile fault diagnostic apparatus) fault diagnosis is carried out to vehicle, failure diagnosis information is obtained, may include event in the failure diagnosis information
Hinder the information such as code, malfunctioning module, wherein error code is the identification information of a kind of vehicle trouble, such as C1203, P1270.Then
User can send the failure diagnosis information to electronic equipment by way of voice or text.
Relating module 602, for determining the association maintenance letter of the target vehicle according to the Fisrt fault diagnostic message
Breath.
In the specific implementation, the critical entities in Fisrt fault diagnostic message can be extracted first with entity recognition techniques
(X), relevant role's ingredient (Y) is determined using sentence structure analysis technology and analytical technology is intended to according to user, extract the
User in one failure diagnosis information is intended to key value (Z), wherein if electronic equipment acquisition is comprising failure diagnosis information
The interactive voice information of user's input then first can carry out synonym standardization, homophonic word standardization to the voice messaging.
Then, it is intended to key value (Z) and logic of propositions relationship library in conjunction with critical entities (X), role's ingredient (Y), user
It carries out fault correlation, the field of physical network is predicted, determine the target topic of vehicle maintenance, and using target topic as pass
Join repair message, association repair message is denoted as Q=(Q1, Q2..., Qs).Wherein, X=(X1,X2,...,Xm), Y=(Y1,
Y2,...,Ym), QiThe calculation method of (i=1,2 ..., s) is as shown in (1) formula.
Generation module 603, for generating maintenance policy tree according to the association repair message and logic of propositions relationship library,
The maintenance policy tree includes multiple child nodes, the corresponding maintenance step of each child node in the multiple child node.
In the specific implementation, being directed to multiple child nodes, one of child node can be the father node of another child node,
And being referred to as child node is with respect to for unique root node in the maintenance policy tree.Correlation dimension can be determined first
The incidence coefficient between information (Q) is repaired, and determines the best process inlet of maintenance policy tree according to incidence coefficient, that is, determines maintenance
The root node of Policy Tree generates maintenance policy tree then according to root node and logic of propositions relationship library.In the electronic device, should
Maintenance policy tree can pass through decision tree structure sequence { O1, O2..., ONStored, O is considered as in maintenance policy tree
A node.Wherein, O1For best process inlet (root node), O1=max (W (Q1, Q2..., Qs)), W (Q1, Q2..., Qs)
For incidence coefficient, there are many kinds of definition mode the embodiment of the present application for W function with no restriction.Specific Oi=(Xr1,bi,Xr2,ω,
C,bc), wherein Xr1、Xr2Indicate specific maintenance step, biIndicate that the logic between the child node and the father node of the child node is closed
System, ω indicate the corresponding weight coefficient of the node, C Xr1、Xr2Type field, bcIndicate biThe class of the logical relation referred to
Type, it should be noted that QiIt can also include other added fields, the embodiment of the present application does not remake to be illustrated one by one.Then basis
O1O is successively determined in logic of propositions relationship library with repair message is associated with2, O3..., ON), wherein logic of propositions relationship library can be with
For logic things network, Fig. 2 gives a kind of possible logic things network.
Optionally, the Fisrt fault diagnostic message of user's input may only include the one of whole fault messages of target vehicle
Part.For example, golo vehicle trouble failure diagnostic apparatus has read error code C1203 and C1207, the first event of user's input simultaneously
Hinder that diagnostic message is " what if reading error code C1203? ".Therefore, module 601 is also used to obtain target vehicle the is obtained
Two failure diagnosis informations.Generation module 603 is also used to be deleted in generated maintenance policy tree according to the second failure diagnosis information
Remove or increase child node.Including two kinds of situations:
The first situation: obtaining the second logical relation information in the second failure diagnosis information, then closes the second logic
It is that information is matched with the first logical relation information (dashed rectangle in Fig. 3) in maintenance policy tree, determines multiple sub- sections
Redundant node in point, then deletes redundant node.
Second situation: obtain the second failure diagnosis information in faulty entity information, faulty entity information can with but not
It is limited to include that the identification information of vehicle accessory or module is repairing then according to faulty entity information and logic of propositions relationship library
Increase child node in Policy Tree.
Decision-making module 604, for from the maintenance policy tree selection target maintenance step construct the target vehicle
Maintenance program.
In the specific implementation, the corresponding weight coefficient of each child node in maintenance policy tree, wherein the weight coefficient is
Binding isotherm is trained a large amount of data, can be to the weight in the subsequent use process to maintenance decision tree
Coefficient is updated.Wherein it is possible to which from maintenance policy tree, successively selection target repairs step, wherein can according to the weight coefficient
Successively to select the corresponding maintenance step of the maximum child node of weight coefficient to repair step as target since root node.For dimension
Repair Policy Tree { O1, O2..., ON, it can be from O1Start to be traversed, saves the corresponding maintenance step of each selected child node
Suddenly (S), and return to Oout=(Xst,Bi,Xnext).Wherein, XstFor the O of current accessediXr1, BiFor the O of current accessediBi。
Xnext=max (w (Qi)|Xst=Xr1), max (w (Qi)|Xst=Xr1) indicate to work as Xst=Xr1When maximum w (Qi), w can be
Common probability function.It wherein, can also be by OoutIt is converted into the intelligible structured statement of user and shows.
Optionally, the device in the embodiment of the present application can also include display module, the maintenance for displaying target vehicle
Scheme, to prompt user to repair according to the maintenance program to target vehicle.
Optionally, display module can be also used for show maintenance policy tree, to recommend plurality of optional to user
Maintenance program, user can then select to close from the Policy Tree according to self-technique strength and the specific fault condition of target vehicle
Suitable maintenance program.
Optionally, the feedback information that module 601 is also used to receive user is obtained, decision-making module is also used to and according to the feedback
Information determines whether target vehicle repairs success.
Generation module 603 is also used to, and when target vehicle repairs successfully, updates the weight of the child node in maintenance policy tree
Coefficient.
In the specific implementation, can be for the corresponding child node of each maintenance step in maintenance program, it is first determined maintenance
There is in multiple child nodes in Policy Tree with the child node cumulative amount of the child node of identical maintenance step, such as: such as Fig. 3
Shown in maintenance policy tree, the cumulative amount of identical child node is 1 with child node " replacement ECM (3GR-FE) "；Then according to
Cumulative amount determines frequency (num) of each child node in the maintenance policy tree, wherein frequency is equal to cumulative number
Amount plus 1；Then according to frequency, the weight coefficient (ω) of each child node is determined.
Generation module 603 is also used to, and when target vehicle repairs failure, is updated in maintenance policy tree.Specifically, can root
According to the maintenance program for having determined that but repairing failure, beta pruning processing is carried out to maintenance decision tree.Specifically, being based on maintenance policy tree
{O1, O2..., ONAnd Oout=(Xst,Bi,Xnext), it can be by Xr1=XnextOiIt is deleted from maintenance policy tree.
In the embodiment of the present application, the Fisrt fault diagnostic message of target vehicle is obtained first；Then according to described first
Failure diagnosis information determines the association repair message of the target vehicle；Then it is patrolled according to the association repair message with default
Relationship library is collected, maintenance policy tree is generated, the maintenance policy tree includes multiple child nodes, every height in the multiple child node
Node corresponds to a maintenance step；The maintenance step is finally selected to construct the target vehicle from the maintenance policy tree
Vehicle maintenance efficiency can be improved in maintenance program.
Referring to FIG. 7, Fig. 7 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present application proposes.As shown, should
Electronic equipment may include: at least one processor 701, such as CPU, at least one communication interface 702, at least one processor
703, at least one bus 704.Wherein, bus 704 is for realizing the connection communication between these components.Wherein, the application is real
The communication interface 702 for applying electronic equipment in example is wired sending port, or wireless device, for example including antenna assembly,
For carrying out the communication of signaling or data with other node devices.Memory 703 can be high speed RAM memory, be also possible to
Non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.Memory 703 is optional
It can also be that at least one is located remotely from the storage device of aforementioned processor 701.Batch processing code is stored in memory 703,
And processor 701 is used to call the program code stored in memory, for performing the following operations:
Obtain the Fisrt fault diagnostic message of target vehicle；
According to the Fisrt fault diagnostic message, the association repair message of the target vehicle is determined；
According to the association repair message and logic of propositions relationship library, maintenance policy tree, the maintenance policy tree packet are generated
Multiple child nodes are included, the corresponding maintenance step of each child node in the multiple child node；
Selection target maintenance step constructs the maintenance program of the target vehicle from the maintenance policy tree.
Wherein, the maintenance policy tree further includes a root node, and the root node is that the source of the multiple child node is saved
Point；
Processor 701 is also used to perform the following operations step:
Determine the incidence coefficient between the association repair message；
According to the incidence coefficient, the root node is determined；
According to the root node and logic of propositions relationship library, the maintenance policy tree is generated.
Wherein, the corresponding weight coefficient of each child node；
Processor 701 is also used to perform the following operations step:
According to the weight coefficient, selection target maintenance step constructs the maintenance program from the maintenance policy tree.
Wherein, the weight coefficient is obtained by training data；
Processor 701 is also used to perform the following operations step:
Determining has the identical cumulative amount for repairing the corresponding child node of step；
According to the cumulative amount, frequency of each child node in the maintenance policy tree is determined；
According to the frequency, the weight coefficient of each child node is updated.
Wherein, processor 701 is also used to perform the following operations step:
Obtain the second failure diagnosis information of the target vehicle；
According to second failure diagnosis information, child node is deleted or increased in the maintenance policy tree.
Wherein, including the first logical relation information between child node in the maintenance policy tree；
Processor 701 is also used to perform the following operations step:
Obtain the second logical relation information for including in second failure diagnosis information；
The first logical relation information and the second logical relation information are matched, determine the multiple sub- section
Redundant node in point；
The redundant node is deleted from the maintenance policy tree.
Wherein, processor 701 is also used to perform the following operations step:
Obtain the faulty entity information for including in second failure diagnosis information；
According to the faulty entity information and logic of propositions relationship library, increase son section in the maintenance policy tree
Point.
Wherein, processor 701 is also used to perform the following operations step:
Display reminding information, the prompt information is for prompting user to repair the target carriage according to the maintenance program
?.
It should be noted that the embodiment of the present application also provides a kind of storage medium simultaneously, the storage medium is for storing
Application program, the application program is in the recommended method of execution Fig. 1 and a kind of vehicle maintenance scheme shown in Fig. 4 at runtime
The operation that electronic equipment executes.
It should be noted that the embodiment of the present application also provides a kind of application program simultaneously, the application program is for transporting
The operation that electronic equipment executes in the recommended method of Fig. 1 and a kind of vehicle maintenance scheme shown in Fig. 4 is executed when row.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc..
Above-described specific embodiment has carried out further the purpose of the application, technical scheme and beneficial effects
It is described in detail.Within the spirit and principles of this application, any modification, equivalent replacement, improvement and so on should be included in
Within the protection scope of the application.
Claims (10)
1. a kind of recommended method of vehicle maintenance scheme, which is characterized in that the described method includes:
Obtain the Fisrt fault diagnostic message of target vehicle；
According to the Fisrt fault diagnostic message, the association repair message of the target vehicle is determined；
According to the association repair message and logic of propositions relationship library, maintenance policy tree is generated, the maintenance policy tree includes more
A child node, the corresponding maintenance step of each child node in the multiple child node；
Selection target maintenance step constructs the maintenance program of the target vehicle from the maintenance policy tree.
2. the method as described in claim 1, which is characterized in that the maintenance policy tree further includes a root node, and described
Node is the source node of the multiple child node；
It is described according to the association repair message and logic of propositions relationship library, generating maintenance policy tree includes:
Determine the incidence coefficient between the association repair message；
According to the incidence coefficient, the root node is determined；
According to the root node and logic of propositions relationship library, the maintenance policy tree is generated.
3. the method as described in claim 1, which is characterized in that the corresponding weight coefficient of each child node；
The maintenance program that the selection target from maintenance policy tree maintenance step constructs the target vehicle includes:
According to the weight coefficient, the target maintenance step is selected to construct the maintenance program from the maintenance policy tree.
4. method as claimed in claim 3, which is characterized in that the weight coefficient is obtained by training data；
The method also includes:
Determine the cumulative amount with the child node of identical maintenance step；
According to the cumulative amount, frequency of each child node in the maintenance policy tree is determined；
According to the frequency, the weight coefficient of each child node is updated.
5. the method as described in claim 1, which is characterized in that described according to the association repair message and logic of propositions relationship
Library, generate maintenance policy tree after, further includes:
Obtain the second failure diagnosis information of the target vehicle；
According to second failure diagnosis information, child node is deleted or increased in the maintenance policy tree.
6. method as claimed in claim 5, which is characterized in that include the first logical relation information in the maintenance policy tree；
It is described according to second failure diagnosis information, deleted in the maintenance policy tree or increase child node and include:
Obtain the second logical relation information for including in second failure diagnosis information；
The first logical relation information and the second logical relation information are matched, determined in the multiple child node
Redundant node；
The redundant node is deleted from the maintenance policy tree.
7. method as claimed in claim 5, which is characterized in that it is described according to second failure diagnosis information, in the dimension
Repairing deletion or increase child node in Policy Tree includes:
Obtain the faulty entity information for including in second failure diagnosis information；
According to the faulty entity information and logic of propositions relationship library, increase child node in the maintenance policy tree.
8. the method according to claim 1 to 7, which is characterized in that it is described from the maintenance policy tree selection described in
Maintenance step constructs after the maintenance program of the target vehicle, further includes:
Display reminding information, the prompt information is for prompting user to repair the target vehicle according to the maintenance program.
9. a kind of recommendation apparatus of vehicle maintenance scheme, which is characterized in that described device includes:
Module is obtained, for obtaining the Fisrt fault diagnostic message of target vehicle；
Relating module, for determining the association repair message of the target vehicle according to the Fisrt fault diagnostic message；
Generation module, for generating maintenance policy tree, the maintenance according to the association repair message and logic of propositions relationship library
Policy Tree includes multiple child nodes, the corresponding maintenance step of each child node in the multiple child node；
Decision-making module, for from the maintenance policy tree selection target maintenance step construct the maintenance side of the target vehicle
Case.
10. a kind of electronic equipment characterized by comprising processor, memory, communication interface and bus；
The processor, the memory are connected by the bus with the communication interface and complete mutual communication；
The memory stores executable program code；
The processor is run and the executable program by reading the executable program code stored in the memory
The corresponding program of code, for executing the recommended method such as the described in any item vehicle maintenance schemes of claim 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287974.7A CN109582670B (en) | 2018-10-31 | 2018-10-31 | Recommendation method of vehicle maintenance scheme and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287974.7A CN109582670B (en) | 2018-10-31 | 2018-10-31 | Recommendation method of vehicle maintenance scheme and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109582670A true CN109582670A (en) | 2019-04-05 |
| CN109582670B CN109582670B (en) | 2023-04-07 |
Family
ID=65920972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811287974.7A Active CN109582670B (en) | 2018-10-31 | 2018-10-31 | Recommendation method of vehicle maintenance scheme and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109582670B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110795336A (en) * | 2019-09-25 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Application program control method, device, equipment and readable storage medium |
| CN111027724A (en) * | 2019-12-10 | 2020-04-17 | 新石器慧通（北京）科技有限公司 | Fault processing method and device, electronic equipment and storage medium |
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
| CN115134212A (en) * | 2022-06-29 | 2022-09-30 | 中国工商银行股份有限公司 | Policy pushing method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020007237A1 (en) * | 2000-06-14 | 2002-01-17 | Phung Tam A. | Method and system for the diagnosis of vehicles |
| CN102708134A (en) * | 2011-03-10 | 2012-10-03 | 通用汽车环球科技运作有限责任公司 | Developing fault model from service procedures |
| CN105956669A (en) * | 2016-05-06 | 2016-09-21 | 深圳市元征科技股份有限公司 | Vehicle maintenance strategy pushing method and device |
| WO2016188279A1 (en) * | 2015-05-25 | 2016-12-01 | 阿里巴巴集团控股有限公司 | Generating method and device for fault spectra, and detecting method and device based on fault spectra |
| CN108182274A (en) * | 2018-01-23 | 2018-06-19 | 广东欧珀移动通信有限公司 | The maintenance process method and Related product of electronic equipment |
-
2018
- 2018-10-31 CN CN201811287974.7A patent/CN109582670B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020007237A1 (en) * | 2000-06-14 | 2002-01-17 | Phung Tam A. | Method and system for the diagnosis of vehicles |
| CN102708134A (en) * | 2011-03-10 | 2012-10-03 | 通用汽车环球科技运作有限责任公司 | Developing fault model from service procedures |
| WO2016188279A1 (en) * | 2015-05-25 | 2016-12-01 | 阿里巴巴集团控股有限公司 | Generating method and device for fault spectra, and detecting method and device based on fault spectra |
| CN105956669A (en) * | 2016-05-06 | 2016-09-21 | 深圳市元征科技股份有限公司 | Vehicle maintenance strategy pushing method and device |
| CN108182274A (en) * | 2018-01-23 | 2018-06-19 | 广东欧珀移动通信有限公司 | The maintenance process method and Related product of electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 梁先登等: "地铁设备维修策略优选方法及实证", 《城市轨道交通研究》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110795336A (en) * | 2019-09-25 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Application program control method, device, equipment and readable storage medium |
| CN111027724A (en) * | 2019-12-10 | 2020-04-17 | 新石器慧通（北京）科技有限公司 | Fault processing method and device, electronic equipment and storage medium |
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
| CN115134212A (en) * | 2022-06-29 | 2022-09-30 | 中国工商银行股份有限公司 | Policy pushing method and device, computer equipment and storage medium |
| CN115134212B (en) * | 2022-06-29 | 2024-04-19 | 中国工商银行股份有限公司 | Policy pushing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109582670B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109582670A (en) | A kind of recommended method and relevant device of vehicle maintenance scheme | |
| US10679008B2 (en) | Knowledge base for analysis of text | |
| US20180114234A1 (en) | Systems and methods for monitoring and analyzing computer and network activity | |
| US10394770B2 (en) | Methods and systems for implementing a data reconciliation framework | |
| US8984339B2 (en) | System and method for test case generation using components | |
| WO2018120721A1 (en) | Method and system for testing user interface, electronic device, and computer readable storage medium | |
| US8984340B2 (en) | System and method for test case generation using action keywords | |
| US20110016451A1 (en) | Method and system for generating test cases for a software application | |
| US20130198320A1 (en) | System And Method For Processing Web Service Test Cases | |
| CN114616560A (en) | Techniques for adaptive and context-aware automation service composition for Machine Learning (ML) | |
| WO2023125851A1 (en) | Remote diagnostics method and apparatus, electronic device and storage medium | |
| CN109660533B (en) | Method and device for identifying abnormal flow in real time, computer equipment and storage medium | |
| CN107194256A (en) | Riskless asset baseline reinforcement means and device | |
| US11481554B2 (en) | Systems and methods for training and evaluating machine learning models using generalized vocabulary tokens for document processing | |
| CN109144852A (en) | Scan method, device, computer equipment and the storage medium of static code | |
| EP4134877A1 (en) | Training method and apparatus for fault recognition model, fault recognition method and apparatus, and electronic device | |
| US9959193B2 (en) | Increasing accuracy of traceability links and structured data | |
| CN111258832B (en) | Interface parameter verification method, device, equipment and medium | |
| CN110716843B (en) | System fault analysis processing method and device, storage medium and electronic equipment | |
| US20220164703A1 (en) | Model acceptance determination support system and model acceptance determination support method | |
| CN116185853A (en) | Code verification method and device | |
| US9524204B2 (en) | Methods and apparatus for customizing and using a reusable database framework for fault processing applications | |
| US20230113860A1 (en) | Proactive network application problem log analyzer | |
| CN109146096A (en) | Report processing method, device, storage medium and the electronic equipment of event for repairment | |
| WO2022101234A1 (en) | System and method for automated or semi-automated identification of malfunction area(s) for maintenance cases |
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 |